/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp

Bug Summary

File:	tools/clang/lib/CodeGen/CGBuiltin.cpp
Warning:	line 8101, column 22 Division by zero

Annotated Source Code

Press '?' to see keyboard shortcuts

Show analyzer invocation

clang -cc1 -triple x86_64-pc-linux-gnu -analyze -disable-free -disable-llvm-verifier -discard-value-names -main-file-name CGBuiltin.cpp -analyzer-store=region -analyzer-opt-analyze-nested-blocks -analyzer-eagerly-assume -analyzer-checker=core -analyzer-checker=apiModeling -analyzer-checker=unix -analyzer-checker=deadcode -analyzer-checker=cplusplus -analyzer-checker=security.insecureAPI.UncheckedReturn -analyzer-checker=security.insecureAPI.getpw -analyzer-checker=security.insecureAPI.gets -analyzer-checker=security.insecureAPI.mktemp -analyzer-checker=security.insecureAPI.mkstemp -analyzer-checker=security.insecureAPI.vfork -analyzer-checker=nullability.NullPassedToNonnull -analyzer-checker=nullability.NullReturnedFromNonnull -analyzer-output plist -w -mrelocation-model pic -pic-level 2 -mthread-model posix -relaxed-aliasing -fmath-errno -masm-verbose -mconstructor-aliases -munwind-tables -fuse-init-array -target-cpu x86-64 -dwarf-column-info -debugger-tuning=gdb -momit-leaf-frame-pointer -ffunction-sections -fdata-sections -resource-dir /usr/lib/llvm-7/lib/clang/7.0.0 -D _DEBUG -D _GNU_SOURCE -D __STDC_CONSTANT_MACROS -D __STDC_FORMAT_MACROS -D __STDC_LIMIT_MACROS -I /build/llvm-toolchain-snapshot-7~svn324650/build-llvm/tools/clang/lib/CodeGen -I /build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen -I /build/llvm-toolchain-snapshot-7~svn324650/tools/clang/include -I /build/llvm-toolchain-snapshot-7~svn324650/build-llvm/tools/clang/include -I /build/llvm-toolchain-snapshot-7~svn324650/build-llvm/include -I /build/llvm-toolchain-snapshot-7~svn324650/include -U NDEBUG -internal-isystem /usr/lib/gcc/x86_64-linux-gnu/7.3.0/../../../../include/c++/7.3.0 -internal-isystem /usr/lib/gcc/x86_64-linux-gnu/7.3.0/../../../../include/x86_64-linux-gnu/c++/7.3.0 -internal-isystem /usr/lib/gcc/x86_64-linux-gnu/7.3.0/../../../../include/x86_64-linux-gnu/c++/7.3.0 -internal-isystem /usr/lib/gcc/x86_64-linux-gnu/7.3.0/../../../../include/c++/7.3.0/backward -internal-isystem /usr/include/clang/7.0.0/include/ -internal-isystem /usr/local/include -internal-isystem /usr/lib/llvm-7/lib/clang/7.0.0/include -internal-externc-isystem /usr/include/x86_64-linux-gnu -internal-externc-isystem /include -internal-externc-isystem /usr/include -O2 -Wno-unused-parameter -Wwrite-strings -Wno-missing-field-initializers -Wno-long-long -Wno-maybe-uninitialized -Wno-comment -std=c++11 -fdeprecated-macro -fdebug-compilation-dir /build/llvm-toolchain-snapshot-7~svn324650/build-llvm/tools/clang/lib/CodeGen -ferror-limit 19 -fmessage-length 0 -fvisibility-inlines-hidden -fobjc-runtime=gcc -fno-common -fdiagnostics-show-option -vectorize-loops -vectorize-slp -analyzer-checker optin.performance.Padding -analyzer-output=html -analyzer-config stable-report-filename=true -o /tmp/scan-build-2018-02-09-212803-22585-1 -x c++ /build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp

/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp

→

1//===---- CGBuiltin.cpp - Emit LLVM Code for builtins ---------------------===//
2//
3//                     The LLVM Compiler Infrastructure
4//
5// This file is distributed under the University of Illinois Open Source
6// License. See LICENSE.TXT for details.
7//
8//===----------------------------------------------------------------------===//
9//
10// This contains code to emit Builtin calls as LLVM code.
11//
12//===----------------------------------------------------------------------===//

14#include "CGCXXABI.h"
15#include "CGObjCRuntime.h"
16#include "CGOpenCLRuntime.h"
17#include "CodeGenFunction.h"
18#include "CodeGenModule.h"
19#include "ConstantEmitter.h"
20#include "TargetInfo.h"
21#include "clang/AST/ASTContext.h"
22#include "clang/AST/Decl.h"
23#include "clang/Analysis/Analyses/OSLog.h"
24#include "clang/Basic/TargetBuiltins.h"
25#include "clang/Basic/TargetInfo.h"
26#include "clang/CodeGen/CGFunctionInfo.h"
27#include "llvm/ADT/StringExtras.h"
28#include "llvm/IR/CallSite.h"
29#include "llvm/IR/DataLayout.h"
30#include "llvm/IR/InlineAsm.h"
31#include "llvm/IR/Intrinsics.h"
32#include "llvm/IR/MDBuilder.h"
33#include "llvm/Support/ConvertUTF.h"
34#include "llvm/Support/ScopedPrinter.h"
35#include "llvm/Support/TargetParser.h"
36#include <sstream>

38using namespace clang;
39using namespace CodeGen;
40using namespace llvm;

42static
43int64_t clamp(int64_t Value, int64_t Low, int64_t High) {
return std::min(High, std::max(Low, Value));
45}

47/// getBuiltinLibFunction - Given a builtin id for a function like
48/// "__builtin_fabsf", return a Function* for "fabsf".
49llvm::Constant *CodeGenModule::getBuiltinLibFunction(const FunctionDecl *FD,
                                                   unsigned BuiltinID) {
assert(Context.BuiltinInfo.isLibFunction(BuiltinID))(static_cast <bool> (Context.BuiltinInfo.isLibFunction(
BuiltinID)) ? void (0) : __assert_fail ("Context.BuiltinInfo.isLibFunction(BuiltinID)"
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 51, __extension__ __PRETTY_FUNCTION__));

// Get the name, skip over the __builtin_ prefix (if necessary).
StringRef Name;
GlobalDecl D(FD);

// If the builtin has been declared explicitly with an assembler label,
// use the mangled name. This differs from the plain label on platforms
// that prefix labels.
if (FD->hasAttr<AsmLabelAttr>())
  Name = getMangledName(D);
else
  Name = Context.BuiltinInfo.getName(BuiltinID) + 10;

llvm::FunctionType *Ty =
  cast<llvm::FunctionType>(getTypes().ConvertType(FD->getType()));

return GetOrCreateLLVMFunction(Name, Ty, D, /*ForVTable=*/false);
69}

71/// Emit the conversions required to turn the given value into an
72/// integer of the given size.
73static Value *EmitToInt(CodeGenFunction &CGF, llvm::Value *V,
                      QualType T, llvm::IntegerType *IntType) {
V = CGF.EmitToMemory(V, T);

if (V->getType()->isPointerTy())
  return CGF.Builder.CreatePtrToInt(V, IntType);

assert(V->getType() == IntType)(static_cast <bool> (V->getType() == IntType) ? void
 (0) : __assert_fail ("V->getType() == IntType", "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 80, __extension__ __PRETTY_FUNCTION__));
return V;
82}

84static Value *EmitFromInt(CodeGenFunction &CGF, llvm::Value *V,
                        QualType T, llvm::Type *ResultType) {
V = CGF.EmitFromMemory(V, T);

if (ResultType->isPointerTy())
  return CGF.Builder.CreateIntToPtr(V, ResultType);

assert(V->getType() == ResultType)(static_cast <bool> (V->getType() == ResultType) ? void
 (0) : __assert_fail ("V->getType() == ResultType", "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 91, __extension__ __PRETTY_FUNCTION__));
return V;
93}

95/// Utility to insert an atomic instruction based on Instrinsic::ID
96/// and the expression node.
97static Value *MakeBinaryAtomicValue(CodeGenFunction &CGF,
                                  llvm::AtomicRMWInst::BinOp Kind,
                                  const CallExpr *E) {
QualType T = E->getType();
assert(E->getArg(0)->getType()->isPointerType())(static_cast <bool> (E->getArg(0)->getType()->
isPointerType()) ? void (0) : __assert_fail ("E->getArg(0)->getType()->isPointerType()"
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 101, __extension__ __PRETTY_FUNCTION__));
assert(CGF.getContext().hasSameUnqualifiedType(T,(static_cast <bool> (CGF.getContext().hasSameUnqualifiedType
(T, E->getArg(0)->getType()->getPointeeType())) ? void
 (0) : __assert_fail ("CGF.getContext().hasSameUnqualifiedType(T, E->getArg(0)->getType()->getPointeeType())"
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 103, __extension__ __PRETTY_FUNCTION__))
                                E->getArg(0)->getType()->getPointeeType()))(static_cast <bool> (CGF.getContext().hasSameUnqualifiedType
(T, E->getArg(0)->getType()->getPointeeType())) ? void
 (0) : __assert_fail ("CGF.getContext().hasSameUnqualifiedType(T, E->getArg(0)->getType()->getPointeeType())"
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 103, __extension__ __PRETTY_FUNCTION__));
assert(CGF.getContext().hasSameUnqualifiedType(T, E->getArg(1)->getType()))(static_cast <bool> (CGF.getContext().hasSameUnqualifiedType
(T, E->getArg(1)->getType())) ? void (0) : __assert_fail
 ("CGF.getContext().hasSameUnqualifiedType(T, E->getArg(1)->getType())"
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 104, __extension__ __PRETTY_FUNCTION__));

llvm::Value *DestPtr = CGF.EmitScalarExpr(E->getArg(0));
unsigned AddrSpace = DestPtr->getType()->getPointerAddressSpace();

llvm::IntegerType *IntType =
  llvm::IntegerType::get(CGF.getLLVMContext(),
                         CGF.getContext().getTypeSize(T));
llvm::Type *IntPtrType = IntType->getPointerTo(AddrSpace);

llvm::Value *Args[2];
Args[0] = CGF.Builder.CreateBitCast(DestPtr, IntPtrType);
Args[1] = CGF.EmitScalarExpr(E->getArg(1));
llvm::Type *ValueType = Args[1]->getType();
Args[1] = EmitToInt(CGF, Args[1], T, IntType);

llvm::Value *Result = CGF.Builder.CreateAtomicRMW(
    Kind, Args[0], Args[1], llvm::AtomicOrdering::SequentiallyConsistent);
return EmitFromInt(CGF, Result, T, ValueType);
123}

125static Value *EmitNontemporalStore(CodeGenFunction &CGF, const CallExpr *E) {
Value *Val = CGF.EmitScalarExpr(E->getArg(0));
Value *Address = CGF.EmitScalarExpr(E->getArg(1));

// Convert the type of the pointer to a pointer to the stored type.
Val = CGF.EmitToMemory(Val, E->getArg(0)->getType());
Value *BC = CGF.Builder.CreateBitCast(
    Address, llvm::PointerType::getUnqual(Val->getType()), "cast");
LValue LV = CGF.MakeNaturalAlignAddrLValue(BC, E->getArg(0)->getType());
LV.setNontemporal(true);
CGF.EmitStoreOfScalar(Val, LV, false);
return nullptr;
137}

139static Value *EmitNontemporalLoad(CodeGenFunction &CGF, const CallExpr *E) {
Value *Address = CGF.EmitScalarExpr(E->getArg(0));

LValue LV = CGF.MakeNaturalAlignAddrLValue(Address, E->getType());
LV.setNontemporal(true);
return CGF.EmitLoadOfScalar(LV, E->getExprLoc());
145}

147static RValue EmitBinaryAtomic(CodeGenFunction &CGF,
                             llvm::AtomicRMWInst::BinOp Kind,
                             const CallExpr *E) {
return RValue::get(MakeBinaryAtomicValue(CGF, Kind, E));
151}

153/// Utility to insert an atomic instruction based Instrinsic::ID and
154/// the expression node, where the return value is the result of the
155/// operation.
156static RValue EmitBinaryAtomicPost(CodeGenFunction &CGF,
                                 llvm::AtomicRMWInst::BinOp Kind,
                                 const CallExpr *E,
                                 Instruction::BinaryOps Op,
                                 bool Invert = false) {
QualType T = E->getType();
assert(E->getArg(0)->getType()->isPointerType())(static_cast <bool> (E->getArg(0)->getType()->
isPointerType()) ? void (0) : __assert_fail ("E->getArg(0)->getType()->isPointerType()"
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 162, __extension__ __PRETTY_FUNCTION__));
assert(CGF.getContext().hasSameUnqualifiedType(T,(static_cast <bool> (CGF.getContext().hasSameUnqualifiedType
(T, E->getArg(0)->getType()->getPointeeType())) ? void
 (0) : __assert_fail ("CGF.getContext().hasSameUnqualifiedType(T, E->getArg(0)->getType()->getPointeeType())"
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 164, __extension__ __PRETTY_FUNCTION__))
                                E->getArg(0)->getType()->getPointeeType()))(static_cast <bool> (CGF.getContext().hasSameUnqualifiedType
(T, E->getArg(0)->getType()->getPointeeType())) ? void
 (0) : __assert_fail ("CGF.getContext().hasSameUnqualifiedType(T, E->getArg(0)->getType()->getPointeeType())"
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 164, __extension__ __PRETTY_FUNCTION__));
assert(CGF.getContext().hasSameUnqualifiedType(T, E->getArg(1)->getType()))(static_cast <bool> (CGF.getContext().hasSameUnqualifiedType
(T, E->getArg(1)->getType())) ? void (0) : __assert_fail
 ("CGF.getContext().hasSameUnqualifiedType(T, E->getArg(1)->getType())"
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 165, __extension__ __PRETTY_FUNCTION__));

llvm::Value *DestPtr = CGF.EmitScalarExpr(E->getArg(0));
unsigned AddrSpace = DestPtr->getType()->getPointerAddressSpace();

llvm::IntegerType *IntType =
  llvm::IntegerType::get(CGF.getLLVMContext(),
                         CGF.getContext().getTypeSize(T));
llvm::Type *IntPtrType = IntType->getPointerTo(AddrSpace);

llvm::Value *Args[2];
Args[1] = CGF.EmitScalarExpr(E->getArg(1));
llvm::Type *ValueType = Args[1]->getType();
Args[1] = EmitToInt(CGF, Args[1], T, IntType);
Args[0] = CGF.Builder.CreateBitCast(DestPtr, IntPtrType);

llvm::Value *Result = CGF.Builder.CreateAtomicRMW(
    Kind, Args[0], Args[1], llvm::AtomicOrdering::SequentiallyConsistent);
Result = CGF.Builder.CreateBinOp(Op, Result, Args[1]);
if (Invert)
  Result = CGF.Builder.CreateBinOp(llvm::Instruction::Xor, Result,
                                   llvm::ConstantInt::get(IntType, -1));
Result = EmitFromInt(CGF, Result, T, ValueType);
return RValue::get(Result);
189}

191/// @brief Utility to insert an atomic cmpxchg instruction.
192///
193/// @param CGF The current codegen function.
194/// @param E   Builtin call expression to convert to cmpxchg.
195///            arg0 - address to operate on
196///            arg1 - value to compare with
197///            arg2 - new value
198/// @param ReturnBool Specifies whether to return success flag of
199///                   cmpxchg result or the old value.
200///
201/// @returns result of cmpxchg, according to ReturnBool
202static Value *MakeAtomicCmpXchgValue(CodeGenFunction &CGF, const CallExpr *E,
                                   bool ReturnBool) {
QualType T = ReturnBool ? E->getArg(1)->getType() : E->getType();
llvm::Value *DestPtr = CGF.EmitScalarExpr(E->getArg(0));
unsigned AddrSpace = DestPtr->getType()->getPointerAddressSpace();

llvm::IntegerType *IntType = llvm::IntegerType::get(
    CGF.getLLVMContext(), CGF.getContext().getTypeSize(T));
llvm::Type *IntPtrType = IntType->getPointerTo(AddrSpace);

Value *Args[3];
Args[0] = CGF.Builder.CreateBitCast(DestPtr, IntPtrType);
Args[1] = CGF.EmitScalarExpr(E->getArg(1));
llvm::Type *ValueType = Args[1]->getType();
Args[1] = EmitToInt(CGF, Args[1], T, IntType);
Args[2] = EmitToInt(CGF, CGF.EmitScalarExpr(E->getArg(2)), T, IntType);

Value *Pair = CGF.Builder.CreateAtomicCmpXchg(
    Args[0], Args[1], Args[2], llvm::AtomicOrdering::SequentiallyConsistent,
    llvm::AtomicOrdering::SequentiallyConsistent);
if (ReturnBool)
  // Extract boolean success flag and zext it to int.
  return CGF.Builder.CreateZExt(CGF.Builder.CreateExtractValue(Pair, 1),
                                CGF.ConvertType(E->getType()));
else
  // Extract old value and emit it using the same type as compare value.
  return EmitFromInt(CGF, CGF.Builder.CreateExtractValue(Pair, 0), T,
                     ValueType);
230}

232// Emit a simple mangled intrinsic that has 1 argument and a return type
233// matching the argument type.
234static Value *emitUnaryBuiltin(CodeGenFunction &CGF,
                             const CallExpr *E,
                             unsigned IntrinsicID) {
llvm::Value *Src0 = CGF.EmitScalarExpr(E->getArg(0));

Value *F = CGF.CGM.getIntrinsic(IntrinsicID, Src0->getType());
return CGF.Builder.CreateCall(F, Src0);
241}

243// Emit an intrinsic that has 2 operands of the same type as its result.
244static Value *emitBinaryBuiltin(CodeGenFunction &CGF,
                              const CallExpr *E,
                              unsigned IntrinsicID) {
llvm::Value *Src0 = CGF.EmitScalarExpr(E->getArg(0));
llvm::Value *Src1 = CGF.EmitScalarExpr(E->getArg(1));

Value *F = CGF.CGM.getIntrinsic(IntrinsicID, Src0->getType());
return CGF.Builder.CreateCall(F, { Src0, Src1 });
252}

254// Emit an intrinsic that has 3 operands of the same type as its result.
255static Value *emitTernaryBuiltin(CodeGenFunction &CGF,
                               const CallExpr *E,
                               unsigned IntrinsicID) {
llvm::Value *Src0 = CGF.EmitScalarExpr(E->getArg(0));
llvm::Value *Src1 = CGF.EmitScalarExpr(E->getArg(1));
llvm::Value *Src2 = CGF.EmitScalarExpr(E->getArg(2));

Value *F = CGF.CGM.getIntrinsic(IntrinsicID, Src0->getType());
return CGF.Builder.CreateCall(F, { Src0, Src1, Src2 });
264}

266// Emit an intrinsic that has 1 float or double operand, and 1 integer.
267static Value *emitFPIntBuiltin(CodeGenFunction &CGF,
                             const CallExpr *E,
                             unsigned IntrinsicID) {
llvm::Value *Src0 = CGF.EmitScalarExpr(E->getArg(0));
llvm::Value *Src1 = CGF.EmitScalarExpr(E->getArg(1));

Value *F = CGF.CGM.getIntrinsic(IntrinsicID, Src0->getType());
return CGF.Builder.CreateCall(F, {Src0, Src1});
275}

277/// EmitFAbs - Emit a call to @llvm.fabs().
278static Value *EmitFAbs(CodeGenFunction &CGF, Value *V) {
Value *F = CGF.CGM.getIntrinsic(Intrinsic::fabs, V->getType());
llvm::CallInst *Call = CGF.Builder.CreateCall(F, V);
Call->setDoesNotAccessMemory();
return Call;
283}

285/// Emit the computation of the sign bit for a floating point value. Returns
286/// the i1 sign bit value.
287static Value *EmitSignBit(CodeGenFunction &CGF, Value *V) {
LLVMContext &C = CGF.CGM.getLLVMContext();

llvm::Type *Ty = V->getType();
int Width = Ty->getPrimitiveSizeInBits();
llvm::Type *IntTy = llvm::IntegerType::get(C, Width);
V = CGF.Builder.CreateBitCast(V, IntTy);
if (Ty->isPPC_FP128Ty()) {
  // We want the sign bit of the higher-order double. The bitcast we just
  // did works as if the double-double was stored to memory and then
  // read as an i128. The "store" will put the higher-order double in the
  // lower address in both little- and big-Endian modes, but the "load"
  // will treat those bits as a different part of the i128: the low bits in
  // little-Endian, the high bits in big-Endian. Therefore, on big-Endian
  // we need to shift the high bits down to the low before truncating.
  Width >>= 1;
  if (CGF.getTarget().isBigEndian()) {
    Value *ShiftCst = llvm::ConstantInt::get(IntTy, Width);
    V = CGF.Builder.CreateLShr(V, ShiftCst);
  }
  // We are truncating value in order to extract the higher-order
  // double, which we will be using to extract the sign from.
  IntTy = llvm::IntegerType::get(C, Width);
  V = CGF.Builder.CreateTrunc(V, IntTy);
}
Value *Zero = llvm::Constant::getNullValue(IntTy);
return CGF.Builder.CreateICmpSLT(V, Zero);
314}

316static RValue emitLibraryCall(CodeGenFunction &CGF, const FunctionDecl *FD,
                            const CallExpr *E, llvm::Constant *calleeValue) {
CGCallee callee = CGCallee::forDirect(calleeValue, FD);
return CGF.EmitCall(E->getCallee()->getType(), callee, E, ReturnValueSlot());
320}

322/// \brief Emit a call to llvm.{sadd,uadd,ssub,usub,smul,umul}.with.overflow.*
323/// depending on IntrinsicID.
324///
325/// \arg CGF The current codegen function.
326/// \arg IntrinsicID The ID for the Intrinsic we wish to generate.
327/// \arg X The first argument to the llvm.*.with.overflow.*.
328/// \arg Y The second argument to the llvm.*.with.overflow.*.
329/// \arg Carry The carry returned by the llvm.*.with.overflow.*.
330/// \returns The result (i.e. sum/product) returned by the intrinsic.
331static llvm::Value *EmitOverflowIntrinsic(CodeGenFunction &CGF,
                                        const llvm::Intrinsic::ID IntrinsicID,
                                        llvm::Value *X, llvm::Value *Y,
                                        llvm::Value *&Carry) {
// Make sure we have integers of the same width.
assert(X->getType() == Y->getType() &&(static_cast <bool> (X->getType() == Y->getType()
 && "Arguments must be the same type. (Did you forget to make sure both "
 "arguments have the same integer width?)") ? void (0) : __assert_fail
 ("X->getType() == Y->getType() && \"Arguments must be the same type. (Did you forget to make sure both \" \"arguments have the same integer width?)\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 338, __extension__ __PRETTY_FUNCTION__))
       "Arguments must be the same type. (Did you forget to make sure both "(static_cast <bool> (X->getType() == Y->getType()
 && "Arguments must be the same type. (Did you forget to make sure both "
 "arguments have the same integer width?)") ? void (0) : __assert_fail
 ("X->getType() == Y->getType() && \"Arguments must be the same type. (Did you forget to make sure both \" \"arguments have the same integer width?)\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 338, __extension__ __PRETTY_FUNCTION__))
       "arguments have the same integer width?)")(static_cast <bool> (X->getType() == Y->getType()
 && "Arguments must be the same type. (Did you forget to make sure both "
 "arguments have the same integer width?)") ? void (0) : __assert_fail
 ("X->getType() == Y->getType() && \"Arguments must be the same type. (Did you forget to make sure both \" \"arguments have the same integer width?)\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 338, __extension__ __PRETTY_FUNCTION__));

llvm::Value *Callee = CGF.CGM.getIntrinsic(IntrinsicID, X->getType());
llvm::Value *Tmp = CGF.Builder.CreateCall(Callee, {X, Y});
Carry = CGF.Builder.CreateExtractValue(Tmp, 1);
return CGF.Builder.CreateExtractValue(Tmp, 0);
344}

346static Value *emitRangedBuiltin(CodeGenFunction &CGF,
                              unsigned IntrinsicID,
                              int low, int high) {
  llvm::MDBuilder MDHelper(CGF.getLLVMContext());
  llvm::MDNode *RNode = MDHelper.createRange(APInt(32, low), APInt(32, high));
  Value *F = CGF.CGM.getIntrinsic(IntrinsicID, {});
  llvm::Instruction *Call = CGF.Builder.CreateCall(F);
  Call->setMetadata(llvm::LLVMContext::MD_range, RNode);
  return Call;
355}

357namespace {
struct WidthAndSignedness {
  unsigned Width;
  bool Signed;
};
362}

364static WidthAndSignedness
365getIntegerWidthAndSignedness(const clang::ASTContext &context,
                           const clang::QualType Type) {
assert(Type->isIntegerType() && "Given type is not an integer.")(static_cast <bool> (Type->isIntegerType() &&
 "Given type is not an integer.") ? void (0) : __assert_fail (
"Type->isIntegerType() && \"Given type is not an integer.\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 367, __extension__ __PRETTY_FUNCTION__));
unsigned Width = Type->isBooleanType() ? 1 : context.getTypeInfo(Type).Width;
bool Signed = Type->isSignedIntegerType();
return {Width, Signed};
371}

373// Given one or more integer types, this function produces an integer type that
374// encompasses them: any value in one of the given types could be expressed in
375// the encompassing type.
376static struct WidthAndSignedness
377EncompassingIntegerType(ArrayRef<struct WidthAndSignedness> Types) {
assert(Types.size() > 0 && "Empty list of types.")(static_cast <bool> (Types.size() > 0 && "Empty list of types."
) ? void (0) : __assert_fail ("Types.size() > 0 && \"Empty list of types.\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 378, __extension__ __PRETTY_FUNCTION__));

// If any of the given types is signed, we must return a signed type.
bool Signed = false;
for (const auto &Type : Types) {
  Signed |= Type.Signed;
}

// The encompassing type must have a width greater than or equal to the width
// of the specified types.  Aditionally, if the encompassing type is signed,
// its width must be strictly greater than the width of any unsigned types
// given.
unsigned Width = 0;
for (const auto &Type : Types) {
  unsigned MinWidth = Type.Width + (Signed && !Type.Signed);
  if (Width < MinWidth) {
    Width = MinWidth;
  }
}

return {Width, Signed};
399}

401Value *CodeGenFunction::EmitVAStartEnd(Value *ArgValue, bool IsStart) {
llvm::Type *DestType = Int8PtrTy;
if (ArgValue->getType() != DestType)
  ArgValue =
      Builder.CreateBitCast(ArgValue, DestType, ArgValue->getName().data());

Intrinsic::ID inst = IsStart ? Intrinsic::vastart : Intrinsic::vaend;
return Builder.CreateCall(CGM.getIntrinsic(inst), ArgValue);
409}

411/// Checks if using the result of __builtin_object_size(p, @p From) in place of
412/// __builtin_object_size(p, @p To) is correct
413static bool areBOSTypesCompatible(int From, int To) {
// Note: Our __builtin_object_size implementation currently treats Type=0 and
// Type=2 identically. Encoding this implementation detail here may make
// improving __builtin_object_size difficult in the future, so it's omitted.
return From == To || (From == 0 && To == 1) || (From == 3 && To == 2);
418}

420static llvm::Value *
421getDefaultBuiltinObjectSizeResult(unsigned Type, llvm::IntegerType *ResType) {
return ConstantInt::get(ResType, (Type & 2) ? 0 : -1, /*isSigned=*/true);
423}

425llvm::Value *
426CodeGenFunction::evaluateOrEmitBuiltinObjectSize(const Expr *E, unsigned Type,
                                               llvm::IntegerType *ResType,
                                               llvm::Value *EmittedE) {
uint64_t ObjectSize;
if (!E->tryEvaluateObjectSize(ObjectSize, getContext(), Type))
  return emitBuiltinObjectSize(E, Type, ResType, EmittedE);
return ConstantInt::get(ResType, ObjectSize, /*isSigned=*/true);
433}

435/// Returns a Value corresponding to the size of the given expression.
436/// This Value may be either of the following:
437///   - A llvm::Argument (if E is a param with the pass_object_size attribute on
438///     it)
439///   - A call to the @llvm.objectsize intrinsic
440///
441/// EmittedE is the result of emitting `E` as a scalar expr. If it's non-null
442/// and we wouldn't otherwise try to reference a pass_object_size parameter,
443/// we'll call @llvm.objectsize on EmittedE, rather than emitting E.
444llvm::Value *
445CodeGenFunction::emitBuiltinObjectSize(const Expr *E, unsigned Type,
                                     llvm::IntegerType *ResType,
                                     llvm::Value *EmittedE) {
// We need to reference an argument if the pointer is a parameter with the
// pass_object_size attribute.
if (auto *D = dyn_cast<DeclRefExpr>(E->IgnoreParenImpCasts())) {
  auto *Param = dyn_cast<ParmVarDecl>(D->getDecl());
  auto *PS = D->getDecl()->getAttr<PassObjectSizeAttr>();
  if (Param != nullptr && PS != nullptr &&
      areBOSTypesCompatible(PS->getType(), Type)) {
    auto Iter = SizeArguments.find(Param);
    assert(Iter != SizeArguments.end())(static_cast <bool> (Iter != SizeArguments.end()) ? void
 (0) : __assert_fail ("Iter != SizeArguments.end()", "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 456, __extension__ __PRETTY_FUNCTION__));

    const ImplicitParamDecl *D = Iter->second;
    auto DIter = LocalDeclMap.find(D);
    assert(DIter != LocalDeclMap.end())(static_cast <bool> (DIter != LocalDeclMap.end()) ? void
 (0) : __assert_fail ("DIter != LocalDeclMap.end()", "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 460, __extension__ __PRETTY_FUNCTION__));

    return EmitLoadOfScalar(DIter->second, /*volatile=*/false,
                            getContext().getSizeType(), E->getLocStart());
  }
}

// LLVM can't handle Type=3 appropriately, and __builtin_object_size shouldn't
// evaluate E for side-effects. In either case, we shouldn't lower to
// @llvm.objectsize.
if (Type == 3 || (!EmittedE && E->HasSideEffects(getContext())))
  return getDefaultBuiltinObjectSizeResult(Type, ResType);

Value *Ptr = EmittedE ? EmittedE : EmitScalarExpr(E);
assert(Ptr->getType()->isPointerTy() &&(static_cast <bool> (Ptr->getType()->isPointerTy(
) && "Non-pointer passed to __builtin_object_size?") ?
 void (0) : __assert_fail ("Ptr->getType()->isPointerTy() && \"Non-pointer passed to __builtin_object_size?\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 475, __extension__ __PRETTY_FUNCTION__))
       "Non-pointer passed to __builtin_object_size?")(static_cast <bool> (Ptr->getType()->isPointerTy(
) && "Non-pointer passed to __builtin_object_size?") ?
 void (0) : __assert_fail ("Ptr->getType()->isPointerTy() && \"Non-pointer passed to __builtin_object_size?\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 475, __extension__ __PRETTY_FUNCTION__));

Value *F = CGM.getIntrinsic(Intrinsic::objectsize, {ResType, Ptr->getType()});

// LLVM only supports 0 and 2, make sure that we pass along that as a boolean.
Value *Min = Builder.getInt1((Type & 2) != 0);
// For GCC compatability, __builtin_object_size treat NULL as unknown size.
Value *NullIsUnknown = Builder.getTrue();
return Builder.CreateCall(F, {Ptr, Min, NullIsUnknown});
484}

486// Many of MSVC builtins are on both x64 and ARM; to avoid repeating code, we
487// handle them here.
488enum class CodeGenFunction::MSVCIntrin {
_BitScanForward,
_BitScanReverse,
_InterlockedAnd,
_InterlockedDecrement,
_InterlockedExchange,
_InterlockedExchangeAdd,
_InterlockedExchangeSub,
_InterlockedIncrement,
_InterlockedOr,
_InterlockedXor,
_interlockedbittestandset,
__fastfail,
501};

503Value *CodeGenFunction::EmitMSVCBuiltinExpr(MSVCIntrin BuiltinID,
                                          const CallExpr *E) {
switch (BuiltinID) {
case MSVCIntrin::_BitScanForward:
case MSVCIntrin::_BitScanReverse: {
  Value *ArgValue = EmitScalarExpr(E->getArg(1));

  llvm::Type *ArgType = ArgValue->getType();
  llvm::Type *IndexType =
    EmitScalarExpr(E->getArg(0))->getType()->getPointerElementType();
  llvm::Type *ResultType = ConvertType(E->getType());

  Value *ArgZero = llvm::Constant::getNullValue(ArgType);
  Value *ResZero = llvm::Constant::getNullValue(ResultType);
  Value *ResOne = llvm::ConstantInt::get(ResultType, 1);

  BasicBlock *Begin = Builder.GetInsertBlock();
  BasicBlock *End = createBasicBlock("bitscan_end", this->CurFn);
  Builder.SetInsertPoint(End);
  PHINode *Result = Builder.CreatePHI(ResultType, 2, "bitscan_result");

  Builder.SetInsertPoint(Begin);
  Value *IsZero = Builder.CreateICmpEQ(ArgValue, ArgZero);
  BasicBlock *NotZero = createBasicBlock("bitscan_not_zero", this->CurFn);
  Builder.CreateCondBr(IsZero, End, NotZero);
  Result->addIncoming(ResZero, Begin);

  Builder.SetInsertPoint(NotZero);
  Address IndexAddress = EmitPointerWithAlignment(E->getArg(0));

  if (BuiltinID == MSVCIntrin::_BitScanForward) {
    Value *F = CGM.getIntrinsic(Intrinsic::cttz, ArgType);
    Value *ZeroCount = Builder.CreateCall(F, {ArgValue, Builder.getTrue()});
    ZeroCount = Builder.CreateIntCast(ZeroCount, IndexType, false);
    Builder.CreateStore(ZeroCount, IndexAddress, false);
  } else {
    unsigned ArgWidth = cast<llvm::IntegerType>(ArgType)->getBitWidth();
    Value *ArgTypeLastIndex = llvm::ConstantInt::get(IndexType, ArgWidth - 1);

    Value *F = CGM.getIntrinsic(Intrinsic::ctlz, ArgType);
    Value *ZeroCount = Builder.CreateCall(F, {ArgValue, Builder.getTrue()});
    ZeroCount = Builder.CreateIntCast(ZeroCount, IndexType, false);
    Value *Index = Builder.CreateNSWSub(ArgTypeLastIndex, ZeroCount);
    Builder.CreateStore(Index, IndexAddress, false);
  }
  Builder.CreateBr(End);
  Result->addIncoming(ResOne, NotZero);

  Builder.SetInsertPoint(End);
  return Result;
}
case MSVCIntrin::_InterlockedAnd:
  return MakeBinaryAtomicValue(*this, AtomicRMWInst::And, E);
case MSVCIntrin::_InterlockedExchange:
  return MakeBinaryAtomicValue(*this, AtomicRMWInst::Xchg, E);
case MSVCIntrin::_InterlockedExchangeAdd:
  return MakeBinaryAtomicValue(*this, AtomicRMWInst::Add, E);
case MSVCIntrin::_InterlockedExchangeSub:
  return MakeBinaryAtomicValue(*this, AtomicRMWInst::Sub, E);
case MSVCIntrin::_InterlockedOr:
  return MakeBinaryAtomicValue(*this, AtomicRMWInst::Or, E);
case MSVCIntrin::_InterlockedXor:
  return MakeBinaryAtomicValue(*this, AtomicRMWInst::Xor, E);

case MSVCIntrin::_interlockedbittestandset: {
  llvm::Value *Addr = EmitScalarExpr(E->getArg(0));
  llvm::Value *Bit = EmitScalarExpr(E->getArg(1));
  AtomicRMWInst *RMWI = Builder.CreateAtomicRMW(
      AtomicRMWInst::Or, Addr,
      Builder.CreateShl(ConstantInt::get(Bit->getType(), 1), Bit),
      llvm::AtomicOrdering::SequentiallyConsistent);
  // Shift the relevant bit to the least significant position, truncate to
  // the result type, and test the low bit.
  llvm::Value *Shifted = Builder.CreateLShr(RMWI, Bit);
  llvm::Value *Truncated =
      Builder.CreateTrunc(Shifted, ConvertType(E->getType()));
  return Builder.CreateAnd(Truncated,
                           ConstantInt::get(Truncated->getType(), 1));
}

case MSVCIntrin::_InterlockedDecrement: {
  llvm::Type *IntTy = ConvertType(E->getType());
  AtomicRMWInst *RMWI = Builder.CreateAtomicRMW(
    AtomicRMWInst::Sub,
    EmitScalarExpr(E->getArg(0)),
    ConstantInt::get(IntTy, 1),
    llvm::AtomicOrdering::SequentiallyConsistent);
  return Builder.CreateSub(RMWI, ConstantInt::get(IntTy, 1));
}
case MSVCIntrin::_InterlockedIncrement: {
  llvm::Type *IntTy = ConvertType(E->getType());
  AtomicRMWInst *RMWI = Builder.CreateAtomicRMW(
    AtomicRMWInst::Add,
    EmitScalarExpr(E->getArg(0)),
    ConstantInt::get(IntTy, 1),
    llvm::AtomicOrdering::SequentiallyConsistent);
  return Builder.CreateAdd(RMWI, ConstantInt::get(IntTy, 1));
}

case MSVCIntrin::__fastfail: {
  // Request immediate process termination from the kernel. The instruction
  // sequences to do this are documented on MSDN:
  // https://msdn.microsoft.com/en-us/library/dn774154.aspx
  llvm::Triple::ArchType ISA = getTarget().getTriple().getArch();
  StringRef Asm, Constraints;
  switch (ISA) {
  default:
    ErrorUnsupported(E, "__fastfail call for this architecture");
    break;
  case llvm::Triple::x86:
  case llvm::Triple::x86_64:
    Asm = "int $$0x29";
    Constraints = "{cx}";
    break;
  case llvm::Triple::thumb:
    Asm = "udf #251";
    Constraints = "{r0}";
    break;
  }
  llvm::FunctionType *FTy = llvm::FunctionType::get(VoidTy, {Int32Ty}, false);
  llvm::InlineAsm *IA =
      llvm::InlineAsm::get(FTy, Asm, Constraints, /*SideEffects=*/true);
  llvm::AttributeList NoReturnAttr = llvm::AttributeList::get(
      getLLVMContext(), llvm::AttributeList::FunctionIndex,
      llvm::Attribute::NoReturn);
  CallSite CS = Builder.CreateCall(IA, EmitScalarExpr(E->getArg(0)));
  CS.setAttributes(NoReturnAttr);
  return CS.getInstruction();
}
}
llvm_unreachable("Incorrect MSVC intrinsic!")::llvm::llvm_unreachable_internal("Incorrect MSVC intrinsic!"
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 633);
634}

636namespace {
637// ARC cleanup for __builtin_os_log_format
638struct CallObjCArcUse final : EHScopeStack::Cleanup {
CallObjCArcUse(llvm::Value *object) : object(object) {}
llvm::Value *object;

void Emit(CodeGenFunction &CGF, Flags flags) override {
  CGF.EmitARCIntrinsicUse(object);
}
645};
646}

648Value *CodeGenFunction::EmitCheckedArgForBuiltin(const Expr *E,
                                               BuiltinCheckKind Kind) {
assert((Kind == BCK_CLZPassedZero || Kind == BCK_CTZPassedZero)(static_cast <bool> ((Kind == BCK_CLZPassedZero || Kind
 == BCK_CTZPassedZero) && "Unsupported builtin check kind"
) ? void (0) : __assert_fail ("(Kind == BCK_CLZPassedZero || Kind == BCK_CTZPassedZero) && \"Unsupported builtin check kind\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 651, __extension__ __PRETTY_FUNCTION__))
        && "Unsupported builtin check kind")(static_cast <bool> ((Kind == BCK_CLZPassedZero || Kind
 == BCK_CTZPassedZero) && "Unsupported builtin check kind"
) ? void (0) : __assert_fail ("(Kind == BCK_CLZPassedZero || Kind == BCK_CTZPassedZero) && \"Unsupported builtin check kind\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 651, __extension__ __PRETTY_FUNCTION__));

Value *ArgValue = EmitScalarExpr(E);
if (!SanOpts.has(SanitizerKind::Builtin) || !getTarget().isCLZForZeroUndef())
  return ArgValue;

SanitizerScope SanScope(this);
Value *Cond = Builder.CreateICmpNE(
    ArgValue, llvm::Constant::getNullValue(ArgValue->getType()));
EmitCheck(std::make_pair(Cond, SanitizerKind::Builtin),
          SanitizerHandler::InvalidBuiltin,
          {EmitCheckSourceLocation(E->getExprLoc()),
           llvm::ConstantInt::get(Builder.getInt8Ty(), Kind)},
          None);
return ArgValue;
666}

668/// Get the argument type for arguments to os_log_helper.
669static CanQualType getOSLogArgType(ASTContext &C, int Size) {
QualType UnsignedTy = C.getIntTypeForBitwidth(Size * 8, /*Signed=*/false);
return C.getCanonicalType(UnsignedTy);
672}

674llvm::Function *CodeGenFunction::generateBuiltinOSLogHelperFunction(
  const analyze_os_log::OSLogBufferLayout &Layout,
  CharUnits BufferAlignment) {
ASTContext &Ctx = getContext();

llvm::SmallString<64> Name;
{
  raw_svector_ostream OS(Name);
  OS << "__os_log_helper";
  OS << "_" << BufferAlignment.getQuantity();
  OS << "_" << int(Layout.getSummaryByte());
  OS << "_" << int(Layout.getNumArgsByte());
  for (const auto &Item : Layout.Items)
    OS << "_" << int(Item.getSizeByte()) << "_"
       << int(Item.getDescriptorByte());
}

if (llvm::Function *F = CGM.getModule().getFunction(Name))
  return F;

llvm::SmallVector<ImplicitParamDecl, 4> Params;
Params.emplace_back(Ctx, nullptr, SourceLocation(), &Ctx.Idents.get("buffer"),
                    Ctx.VoidPtrTy, ImplicitParamDecl::Other);

for (unsigned int I = 0, E = Layout.Items.size(); I < E; ++I) {
  char Size = Layout.Items[I].getSizeByte();
  if (!Size)
    continue;

  Params.emplace_back(
      Ctx, nullptr, SourceLocation(),
      &Ctx.Idents.get(std::string("arg") + llvm::to_string(I)),
      getOSLogArgType(Ctx, Size), ImplicitParamDecl::Other);
}

FunctionArgList Args;
for (auto &P : Params)
  Args.push_back(&P);

// The helper function has linkonce_odr linkage to enable the linker to merge
// identical functions. To ensure the merging always happens, 'noinline' is
// attached to the function when compiling with -Oz.
const CGFunctionInfo &FI =
    CGM.getTypes().arrangeBuiltinFunctionDeclaration(Ctx.VoidTy, Args);
llvm::FunctionType *FuncTy = CGM.getTypes().GetFunctionType(FI);
llvm::Function *Fn = llvm::Function::Create(
    FuncTy, llvm::GlobalValue::LinkOnceODRLinkage, Name, &CGM.getModule());
Fn->setVisibility(llvm::GlobalValue::HiddenVisibility);
CGM.SetLLVMFunctionAttributes(nullptr, FI, Fn);
CGM.SetLLVMFunctionAttributesForDefinition(nullptr, Fn);

// Attach 'noinline' at -Oz.
if (CGM.getCodeGenOpts().OptimizeSize == 2)
  Fn->addFnAttr(llvm::Attribute::NoInline);

auto NL = ApplyDebugLocation::CreateEmpty(*this);
IdentifierInfo *II = &Ctx.Idents.get(Name);
FunctionDecl *FD = FunctionDecl::Create(
    Ctx, Ctx.getTranslationUnitDecl(), SourceLocation(), SourceLocation(), II,
    Ctx.VoidTy, nullptr, SC_PrivateExtern, false, false);

StartFunction(FD, Ctx.VoidTy, Fn, FI, Args);

// Create a scope with an artificial location for the body of this function.
auto AL = ApplyDebugLocation::CreateArtificial(*this);

CharUnits Offset;
Address BufAddr(Builder.CreateLoad(GetAddrOfLocalVar(&Params[0]), "buf"),
                BufferAlignment);
Builder.CreateStore(Builder.getInt8(Layout.getSummaryByte()),
                    Builder.CreateConstByteGEP(BufAddr, Offset++, "summary"));
Builder.CreateStore(Builder.getInt8(Layout.getNumArgsByte()),
                    Builder.CreateConstByteGEP(BufAddr, Offset++, "numArgs"));

unsigned I = 1;
for (const auto &Item : Layout.Items) {
  Builder.CreateStore(
      Builder.getInt8(Item.getDescriptorByte()),
      Builder.CreateConstByteGEP(BufAddr, Offset++, "argDescriptor"));
  Builder.CreateStore(
      Builder.getInt8(Item.getSizeByte()),
      Builder.CreateConstByteGEP(BufAddr, Offset++, "argSize"));

  CharUnits Size = Item.size();
  if (!Size.getQuantity())
    continue;

  Address Arg = GetAddrOfLocalVar(&Params[I]);
  Address Addr = Builder.CreateConstByteGEP(BufAddr, Offset, "argData");
  Addr = Builder.CreateBitCast(Addr, Arg.getPointer()->getType(),
                               "argDataCast");
  Builder.CreateStore(Builder.CreateLoad(Arg), Addr);
  Offset += Size;
  ++I;
}

FinishFunction();

return Fn;
773}

775RValue CodeGenFunction::emitBuiltinOSLogFormat(const CallExpr &E) {
assert(E.getNumArgs() >= 2 &&(static_cast <bool> (E.getNumArgs() >= 2 && "__builtin_os_log_format takes at least 2 arguments"
) ? void (0) : __assert_fail ("E.getNumArgs() >= 2 && \"__builtin_os_log_format takes at least 2 arguments\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 777, __extension__ __PRETTY_FUNCTION__))
       "__builtin_os_log_format takes at least 2 arguments")(static_cast <bool> (E.getNumArgs() >= 2 && "__builtin_os_log_format takes at least 2 arguments"
) ? void (0) : __assert_fail ("E.getNumArgs() >= 2 && \"__builtin_os_log_format takes at least 2 arguments\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 777, __extension__ __PRETTY_FUNCTION__));
ASTContext &Ctx = getContext();
analyze_os_log::OSLogBufferLayout Layout;
analyze_os_log::computeOSLogBufferLayout(Ctx, &E, Layout);
Address BufAddr = EmitPointerWithAlignment(E.getArg(0));
llvm::SmallVector<llvm::Value *, 4> RetainableOperands;

// Ignore argument 1, the format string. It is not currently used.
CallArgList Args;
Args.add(RValue::get(BufAddr.getPointer()), Ctx.VoidPtrTy);

for (const auto &Item : Layout.Items) {
  int Size = Item.getSizeByte();
  if (!Size)
    continue;

  llvm::Value *ArgVal;

  if (const Expr *TheExpr = Item.getExpr()) {
    ArgVal = EmitScalarExpr(TheExpr, /*Ignore*/ false);

    // Check if this is a retainable type.
    if (TheExpr->getType()->isObjCRetainableType()) {
      assert(getEvaluationKind(TheExpr->getType()) == TEK_Scalar &&(static_cast <bool> (getEvaluationKind(TheExpr->getType
()) == TEK_Scalar && "Only scalar can be a ObjC retainable type"
) ? void (0) : __assert_fail ("getEvaluationKind(TheExpr->getType()) == TEK_Scalar && \"Only scalar can be a ObjC retainable type\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 801, __extension__ __PRETTY_FUNCTION__))
             "Only scalar can be a ObjC retainable type")(static_cast <bool> (getEvaluationKind(TheExpr->getType
()) == TEK_Scalar && "Only scalar can be a ObjC retainable type"
) ? void (0) : __assert_fail ("getEvaluationKind(TheExpr->getType()) == TEK_Scalar && \"Only scalar can be a ObjC retainable type\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 801, __extension__ __PRETTY_FUNCTION__));
      // Check if the object is constant, if not, save it in
      // RetainableOperands.
      if (!isa<Constant>(ArgVal))
        RetainableOperands.push_back(ArgVal);
    }
  } else {
    ArgVal = Builder.getInt32(Item.getConstValue().getQuantity());
  }

  unsigned ArgValSize =
      CGM.getDataLayout().getTypeSizeInBits(ArgVal->getType());
  llvm::IntegerType *IntTy = llvm::Type::getIntNTy(getLLVMContext(),
                                                   ArgValSize);
  ArgVal = Builder.CreateBitOrPointerCast(ArgVal, IntTy);
  CanQualType ArgTy = getOSLogArgType(Ctx, Size);
  // If ArgVal has type x86_fp80, zero-extend ArgVal.
  ArgVal = Builder.CreateZExtOrBitCast(ArgVal, ConvertType(ArgTy));
  Args.add(RValue::get(ArgVal), ArgTy);
}

const CGFunctionInfo &FI =
    CGM.getTypes().arrangeBuiltinFunctionCall(Ctx.VoidTy, Args);
llvm::Function *F = CodeGenFunction(CGM).generateBuiltinOSLogHelperFunction(
    Layout, BufAddr.getAlignment());
EmitCall(FI, CGCallee::forDirect(F), ReturnValueSlot(), Args);

// Push a clang.arc.use cleanup for each object in RetainableOperands. The
// cleanup will cause the use to appear after the final log call, keeping
// the object valid while it’s held in the log buffer.  Note that if there’s
// a release cleanup on the object, it will already be active; since
// cleanups are emitted in reverse order, the use will occur before the
// object is released.
if (!RetainableOperands.empty() && getLangOpts().ObjCAutoRefCount &&
    CGM.getCodeGenOpts().OptimizationLevel != 0)
  for (llvm::Value *Object : RetainableOperands)
    pushFullExprCleanup<CallObjCArcUse>(getARCCleanupKind(), Object);

return RValue::get(BufAddr.getPointer());
840}

842/// Determine if a binop is a checked mixed-sign multiply we can specialize.
843static bool isSpecialMixedSignMultiply(unsigned BuiltinID,
                                     WidthAndSignedness Op1Info,
                                     WidthAndSignedness Op2Info,
                                     WidthAndSignedness ResultInfo) {
return BuiltinID == Builtin::BI__builtin_mul_overflow &&
       Op1Info.Width == Op2Info.Width && Op1Info.Width >= ResultInfo.Width &&
       Op1Info.Signed != Op2Info.Signed;
850}

852/// Emit a checked mixed-sign multiply. This is a cheaper specialization of
853/// the generic checked-binop irgen.
854static RValue
855EmitCheckedMixedSignMultiply(CodeGenFunction &CGF, const clang::Expr *Op1,
                           WidthAndSignedness Op1Info, const clang::Expr *Op2,
                           WidthAndSignedness Op2Info,
                           const clang::Expr *ResultArg, QualType ResultQTy,
                           WidthAndSignedness ResultInfo) {
assert(isSpecialMixedSignMultiply(Builtin::BI__builtin_mul_overflow, Op1Info,(static_cast <bool> (isSpecialMixedSignMultiply(Builtin
::BI__builtin_mul_overflow, Op1Info, Op2Info, ResultInfo) &&
 "Not a mixed-sign multipliction we can specialize") ? void (
0) : __assert_fail ("isSpecialMixedSignMultiply(Builtin::BI__builtin_mul_overflow, Op1Info, Op2Info, ResultInfo) && \"Not a mixed-sign multipliction we can specialize\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 862, __extension__ __PRETTY_FUNCTION__))
                                  Op2Info, ResultInfo) &&(static_cast <bool> (isSpecialMixedSignMultiply(Builtin
::BI__builtin_mul_overflow, Op1Info, Op2Info, ResultInfo) &&
 "Not a mixed-sign multipliction we can specialize") ? void (
0) : __assert_fail ("isSpecialMixedSignMultiply(Builtin::BI__builtin_mul_overflow, Op1Info, Op2Info, ResultInfo) && \"Not a mixed-sign multipliction we can specialize\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 862, __extension__ __PRETTY_FUNCTION__))
       "Not a mixed-sign multipliction we can specialize")(static_cast <bool> (isSpecialMixedSignMultiply(Builtin
::BI__builtin_mul_overflow, Op1Info, Op2Info, ResultInfo) &&
 "Not a mixed-sign multipliction we can specialize") ? void (
0) : __assert_fail ("isSpecialMixedSignMultiply(Builtin::BI__builtin_mul_overflow, Op1Info, Op2Info, ResultInfo) && \"Not a mixed-sign multipliction we can specialize\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 862, __extension__ __PRETTY_FUNCTION__));

// Emit the signed and unsigned operands.
const clang::Expr *SignedOp = Op1Info.Signed ? Op1 : Op2;
const clang::Expr *UnsignedOp = Op1Info.Signed ? Op2 : Op1;
llvm::Value *Signed = CGF.EmitScalarExpr(SignedOp);
llvm::Value *Unsigned = CGF.EmitScalarExpr(UnsignedOp);

llvm::Type *OpTy = Signed->getType();
llvm::Value *Zero = llvm::Constant::getNullValue(OpTy);
Address ResultPtr = CGF.EmitPointerWithAlignment(ResultArg);
llvm::Type *ResTy = ResultPtr.getElementType();

// Take the absolute value of the signed operand.
llvm::Value *IsNegative = CGF.Builder.CreateICmpSLT(Signed, Zero);
llvm::Value *AbsOfNegative = CGF.Builder.CreateSub(Zero, Signed);
llvm::Value *AbsSigned =
    CGF.Builder.CreateSelect(IsNegative, AbsOfNegative, Signed);

// Perform a checked unsigned multiplication.
llvm::Value *UnsignedOverflow;
llvm::Value *UnsignedResult =
    EmitOverflowIntrinsic(CGF, llvm::Intrinsic::umul_with_overflow, AbsSigned,
                          Unsigned, UnsignedOverflow);

llvm::Value *Overflow, *Result;
if (ResultInfo.Signed) {
  // Signed overflow occurs if the result is greater than INT_MAX or lesser
  // than INT_MIN, i.e when |Result| > (INT_MAX + IsNegative).
  auto IntMax = llvm::APInt::getSignedMaxValue(ResultInfo.Width)
                    .zextOrSelf(Op1Info.Width);
  llvm::Value *MaxResult =
      CGF.Builder.CreateAdd(llvm::ConstantInt::get(OpTy, IntMax),
                            CGF.Builder.CreateZExt(IsNegative, OpTy));
  llvm::Value *SignedOverflow =
      CGF.Builder.CreateICmpUGT(UnsignedResult, MaxResult);
  Overflow = CGF.Builder.CreateOr(UnsignedOverflow, SignedOverflow);

  // Prepare the signed result (possibly by negating it).
  llvm::Value *NegativeResult = CGF.Builder.CreateNeg(UnsignedResult);
  llvm::Value *SignedResult =
      CGF.Builder.CreateSelect(IsNegative, NegativeResult, UnsignedResult);
  Result = CGF.Builder.CreateTrunc(SignedResult, ResTy);
} else {
  // Unsigned overflow occurs if the result is < 0 or greater than UINT_MAX.
  llvm::Value *Underflow = CGF.Builder.CreateAnd(
      IsNegative, CGF.Builder.CreateIsNotNull(UnsignedResult));
  Overflow = CGF.Builder.CreateOr(UnsignedOverflow, Underflow);
  if (ResultInfo.Width < Op1Info.Width) {
    auto IntMax =
        llvm::APInt::getMaxValue(ResultInfo.Width).zext(Op1Info.Width);
    llvm::Value *TruncOverflow = CGF.Builder.CreateICmpUGT(
        UnsignedResult, llvm::ConstantInt::get(OpTy, IntMax));
    Overflow = CGF.Builder.CreateOr(Overflow, TruncOverflow);
  }

  // Negate the product if it would be negative in infinite precision.
  Result = CGF.Builder.CreateSelect(
      IsNegative, CGF.Builder.CreateNeg(UnsignedResult), UnsignedResult);

  Result = CGF.Builder.CreateTrunc(Result, ResTy);
}
assert(Overflow && Result && "Missing overflow or result")(static_cast <bool> (Overflow && Result &&
 "Missing overflow or result") ? void (0) : __assert_fail ("Overflow && Result && \"Missing overflow or result\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 924, __extension__ __PRETTY_FUNCTION__));

bool isVolatile =
    ResultArg->getType()->getPointeeType().isVolatileQualified();
CGF.Builder.CreateStore(CGF.EmitToMemory(Result, ResultQTy), ResultPtr,
                        isVolatile);
return RValue::get(Overflow);
931}

933RValue CodeGenFunction::EmitBuiltinExpr(const FunctionDecl *FD,
                                      unsigned BuiltinID, const CallExpr *E,
                                      ReturnValueSlot ReturnValue) {
// See if we can constant fold this builtin.  If so, don't emit it at all.
Expr::EvalResult Result;
if (E->EvaluateAsRValue(Result, CGM.getContext()) &&
    !Result.hasSideEffects()) {
  if (Result.Val.isInt())
    return RValue::get(llvm::ConstantInt::get(getLLVMContext(),
                                              Result.Val.getInt()));
  if (Result.Val.isFloat())
    return RValue::get(llvm::ConstantFP::get(getLLVMContext(),
                                             Result.Val.getFloat()));
}

// There are LLVM math intrinsics/instructions corresponding to math library
// functions except the LLVM op will never set errno while the math library
// might. Also, math builtins have the same semantics as their math library
// twins. Thus, we can transform math library and builtin calls to their
// LLVM counterparts if the call is marked 'const' (known to never set errno).
if (FD->hasAttr<ConstAttr>()) {
  switch (BuiltinID) {
  case Builtin::BIceil:
  case Builtin::BIceilf:
  case Builtin::BIceill:
  case Builtin::BI__builtin_ceil:
  case Builtin::BI__builtin_ceilf:
  case Builtin::BI__builtin_ceill:
    return RValue::get(emitUnaryBuiltin(*this, E, Intrinsic::ceil));

  case Builtin::BIcopysign:
  case Builtin::BIcopysignf:
  case Builtin::BIcopysignl:
  case Builtin::BI__builtin_copysign:
  case Builtin::BI__builtin_copysignf:
  case Builtin::BI__builtin_copysignl:
  case Builtin::BI__builtin_copysignf128:
    return RValue::get(emitBinaryBuiltin(*this, E, Intrinsic::copysign));

  case Builtin::BIcos:
  case Builtin::BIcosf:
  case Builtin::BIcosl:
  case Builtin::BI__builtin_cos:
  case Builtin::BI__builtin_cosf:
  case Builtin::BI__builtin_cosl:
    return RValue::get(emitUnaryBuiltin(*this, E, Intrinsic::cos));

  case Builtin::BIexp:
  case Builtin::BIexpf:
  case Builtin::BIexpl:
  case Builtin::BI__builtin_exp:
  case Builtin::BI__builtin_expf:
  case Builtin::BI__builtin_expl:
    return RValue::get(emitUnaryBuiltin(*this, E, Intrinsic::exp));

  case Builtin::BIexp2:
  case Builtin::BIexp2f:
  case Builtin::BIexp2l:
  case Builtin::BI__builtin_exp2:
  case Builtin::BI__builtin_exp2f:
  case Builtin::BI__builtin_exp2l:
    return RValue::get(emitUnaryBuiltin(*this, E, Intrinsic::exp2));

  case Builtin::BIfabs:
  case Builtin::BIfabsf:
  case Builtin::BIfabsl:
  case Builtin::BI__builtin_fabs:
  case Builtin::BI__builtin_fabsf:
  case Builtin::BI__builtin_fabsl:
  case Builtin::BI__builtin_fabsf128:
    return RValue::get(emitUnaryBuiltin(*this, E, Intrinsic::fabs));

  case Builtin::BIfloor:
  case Builtin::BIfloorf:
  case Builtin::BIfloorl:
  case Builtin::BI__builtin_floor:
  case Builtin::BI__builtin_floorf:
  case Builtin::BI__builtin_floorl:
    return RValue::get(emitUnaryBuiltin(*this, E, Intrinsic::floor));

  case Builtin::BIfma:
  case Builtin::BIfmaf:
  case Builtin::BIfmal:
  case Builtin::BI__builtin_fma:
  case Builtin::BI__builtin_fmaf:
  case Builtin::BI__builtin_fmal:
    return RValue::get(emitTernaryBuiltin(*this, E, Intrinsic::fma));

  case Builtin::BIfmax:
  case Builtin::BIfmaxf:
  case Builtin::BIfmaxl:
  case Builtin::BI__builtin_fmax:
  case Builtin::BI__builtin_fmaxf:
  case Builtin::BI__builtin_fmaxl:
    return RValue::get(emitBinaryBuiltin(*this, E, Intrinsic::maxnum));

  case Builtin::BIfmin:
  case Builtin::BIfminf:
  case Builtin::BIfminl:
  case Builtin::BI__builtin_fmin:
  case Builtin::BI__builtin_fminf:
  case Builtin::BI__builtin_fminl:
    return RValue::get(emitBinaryBuiltin(*this, E, Intrinsic::minnum));

  // fmod() is a special-case. It maps to the frem instruction rather than an
  // LLVM intrinsic.
  case Builtin::BIfmod:
  case Builtin::BIfmodf:
  case Builtin::BIfmodl:
  case Builtin::BI__builtin_fmod:
  case Builtin::BI__builtin_fmodf:
  case Builtin::BI__builtin_fmodl: {
    Value *Arg1 = EmitScalarExpr(E->getArg(0));
    Value *Arg2 = EmitScalarExpr(E->getArg(1));
    return RValue::get(Builder.CreateFRem(Arg1, Arg2, "fmod"));
  }

  case Builtin::BIlog:
  case Builtin::BIlogf:
  case Builtin::BIlogl:
  case Builtin::BI__builtin_log:
  case Builtin::BI__builtin_logf:
  case Builtin::BI__builtin_logl:
    return RValue::get(emitUnaryBuiltin(*this, E, Intrinsic::log));

  case Builtin::BIlog10:
  case Builtin::BIlog10f:
  case Builtin::BIlog10l:
  case Builtin::BI__builtin_log10:
  case Builtin::BI__builtin_log10f:
  case Builtin::BI__builtin_log10l:
    return RValue::get(emitUnaryBuiltin(*this, E, Intrinsic::log10));

  case Builtin::BIlog2:
  case Builtin::BIlog2f:
  case Builtin::BIlog2l:
  case Builtin::BI__builtin_log2:
  case Builtin::BI__builtin_log2f:
  case Builtin::BI__builtin_log2l:
    return RValue::get(emitUnaryBuiltin(*this, E, Intrinsic::log2));

  case Builtin::BInearbyint:
  case Builtin::BInearbyintf:
  case Builtin::BInearbyintl:
  case Builtin::BI__builtin_nearbyint:
  case Builtin::BI__builtin_nearbyintf:
  case Builtin::BI__builtin_nearbyintl:
    return RValue::get(emitUnaryBuiltin(*this, E, Intrinsic::nearbyint));

  case Builtin::BIpow:
  case Builtin::BIpowf:
  case Builtin::BIpowl:
  case Builtin::BI__builtin_pow:
  case Builtin::BI__builtin_powf:
  case Builtin::BI__builtin_powl:
    return RValue::get(emitBinaryBuiltin(*this, E, Intrinsic::pow));

  case Builtin::BIrint:
  case Builtin::BIrintf:
  case Builtin::BIrintl:
  case Builtin::BI__builtin_rint:
  case Builtin::BI__builtin_rintf:
  case Builtin::BI__builtin_rintl:
    return RValue::get(emitUnaryBuiltin(*this, E, Intrinsic::rint));

  case Builtin::BIround:
  case Builtin::BIroundf:
  case Builtin::BIroundl:
  case Builtin::BI__builtin_round:
  case Builtin::BI__builtin_roundf:
  case Builtin::BI__builtin_roundl:
    return RValue::get(emitUnaryBuiltin(*this, E, Intrinsic::round));

  case Builtin::BIsin:
  case Builtin::BIsinf:
  case Builtin::BIsinl:
  case Builtin::BI__builtin_sin:
  case Builtin::BI__builtin_sinf:
  case Builtin::BI__builtin_sinl:
    return RValue::get(emitUnaryBuiltin(*this, E, Intrinsic::sin));

  case Builtin::BIsqrt:
  case Builtin::BIsqrtf:
  case Builtin::BIsqrtl:
  case Builtin::BI__builtin_sqrt:
  case Builtin::BI__builtin_sqrtf:
  case Builtin::BI__builtin_sqrtl:
    return RValue::get(emitUnaryBuiltin(*this, E, Intrinsic::sqrt));

  case Builtin::BItrunc:
  case Builtin::BItruncf:
  case Builtin::BItruncl:
  case Builtin::BI__builtin_trunc:
  case Builtin::BI__builtin_truncf:
  case Builtin::BI__builtin_truncl:
    return RValue::get(emitUnaryBuiltin(*this, E, Intrinsic::trunc));

  default:
    break;
  }
}

switch (BuiltinID) {
default: break;
case Builtin::BI__builtin___CFStringMakeConstantString:
case Builtin::BI__builtin___NSStringMakeConstantString:
  return RValue::get(ConstantEmitter(*this).emitAbstract(E, E->getType()));
case Builtin::BI__builtin_stdarg_start:
case Builtin::BI__builtin_va_start:
case Builtin::BI__va_start:
case Builtin::BI__builtin_va_end:
  return RValue::get(
      EmitVAStartEnd(BuiltinID == Builtin::BI__va_start
                         ? EmitScalarExpr(E->getArg(0))
                         : EmitVAListRef(E->getArg(0)).getPointer(),
                     BuiltinID != Builtin::BI__builtin_va_end));
case Builtin::BI__builtin_va_copy: {
  Value *DstPtr = EmitVAListRef(E->getArg(0)).getPointer();
  Value *SrcPtr = EmitVAListRef(E->getArg(1)).getPointer();

  llvm::Type *Type = Int8PtrTy;

  DstPtr = Builder.CreateBitCast(DstPtr, Type);
  SrcPtr = Builder.CreateBitCast(SrcPtr, Type);
  return RValue::get(Builder.CreateCall(CGM.getIntrinsic(Intrinsic::vacopy),
                                        {DstPtr, SrcPtr}));
}
case Builtin::BI__builtin_abs:
case Builtin::BI__builtin_labs:
case Builtin::BI__builtin_llabs: {
  Value *ArgValue = EmitScalarExpr(E->getArg(0));

  Value *NegOp = Builder.CreateNeg(ArgValue, "neg");
  Value *CmpResult =
  Builder.CreateICmpSGE(ArgValue,
                        llvm::Constant::getNullValue(ArgValue->getType()),
                                                          "abscond");
  Value *Result =
    Builder.CreateSelect(CmpResult, ArgValue, NegOp, "abs");

  return RValue::get(Result);
}
case Builtin::BI__builtin_conj:
case Builtin::BI__builtin_conjf:
case Builtin::BI__builtin_conjl: {
  ComplexPairTy ComplexVal = EmitComplexExpr(E->getArg(0));
  Value *Real = ComplexVal.first;
  Value *Imag = ComplexVal.second;
  Value *Zero =
    Imag->getType()->isFPOrFPVectorTy()
      ? llvm::ConstantFP::getZeroValueForNegation(Imag->getType())
      : llvm::Constant::getNullValue(Imag->getType());

  Imag = Builder.CreateFSub(Zero, Imag, "sub");
  return RValue::getComplex(std::make_pair(Real, Imag));
}
case Builtin::BI__builtin_creal:
case Builtin::BI__builtin_crealf:
case Builtin::BI__builtin_creall:
case Builtin::BIcreal:
case Builtin::BIcrealf:
case Builtin::BIcreall: {
  ComplexPairTy ComplexVal = EmitComplexExpr(E->getArg(0));
  return RValue::get(ComplexVal.first);
}

case Builtin::BI__builtin_cimag:
case Builtin::BI__builtin_cimagf:
case Builtin::BI__builtin_cimagl:
case Builtin::BIcimag:
case Builtin::BIcimagf:
case Builtin::BIcimagl: {
  ComplexPairTy ComplexVal = EmitComplexExpr(E->getArg(0));
  return RValue::get(ComplexVal.second);
}

case Builtin::BI__builtin_ctzs:
case Builtin::BI__builtin_ctz:
case Builtin::BI__builtin_ctzl:
case Builtin::BI__builtin_ctzll: {
  Value *ArgValue = EmitCheckedArgForBuiltin(E->getArg(0), BCK_CTZPassedZero);

  llvm::Type *ArgType = ArgValue->getType();
  Value *F = CGM.getIntrinsic(Intrinsic::cttz, ArgType);

  llvm::Type *ResultType = ConvertType(E->getType());
  Value *ZeroUndef = Builder.getInt1(getTarget().isCLZForZeroUndef());
  Value *Result = Builder.CreateCall(F, {ArgValue, ZeroUndef});
  if (Result->getType() != ResultType)
    Result = Builder.CreateIntCast(Result, ResultType, /*isSigned*/true,
                                   "cast");
  return RValue::get(Result);
}
case Builtin::BI__builtin_clzs:
case Builtin::BI__builtin_clz:
case Builtin::BI__builtin_clzl:
case Builtin::BI__builtin_clzll: {
  Value *ArgValue = EmitCheckedArgForBuiltin(E->getArg(0), BCK_CLZPassedZero);

  llvm::Type *ArgType = ArgValue->getType();
  Value *F = CGM.getIntrinsic(Intrinsic::ctlz, ArgType);

  llvm::Type *ResultType = ConvertType(E->getType());
  Value *ZeroUndef = Builder.getInt1(getTarget().isCLZForZeroUndef());
  Value *Result = Builder.CreateCall(F, {ArgValue, ZeroUndef});
  if (Result->getType() != ResultType)
    Result = Builder.CreateIntCast(Result, ResultType, /*isSigned*/true,
                                   "cast");
  return RValue::get(Result);
}
case Builtin::BI__builtin_ffs:
case Builtin::BI__builtin_ffsl:
case Builtin::BI__builtin_ffsll: {
  // ffs(x) -> x ? cttz(x) + 1 : 0
  Value *ArgValue = EmitScalarExpr(E->getArg(0));

  llvm::Type *ArgType = ArgValue->getType();
  Value *F = CGM.getIntrinsic(Intrinsic::cttz, ArgType);

  llvm::Type *ResultType = ConvertType(E->getType());
  Value *Tmp =
      Builder.CreateAdd(Builder.CreateCall(F, {ArgValue, Builder.getTrue()}),
                        llvm::ConstantInt::get(ArgType, 1));
  Value *Zero = llvm::Constant::getNullValue(ArgType);
  Value *IsZero = Builder.CreateICmpEQ(ArgValue, Zero, "iszero");
  Value *Result = Builder.CreateSelect(IsZero, Zero, Tmp, "ffs");
  if (Result->getType() != ResultType)
    Result = Builder.CreateIntCast(Result, ResultType, /*isSigned*/true,
                                   "cast");
  return RValue::get(Result);
}
case Builtin::BI__builtin_parity:
case Builtin::BI__builtin_parityl:
case Builtin::BI__builtin_parityll: {
  // parity(x) -> ctpop(x) & 1
  Value *ArgValue = EmitScalarExpr(E->getArg(0));

  llvm::Type *ArgType = ArgValue->getType();
  Value *F = CGM.getIntrinsic(Intrinsic::ctpop, ArgType);

  llvm::Type *ResultType = ConvertType(E->getType());
  Value *Tmp = Builder.CreateCall(F, ArgValue);
  Value *Result = Builder.CreateAnd(Tmp, llvm::ConstantInt::get(ArgType, 1));
  if (Result->getType() != ResultType)
    Result = Builder.CreateIntCast(Result, ResultType, /*isSigned*/true,
                                   "cast");
  return RValue::get(Result);
}
case Builtin::BI__popcnt16:
case Builtin::BI__popcnt:
case Builtin::BI__popcnt64:
case Builtin::BI__builtin_popcount:
case Builtin::BI__builtin_popcountl:
case Builtin::BI__builtin_popcountll: {
  Value *ArgValue = EmitScalarExpr(E->getArg(0));

  llvm::Type *ArgType = ArgValue->getType();
  Value *F = CGM.getIntrinsic(Intrinsic::ctpop, ArgType);

  llvm::Type *ResultType = ConvertType(E->getType());
  Value *Result = Builder.CreateCall(F, ArgValue);
  if (Result->getType() != ResultType)
    Result = Builder.CreateIntCast(Result, ResultType, /*isSigned*/true,
                                   "cast");
  return RValue::get(Result);
}
case Builtin::BI_rotr8:
case Builtin::BI_rotr16:
case Builtin::BI_rotr:
case Builtin::BI_lrotr:
case Builtin::BI_rotr64: {
  Value *Val = EmitScalarExpr(E->getArg(0));
  Value *Shift = EmitScalarExpr(E->getArg(1));

  llvm::Type *ArgType = Val->getType();
  Shift = Builder.CreateIntCast(Shift, ArgType, false);
  unsigned ArgWidth = cast<llvm::IntegerType>(ArgType)->getBitWidth();
  Value *ArgTypeSize = llvm::ConstantInt::get(ArgType, ArgWidth);
  Value *ArgZero = llvm::Constant::getNullValue(ArgType);

  Value *Mask = llvm::ConstantInt::get(ArgType, ArgWidth - 1);
  Shift = Builder.CreateAnd(Shift, Mask);
  Value *LeftShift = Builder.CreateSub(ArgTypeSize, Shift);

  Value *RightShifted = Builder.CreateLShr(Val, Shift);
  Value *LeftShifted = Builder.CreateShl(Val, LeftShift);
  Value *Rotated = Builder.CreateOr(LeftShifted, RightShifted);

  Value *ShiftIsZero = Builder.CreateICmpEQ(Shift, ArgZero);
  Value *Result = Builder.CreateSelect(ShiftIsZero, Val, Rotated);
  return RValue::get(Result);
}
case Builtin::BI_rotl8:
case Builtin::BI_rotl16:
case Builtin::BI_rotl:
case Builtin::BI_lrotl:
case Builtin::BI_rotl64: {
  Value *Val = EmitScalarExpr(E->getArg(0));
  Value *Shift = EmitScalarExpr(E->getArg(1));

  llvm::Type *ArgType = Val->getType();
  Shift = Builder.CreateIntCast(Shift, ArgType, false);
  unsigned ArgWidth = cast<llvm::IntegerType>(ArgType)->getBitWidth();
  Value *ArgTypeSize = llvm::ConstantInt::get(ArgType, ArgWidth);
  Value *ArgZero = llvm::Constant::getNullValue(ArgType);

  Value *Mask = llvm::ConstantInt::get(ArgType, ArgWidth - 1);
  Shift = Builder.CreateAnd(Shift, Mask);
  Value *RightShift = Builder.CreateSub(ArgTypeSize, Shift);

  Value *LeftShifted = Builder.CreateShl(Val, Shift);
  Value *RightShifted = Builder.CreateLShr(Val, RightShift);
  Value *Rotated = Builder.CreateOr(LeftShifted, RightShifted);

  Value *ShiftIsZero = Builder.CreateICmpEQ(Shift, ArgZero);
  Value *Result = Builder.CreateSelect(ShiftIsZero, Val, Rotated);
  return RValue::get(Result);
}
case Builtin::BI__builtin_unpredictable: {
  // Always return the argument of __builtin_unpredictable. LLVM does not
  // handle this builtin. Metadata for this builtin should be added directly
  // to instructions such as branches or switches that use it.
  return RValue::get(EmitScalarExpr(E->getArg(0)));
}
case Builtin::BI__builtin_expect: {
  Value *ArgValue = EmitScalarExpr(E->getArg(0));
  llvm::Type *ArgType = ArgValue->getType();

  Value *ExpectedValue = EmitScalarExpr(E->getArg(1));
  // Don't generate llvm.expect on -O0 as the backend won't use it for
  // anything.
  // Note, we still IRGen ExpectedValue because it could have side-effects.
  if (CGM.getCodeGenOpts().OptimizationLevel == 0)
    return RValue::get(ArgValue);

  Value *FnExpect = CGM.getIntrinsic(Intrinsic::expect, ArgType);
  Value *Result =
      Builder.CreateCall(FnExpect, {ArgValue, ExpectedValue}, "expval");
  return RValue::get(Result);
}
case Builtin::BI__builtin_assume_aligned: {
  Value *PtrValue = EmitScalarExpr(E->getArg(0));
  Value *OffsetValue =
    (E->getNumArgs() > 2) ? EmitScalarExpr(E->getArg(2)) : nullptr;

  Value *AlignmentValue = EmitScalarExpr(E->getArg(1));
  ConstantInt *AlignmentCI = cast<ConstantInt>(AlignmentValue);
  unsigned Alignment = (unsigned) AlignmentCI->getZExtValue();

  EmitAlignmentAssumption(PtrValue, Alignment, OffsetValue);
  return RValue::get(PtrValue);
}
case Builtin::BI__assume:
case Builtin::BI__builtin_assume: {
  if (E->getArg(0)->HasSideEffects(getContext()))
    return RValue::get(nullptr);

  Value *ArgValue = EmitScalarExpr(E->getArg(0));
  Value *FnAssume = CGM.getIntrinsic(Intrinsic::assume);
  return RValue::get(Builder.CreateCall(FnAssume, ArgValue));
}
case Builtin::BI__builtin_bswap16:
case Builtin::BI__builtin_bswap32:
case Builtin::BI__builtin_bswap64: {
  return RValue::get(emitUnaryBuiltin(*this, E, Intrinsic::bswap));
}
case Builtin::BI__builtin_bitreverse8:
case Builtin::BI__builtin_bitreverse16:
case Builtin::BI__builtin_bitreverse32:
case Builtin::BI__builtin_bitreverse64: {
  return RValue::get(emitUnaryBuiltin(*this, E, Intrinsic::bitreverse));
}
case Builtin::BI__builtin_object_size: {
  unsigned Type =
      E->getArg(1)->EvaluateKnownConstInt(getContext()).getZExtValue();
  auto *ResType = cast<llvm::IntegerType>(ConvertType(E->getType()));

  // We pass this builtin onto the optimizer so that it can figure out the
  // object size in more complex cases.
  return RValue::get(emitBuiltinObjectSize(E->getArg(0), Type, ResType,
                                           /*EmittedE=*/nullptr));
}
case Builtin::BI__builtin_prefetch: {
  Value *Locality, *RW, *Address = EmitScalarExpr(E->getArg(0));
  // FIXME: Technically these constants should of type 'int', yes?
  RW = (E->getNumArgs() > 1) ? EmitScalarExpr(E->getArg(1)) :
    llvm::ConstantInt::get(Int32Ty, 0);
  Locality = (E->getNumArgs() > 2) ? EmitScalarExpr(E->getArg(2)) :
    llvm::ConstantInt::get(Int32Ty, 3);
  Value *Data = llvm::ConstantInt::get(Int32Ty, 1);
  Value *F = CGM.getIntrinsic(Intrinsic::prefetch);
  return RValue::get(Builder.CreateCall(F, {Address, RW, Locality, Data}));
}
case Builtin::BI__builtin_readcyclecounter: {
  Value *F = CGM.getIntrinsic(Intrinsic::readcyclecounter);
  return RValue::get(Builder.CreateCall(F));
}
case Builtin::BI__builtin___clear_cache: {
  Value *Begin = EmitScalarExpr(E->getArg(0));
  Value *End = EmitScalarExpr(E->getArg(1));
  Value *F = CGM.getIntrinsic(Intrinsic::clear_cache);
  return RValue::get(Builder.CreateCall(F, {Begin, End}));
}
case Builtin::BI__builtin_trap:
  return RValue::get(EmitTrapCall(Intrinsic::trap));
case Builtin::BI__debugbreak:
  return RValue::get(EmitTrapCall(Intrinsic::debugtrap));
case Builtin::BI__builtin_unreachable: {
  EmitUnreachable(E->getExprLoc());

  // We do need to preserve an insertion point.
  EmitBlock(createBasicBlock("unreachable.cont"));

  return RValue::get(nullptr);
}

case Builtin::BI__builtin_powi:
case Builtin::BI__builtin_powif:
case Builtin::BI__builtin_powil: {
  Value *Base = EmitScalarExpr(E->getArg(0));
  Value *Exponent = EmitScalarExpr(E->getArg(1));
  llvm::Type *ArgType = Base->getType();
  Value *F = CGM.getIntrinsic(Intrinsic::powi, ArgType);
  return RValue::get(Builder.CreateCall(F, {Base, Exponent}));
}

case Builtin::BI__builtin_isgreater:
case Builtin::BI__builtin_isgreaterequal:
case Builtin::BI__builtin_isless:
case Builtin::BI__builtin_islessequal:
case Builtin::BI__builtin_islessgreater:
case Builtin::BI__builtin_isunordered: {
  // Ordered comparisons: we know the arguments to these are matching scalar
  // floating point values.
  Value *LHS = EmitScalarExpr(E->getArg(0));
  Value *RHS = EmitScalarExpr(E->getArg(1));

  switch (BuiltinID) {
  default: llvm_unreachable("Unknown ordered comparison")::llvm::llvm_unreachable_internal("Unknown ordered comparison"
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 1471);
  case Builtin::BI__builtin_isgreater:
    LHS = Builder.CreateFCmpOGT(LHS, RHS, "cmp");
    break;
  case Builtin::BI__builtin_isgreaterequal:
    LHS = Builder.CreateFCmpOGE(LHS, RHS, "cmp");
    break;
  case Builtin::BI__builtin_isless:
    LHS = Builder.CreateFCmpOLT(LHS, RHS, "cmp");
    break;
  case Builtin::BI__builtin_islessequal:
    LHS = Builder.CreateFCmpOLE(LHS, RHS, "cmp");
    break;
  case Builtin::BI__builtin_islessgreater:
    LHS = Builder.CreateFCmpONE(LHS, RHS, "cmp");
    break;
  case Builtin::BI__builtin_isunordered:
    LHS = Builder.CreateFCmpUNO(LHS, RHS, "cmp");
    break;
  }
  // ZExt bool to int type.
  return RValue::get(Builder.CreateZExt(LHS, ConvertType(E->getType())));
}
case Builtin::BI__builtin_isnan: {
  Value *V = EmitScalarExpr(E->getArg(0));
  V = Builder.CreateFCmpUNO(V, V, "cmp");
  return RValue::get(Builder.CreateZExt(V, ConvertType(E->getType())));
}

case Builtin::BIfinite:
case Builtin::BI__finite:
case Builtin::BIfinitef:
case Builtin::BI__finitef:
case Builtin::BIfinitel:
case Builtin::BI__finitel:
case Builtin::BI__builtin_isinf:
case Builtin::BI__builtin_isfinite: {
  // isinf(x)    --> fabs(x) == infinity
  // isfinite(x) --> fabs(x) != infinity
  // x != NaN via the ordered compare in either case.
  Value *V = EmitScalarExpr(E->getArg(0));
  Value *Fabs = EmitFAbs(*this, V);
  Constant *Infinity = ConstantFP::getInfinity(V->getType());
  CmpInst::Predicate Pred = (BuiltinID == Builtin::BI__builtin_isinf)
                                ? CmpInst::FCMP_OEQ
                                : CmpInst::FCMP_ONE;
  Value *FCmp = Builder.CreateFCmp(Pred, Fabs, Infinity, "cmpinf");
  return RValue::get(Builder.CreateZExt(FCmp, ConvertType(E->getType())));
}

case Builtin::BI__builtin_isinf_sign: {
  // isinf_sign(x) -> fabs(x) == infinity ? (signbit(x) ? -1 : 1) : 0
  Value *Arg = EmitScalarExpr(E->getArg(0));
  Value *AbsArg = EmitFAbs(*this, Arg);
  Value *IsInf = Builder.CreateFCmpOEQ(
      AbsArg, ConstantFP::getInfinity(Arg->getType()), "isinf");
  Value *IsNeg = EmitSignBit(*this, Arg);

  llvm::Type *IntTy = ConvertType(E->getType());
  Value *Zero = Constant::getNullValue(IntTy);
  Value *One = ConstantInt::get(IntTy, 1);
  Value *NegativeOne = ConstantInt::get(IntTy, -1);
  Value *SignResult = Builder.CreateSelect(IsNeg, NegativeOne, One);
  Value *Result = Builder.CreateSelect(IsInf, SignResult, Zero);
  return RValue::get(Result);
}

case Builtin::BI__builtin_isnormal: {
  // isnormal(x) --> x == x && fabsf(x) < infinity && fabsf(x) >= float_min
  Value *V = EmitScalarExpr(E->getArg(0));
  Value *Eq = Builder.CreateFCmpOEQ(V, V, "iseq");

  Value *Abs = EmitFAbs(*this, V);
  Value *IsLessThanInf =
    Builder.CreateFCmpULT(Abs, ConstantFP::getInfinity(V->getType()),"isinf");
  APFloat Smallest = APFloat::getSmallestNormalized(
                 getContext().getFloatTypeSemantics(E->getArg(0)->getType()));
  Value *IsNormal =
    Builder.CreateFCmpUGE(Abs, ConstantFP::get(V->getContext(), Smallest),
                          "isnormal");
  V = Builder.CreateAnd(Eq, IsLessThanInf, "and");
  V = Builder.CreateAnd(V, IsNormal, "and");
  return RValue::get(Builder.CreateZExt(V, ConvertType(E->getType())));
}

case Builtin::BI__builtin_fpclassify: {
  Value *V = EmitScalarExpr(E->getArg(5));
  llvm::Type *Ty = ConvertType(E->getArg(5)->getType());

  // Create Result
  BasicBlock *Begin = Builder.GetInsertBlock();
  BasicBlock *End = createBasicBlock("fpclassify_end", this->CurFn);
  Builder.SetInsertPoint(End);
  PHINode *Result =
    Builder.CreatePHI(ConvertType(E->getArg(0)->getType()), 4,
                      "fpclassify_result");

  // if (V==0) return FP_ZERO
  Builder.SetInsertPoint(Begin);
  Value *IsZero = Builder.CreateFCmpOEQ(V, Constant::getNullValue(Ty),
                                        "iszero");
  Value *ZeroLiteral = EmitScalarExpr(E->getArg(4));
  BasicBlock *NotZero = createBasicBlock("fpclassify_not_zero", this->CurFn);
  Builder.CreateCondBr(IsZero, End, NotZero);
  Result->addIncoming(ZeroLiteral, Begin);

  // if (V != V) return FP_NAN
  Builder.SetInsertPoint(NotZero);
  Value *IsNan = Builder.CreateFCmpUNO(V, V, "cmp");
  Value *NanLiteral = EmitScalarExpr(E->getArg(0));
  BasicBlock *NotNan = createBasicBlock("fpclassify_not_nan", this->CurFn);
  Builder.CreateCondBr(IsNan, End, NotNan);
  Result->addIncoming(NanLiteral, NotZero);

  // if (fabs(V) == infinity) return FP_INFINITY
  Builder.SetInsertPoint(NotNan);
  Value *VAbs = EmitFAbs(*this, V);
  Value *IsInf =
    Builder.CreateFCmpOEQ(VAbs, ConstantFP::getInfinity(V->getType()),
                          "isinf");
  Value *InfLiteral = EmitScalarExpr(E->getArg(1));
  BasicBlock *NotInf = createBasicBlock("fpclassify_not_inf", this->CurFn);
  Builder.CreateCondBr(IsInf, End, NotInf);
  Result->addIncoming(InfLiteral, NotNan);

  // if (fabs(V) >= MIN_NORMAL) return FP_NORMAL else FP_SUBNORMAL
  Builder.SetInsertPoint(NotInf);
  APFloat Smallest = APFloat::getSmallestNormalized(
      getContext().getFloatTypeSemantics(E->getArg(5)->getType()));
  Value *IsNormal =
    Builder.CreateFCmpUGE(VAbs, ConstantFP::get(V->getContext(), Smallest),
                          "isnormal");
  Value *NormalResult =
    Builder.CreateSelect(IsNormal, EmitScalarExpr(E->getArg(2)),
                         EmitScalarExpr(E->getArg(3)));
  Builder.CreateBr(End);
  Result->addIncoming(NormalResult, NotInf);

  // return Result
  Builder.SetInsertPoint(End);
  return RValue::get(Result);
}

case Builtin::BIalloca:
case Builtin::BI_alloca:
case Builtin::BI__builtin_alloca: {
  Value *Size = EmitScalarExpr(E->getArg(0));
  const TargetInfo &TI = getContext().getTargetInfo();
  // The alignment of the alloca should correspond to __BIGGEST_ALIGNMENT__.
  unsigned SuitableAlignmentInBytes =
      CGM.getContext()
          .toCharUnitsFromBits(TI.getSuitableAlign())
          .getQuantity();
  AllocaInst *AI = Builder.CreateAlloca(Builder.getInt8Ty(), Size);
  AI->setAlignment(SuitableAlignmentInBytes);
  return RValue::get(AI);
}

case Builtin::BI__builtin_alloca_with_align: {
  Value *Size = EmitScalarExpr(E->getArg(0));
  Value *AlignmentInBitsValue = EmitScalarExpr(E->getArg(1));
  auto *AlignmentInBitsCI = cast<ConstantInt>(AlignmentInBitsValue);
  unsigned AlignmentInBits = AlignmentInBitsCI->getZExtValue();
  unsigned AlignmentInBytes =
      CGM.getContext().toCharUnitsFromBits(AlignmentInBits).getQuantity();
  AllocaInst *AI = Builder.CreateAlloca(Builder.getInt8Ty(), Size);
  AI->setAlignment(AlignmentInBytes);
  return RValue::get(AI);
}

case Builtin::BIbzero:
case Builtin::BI__builtin_bzero: {
  Address Dest = EmitPointerWithAlignment(E->getArg(0));
  Value *SizeVal = EmitScalarExpr(E->getArg(1));
  EmitNonNullArgCheck(RValue::get(Dest.getPointer()), E->getArg(0)->getType(),
                      E->getArg(0)->getExprLoc(), FD, 0);
  Builder.CreateMemSet(Dest, Builder.getInt8(0), SizeVal, false);
  return RValue::get(nullptr);
}
case Builtin::BImemcpy:
case Builtin::BI__builtin_memcpy: {
  Address Dest = EmitPointerWithAlignment(E->getArg(0));
  Address Src = EmitPointerWithAlignment(E->getArg(1));
  Value *SizeVal = EmitScalarExpr(E->getArg(2));
  EmitNonNullArgCheck(RValue::get(Dest.getPointer()), E->getArg(0)->getType(),
                      E->getArg(0)->getExprLoc(), FD, 0);
  EmitNonNullArgCheck(RValue::get(Src.getPointer()), E->getArg(1)->getType(),
                      E->getArg(1)->getExprLoc(), FD, 1);
  Builder.CreateMemCpy(Dest, Src, SizeVal, false);
  return RValue::get(Dest.getPointer());
}

case Builtin::BI__builtin_char_memchr:
  BuiltinID = Builtin::BI__builtin_memchr;
  break;

case Builtin::BI__builtin___memcpy_chk: {
  // fold __builtin_memcpy_chk(x, y, cst1, cst2) to memcpy iff cst1<=cst2.
  llvm::APSInt Size, DstSize;
  if (!E->getArg(2)->EvaluateAsInt(Size, CGM.getContext()) ||
      !E->getArg(3)->EvaluateAsInt(DstSize, CGM.getContext()))
    break;
  if (Size.ugt(DstSize))
    break;
  Address Dest = EmitPointerWithAlignment(E->getArg(0));
  Address Src = EmitPointerWithAlignment(E->getArg(1));
  Value *SizeVal = llvm::ConstantInt::get(Builder.getContext(), Size);
  Builder.CreateMemCpy(Dest, Src, SizeVal, false);
  return RValue::get(Dest.getPointer());
}

case Builtin::BI__builtin_objc_memmove_collectable: {
  Address DestAddr = EmitPointerWithAlignment(E->getArg(0));
  Address SrcAddr = EmitPointerWithAlignment(E->getArg(1));
  Value *SizeVal = EmitScalarExpr(E->getArg(2));
  CGM.getObjCRuntime().EmitGCMemmoveCollectable(*this,
                                                DestAddr, SrcAddr, SizeVal);
  return RValue::get(DestAddr.getPointer());
}

case Builtin::BI__builtin___memmove_chk: {
  // fold __builtin_memmove_chk(x, y, cst1, cst2) to memmove iff cst1<=cst2.
  llvm::APSInt Size, DstSize;
  if (!E->getArg(2)->EvaluateAsInt(Size, CGM.getContext()) ||
      !E->getArg(3)->EvaluateAsInt(DstSize, CGM.getContext()))
    break;
  if (Size.ugt(DstSize))
    break;
  Address Dest = EmitPointerWithAlignment(E->getArg(0));
  Address Src = EmitPointerWithAlignment(E->getArg(1));
  Value *SizeVal = llvm::ConstantInt::get(Builder.getContext(), Size);
  Builder.CreateMemMove(Dest, Src, SizeVal, false);
  return RValue::get(Dest.getPointer());
}

case Builtin::BImemmove:
case Builtin::BI__builtin_memmove: {
  Address Dest = EmitPointerWithAlignment(E->getArg(0));
  Address Src = EmitPointerWithAlignment(E->getArg(1));
  Value *SizeVal = EmitScalarExpr(E->getArg(2));
  EmitNonNullArgCheck(RValue::get(Dest.getPointer()), E->getArg(0)->getType(),
                      E->getArg(0)->getExprLoc(), FD, 0);
  EmitNonNullArgCheck(RValue::get(Src.getPointer()), E->getArg(1)->getType(),
                      E->getArg(1)->getExprLoc(), FD, 1);
  Builder.CreateMemMove(Dest, Src, SizeVal, false);
  return RValue::get(Dest.getPointer());
}
case Builtin::BImemset:
case Builtin::BI__builtin_memset: {
  Address Dest = EmitPointerWithAlignment(E->getArg(0));
  Value *ByteVal = Builder.CreateTrunc(EmitScalarExpr(E->getArg(1)),
                                       Builder.getInt8Ty());
  Value *SizeVal = EmitScalarExpr(E->getArg(2));
  EmitNonNullArgCheck(RValue::get(Dest.getPointer()), E->getArg(0)->getType(),
                      E->getArg(0)->getExprLoc(), FD, 0);
  Builder.CreateMemSet(Dest, ByteVal, SizeVal, false);
  return RValue::get(Dest.getPointer());
}
case Builtin::BI__builtin___memset_chk: {
  // fold __builtin_memset_chk(x, y, cst1, cst2) to memset iff cst1<=cst2.
  llvm::APSInt Size, DstSize;
  if (!E->getArg(2)->EvaluateAsInt(Size, CGM.getContext()) ||
      !E->getArg(3)->EvaluateAsInt(DstSize, CGM.getContext()))
    break;
  if (Size.ugt(DstSize))
    break;
  Address Dest = EmitPointerWithAlignment(E->getArg(0));
  Value *ByteVal = Builder.CreateTrunc(EmitScalarExpr(E->getArg(1)),
                                       Builder.getInt8Ty());
  Value *SizeVal = llvm::ConstantInt::get(Builder.getContext(), Size);
  Builder.CreateMemSet(Dest, ByteVal, SizeVal, false);
  return RValue::get(Dest.getPointer());
}
case Builtin::BI__builtin_wmemcmp: {
  // The MSVC runtime library does not provide a definition of wmemcmp, so we
  // need an inline implementation.
  if (!getTarget().getTriple().isOSMSVCRT())
    break;

  llvm::Type *WCharTy = ConvertType(getContext().WCharTy);

  Value *Dst = EmitScalarExpr(E->getArg(0));
  Value *Src = EmitScalarExpr(E->getArg(1));
  Value *Size = EmitScalarExpr(E->getArg(2));

  BasicBlock *Entry = Builder.GetInsertBlock();
  BasicBlock *CmpGT = createBasicBlock("wmemcmp.gt");
  BasicBlock *CmpLT = createBasicBlock("wmemcmp.lt");
  BasicBlock *Next = createBasicBlock("wmemcmp.next");
  BasicBlock *Exit = createBasicBlock("wmemcmp.exit");
  Value *SizeEq0 = Builder.CreateICmpEQ(Size, ConstantInt::get(SizeTy, 0));
  Builder.CreateCondBr(SizeEq0, Exit, CmpGT);

  EmitBlock(CmpGT);
  PHINode *DstPhi = Builder.CreatePHI(Dst->getType(), 2);
  DstPhi->addIncoming(Dst, Entry);
  PHINode *SrcPhi = Builder.CreatePHI(Src->getType(), 2);
  SrcPhi->addIncoming(Src, Entry);
  PHINode *SizePhi = Builder.CreatePHI(SizeTy, 2);
  SizePhi->addIncoming(Size, Entry);
  CharUnits WCharAlign =
      getContext().getTypeAlignInChars(getContext().WCharTy);
  Value *DstCh = Builder.CreateAlignedLoad(WCharTy, DstPhi, WCharAlign);
  Value *SrcCh = Builder.CreateAlignedLoad(WCharTy, SrcPhi, WCharAlign);
  Value *DstGtSrc = Builder.CreateICmpUGT(DstCh, SrcCh);
  Builder.CreateCondBr(DstGtSrc, Exit, CmpLT);

  EmitBlock(CmpLT);
  Value *DstLtSrc = Builder.CreateICmpULT(DstCh, SrcCh);
  Builder.CreateCondBr(DstLtSrc, Exit, Next);

  EmitBlock(Next);
  Value *NextDst = Builder.CreateConstInBoundsGEP1_32(WCharTy, DstPhi, 1);
  Value *NextSrc = Builder.CreateConstInBoundsGEP1_32(WCharTy, SrcPhi, 1);
  Value *NextSize = Builder.CreateSub(SizePhi, ConstantInt::get(SizeTy, 1));
  Value *NextSizeEq0 =
      Builder.CreateICmpEQ(NextSize, ConstantInt::get(SizeTy, 0));
  Builder.CreateCondBr(NextSizeEq0, Exit, CmpGT);
  DstPhi->addIncoming(NextDst, Next);
  SrcPhi->addIncoming(NextSrc, Next);
  SizePhi->addIncoming(NextSize, Next);

  EmitBlock(Exit);
  PHINode *Ret = Builder.CreatePHI(IntTy, 4);
  Ret->addIncoming(ConstantInt::get(IntTy, 0), Entry);
  Ret->addIncoming(ConstantInt::get(IntTy, 1), CmpGT);
  Ret->addIncoming(ConstantInt::get(IntTy, -1), CmpLT);
  Ret->addIncoming(ConstantInt::get(IntTy, 0), Next);
  return RValue::get(Ret);
}
case Builtin::BI__builtin_dwarf_cfa: {
  // The offset in bytes from the first argument to the CFA.
  //
  // Why on earth is this in the frontend?  Is there any reason at
  // all that the backend can't reasonably determine this while
  // lowering llvm.eh.dwarf.cfa()?
  //
  // TODO: If there's a satisfactory reason, add a target hook for
  // this instead of hard-coding 0, which is correct for most targets.
  int32_t Offset = 0;

  Value *F = CGM.getIntrinsic(Intrinsic::eh_dwarf_cfa);
  return RValue::get(Builder.CreateCall(F,
                                    llvm::ConstantInt::get(Int32Ty, Offset)));
}
case Builtin::BI__builtin_return_address: {
  Value *Depth = ConstantEmitter(*this).emitAbstract(E->getArg(0),
                                                 getContext().UnsignedIntTy);
  Value *F = CGM.getIntrinsic(Intrinsic::returnaddress);
  return RValue::get(Builder.CreateCall(F, Depth));
}
case Builtin::BI_ReturnAddress: {
  Value *F = CGM.getIntrinsic(Intrinsic::returnaddress);
  return RValue::get(Builder.CreateCall(F, Builder.getInt32(0)));
}
case Builtin::BI__builtin_frame_address: {
  Value *Depth = ConstantEmitter(*this).emitAbstract(E->getArg(0),
                                                 getContext().UnsignedIntTy);
  Value *F = CGM.getIntrinsic(Intrinsic::frameaddress);
  return RValue::get(Builder.CreateCall(F, Depth));
}
case Builtin::BI__builtin_extract_return_addr: {
  Value *Address = EmitScalarExpr(E->getArg(0));
  Value *Result = getTargetHooks().decodeReturnAddress(*this, Address);
  return RValue::get(Result);
}
case Builtin::BI__builtin_frob_return_addr: {
  Value *Address = EmitScalarExpr(E->getArg(0));
  Value *Result = getTargetHooks().encodeReturnAddress(*this, Address);
  return RValue::get(Result);
}
case Builtin::BI__builtin_dwarf_sp_column: {
  llvm::IntegerType *Ty
    = cast<llvm::IntegerType>(ConvertType(E->getType()));
  int Column = getTargetHooks().getDwarfEHStackPointer(CGM);
  if (Column == -1) {
    CGM.ErrorUnsupported(E, "__builtin_dwarf_sp_column");
    return RValue::get(llvm::UndefValue::get(Ty));
  }
  return RValue::get(llvm::ConstantInt::get(Ty, Column, true));
}
case Builtin::BI__builtin_init_dwarf_reg_size_table: {
  Value *Address = EmitScalarExpr(E->getArg(0));
  if (getTargetHooks().initDwarfEHRegSizeTable(*this, Address))
    CGM.ErrorUnsupported(E, "__builtin_init_dwarf_reg_size_table");
  return RValue::get(llvm::UndefValue::get(ConvertType(E->getType())));
}
case Builtin::BI__builtin_eh_return: {
  Value *Int = EmitScalarExpr(E->getArg(0));
  Value *Ptr = EmitScalarExpr(E->getArg(1));

  llvm::IntegerType *IntTy = cast<llvm::IntegerType>(Int->getType());
  assert((IntTy->getBitWidth() == 32 || IntTy->getBitWidth() == 64) &&(static_cast <bool> ((IntTy->getBitWidth() == 32 || IntTy
->getBitWidth() == 64) && "LLVM's __builtin_eh_return only supports 32- and 64-bit variants"
) ? void (0) : __assert_fail ("(IntTy->getBitWidth() == 32 || IntTy->getBitWidth() == 64) && \"LLVM's __builtin_eh_return only supports 32- and 64-bit variants\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 1864, __extension__ __PRETTY_FUNCTION__))
         "LLVM's __builtin_eh_return only supports 32- and 64-bit variants")(static_cast <bool> ((IntTy->getBitWidth() == 32 || IntTy
->getBitWidth() == 64) && "LLVM's __builtin_eh_return only supports 32- and 64-bit variants"
) ? void (0) : __assert_fail ("(IntTy->getBitWidth() == 32 || IntTy->getBitWidth() == 64) && \"LLVM's __builtin_eh_return only supports 32- and 64-bit variants\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 1864, __extension__ __PRETTY_FUNCTION__));
  Value *F = CGM.getIntrinsic(IntTy->getBitWidth() == 32
                                ? Intrinsic::eh_return_i32
                                : Intrinsic::eh_return_i64);
  Builder.CreateCall(F, {Int, Ptr});
  Builder.CreateUnreachable();

  // We do need to preserve an insertion point.
  EmitBlock(createBasicBlock("builtin_eh_return.cont"));

  return RValue::get(nullptr);
}
case Builtin::BI__builtin_unwind_init: {
  Value *F = CGM.getIntrinsic(Intrinsic::eh_unwind_init);
  return RValue::get(Builder.CreateCall(F));
}
case Builtin::BI__builtin_extend_pointer: {
  // Extends a pointer to the size of an _Unwind_Word, which is
  // uint64_t on all platforms.  Generally this gets poked into a
  // register and eventually used as an address, so if the
  // addressing registers are wider than pointers and the platform
  // doesn't implicitly ignore high-order bits when doing
  // addressing, we need to make sure we zext / sext based on
  // the platform's expectations.
  //
  // See: http://gcc.gnu.org/ml/gcc-bugs/2002-02/msg00237.html

  // Cast the pointer to intptr_t.
  Value *Ptr = EmitScalarExpr(E->getArg(0));
  Value *Result = Builder.CreatePtrToInt(Ptr, IntPtrTy, "extend.cast");

  // If that's 64 bits, we're done.
  if (IntPtrTy->getBitWidth() == 64)
    return RValue::get(Result);

  // Otherwise, ask the codegen data what to do.
  if (getTargetHooks().extendPointerWithSExt())
    return RValue::get(Builder.CreateSExt(Result, Int64Ty, "extend.sext"));
  else
    return RValue::get(Builder.CreateZExt(Result, Int64Ty, "extend.zext"));
}
case Builtin::BI__builtin_setjmp: {
  // Buffer is a void**.
  Address Buf = EmitPointerWithAlignment(E->getArg(0));

  // Store the frame pointer to the setjmp buffer.
  Value *FrameAddr =
    Builder.CreateCall(CGM.getIntrinsic(Intrinsic::frameaddress),
                       ConstantInt::get(Int32Ty, 0));
  Builder.CreateStore(FrameAddr, Buf);

  // Store the stack pointer to the setjmp buffer.
  Value *StackAddr =
      Builder.CreateCall(CGM.getIntrinsic(Intrinsic::stacksave));
  Address StackSaveSlot =
    Builder.CreateConstInBoundsGEP(Buf, 2, getPointerSize());
  Builder.CreateStore(StackAddr, StackSaveSlot);

  // Call LLVM's EH setjmp, which is lightweight.
  Value *F = CGM.getIntrinsic(Intrinsic::eh_sjlj_setjmp);
  Buf = Builder.CreateBitCast(Buf, Int8PtrTy);
  return RValue::get(Builder.CreateCall(F, Buf.getPointer()));
}
case Builtin::BI__builtin_longjmp: {
  Value *Buf = EmitScalarExpr(E->getArg(0));
  Buf = Builder.CreateBitCast(Buf, Int8PtrTy);

  // Call LLVM's EH longjmp, which is lightweight.
  Builder.CreateCall(CGM.getIntrinsic(Intrinsic::eh_sjlj_longjmp), Buf);

  // longjmp doesn't return; mark this as unreachable.
  Builder.CreateUnreachable();

  // We do need to preserve an insertion point.
  EmitBlock(createBasicBlock("longjmp.cont"));

  return RValue::get(nullptr);
}
case Builtin::BI__sync_fetch_and_add:
case Builtin::BI__sync_fetch_and_sub:
case Builtin::BI__sync_fetch_and_or:
case Builtin::BI__sync_fetch_and_and:
case Builtin::BI__sync_fetch_and_xor:
case Builtin::BI__sync_fetch_and_nand:
case Builtin::BI__sync_add_and_fetch:
case Builtin::BI__sync_sub_and_fetch:
case Builtin::BI__sync_and_and_fetch:
case Builtin::BI__sync_or_and_fetch:
case Builtin::BI__sync_xor_and_fetch:
case Builtin::BI__sync_nand_and_fetch:
case Builtin::BI__sync_val_compare_and_swap:
case Builtin::BI__sync_bool_compare_and_swap:
case Builtin::BI__sync_lock_test_and_set:
case Builtin::BI__sync_lock_release:
case Builtin::BI__sync_swap:
  llvm_unreachable("Shouldn't make it through sema")::llvm::llvm_unreachable_internal("Shouldn't make it through sema"
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 1959);
case Builtin::BI__sync_fetch_and_add_1:
case Builtin::BI__sync_fetch_and_add_2:
case Builtin::BI__sync_fetch_and_add_4:
case Builtin::BI__sync_fetch_and_add_8:
case Builtin::BI__sync_fetch_and_add_16:
  return EmitBinaryAtomic(*this, llvm::AtomicRMWInst::Add, E);
case Builtin::BI__sync_fetch_and_sub_1:
case Builtin::BI__sync_fetch_and_sub_2:
case Builtin::BI__sync_fetch_and_sub_4:
case Builtin::BI__sync_fetch_and_sub_8:
case Builtin::BI__sync_fetch_and_sub_16:
  return EmitBinaryAtomic(*this, llvm::AtomicRMWInst::Sub, E);
case Builtin::BI__sync_fetch_and_or_1:
case Builtin::BI__sync_fetch_and_or_2:
case Builtin::BI__sync_fetch_and_or_4:
case Builtin::BI__sync_fetch_and_or_8:
case Builtin::BI__sync_fetch_and_or_16:
  return EmitBinaryAtomic(*this, llvm::AtomicRMWInst::Or, E);
case Builtin::BI__sync_fetch_and_and_1:
case Builtin::BI__sync_fetch_and_and_2:
case Builtin::BI__sync_fetch_and_and_4:
case Builtin::BI__sync_fetch_and_and_8:
case Builtin::BI__sync_fetch_and_and_16:
  return EmitBinaryAtomic(*this, llvm::AtomicRMWInst::And, E);
case Builtin::BI__sync_fetch_and_xor_1:
case Builtin::BI__sync_fetch_and_xor_2:
case Builtin::BI__sync_fetch_and_xor_4:
case Builtin::BI__sync_fetch_and_xor_8:
case Builtin::BI__sync_fetch_and_xor_16:
  return EmitBinaryAtomic(*this, llvm::AtomicRMWInst::Xor, E);
case Builtin::BI__sync_fetch_and_nand_1:
case Builtin::BI__sync_fetch_and_nand_2:
case Builtin::BI__sync_fetch_and_nand_4:
case Builtin::BI__sync_fetch_and_nand_8:
case Builtin::BI__sync_fetch_and_nand_16:
  return EmitBinaryAtomic(*this, llvm::AtomicRMWInst::Nand, E);

// Clang extensions: not overloaded yet.
case Builtin::BI__sync_fetch_and_min:
  return EmitBinaryAtomic(*this, llvm::AtomicRMWInst::Min, E);
case Builtin::BI__sync_fetch_and_max:
  return EmitBinaryAtomic(*this, llvm::AtomicRMWInst::Max, E);
case Builtin::BI__sync_fetch_and_umin:
  return EmitBinaryAtomic(*this, llvm::AtomicRMWInst::UMin, E);
case Builtin::BI__sync_fetch_and_umax:
  return EmitBinaryAtomic(*this, llvm::AtomicRMWInst::UMax, E);

case Builtin::BI__sync_add_and_fetch_1:
case Builtin::BI__sync_add_and_fetch_2:
case Builtin::BI__sync_add_and_fetch_4:
case Builtin::BI__sync_add_and_fetch_8:
case Builtin::BI__sync_add_and_fetch_16:
  return EmitBinaryAtomicPost(*this, llvm::AtomicRMWInst::Add, E,
                              llvm::Instruction::Add);
case Builtin::BI__sync_sub_and_fetch_1:
case Builtin::BI__sync_sub_and_fetch_2:
case Builtin::BI__sync_sub_and_fetch_4:
case Builtin::BI__sync_sub_and_fetch_8:
case Builtin::BI__sync_sub_and_fetch_16:
  return EmitBinaryAtomicPost(*this, llvm::AtomicRMWInst::Sub, E,
                              llvm::Instruction::Sub);
case Builtin::BI__sync_and_and_fetch_1:
case Builtin::BI__sync_and_and_fetch_2:
case Builtin::BI__sync_and_and_fetch_4:
case Builtin::BI__sync_and_and_fetch_8:
case Builtin::BI__sync_and_and_fetch_16:
  return EmitBinaryAtomicPost(*this, llvm::AtomicRMWInst::And, E,
                              llvm::Instruction::And);
case Builtin::BI__sync_or_and_fetch_1:
case Builtin::BI__sync_or_and_fetch_2:
case Builtin::BI__sync_or_and_fetch_4:
case Builtin::BI__sync_or_and_fetch_8:
case Builtin::BI__sync_or_and_fetch_16:
  return EmitBinaryAtomicPost(*this, llvm::AtomicRMWInst::Or, E,
                              llvm::Instruction::Or);
case Builtin::BI__sync_xor_and_fetch_1:
case Builtin::BI__sync_xor_and_fetch_2:
case Builtin::BI__sync_xor_and_fetch_4:
case Builtin::BI__sync_xor_and_fetch_8:
case Builtin::BI__sync_xor_and_fetch_16:
  return EmitBinaryAtomicPost(*this, llvm::AtomicRMWInst::Xor, E,
                              llvm::Instruction::Xor);
case Builtin::BI__sync_nand_and_fetch_1:
case Builtin::BI__sync_nand_and_fetch_2:
case Builtin::BI__sync_nand_and_fetch_4:
case Builtin::BI__sync_nand_and_fetch_8:
case Builtin::BI__sync_nand_and_fetch_16:
  return EmitBinaryAtomicPost(*this, llvm::AtomicRMWInst::Nand, E,
                              llvm::Instruction::And, true);

case Builtin::BI__sync_val_compare_and_swap_1:
case Builtin::BI__sync_val_compare_and_swap_2:
case Builtin::BI__sync_val_compare_and_swap_4:
case Builtin::BI__sync_val_compare_and_swap_8:
case Builtin::BI__sync_val_compare_and_swap_16:
  return RValue::get(MakeAtomicCmpXchgValue(*this, E, false));

case Builtin::BI__sync_bool_compare_and_swap_1:
case Builtin::BI__sync_bool_compare_and_swap_2:
case Builtin::BI__sync_bool_compare_and_swap_4:
case Builtin::BI__sync_bool_compare_and_swap_8:
case Builtin::BI__sync_bool_compare_and_swap_16:
  return RValue::get(MakeAtomicCmpXchgValue(*this, E, true));

case Builtin::BI__sync_swap_1:
case Builtin::BI__sync_swap_2:
case Builtin::BI__sync_swap_4:
case Builtin::BI__sync_swap_8:
case Builtin::BI__sync_swap_16:
  return EmitBinaryAtomic(*this, llvm::AtomicRMWInst::Xchg, E);

case Builtin::BI__sync_lock_test_and_set_1:
case Builtin::BI__sync_lock_test_and_set_2:
case Builtin::BI__sync_lock_test_and_set_4:
case Builtin::BI__sync_lock_test_and_set_8:
case Builtin::BI__sync_lock_test_and_set_16:
  return EmitBinaryAtomic(*this, llvm::AtomicRMWInst::Xchg, E);

case Builtin::BI__sync_lock_release_1:
case Builtin::BI__sync_lock_release_2:
case Builtin::BI__sync_lock_release_4:
case Builtin::BI__sync_lock_release_8:
case Builtin::BI__sync_lock_release_16: {
  Value *Ptr = EmitScalarExpr(E->getArg(0));
  QualType ElTy = E->getArg(0)->getType()->getPointeeType();
  CharUnits StoreSize = getContext().getTypeSizeInChars(ElTy);
  llvm::Type *ITy = llvm::IntegerType::get(getLLVMContext(),
                                           StoreSize.getQuantity() * 8);
  Ptr = Builder.CreateBitCast(Ptr, ITy->getPointerTo());
  llvm::StoreInst *Store =
    Builder.CreateAlignedStore(llvm::Constant::getNullValue(ITy), Ptr,
                               StoreSize);
  Store->setAtomic(llvm::AtomicOrdering::Release);
  return RValue::get(nullptr);
}

case Builtin::BI__sync_synchronize: {
  // We assume this is supposed to correspond to a C++0x-style
  // sequentially-consistent fence (i.e. this is only usable for
  // synchonization, not device I/O or anything like that). This intrinsic
  // is really badly designed in the sense that in theory, there isn't
  // any way to safely use it... but in practice, it mostly works
  // to use it with non-atomic loads and stores to get acquire/release
  // semantics.
  Builder.CreateFence(llvm::AtomicOrdering::SequentiallyConsistent);
  return RValue::get(nullptr);
}

case Builtin::BI__builtin_nontemporal_load:
  return RValue::get(EmitNontemporalLoad(*this, E));
case Builtin::BI__builtin_nontemporal_store:
  return RValue::get(EmitNontemporalStore(*this, E));
case Builtin::BI__c11_atomic_is_lock_free:
case Builtin::BI__atomic_is_lock_free: {
  // Call "bool __atomic_is_lock_free(size_t size, void *ptr)". For the
  // __c11 builtin, ptr is 0 (indicating a properly-aligned object), since
  // _Atomic(T) is always properly-aligned.
  const char *LibCallName = "__atomic_is_lock_free";
  CallArgList Args;
  Args.add(RValue::get(EmitScalarExpr(E->getArg(0))),
           getContext().getSizeType());
  if (BuiltinID == Builtin::BI__atomic_is_lock_free)
    Args.add(RValue::get(EmitScalarExpr(E->getArg(1))),
             getContext().VoidPtrTy);
  else
    Args.add(RValue::get(llvm::Constant::getNullValue(VoidPtrTy)),
             getContext().VoidPtrTy);
  const CGFunctionInfo &FuncInfo =
      CGM.getTypes().arrangeBuiltinFunctionCall(E->getType(), Args);
  llvm::FunctionType *FTy = CGM.getTypes().GetFunctionType(FuncInfo);
  llvm::Constant *Func = CGM.CreateRuntimeFunction(FTy, LibCallName);
  return EmitCall(FuncInfo, CGCallee::forDirect(Func),
                  ReturnValueSlot(), Args);
}

case Builtin::BI__atomic_test_and_set: {
  // Look at the argument type to determine whether this is a volatile
  // operation. The parameter type is always volatile.
  QualType PtrTy = E->getArg(0)->IgnoreImpCasts()->getType();
  bool Volatile =
      PtrTy->castAs<PointerType>()->getPointeeType().isVolatileQualified();

  Value *Ptr = EmitScalarExpr(E->getArg(0));
  unsigned AddrSpace = Ptr->getType()->getPointerAddressSpace();
  Ptr = Builder.CreateBitCast(Ptr, Int8Ty->getPointerTo(AddrSpace));
  Value *NewVal = Builder.getInt8(1);
  Value *Order = EmitScalarExpr(E->getArg(1));
  if (isa<llvm::ConstantInt>(Order)) {
    int ord = cast<llvm::ConstantInt>(Order)->getZExtValue();
    AtomicRMWInst *Result = nullptr;
    switch (ord) {
    case 0:  // memory_order_relaxed
    default: // invalid order
      Result = Builder.CreateAtomicRMW(llvm::AtomicRMWInst::Xchg, Ptr, NewVal,
                                       llvm::AtomicOrdering::Monotonic);
      break;
    case 1: // memory_order_consume
    case 2: // memory_order_acquire
      Result = Builder.CreateAtomicRMW(llvm::AtomicRMWInst::Xchg, Ptr, NewVal,
                                       llvm::AtomicOrdering::Acquire);
      break;
    case 3: // memory_order_release
      Result = Builder.CreateAtomicRMW(llvm::AtomicRMWInst::Xchg, Ptr, NewVal,
                                       llvm::AtomicOrdering::Release);
      break;
    case 4: // memory_order_acq_rel

      Result = Builder.CreateAtomicRMW(llvm::AtomicRMWInst::Xchg, Ptr, NewVal,
                                       llvm::AtomicOrdering::AcquireRelease);
      break;
    case 5: // memory_order_seq_cst
      Result = Builder.CreateAtomicRMW(
          llvm::AtomicRMWInst::Xchg, Ptr, NewVal,
          llvm::AtomicOrdering::SequentiallyConsistent);
      break;
    }
    Result->setVolatile(Volatile);
    return RValue::get(Builder.CreateIsNotNull(Result, "tobool"));
  }

  llvm::BasicBlock *ContBB = createBasicBlock("atomic.continue", CurFn);

  llvm::BasicBlock *BBs[5] = {
    createBasicBlock("monotonic", CurFn),
    createBasicBlock("acquire", CurFn),
    createBasicBlock("release", CurFn),
    createBasicBlock("acqrel", CurFn),
    createBasicBlock("seqcst", CurFn)
  };
  llvm::AtomicOrdering Orders[5] = {
      llvm::AtomicOrdering::Monotonic, llvm::AtomicOrdering::Acquire,
      llvm::AtomicOrdering::Release, llvm::AtomicOrdering::AcquireRelease,
      llvm::AtomicOrdering::SequentiallyConsistent};

  Order = Builder.CreateIntCast(Order, Builder.getInt32Ty(), false);
  llvm::SwitchInst *SI = Builder.CreateSwitch(Order, BBs[0]);

  Builder.SetInsertPoint(ContBB);
  PHINode *Result = Builder.CreatePHI(Int8Ty, 5, "was_set");

  for (unsigned i = 0; i < 5; ++i) {
    Builder.SetInsertPoint(BBs[i]);
    AtomicRMWInst *RMW = Builder.CreateAtomicRMW(llvm::AtomicRMWInst::Xchg,
                                                 Ptr, NewVal, Orders[i]);
    RMW->setVolatile(Volatile);
    Result->addIncoming(RMW, BBs[i]);
    Builder.CreateBr(ContBB);
  }

  SI->addCase(Builder.getInt32(0), BBs[0]);
  SI->addCase(Builder.getInt32(1), BBs[1]);
  SI->addCase(Builder.getInt32(2), BBs[1]);
  SI->addCase(Builder.getInt32(3), BBs[2]);
  SI->addCase(Builder.getInt32(4), BBs[3]);
  SI->addCase(Builder.getInt32(5), BBs[4]);

  Builder.SetInsertPoint(ContBB);
  return RValue::get(Builder.CreateIsNotNull(Result, "tobool"));
}

case Builtin::BI__atomic_clear: {
  QualType PtrTy = E->getArg(0)->IgnoreImpCasts()->getType();
  bool Volatile =
      PtrTy->castAs<PointerType>()->getPointeeType().isVolatileQualified();

  Address Ptr = EmitPointerWithAlignment(E->getArg(0));
  unsigned AddrSpace = Ptr.getPointer()->getType()->getPointerAddressSpace();
  Ptr = Builder.CreateBitCast(Ptr, Int8Ty->getPointerTo(AddrSpace));
  Value *NewVal = Builder.getInt8(0);
  Value *Order = EmitScalarExpr(E->getArg(1));
  if (isa<llvm::ConstantInt>(Order)) {
    int ord = cast<llvm::ConstantInt>(Order)->getZExtValue();
    StoreInst *Store = Builder.CreateStore(NewVal, Ptr, Volatile);
    switch (ord) {
    case 0:  // memory_order_relaxed
    default: // invalid order
      Store->setOrdering(llvm::AtomicOrdering::Monotonic);
      break;
    case 3:  // memory_order_release
      Store->setOrdering(llvm::AtomicOrdering::Release);
      break;
    case 5:  // memory_order_seq_cst
      Store->setOrdering(llvm::AtomicOrdering::SequentiallyConsistent);
      break;
    }
    return RValue::get(nullptr);
  }

  llvm::BasicBlock *ContBB = createBasicBlock("atomic.continue", CurFn);

  llvm::BasicBlock *BBs[3] = {
    createBasicBlock("monotonic", CurFn),
    createBasicBlock("release", CurFn),
    createBasicBlock("seqcst", CurFn)
  };
  llvm::AtomicOrdering Orders[3] = {
      llvm::AtomicOrdering::Monotonic, llvm::AtomicOrdering::Release,
      llvm::AtomicOrdering::SequentiallyConsistent};

  Order = Builder.CreateIntCast(Order, Builder.getInt32Ty(), false);
  llvm::SwitchInst *SI = Builder.CreateSwitch(Order, BBs[0]);

  for (unsigned i = 0; i < 3; ++i) {
    Builder.SetInsertPoint(BBs[i]);
    StoreInst *Store = Builder.CreateStore(NewVal, Ptr, Volatile);
    Store->setOrdering(Orders[i]);
    Builder.CreateBr(ContBB);
  }

  SI->addCase(Builder.getInt32(0), BBs[0]);
  SI->addCase(Builder.getInt32(3), BBs[1]);
  SI->addCase(Builder.getInt32(5), BBs[2]);

  Builder.SetInsertPoint(ContBB);
  return RValue::get(nullptr);
}

case Builtin::BI__atomic_thread_fence:
case Builtin::BI__atomic_signal_fence:
case Builtin::BI__c11_atomic_thread_fence:
case Builtin::BI__c11_atomic_signal_fence: {
  llvm::SyncScope::ID SSID;
  if (BuiltinID == Builtin::BI__atomic_signal_fence ||
      BuiltinID == Builtin::BI__c11_atomic_signal_fence)
    SSID = llvm::SyncScope::SingleThread;
  else
    SSID = llvm::SyncScope::System;
  Value *Order = EmitScalarExpr(E->getArg(0));
  if (isa<llvm::ConstantInt>(Order)) {
    int ord = cast<llvm::ConstantInt>(Order)->getZExtValue();
    switch (ord) {
    case 0:  // memory_order_relaxed
    default: // invalid order
      break;
    case 1:  // memory_order_consume
    case 2:  // memory_order_acquire
      Builder.CreateFence(llvm::AtomicOrdering::Acquire, SSID);
      break;
    case 3:  // memory_order_release
      Builder.CreateFence(llvm::AtomicOrdering::Release, SSID);
      break;
    case 4:  // memory_order_acq_rel
      Builder.CreateFence(llvm::AtomicOrdering::AcquireRelease, SSID);
      break;
    case 5:  // memory_order_seq_cst
      Builder.CreateFence(llvm::AtomicOrdering::SequentiallyConsistent, SSID);
      break;
    }
    return RValue::get(nullptr);
  }

  llvm::BasicBlock *AcquireBB, *ReleaseBB, *AcqRelBB, *SeqCstBB;
  AcquireBB = createBasicBlock("acquire", CurFn);
  ReleaseBB = createBasicBlock("release", CurFn);
  AcqRelBB = createBasicBlock("acqrel", CurFn);
  SeqCstBB = createBasicBlock("seqcst", CurFn);
  llvm::BasicBlock *ContBB = createBasicBlock("atomic.continue", CurFn);

  Order = Builder.CreateIntCast(Order, Builder.getInt32Ty(), false);
  llvm::SwitchInst *SI = Builder.CreateSwitch(Order, ContBB);

  Builder.SetInsertPoint(AcquireBB);
  Builder.CreateFence(llvm::AtomicOrdering::Acquire, SSID);
  Builder.CreateBr(ContBB);
  SI->addCase(Builder.getInt32(1), AcquireBB);
  SI->addCase(Builder.getInt32(2), AcquireBB);

  Builder.SetInsertPoint(ReleaseBB);
  Builder.CreateFence(llvm::AtomicOrdering::Release, SSID);
  Builder.CreateBr(ContBB);
  SI->addCase(Builder.getInt32(3), ReleaseBB);

  Builder.SetInsertPoint(AcqRelBB);
  Builder.CreateFence(llvm::AtomicOrdering::AcquireRelease, SSID);
  Builder.CreateBr(ContBB);
  SI->addCase(Builder.getInt32(4), AcqRelBB);

  Builder.SetInsertPoint(SeqCstBB);
  Builder.CreateFence(llvm::AtomicOrdering::SequentiallyConsistent, SSID);
  Builder.CreateBr(ContBB);
  SI->addCase(Builder.getInt32(5), SeqCstBB);

  Builder.SetInsertPoint(ContBB);
  return RValue::get(nullptr);
}

case Builtin::BI__builtin_signbit:
case Builtin::BI__builtin_signbitf:
case Builtin::BI__builtin_signbitl: {
  return RValue::get(
      Builder.CreateZExt(EmitSignBit(*this, EmitScalarExpr(E->getArg(0))),
                         ConvertType(E->getType())));
}
case Builtin::BI__annotation: {
  // Re-encode each wide string to UTF8 and make an MDString.
  SmallVector<Metadata *, 1> Strings;
  for (const Expr *Arg : E->arguments()) {
    const auto *Str = cast<StringLiteral>(Arg->IgnoreParenCasts());
    assert(Str->getCharByteWidth() == 2)(static_cast <bool> (Str->getCharByteWidth() == 2) ?
 void (0) : __assert_fail ("Str->getCharByteWidth() == 2",
 "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 2358, __extension__ __PRETTY_FUNCTION__));
    StringRef WideBytes = Str->getBytes();
    std::string StrUtf8;
    if (!convertUTF16ToUTF8String(
            makeArrayRef(WideBytes.data(), WideBytes.size()), StrUtf8)) {
      CGM.ErrorUnsupported(E, "non-UTF16 __annotation argument");
      continue;
    }
    Strings.push_back(llvm::MDString::get(getLLVMContext(), StrUtf8));
  }

  // Build and MDTuple of MDStrings and emit the intrinsic call.
  llvm::Value *F = CGM.getIntrinsic(llvm::Intrinsic::codeview_annotation, {});
  MDTuple *StrTuple = MDTuple::get(getLLVMContext(), Strings);
  Builder.CreateCall(F, MetadataAsValue::get(getLLVMContext(), StrTuple));
  return RValue::getIgnored();
}
case Builtin::BI__builtin_annotation: {
  llvm::Value *AnnVal = EmitScalarExpr(E->getArg(0));
  llvm::Value *F = CGM.getIntrinsic(llvm::Intrinsic::annotation,
                                    AnnVal->getType());

  // Get the annotation string, go through casts. Sema requires this to be a
  // non-wide string literal, potentially casted, so the cast<> is safe.
  const Expr *AnnotationStrExpr = E->getArg(1)->IgnoreParenCasts();
  StringRef Str = cast<StringLiteral>(AnnotationStrExpr)->getString();
  return RValue::get(EmitAnnotationCall(F, AnnVal, Str, E->getExprLoc()));
}
case Builtin::BI__builtin_addcb:
case Builtin::BI__builtin_addcs:
case Builtin::BI__builtin_addc:
case Builtin::BI__builtin_addcl:
case Builtin::BI__builtin_addcll:
case Builtin::BI__builtin_subcb:
case Builtin::BI__builtin_subcs:
case Builtin::BI__builtin_subc:
case Builtin::BI__builtin_subcl:
case Builtin::BI__builtin_subcll: {

  // We translate all of these builtins from expressions of the form:
  //   int x = ..., y = ..., carryin = ..., carryout, result;
  //   result = __builtin_addc(x, y, carryin, &carryout);
  //
  // to LLVM IR of the form:
  //
  //   %tmp1 = call {i32, i1} @llvm.uadd.with.overflow.i32(i32 %x, i32 %y)
  //   %tmpsum1 = extractvalue {i32, i1} %tmp1, 0
  //   %carry1 = extractvalue {i32, i1} %tmp1, 1
  //   %tmp2 = call {i32, i1} @llvm.uadd.with.overflow.i32(i32 %tmpsum1,
  //                                                       i32 %carryin)
  //   %result = extractvalue {i32, i1} %tmp2, 0
  //   %carry2 = extractvalue {i32, i1} %tmp2, 1
  //   %tmp3 = or i1 %carry1, %carry2
  //   %tmp4 = zext i1 %tmp3 to i32
  //   store i32 %tmp4, i32* %carryout

  // Scalarize our inputs.
  llvm::Value *X = EmitScalarExpr(E->getArg(0));
  llvm::Value *Y = EmitScalarExpr(E->getArg(1));
  llvm::Value *Carryin = EmitScalarExpr(E->getArg(2));
  Address CarryOutPtr = EmitPointerWithAlignment(E->getArg(3));

  // Decide if we are lowering to a uadd.with.overflow or usub.with.overflow.
  llvm::Intrinsic::ID IntrinsicId;
  switch (BuiltinID) {
  default: llvm_unreachable("Unknown multiprecision builtin id.")::llvm::llvm_unreachable_internal("Unknown multiprecision builtin id."
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 2423);
  case Builtin::BI__builtin_addcb:
  case Builtin::BI__builtin_addcs:
  case Builtin::BI__builtin_addc:
  case Builtin::BI__builtin_addcl:
  case Builtin::BI__builtin_addcll:
    IntrinsicId = llvm::Intrinsic::uadd_with_overflow;
    break;
  case Builtin::BI__builtin_subcb:
  case Builtin::BI__builtin_subcs:
  case Builtin::BI__builtin_subc:
  case Builtin::BI__builtin_subcl:
  case Builtin::BI__builtin_subcll:
    IntrinsicId = llvm::Intrinsic::usub_with_overflow;
    break;
  }

  // Construct our resulting LLVM IR expression.
  llvm::Value *Carry1;
  llvm::Value *Sum1 = EmitOverflowIntrinsic(*this, IntrinsicId,
                                            X, Y, Carry1);
  llvm::Value *Carry2;
  llvm::Value *Sum2 = EmitOverflowIntrinsic(*this, IntrinsicId,
                                            Sum1, Carryin, Carry2);
  llvm::Value *CarryOut = Builder.CreateZExt(Builder.CreateOr(Carry1, Carry2),
                                             X->getType());
  Builder.CreateStore(CarryOut, CarryOutPtr);
  return RValue::get(Sum2);
}

case Builtin::BI__builtin_add_overflow:
case Builtin::BI__builtin_sub_overflow:
case Builtin::BI__builtin_mul_overflow: {
  const clang::Expr *LeftArg = E->getArg(0);
  const clang::Expr *RightArg = E->getArg(1);
  const clang::Expr *ResultArg = E->getArg(2);

  clang::QualType ResultQTy =
      ResultArg->getType()->castAs<PointerType>()->getPointeeType();

  WidthAndSignedness LeftInfo =
      getIntegerWidthAndSignedness(CGM.getContext(), LeftArg->getType());
  WidthAndSignedness RightInfo =
      getIntegerWidthAndSignedness(CGM.getContext(), RightArg->getType());
  WidthAndSignedness ResultInfo =
      getIntegerWidthAndSignedness(CGM.getContext(), ResultQTy);

  // Handle mixed-sign multiplication as a special case, because adding
  // runtime or backend support for our generic irgen would be too expensive.
  if (isSpecialMixedSignMultiply(BuiltinID, LeftInfo, RightInfo, ResultInfo))
    return EmitCheckedMixedSignMultiply(*this, LeftArg, LeftInfo, RightArg,
                                        RightInfo, ResultArg, ResultQTy,
                                        ResultInfo);

  WidthAndSignedness EncompassingInfo =
      EncompassingIntegerType({LeftInfo, RightInfo, ResultInfo});

  llvm::Type *EncompassingLLVMTy =
      llvm::IntegerType::get(CGM.getLLVMContext(), EncompassingInfo.Width);

  llvm::Type *ResultLLVMTy = CGM.getTypes().ConvertType(ResultQTy);

  llvm::Intrinsic::ID IntrinsicId;
  switch (BuiltinID) {
  default:
    llvm_unreachable("Unknown overflow builtin id.")::llvm::llvm_unreachable_internal("Unknown overflow builtin id."
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 2488);
  case Builtin::BI__builtin_add_overflow:
    IntrinsicId = EncompassingInfo.Signed
                      ? llvm::Intrinsic::sadd_with_overflow
                      : llvm::Intrinsic::uadd_with_overflow;
    break;
  case Builtin::BI__builtin_sub_overflow:
    IntrinsicId = EncompassingInfo.Signed
                      ? llvm::Intrinsic::ssub_with_overflow
                      : llvm::Intrinsic::usub_with_overflow;
    break;
  case Builtin::BI__builtin_mul_overflow:
    IntrinsicId = EncompassingInfo.Signed
                      ? llvm::Intrinsic::smul_with_overflow
                      : llvm::Intrinsic::umul_with_overflow;
    break;
  }

  llvm::Value *Left = EmitScalarExpr(LeftArg);
  llvm::Value *Right = EmitScalarExpr(RightArg);
  Address ResultPtr = EmitPointerWithAlignment(ResultArg);

  // Extend each operand to the encompassing type.
  Left = Builder.CreateIntCast(Left, EncompassingLLVMTy, LeftInfo.Signed);
  Right = Builder.CreateIntCast(Right, EncompassingLLVMTy, RightInfo.Signed);

  // Perform the operation on the extended values.
  llvm::Value *Overflow, *Result;
  Result = EmitOverflowIntrinsic(*this, IntrinsicId, Left, Right, Overflow);

  if (EncompassingInfo.Width > ResultInfo.Width) {
    // The encompassing type is wider than the result type, so we need to
    // truncate it.
    llvm::Value *ResultTrunc = Builder.CreateTrunc(Result, ResultLLVMTy);

    // To see if the truncation caused an overflow, we will extend
    // the result and then compare it to the original result.
    llvm::Value *ResultTruncExt = Builder.CreateIntCast(
        ResultTrunc, EncompassingLLVMTy, ResultInfo.Signed);
    llvm::Value *TruncationOverflow =
        Builder.CreateICmpNE(Result, ResultTruncExt);

    Overflow = Builder.CreateOr(Overflow, TruncationOverflow);
    Result = ResultTrunc;
  }

  // Finally, store the result using the pointer.
  bool isVolatile =
    ResultArg->getType()->getPointeeType().isVolatileQualified();
  Builder.CreateStore(EmitToMemory(Result, ResultQTy), ResultPtr, isVolatile);

  return RValue::get(Overflow);
}

case Builtin::BI__builtin_uadd_overflow:
case Builtin::BI__builtin_uaddl_overflow:
case Builtin::BI__builtin_uaddll_overflow:
case Builtin::BI__builtin_usub_overflow:
case Builtin::BI__builtin_usubl_overflow:
case Builtin::BI__builtin_usubll_overflow:
case Builtin::BI__builtin_umul_overflow:
case Builtin::BI__builtin_umull_overflow:
case Builtin::BI__builtin_umulll_overflow:
case Builtin::BI__builtin_sadd_overflow:
case Builtin::BI__builtin_saddl_overflow:
case Builtin::BI__builtin_saddll_overflow:
case Builtin::BI__builtin_ssub_overflow:
case Builtin::BI__builtin_ssubl_overflow:
case Builtin::BI__builtin_ssubll_overflow:
case Builtin::BI__builtin_smul_overflow:
case Builtin::BI__builtin_smull_overflow:
case Builtin::BI__builtin_smulll_overflow: {

  // We translate all of these builtins directly to the relevant llvm IR node.

  // Scalarize our inputs.
  llvm::Value *X = EmitScalarExpr(E->getArg(0));
  llvm::Value *Y = EmitScalarExpr(E->getArg(1));
  Address SumOutPtr = EmitPointerWithAlignment(E->getArg(2));

  // Decide which of the overflow intrinsics we are lowering to:
  llvm::Intrinsic::ID IntrinsicId;
  switch (BuiltinID) {
  default: llvm_unreachable("Unknown overflow builtin id.")::llvm::llvm_unreachable_internal("Unknown overflow builtin id."
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 2571);
  case Builtin::BI__builtin_uadd_overflow:
  case Builtin::BI__builtin_uaddl_overflow:
  case Builtin::BI__builtin_uaddll_overflow:
    IntrinsicId = llvm::Intrinsic::uadd_with_overflow;
    break;
  case Builtin::BI__builtin_usub_overflow:
  case Builtin::BI__builtin_usubl_overflow:
  case Builtin::BI__builtin_usubll_overflow:
    IntrinsicId = llvm::Intrinsic::usub_with_overflow;
    break;
  case Builtin::BI__builtin_umul_overflow:
  case Builtin::BI__builtin_umull_overflow:
  case Builtin::BI__builtin_umulll_overflow:
    IntrinsicId = llvm::Intrinsic::umul_with_overflow;
    break;
  case Builtin::BI__builtin_sadd_overflow:
  case Builtin::BI__builtin_saddl_overflow:
  case Builtin::BI__builtin_saddll_overflow:
    IntrinsicId = llvm::Intrinsic::sadd_with_overflow;
    break;
  case Builtin::BI__builtin_ssub_overflow:
  case Builtin::BI__builtin_ssubl_overflow:
  case Builtin::BI__builtin_ssubll_overflow:
    IntrinsicId = llvm::Intrinsic::ssub_with_overflow;
    break;
  case Builtin::BI__builtin_smul_overflow:
  case Builtin::BI__builtin_smull_overflow:
  case Builtin::BI__builtin_smulll_overflow:
    IntrinsicId = llvm::Intrinsic::smul_with_overflow;
    break;
  }


  llvm::Value *Carry;
  llvm::Value *Sum = EmitOverflowIntrinsic(*this, IntrinsicId, X, Y, Carry);
  Builder.CreateStore(Sum, SumOutPtr);

  return RValue::get(Carry);
}
case Builtin::BI__builtin_addressof:
  return RValue::get(EmitLValue(E->getArg(0)).getPointer());
case Builtin::BI__builtin_operator_new:
  return EmitBuiltinNewDeleteCall(FD->getType()->castAs<FunctionProtoType>(),
                                  E->getArg(0), false);
case Builtin::BI__builtin_operator_delete:
  return EmitBuiltinNewDeleteCall(FD->getType()->castAs<FunctionProtoType>(),
                                  E->getArg(0), true);
case Builtin::BI__noop:
  // __noop always evaluates to an integer literal zero.
  return RValue::get(ConstantInt::get(IntTy, 0));
case Builtin::BI__builtin_call_with_static_chain: {
  const CallExpr *Call = cast<CallExpr>(E->getArg(0));
  const Expr *Chain = E->getArg(1);
  return EmitCall(Call->getCallee()->getType(),
                  EmitCallee(Call->getCallee()), Call, ReturnValue,
                  EmitScalarExpr(Chain));
}
case Builtin::BI_InterlockedExchange8:
case Builtin::BI_InterlockedExchange16:
case Builtin::BI_InterlockedExchange:
case Builtin::BI_InterlockedExchangePointer:
  return RValue::get(
      EmitMSVCBuiltinExpr(MSVCIntrin::_InterlockedExchange, E));
case Builtin::BI_InterlockedCompareExchangePointer: {
  llvm::Type *RTy;
  llvm::IntegerType *IntType =
    IntegerType::get(getLLVMContext(),
                     getContext().getTypeSize(E->getType()));
  llvm::Type *IntPtrType = IntType->getPointerTo();

  llvm::Value *Destination =
    Builder.CreateBitCast(EmitScalarExpr(E->getArg(0)), IntPtrType);

  llvm::Value *Exchange = EmitScalarExpr(E->getArg(1));
  RTy = Exchange->getType();
  Exchange = Builder.CreatePtrToInt(Exchange, IntType);

  llvm::Value *Comparand =
    Builder.CreatePtrToInt(EmitScalarExpr(E->getArg(2)), IntType);

  auto Result =
      Builder.CreateAtomicCmpXchg(Destination, Comparand, Exchange,
                                  AtomicOrdering::SequentiallyConsistent,
                                  AtomicOrdering::SequentiallyConsistent);
  Result->setVolatile(true);

  return RValue::get(Builder.CreateIntToPtr(Builder.CreateExtractValue(Result,
                                                                       0),
                                            RTy));
}
case Builtin::BI_InterlockedCompareExchange8:
case Builtin::BI_InterlockedCompareExchange16:
case Builtin::BI_InterlockedCompareExchange:
case Builtin::BI_InterlockedCompareExchange64: {
  AtomicCmpXchgInst *CXI = Builder.CreateAtomicCmpXchg(
      EmitScalarExpr(E->getArg(0)),
      EmitScalarExpr(E->getArg(2)),
      EmitScalarExpr(E->getArg(1)),
      AtomicOrdering::SequentiallyConsistent,
      AtomicOrdering::SequentiallyConsistent);
    CXI->setVolatile(true);
    return RValue::get(Builder.CreateExtractValue(CXI, 0));
}
case Builtin::BI_InterlockedIncrement16:
case Builtin::BI_InterlockedIncrement:
  return RValue::get(
      EmitMSVCBuiltinExpr(MSVCIntrin::_InterlockedIncrement, E));
case Builtin::BI_InterlockedDecrement16:
case Builtin::BI_InterlockedDecrement:
  return RValue::get(
      EmitMSVCBuiltinExpr(MSVCIntrin::_InterlockedDecrement, E));
case Builtin::BI_InterlockedAnd8:
case Builtin::BI_InterlockedAnd16:
case Builtin::BI_InterlockedAnd:
  return RValue::get(EmitMSVCBuiltinExpr(MSVCIntrin::_InterlockedAnd, E));
case Builtin::BI_InterlockedExchangeAdd8:
case Builtin::BI_InterlockedExchangeAdd16:
case Builtin::BI_InterlockedExchangeAdd:
  return RValue::get(
      EmitMSVCBuiltinExpr(MSVCIntrin::_InterlockedExchangeAdd, E));
case Builtin::BI_InterlockedExchangeSub8:
case Builtin::BI_InterlockedExchangeSub16:
case Builtin::BI_InterlockedExchangeSub:
  return RValue::get(
      EmitMSVCBuiltinExpr(MSVCIntrin::_InterlockedExchangeSub, E));
case Builtin::BI_InterlockedOr8:
case Builtin::BI_InterlockedOr16:
case Builtin::BI_InterlockedOr:
  return RValue::get(EmitMSVCBuiltinExpr(MSVCIntrin::_InterlockedOr, E));
case Builtin::BI_InterlockedXor8:
case Builtin::BI_InterlockedXor16:
case Builtin::BI_InterlockedXor:
  return RValue::get(EmitMSVCBuiltinExpr(MSVCIntrin::_InterlockedXor, E));
case Builtin::BI_interlockedbittestandset:
  return RValue::get(
      EmitMSVCBuiltinExpr(MSVCIntrin::_interlockedbittestandset, E));

case Builtin::BI__exception_code:
case Builtin::BI_exception_code:
  return RValue::get(EmitSEHExceptionCode());
case Builtin::BI__exception_info:
case Builtin::BI_exception_info:
  return RValue::get(EmitSEHExceptionInfo());
case Builtin::BI__abnormal_termination:
case Builtin::BI_abnormal_termination:
  return RValue::get(EmitSEHAbnormalTermination());
case Builtin::BI_setjmpex: {
  if (getTarget().getTriple().isOSMSVCRT()) {
    llvm::Type *ArgTypes[] = {Int8PtrTy, Int8PtrTy};
    llvm::AttributeList ReturnsTwiceAttr = llvm::AttributeList::get(
        getLLVMContext(), llvm::AttributeList::FunctionIndex,
        llvm::Attribute::ReturnsTwice);
    llvm::Constant *SetJmpEx = CGM.CreateRuntimeFunction(
        llvm::FunctionType::get(IntTy, ArgTypes, /*isVarArg=*/false),
        "_setjmpex", ReturnsTwiceAttr, /*Local=*/true);
    llvm::Value *Buf = Builder.CreateBitOrPointerCast(
        EmitScalarExpr(E->getArg(0)), Int8PtrTy);
    llvm::Value *FrameAddr =
        Builder.CreateCall(CGM.getIntrinsic(Intrinsic::frameaddress),
                           ConstantInt::get(Int32Ty, 0));
    llvm::Value *Args[] = {Buf, FrameAddr};
    llvm::CallSite CS = EmitRuntimeCallOrInvoke(SetJmpEx, Args);
    CS.setAttributes(ReturnsTwiceAttr);
    return RValue::get(CS.getInstruction());
  }
  break;
}
case Builtin::BI_setjmp: {
  if (getTarget().getTriple().isOSMSVCRT()) {
    llvm::AttributeList ReturnsTwiceAttr = llvm::AttributeList::get(
        getLLVMContext(), llvm::AttributeList::FunctionIndex,
        llvm::Attribute::ReturnsTwice);
    llvm::Value *Buf = Builder.CreateBitOrPointerCast(
        EmitScalarExpr(E->getArg(0)), Int8PtrTy);
    llvm::CallSite CS;
    if (getTarget().getTriple().getArch() == llvm::Triple::x86) {
      llvm::Type *ArgTypes[] = {Int8PtrTy, IntTy};
      llvm::Constant *SetJmp3 = CGM.CreateRuntimeFunction(
          llvm::FunctionType::get(IntTy, ArgTypes, /*isVarArg=*/true),
          "_setjmp3", ReturnsTwiceAttr, /*Local=*/true);
      llvm::Value *Count = ConstantInt::get(IntTy, 0);
      llvm::Value *Args[] = {Buf, Count};
      CS = EmitRuntimeCallOrInvoke(SetJmp3, Args);
    } else {
      llvm::Type *ArgTypes[] = {Int8PtrTy, Int8PtrTy};
      llvm::Constant *SetJmp = CGM.CreateRuntimeFunction(
          llvm::FunctionType::get(IntTy, ArgTypes, /*isVarArg=*/false),
          "_setjmp", ReturnsTwiceAttr, /*Local=*/true);
      llvm::Value *FrameAddr =
          Builder.CreateCall(CGM.getIntrinsic(Intrinsic::frameaddress),
                             ConstantInt::get(Int32Ty, 0));
      llvm::Value *Args[] = {Buf, FrameAddr};
      CS = EmitRuntimeCallOrInvoke(SetJmp, Args);
    }
    CS.setAttributes(ReturnsTwiceAttr);
    return RValue::get(CS.getInstruction());
  }
  break;
}

case Builtin::BI__GetExceptionInfo: {
  if (llvm::GlobalVariable *GV =
          CGM.getCXXABI().getThrowInfo(FD->getParamDecl(0)->getType()))
    return RValue::get(llvm::ConstantExpr::getBitCast(GV, CGM.Int8PtrTy));
  break;
}

case Builtin::BI__fastfail:
  return RValue::get(EmitMSVCBuiltinExpr(MSVCIntrin::__fastfail, E));

case Builtin::BI__builtin_coro_size: {
  auto & Context = getContext();
  auto SizeTy = Context.getSizeType();
  auto T = Builder.getIntNTy(Context.getTypeSize(SizeTy));
  Value *F = CGM.getIntrinsic(Intrinsic::coro_size, T);
  return RValue::get(Builder.CreateCall(F));
}

case Builtin::BI__builtin_coro_id:
  return EmitCoroutineIntrinsic(E, Intrinsic::coro_id);
case Builtin::BI__builtin_coro_promise:
  return EmitCoroutineIntrinsic(E, Intrinsic::coro_promise);
case Builtin::BI__builtin_coro_resume:
  return EmitCoroutineIntrinsic(E, Intrinsic::coro_resume);
case Builtin::BI__builtin_coro_frame:
  return EmitCoroutineIntrinsic(E, Intrinsic::coro_frame);
case Builtin::BI__builtin_coro_free:
  return EmitCoroutineIntrinsic(E, Intrinsic::coro_free);
case Builtin::BI__builtin_coro_destroy:
  return EmitCoroutineIntrinsic(E, Intrinsic::coro_destroy);
case Builtin::BI__builtin_coro_done:
  return EmitCoroutineIntrinsic(E, Intrinsic::coro_done);
case Builtin::BI__builtin_coro_alloc:
  return EmitCoroutineIntrinsic(E, Intrinsic::coro_alloc);
case Builtin::BI__builtin_coro_begin:
  return EmitCoroutineIntrinsic(E, Intrinsic::coro_begin);
case Builtin::BI__builtin_coro_end:
  return EmitCoroutineIntrinsic(E, Intrinsic::coro_end);
case Builtin::BI__builtin_coro_suspend:
  return EmitCoroutineIntrinsic(E, Intrinsic::coro_suspend);
case Builtin::BI__builtin_coro_param:
  return EmitCoroutineIntrinsic(E, Intrinsic::coro_param);

// OpenCL v2.0 s6.13.16.2, Built-in pipe read and write functions
case Builtin::BIread_pipe:
case Builtin::BIwrite_pipe: {
  Value *Arg0 = EmitScalarExpr(E->getArg(0)),
        *Arg1 = EmitScalarExpr(E->getArg(1));
  CGOpenCLRuntime OpenCLRT(CGM);
  Value *PacketSize = OpenCLRT.getPipeElemSize(E->getArg(0));
  Value *PacketAlign = OpenCLRT.getPipeElemAlign(E->getArg(0));

  // Type of the generic packet parameter.
  unsigned GenericAS =
      getContext().getTargetAddressSpace(LangAS::opencl_generic);
  llvm::Type *I8PTy = llvm::PointerType::get(
      llvm::Type::getInt8Ty(getLLVMContext()), GenericAS);

  // Testing which overloaded version we should generate the call for.
  if (2U == E->getNumArgs()) {
    const char *Name = (BuiltinID == Builtin::BIread_pipe) ? "__read_pipe_2"
                                                           : "__write_pipe_2";
    // Creating a generic function type to be able to call with any builtin or
    // user defined type.
    llvm::Type *ArgTys[] = {Arg0->getType(), I8PTy, Int32Ty, Int32Ty};
    llvm::FunctionType *FTy = llvm::FunctionType::get(
        Int32Ty, llvm::ArrayRef<llvm::Type *>(ArgTys), false);
    Value *BCast = Builder.CreatePointerCast(Arg1, I8PTy);
    return RValue::get(
        Builder.CreateCall(CGM.CreateRuntimeFunction(FTy, Name),
                           {Arg0, BCast, PacketSize, PacketAlign}));
  } else {
    assert(4 == E->getNumArgs() &&(static_cast <bool> (4 == E->getNumArgs() &&
 "Illegal number of parameters to pipe function") ? void (0) :
 __assert_fail ("4 == E->getNumArgs() && \"Illegal number of parameters to pipe function\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 2845, __extension__ __PRETTY_FUNCTION__))
           "Illegal number of parameters to pipe function")(static_cast <bool> (4 == E->getNumArgs() &&
 "Illegal number of parameters to pipe function") ? void (0) :
 __assert_fail ("4 == E->getNumArgs() && \"Illegal number of parameters to pipe function\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 2845, __extension__ __PRETTY_FUNCTION__));
    const char *Name = (BuiltinID == Builtin::BIread_pipe) ? "__read_pipe_4"
                                                           : "__write_pipe_4";

    llvm::Type *ArgTys[] = {Arg0->getType(), Arg1->getType(), Int32Ty, I8PTy,
                            Int32Ty, Int32Ty};
    Value *Arg2 = EmitScalarExpr(E->getArg(2)),
          *Arg3 = EmitScalarExpr(E->getArg(3));
    llvm::FunctionType *FTy = llvm::FunctionType::get(
        Int32Ty, llvm::ArrayRef<llvm::Type *>(ArgTys), false);
    Value *BCast = Builder.CreatePointerCast(Arg3, I8PTy);
    // We know the third argument is an integer type, but we may need to cast
    // it to i32.
    if (Arg2->getType() != Int32Ty)
      Arg2 = Builder.CreateZExtOrTrunc(Arg2, Int32Ty);
    return RValue::get(Builder.CreateCall(
        CGM.CreateRuntimeFunction(FTy, Name),
        {Arg0, Arg1, Arg2, BCast, PacketSize, PacketAlign}));
  }
}
// OpenCL v2.0 s6.13.16 ,s9.17.3.5 - Built-in pipe reserve read and write
// functions
case Builtin::BIreserve_read_pipe:
case Builtin::BIreserve_write_pipe:
case Builtin::BIwork_group_reserve_read_pipe:
case Builtin::BIwork_group_reserve_write_pipe:
case Builtin::BIsub_group_reserve_read_pipe:
case Builtin::BIsub_group_reserve_write_pipe: {
  // Composing the mangled name for the function.
  const char *Name;
  if (BuiltinID == Builtin::BIreserve_read_pipe)
    Name = "__reserve_read_pipe";
  else if (BuiltinID == Builtin::BIreserve_write_pipe)
    Name = "__reserve_write_pipe";
  else if (BuiltinID == Builtin::BIwork_group_reserve_read_pipe)
    Name = "__work_group_reserve_read_pipe";
  else if (BuiltinID == Builtin::BIwork_group_reserve_write_pipe)
    Name = "__work_group_reserve_write_pipe";
  else if (BuiltinID == Builtin::BIsub_group_reserve_read_pipe)
    Name = "__sub_group_reserve_read_pipe";
  else
    Name = "__sub_group_reserve_write_pipe";

  Value *Arg0 = EmitScalarExpr(E->getArg(0)),
        *Arg1 = EmitScalarExpr(E->getArg(1));
  llvm::Type *ReservedIDTy = ConvertType(getContext().OCLReserveIDTy);
  CGOpenCLRuntime OpenCLRT(CGM);
  Value *PacketSize = OpenCLRT.getPipeElemSize(E->getArg(0));
  Value *PacketAlign = OpenCLRT.getPipeElemAlign(E->getArg(0));

  // Building the generic function prototype.
  llvm::Type *ArgTys[] = {Arg0->getType(), Int32Ty, Int32Ty, Int32Ty};
  llvm::FunctionType *FTy = llvm::FunctionType::get(
      ReservedIDTy, llvm::ArrayRef<llvm::Type *>(ArgTys), false);
  // We know the second argument is an integer type, but we may need to cast
  // it to i32.
  if (Arg1->getType() != Int32Ty)
    Arg1 = Builder.CreateZExtOrTrunc(Arg1, Int32Ty);
  return RValue::get(
      Builder.CreateCall(CGM.CreateRuntimeFunction(FTy, Name),
                         {Arg0, Arg1, PacketSize, PacketAlign}));
}
// OpenCL v2.0 s6.13.16, s9.17.3.5 - Built-in pipe commit read and write
// functions
case Builtin::BIcommit_read_pipe:
case Builtin::BIcommit_write_pipe:
case Builtin::BIwork_group_commit_read_pipe:
case Builtin::BIwork_group_commit_write_pipe:
case Builtin::BIsub_group_commit_read_pipe:
case Builtin::BIsub_group_commit_write_pipe: {
  const char *Name;
  if (BuiltinID == Builtin::BIcommit_read_pipe)
    Name = "__commit_read_pipe";
  else if (BuiltinID == Builtin::BIcommit_write_pipe)
    Name = "__commit_write_pipe";
  else if (BuiltinID == Builtin::BIwork_group_commit_read_pipe)
    Name = "__work_group_commit_read_pipe";
  else if (BuiltinID == Builtin::BIwork_group_commit_write_pipe)
    Name = "__work_group_commit_write_pipe";
  else if (BuiltinID == Builtin::BIsub_group_commit_read_pipe)
    Name = "__sub_group_commit_read_pipe";
  else
    Name = "__sub_group_commit_write_pipe";

  Value *Arg0 = EmitScalarExpr(E->getArg(0)),
        *Arg1 = EmitScalarExpr(E->getArg(1));
  CGOpenCLRuntime OpenCLRT(CGM);
  Value *PacketSize = OpenCLRT.getPipeElemSize(E->getArg(0));
  Value *PacketAlign = OpenCLRT.getPipeElemAlign(E->getArg(0));

  // Building the generic function prototype.
  llvm::Type *ArgTys[] = {Arg0->getType(), Arg1->getType(), Int32Ty, Int32Ty};
  llvm::FunctionType *FTy =
      llvm::FunctionType::get(llvm::Type::getVoidTy(getLLVMContext()),
                              llvm::ArrayRef<llvm::Type *>(ArgTys), false);

  return RValue::get(
      Builder.CreateCall(CGM.CreateRuntimeFunction(FTy, Name),
                         {Arg0, Arg1, PacketSize, PacketAlign}));
}
// OpenCL v2.0 s6.13.16.4 Built-in pipe query functions
case Builtin::BIget_pipe_num_packets:
case Builtin::BIget_pipe_max_packets: {
  const char *Name;
  if (BuiltinID == Builtin::BIget_pipe_num_packets)
    Name = "__get_pipe_num_packets";
  else
    Name = "__get_pipe_max_packets";

  // Building the generic function prototype.
  Value *Arg0 = EmitScalarExpr(E->getArg(0));
  CGOpenCLRuntime OpenCLRT(CGM);
  Value *PacketSize = OpenCLRT.getPipeElemSize(E->getArg(0));
  Value *PacketAlign = OpenCLRT.getPipeElemAlign(E->getArg(0));
  llvm::Type *ArgTys[] = {Arg0->getType(), Int32Ty, Int32Ty};
  llvm::FunctionType *FTy = llvm::FunctionType::get(
      Int32Ty, llvm::ArrayRef<llvm::Type *>(ArgTys), false);

  return RValue::get(Builder.CreateCall(CGM.CreateRuntimeFunction(FTy, Name),
                                        {Arg0, PacketSize, PacketAlign}));
}

// OpenCL v2.0 s6.13.9 - Address space qualifier functions.
case Builtin::BIto_global:
case Builtin::BIto_local:
case Builtin::BIto_private: {
  auto Arg0 = EmitScalarExpr(E->getArg(0));
  auto NewArgT = llvm::PointerType::get(Int8Ty,
    CGM.getContext().getTargetAddressSpace(LangAS::opencl_generic));
  auto NewRetT = llvm::PointerType::get(Int8Ty,
    CGM.getContext().getTargetAddressSpace(
      E->getType()->getPointeeType().getAddressSpace()));
  auto FTy = llvm::FunctionType::get(NewRetT, {NewArgT}, false);
  llvm::Value *NewArg;
  if (Arg0->getType()->getPointerAddressSpace() !=
      NewArgT->getPointerAddressSpace())
    NewArg = Builder.CreateAddrSpaceCast(Arg0, NewArgT);
  else
    NewArg = Builder.CreateBitOrPointerCast(Arg0, NewArgT);
  auto NewName = std::string("__") + E->getDirectCallee()->getName().str();
  auto NewCall =
      Builder.CreateCall(CGM.CreateRuntimeFunction(FTy, NewName), {NewArg});
  return RValue::get(Builder.CreateBitOrPointerCast(NewCall,
    ConvertType(E->getType())));
}

// OpenCL v2.0, s6.13.17 - Enqueue kernel function.
// It contains four different overload formats specified in Table 6.13.17.1.
case Builtin::BIenqueue_kernel: {
  StringRef Name; // Generated function call name
  unsigned NumArgs = E->getNumArgs();

  llvm::Type *QueueTy = ConvertType(getContext().OCLQueueTy);
  llvm::Type *GenericVoidPtrTy = Builder.getInt8PtrTy(
      getContext().getTargetAddressSpace(LangAS::opencl_generic));

  llvm::Value *Queue = EmitScalarExpr(E->getArg(0));
  llvm::Value *Flags = EmitScalarExpr(E->getArg(1));
  LValue NDRangeL = EmitAggExprToLValue(E->getArg(2));
  llvm::Value *Range = NDRangeL.getAddress().getPointer();
  llvm::Type *RangeTy = NDRangeL.getAddress().getType();

  if (NumArgs == 4) {
    // The most basic form of the call with parameters:
    // queue_t, kernel_enqueue_flags_t, ndrange_t, block(void)
    Name = "__enqueue_kernel_basic";
    llvm::Type *ArgTys[] = {QueueTy, Int32Ty, RangeTy, GenericVoidPtrTy,
                            GenericVoidPtrTy};
    llvm::FunctionType *FTy = llvm::FunctionType::get(
        Int32Ty, llvm::ArrayRef<llvm::Type *>(ArgTys), false);

    auto Info =
        CGM.getOpenCLRuntime().emitOpenCLEnqueuedBlock(*this, E->getArg(3));
    llvm::Value *Kernel =
        Builder.CreatePointerCast(Info.Kernel, GenericVoidPtrTy);
    llvm::Value *Block =
        Builder.CreatePointerCast(Info.BlockArg, GenericVoidPtrTy);

    AttrBuilder B;
    B.addAttribute(Attribute::ByVal);
    llvm::AttributeList ByValAttrSet =
        llvm::AttributeList::get(CGM.getModule().getContext(), 3U, B);

    auto RTCall =
        Builder.CreateCall(CGM.CreateRuntimeFunction(FTy, Name, ByValAttrSet),
                           {Queue, Flags, Range, Kernel, Block});
    RTCall->setAttributes(ByValAttrSet);
    return RValue::get(RTCall);
  }
  assert(NumArgs >= 5 && "Invalid enqueue_kernel signature")(static_cast <bool> (NumArgs >= 5 && "Invalid enqueue_kernel signature"
) ? void (0) : __assert_fail ("NumArgs >= 5 && \"Invalid enqueue_kernel signature\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 3034, __extension__ __PRETTY_FUNCTION__));

  // Create a temporary array to hold the sizes of local pointer arguments
  // for the block. \p First is the position of the first size argument.
  auto CreateArrayForSizeVar = [=](unsigned First) {
    auto *AT = llvm::ArrayType::get(SizeTy, NumArgs - First);
    auto *Arr = Builder.CreateAlloca(AT);
    llvm::Value *Ptr;
    // Each of the following arguments specifies the size of the corresponding
    // argument passed to the enqueued block.
    auto *Zero = llvm::ConstantInt::get(IntTy, 0);
    for (unsigned I = First; I < NumArgs; ++I) {
      auto *Index = llvm::ConstantInt::get(IntTy, I - First);
      auto *GEP = Builder.CreateGEP(Arr, {Zero, Index});
      if (I == First)
        Ptr = GEP;
      auto *V =
          Builder.CreateZExtOrTrunc(EmitScalarExpr(E->getArg(I)), SizeTy);
      Builder.CreateAlignedStore(
          V, GEP, CGM.getDataLayout().getPrefTypeAlignment(SizeTy));
    }
    return Ptr;
  };

  // Could have events and/or vaargs.
  if (E->getArg(3)->getType()->isBlockPointerType()) {
    // No events passed, but has variadic arguments.
    Name = "__enqueue_kernel_vaargs";
    auto Info =
        CGM.getOpenCLRuntime().emitOpenCLEnqueuedBlock(*this, E->getArg(3));
    llvm::Value *Kernel =
        Builder.CreatePointerCast(Info.Kernel, GenericVoidPtrTy);
    auto *Block = Builder.CreatePointerCast(Info.BlockArg, GenericVoidPtrTy);
    auto *PtrToSizeArray = CreateArrayForSizeVar(4);

    // Create a vector of the arguments, as well as a constant value to
    // express to the runtime the number of variadic arguments.
    std::vector<llvm::Value *> Args = {
        Queue,  Flags, Range,
        Kernel, Block, ConstantInt::get(IntTy, NumArgs - 4),
        PtrToSizeArray};
    std::vector<llvm::Type *> ArgTys = {
        QueueTy,          IntTy,            RangeTy,
        GenericVoidPtrTy, GenericVoidPtrTy, IntTy,
        PtrToSizeArray->getType()};

    llvm::FunctionType *FTy = llvm::FunctionType::get(
        Int32Ty, llvm::ArrayRef<llvm::Type *>(ArgTys), false);
    return RValue::get(
        Builder.CreateCall(CGM.CreateRuntimeFunction(FTy, Name),
                           llvm::ArrayRef<llvm::Value *>(Args)));
  }
  // Any calls now have event arguments passed.
  if (NumArgs >= 7) {
    llvm::Type *EventTy = ConvertType(getContext().OCLClkEventTy);
    llvm::Type *EventPtrTy = EventTy->getPointerTo(
        CGM.getContext().getTargetAddressSpace(LangAS::opencl_generic));

    llvm::Value *NumEvents =
        Builder.CreateZExtOrTrunc(EmitScalarExpr(E->getArg(3)), Int32Ty);
    llvm::Value *EventList =
        E->getArg(4)->getType()->isArrayType()
            ? EmitArrayToPointerDecay(E->getArg(4)).getPointer()
            : EmitScalarExpr(E->getArg(4));
    llvm::Value *ClkEvent = EmitScalarExpr(E->getArg(5));
    // Convert to generic address space.
    EventList = Builder.CreatePointerCast(EventList, EventPtrTy);
    ClkEvent = Builder.CreatePointerCast(ClkEvent, EventPtrTy);
    auto Info =
        CGM.getOpenCLRuntime().emitOpenCLEnqueuedBlock(*this, E->getArg(6));
    llvm::Value *Kernel =
        Builder.CreatePointerCast(Info.Kernel, GenericVoidPtrTy);
    llvm::Value *Block =
        Builder.CreatePointerCast(Info.BlockArg, GenericVoidPtrTy);

    std::vector<llvm::Type *> ArgTys = {
        QueueTy,    Int32Ty,    RangeTy,          Int32Ty,
        EventPtrTy, EventPtrTy, GenericVoidPtrTy, GenericVoidPtrTy};

    std::vector<llvm::Value *> Args = {Queue,     Flags,    Range,  NumEvents,
                                       EventList, ClkEvent, Kernel, Block};

    if (NumArgs == 7) {
      // Has events but no variadics.
      Name = "__enqueue_kernel_basic_events";
      llvm::FunctionType *FTy = llvm::FunctionType::get(
          Int32Ty, llvm::ArrayRef<llvm::Type *>(ArgTys), false);
      return RValue::get(
          Builder.CreateCall(CGM.CreateRuntimeFunction(FTy, Name),
                             llvm::ArrayRef<llvm::Value *>(Args)));
    }
    // Has event info and variadics
    // Pass the number of variadics to the runtime function too.
    Args.push_back(ConstantInt::get(Int32Ty, NumArgs - 7));
    ArgTys.push_back(Int32Ty);
    Name = "__enqueue_kernel_events_vaargs";

    auto *PtrToSizeArray = CreateArrayForSizeVar(7);
    Args.push_back(PtrToSizeArray);
    ArgTys.push_back(PtrToSizeArray->getType());

    llvm::FunctionType *FTy = llvm::FunctionType::get(
        Int32Ty, llvm::ArrayRef<llvm::Type *>(ArgTys), false);
    return RValue::get(
        Builder.CreateCall(CGM.CreateRuntimeFunction(FTy, Name),
                           llvm::ArrayRef<llvm::Value *>(Args)));
  }
  LLVM_FALLTHROUGH[[clang::fallthrough]];
}
// OpenCL v2.0 s6.13.17.6 - Kernel query functions need bitcast of block
// parameter.
case Builtin::BIget_kernel_work_group_size: {
  llvm::Type *GenericVoidPtrTy = Builder.getInt8PtrTy(
      getContext().getTargetAddressSpace(LangAS::opencl_generic));
  auto Info =
      CGM.getOpenCLRuntime().emitOpenCLEnqueuedBlock(*this, E->getArg(0));
  Value *Kernel = Builder.CreatePointerCast(Info.Kernel, GenericVoidPtrTy);
  Value *Arg = Builder.CreatePointerCast(Info.BlockArg, GenericVoidPtrTy);
  return RValue::get(Builder.CreateCall(
      CGM.CreateRuntimeFunction(
          llvm::FunctionType::get(IntTy, {GenericVoidPtrTy, GenericVoidPtrTy},
                                  false),
          "__get_kernel_work_group_size_impl"),
      {Kernel, Arg}));
}
case Builtin::BIget_kernel_preferred_work_group_size_multiple: {
  llvm::Type *GenericVoidPtrTy = Builder.getInt8PtrTy(
      getContext().getTargetAddressSpace(LangAS::opencl_generic));
  auto Info =
      CGM.getOpenCLRuntime().emitOpenCLEnqueuedBlock(*this, E->getArg(0));
  Value *Kernel = Builder.CreatePointerCast(Info.Kernel, GenericVoidPtrTy);
  Value *Arg = Builder.CreatePointerCast(Info.BlockArg, GenericVoidPtrTy);
  return RValue::get(Builder.CreateCall(
      CGM.CreateRuntimeFunction(
          llvm::FunctionType::get(IntTy, {GenericVoidPtrTy, GenericVoidPtrTy},
                                  false),
          "__get_kernel_preferred_work_group_multiple_impl"),
      {Kernel, Arg}));
}
case Builtin::BIget_kernel_max_sub_group_size_for_ndrange:
case Builtin::BIget_kernel_sub_group_count_for_ndrange: {
  llvm::Type *GenericVoidPtrTy = Builder.getInt8PtrTy(
      getContext().getTargetAddressSpace(LangAS::opencl_generic));
  LValue NDRangeL = EmitAggExprToLValue(E->getArg(0));
  llvm::Value *NDRange = NDRangeL.getAddress().getPointer();
  auto Info =
      CGM.getOpenCLRuntime().emitOpenCLEnqueuedBlock(*this, E->getArg(1));
  Value *Kernel = Builder.CreatePointerCast(Info.Kernel, GenericVoidPtrTy);
  Value *Block = Builder.CreatePointerCast(Info.BlockArg, GenericVoidPtrTy);
  const char *Name =
      BuiltinID == Builtin::BIget_kernel_max_sub_group_size_for_ndrange
          ? "__get_kernel_max_sub_group_size_for_ndrange_impl"
          : "__get_kernel_sub_group_count_for_ndrange_impl";
  return RValue::get(Builder.CreateCall(
      CGM.CreateRuntimeFunction(
          llvm::FunctionType::get(
              IntTy, {NDRange->getType(), GenericVoidPtrTy, GenericVoidPtrTy},
              false),
          Name),
      {NDRange, Kernel, Block}));
}

case Builtin::BI__builtin_store_half:
case Builtin::BI__builtin_store_halff: {
  Value *Val = EmitScalarExpr(E->getArg(0));
  Address Address = EmitPointerWithAlignment(E->getArg(1));
  Value *HalfVal = Builder.CreateFPTrunc(Val, Builder.getHalfTy());
  return RValue::get(Builder.CreateStore(HalfVal, Address));
}
case Builtin::BI__builtin_load_half: {
  Address Address = EmitPointerWithAlignment(E->getArg(0));
  Value *HalfVal = Builder.CreateLoad(Address);
  return RValue::get(Builder.CreateFPExt(HalfVal, Builder.getDoubleTy()));
}
case Builtin::BI__builtin_load_halff: {
  Address Address = EmitPointerWithAlignment(E->getArg(0));
  Value *HalfVal = Builder.CreateLoad(Address);
  return RValue::get(Builder.CreateFPExt(HalfVal, Builder.getFloatTy()));
}
case Builtin::BIprintf:
  if (getTarget().getTriple().isNVPTX())
    return EmitNVPTXDevicePrintfCallExpr(E, ReturnValue);
  break;
case Builtin::BI__builtin_canonicalize:
case Builtin::BI__builtin_canonicalizef:
case Builtin::BI__builtin_canonicalizel:
  return RValue::get(emitUnaryBuiltin(*this, E, Intrinsic::canonicalize));

case Builtin::BI__builtin_thread_pointer: {
  if (!getContext().getTargetInfo().isTLSSupported())
    CGM.ErrorUnsupported(E, "__builtin_thread_pointer");
  // Fall through - it's already mapped to the intrinsic by GCCBuiltin.
  break;
}
case Builtin::BI__builtin_os_log_format:
  return emitBuiltinOSLogFormat(*E);

case Builtin::BI__builtin_os_log_format_buffer_size: {
  analyze_os_log::OSLogBufferLayout Layout;
  analyze_os_log::computeOSLogBufferLayout(CGM.getContext(), E, Layout);
  return RValue::get(ConstantInt::get(ConvertType(E->getType()),
                                      Layout.size().getQuantity()));
}

case Builtin::BI__xray_customevent: {
  if (!ShouldXRayInstrumentFunction())
    return RValue::getIgnored();
  if (const auto *XRayAttr = CurFuncDecl->getAttr<XRayInstrumentAttr>())
    if (XRayAttr->neverXRayInstrument() && !AlwaysEmitXRayCustomEvents())
      return RValue::getIgnored();

  Function *F = CGM.getIntrinsic(Intrinsic::xray_customevent);
  auto FTy = F->getFunctionType();
  auto Arg0 = E->getArg(0);
  auto Arg0Val = EmitScalarExpr(Arg0);
  auto Arg0Ty = Arg0->getType();
  auto PTy0 = FTy->getParamType(0);
  if (PTy0 != Arg0Val->getType()) {
    if (Arg0Ty->isArrayType())
      Arg0Val = EmitArrayToPointerDecay(Arg0).getPointer();
    else
      Arg0Val = Builder.CreatePointerCast(Arg0Val, PTy0);
  }
  auto Arg1 = EmitScalarExpr(E->getArg(1));
  auto PTy1 = FTy->getParamType(1);
  if (PTy1 != Arg1->getType())
    Arg1 = Builder.CreateTruncOrBitCast(Arg1, PTy1);
  return RValue::get(Builder.CreateCall(F, {Arg0Val, Arg1}));
}

case Builtin::BI__builtin_ms_va_start:
case Builtin::BI__builtin_ms_va_end:
  return RValue::get(
      EmitVAStartEnd(EmitMSVAListRef(E->getArg(0)).getPointer(),
                     BuiltinID == Builtin::BI__builtin_ms_va_start));

case Builtin::BI__builtin_ms_va_copy: {
  // Lower this manually. We can't reliably determine whether or not any
  // given va_copy() is for a Win64 va_list from the calling convention
  // alone, because it's legal to do this from a System V ABI function.
  // With opaque pointer types, we won't have enough information in LLVM
  // IR to determine this from the argument types, either. Best to do it
  // now, while we have enough information.
  Address DestAddr = EmitMSVAListRef(E->getArg(0));
  Address SrcAddr = EmitMSVAListRef(E->getArg(1));

  llvm::Type *BPP = Int8PtrPtrTy;

  DestAddr = Address(Builder.CreateBitCast(DestAddr.getPointer(), BPP, "cp"),
                     DestAddr.getAlignment());
  SrcAddr = Address(Builder.CreateBitCast(SrcAddr.getPointer(), BPP, "ap"),
                    SrcAddr.getAlignment());

  Value *ArgPtr = Builder.CreateLoad(SrcAddr, "ap.val");
  return RValue::get(Builder.CreateStore(ArgPtr, DestAddr));
}
}

// If this is an alias for a lib function (e.g. __builtin_sin), emit
// the call using the normal call path, but using the unmangled
// version of the function name.
if (getContext().BuiltinInfo.isLibFunction(BuiltinID))
  return emitLibraryCall(*this, FD, E,
                         CGM.getBuiltinLibFunction(FD, BuiltinID));

// If this is a predefined lib function (e.g. malloc), emit the call
// using exactly the normal call path.
if (getContext().BuiltinInfo.isPredefinedLibFunction(BuiltinID))
  return emitLibraryCall(*this, FD, E,
                    cast<llvm::Constant>(EmitScalarExpr(E->getCallee())));

// Check that a call to a target specific builtin has the correct target
// features.
// This is down here to avoid non-target specific builtins, however, if
// generic builtins start to require generic target features then we
// can move this up to the beginning of the function.
checkTargetFeatures(E, FD);

// See if we have a target specific intrinsic.
const char *Name = getContext().BuiltinInfo.getName(BuiltinID);
Intrinsic::ID IntrinsicID = Intrinsic::not_intrinsic;
StringRef Prefix =
    llvm::Triple::getArchTypePrefix(getTarget().getTriple().getArch());
if (!Prefix.empty()) {
  IntrinsicID = Intrinsic::getIntrinsicForGCCBuiltin(Prefix.data(), Name);
  // NOTE we dont need to perform a compatibility flag check here since the
  // intrinsics are declared in Builtins*.def via LANGBUILTIN which filter the
  // MS builtins via ALL_MS_LANGUAGES and are filtered earlier.
  if (IntrinsicID == Intrinsic::not_intrinsic)
    IntrinsicID = Intrinsic::getIntrinsicForMSBuiltin(Prefix.data(), Name);
}

if (IntrinsicID != Intrinsic::not_intrinsic) {
  SmallVector<Value*, 16> Args;

  // Find out if any arguments are required to be integer constant
  // expressions.
  unsigned ICEArguments = 0;
  ASTContext::GetBuiltinTypeError Error;
  getContext().GetBuiltinType(BuiltinID, Error, &ICEArguments);
  assert(Error == ASTContext::GE_None && "Should not codegen an error")(static_cast <bool> (Error == ASTContext::GE_None &&
 "Should not codegen an error") ? void (0) : __assert_fail ("Error == ASTContext::GE_None && \"Should not codegen an error\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 3334, __extension__ __PRETTY_FUNCTION__));

  Function *F = CGM.getIntrinsic(IntrinsicID);
  llvm::FunctionType *FTy = F->getFunctionType();

  for (unsigned i = 0, e = E->getNumArgs(); i != e; ++i) {
    Value *ArgValue;
    // If this is a normal argument, just emit it as a scalar.
    if ((ICEArguments & (1 << i)) == 0) {
      ArgValue = EmitScalarExpr(E->getArg(i));
    } else {
      // If this is required to be a constant, constant fold it so that we
      // know that the generated intrinsic gets a ConstantInt.
      llvm::APSInt Result;
      bool IsConst = E->getArg(i)->isIntegerConstantExpr(Result,getContext());
      assert(IsConst && "Constant arg isn't actually constant?")(static_cast <bool> (IsConst && "Constant arg isn't actually constant?"
) ? void (0) : __assert_fail ("IsConst && \"Constant arg isn't actually constant?\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 3349, __extension__ __PRETTY_FUNCTION__));
      (void)IsConst;
      ArgValue = llvm::ConstantInt::get(getLLVMContext(), Result);
    }

    // If the intrinsic arg type is different from the builtin arg type
    // we need to do a bit cast.
    llvm::Type *PTy = FTy->getParamType(i);
    if (PTy != ArgValue->getType()) {
      assert(PTy->canLosslesslyBitCastTo(FTy->getParamType(i)) &&(static_cast <bool> (PTy->canLosslesslyBitCastTo(FTy
->getParamType(i)) && "Must be able to losslessly bit cast to param"
) ? void (0) : __assert_fail ("PTy->canLosslesslyBitCastTo(FTy->getParamType(i)) && \"Must be able to losslessly bit cast to param\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 3359, __extension__ __PRETTY_FUNCTION__))
             "Must be able to losslessly bit cast to param")(static_cast <bool> (PTy->canLosslesslyBitCastTo(FTy
->getParamType(i)) && "Must be able to losslessly bit cast to param"
) ? void (0) : __assert_fail ("PTy->canLosslesslyBitCastTo(FTy->getParamType(i)) && \"Must be able to losslessly bit cast to param\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 3359, __extension__ __PRETTY_FUNCTION__));
      ArgValue = Builder.CreateBitCast(ArgValue, PTy);
    }

    Args.push_back(ArgValue);
  }

  Value *V = Builder.CreateCall(F, Args);
  QualType BuiltinRetType = E->getType();

  llvm::Type *RetTy = VoidTy;
  if (!BuiltinRetType->isVoidType())
    RetTy = ConvertType(BuiltinRetType);

  if (RetTy != V->getType()) {
    assert(V->getType()->canLosslesslyBitCastTo(RetTy) &&(static_cast <bool> (V->getType()->canLosslesslyBitCastTo
(RetTy) && "Must be able to losslessly bit cast result type"
) ? void (0) : __assert_fail ("V->getType()->canLosslesslyBitCastTo(RetTy) && \"Must be able to losslessly bit cast result type\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 3375, __extension__ __PRETTY_FUNCTION__))
           "Must be able to losslessly bit cast result type")(static_cast <bool> (V->getType()->canLosslesslyBitCastTo
(RetTy) && "Must be able to losslessly bit cast result type"
) ? void (0) : __assert_fail ("V->getType()->canLosslesslyBitCastTo(RetTy) && \"Must be able to losslessly bit cast result type\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 3375, __extension__ __PRETTY_FUNCTION__));
    V = Builder.CreateBitCast(V, RetTy);
  }

  return RValue::get(V);
}

// See if we have a target specific builtin that needs to be lowered.
if (Value *V = EmitTargetBuiltinExpr(BuiltinID, E))
  return RValue::get(V);

ErrorUnsupported(E, "builtin function");

// Unknown builtin, for now just dump it out and return undef.
return GetUndefRValue(E->getType());
3390}

3392static Value *EmitTargetArchBuiltinExpr(CodeGenFunction *CGF,
                                      unsigned BuiltinID, const CallExpr *E,
                                      llvm::Triple::ArchType Arch) {
switch (Arch) {
case llvm::Triple::arm:
case llvm::Triple::armeb:
case llvm::Triple::thumb:
case llvm::Triple::thumbeb:
  return CGF->EmitARMBuiltinExpr(BuiltinID, E, Arch);
case llvm::Triple::aarch64:
case llvm::Triple::aarch64_be:
  return CGF->EmitAArch64BuiltinExpr(BuiltinID, E, Arch);
case llvm::Triple::x86:
case llvm::Triple::x86_64:
  return CGF->EmitX86BuiltinExpr(BuiltinID, E);
case llvm::Triple::ppc:
case llvm::Triple::ppc64:
case llvm::Triple::ppc64le:
  return CGF->EmitPPCBuiltinExpr(BuiltinID, E);
case llvm::Triple::r600:
case llvm::Triple::amdgcn:
  return CGF->EmitAMDGPUBuiltinExpr(BuiltinID, E);
case llvm::Triple::systemz:
  return CGF->EmitSystemZBuiltinExpr(BuiltinID, E);
case llvm::Triple::nvptx:
case llvm::Triple::nvptx64:
  return CGF->EmitNVPTXBuiltinExpr(BuiltinID, E);
case llvm::Triple::wasm32:
case llvm::Triple::wasm64:
  return CGF->EmitWebAssemblyBuiltinExpr(BuiltinID, E);
case llvm::Triple::hexagon:
  return CGF->EmitHexagonBuiltinExpr(BuiltinID, E);
default:
  return nullptr;
}
3427}

3429Value *CodeGenFunction::EmitTargetBuiltinExpr(unsigned BuiltinID,
                                            const CallExpr *E) {
if (getContext().BuiltinInfo.isAuxBuiltinID(BuiltinID)) {
  assert(getContext().getAuxTargetInfo() && "Missing aux target info")(static_cast <bool> (getContext().getAuxTargetInfo() &&
 "Missing aux target info") ? void (0) : __assert_fail ("getContext().getAuxTargetInfo() && \"Missing aux target info\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 3432, __extension__ __PRETTY_FUNCTION__));
  return EmitTargetArchBuiltinExpr(
      this, getContext().BuiltinInfo.getAuxBuiltinID(BuiltinID), E,
      getContext().getAuxTargetInfo()->getTriple().getArch());
}

return EmitTargetArchBuiltinExpr(this, BuiltinID, E,
                                 getTarget().getTriple().getArch());
3440}

3442static llvm::VectorType *GetNeonType(CodeGenFunction *CGF,
                                   NeonTypeFlags TypeFlags,
                                   llvm::Triple::ArchType Arch,
                                   bool V1Ty=false) {
int IsQuad = TypeFlags.isQuad();
switch (TypeFlags.getEltType()) {
case NeonTypeFlags::Int8:
case NeonTypeFlags::Poly8:
  return llvm::VectorType::get(CGF->Int8Ty, V1Ty ? 1 : (8 << IsQuad));
case NeonTypeFlags::Int16:
case NeonTypeFlags::Poly16:
  return llvm::VectorType::get(CGF->Int16Ty, V1Ty ? 1 : (4 << IsQuad));
case NeonTypeFlags::Float16:
  // FIXME: Only AArch64 backend can so far properly handle half types.
  // Remove else part once ARM backend support for half is complete.
  if (Arch == llvm::Triple::aarch64)
    return llvm::VectorType::get(CGF->HalfTy, V1Ty ? 1 : (4 << IsQuad));
  else
    return llvm::VectorType::get(CGF->Int16Ty, V1Ty ? 1 : (4 << IsQuad));
case NeonTypeFlags::Int32:
  return llvm::VectorType::get(CGF->Int32Ty, V1Ty ? 1 : (2 << IsQuad));
case NeonTypeFlags::Int64:
case NeonTypeFlags::Poly64:
  return llvm::VectorType::get(CGF->Int64Ty, V1Ty ? 1 : (1 << IsQuad));
case NeonTypeFlags::Poly128:
  // FIXME: i128 and f128 doesn't get fully support in Clang and llvm.
  // There is a lot of i128 and f128 API missing.
  // so we use v16i8 to represent poly128 and get pattern matched.
  return llvm::VectorType::get(CGF->Int8Ty, 16);
case NeonTypeFlags::Float32:
  return llvm::VectorType::get(CGF->FloatTy, V1Ty ? 1 : (2 << IsQuad));
case NeonTypeFlags::Float64:
  return llvm::VectorType::get(CGF->DoubleTy, V1Ty ? 1 : (1 << IsQuad));
}
llvm_unreachable("Unknown vector element type!")::llvm::llvm_unreachable_internal("Unknown vector element type!"
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 3476);
3477}

3479static llvm::VectorType *GetFloatNeonType(CodeGenFunction *CGF,
                                        NeonTypeFlags IntTypeFlags) {
int IsQuad = IntTypeFlags.isQuad();
switch (IntTypeFlags.getEltType()) {
case NeonTypeFlags::Int16:
  return llvm::VectorType::get(CGF->HalfTy, (4 << IsQuad));
case NeonTypeFlags::Int32:
  return llvm::VectorType::get(CGF->FloatTy, (2 << IsQuad));
case NeonTypeFlags::Int64:
  return llvm::VectorType::get(CGF->DoubleTy, (1 << IsQuad));
default:
  llvm_unreachable("Type can't be converted to floating-point!")::llvm::llvm_unreachable_internal("Type can't be converted to floating-point!"
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 3490);
}
3492}

3494Value *CodeGenFunction::EmitNeonSplat(Value *V, Constant *C) {
unsigned nElts = V->getType()->getVectorNumElements();
Value* SV = llvm::ConstantVector::getSplat(nElts, C);
return Builder.CreateShuffleVector(V, V, SV, "lane");
3498}

3500Value *CodeGenFunction::EmitNeonCall(Function *F, SmallVectorImpl<Value*> &Ops,
                                   const char *name,
                                   unsigned shift, bool rightshift) {
unsigned j = 0;
for (Function::const_arg_iterator ai = F->arg_begin(), ae = F->arg_end();
     ai != ae; ++ai, ++j)
  if (shift > 0 && shift == j)
    Ops[j] = EmitNeonShiftVector(Ops[j], ai->getType(), rightshift);
  else
    Ops[j] = Builder.CreateBitCast(Ops[j], ai->getType(), name);

return Builder.CreateCall(F, Ops, name);
3512}

3514Value *CodeGenFunction::EmitNeonShiftVector(Value *V, llvm::Type *Ty,
                                          bool neg) {
int SV = cast<ConstantInt>(V)->getSExtValue();
return ConstantInt::get(Ty, neg ? -SV : SV);
3518}

3520// \brief Right-shift a vector by a constant.
3521Value *CodeGenFunction::EmitNeonRShiftImm(Value *Vec, Value *Shift,
                                        llvm::Type *Ty, bool usgn,
                                        const char *name) {
llvm::VectorType *VTy = cast<llvm::VectorType>(Ty);

int ShiftAmt = cast<ConstantInt>(Shift)->getSExtValue();
int EltSize = VTy->getScalarSizeInBits();

Vec = Builder.CreateBitCast(Vec, Ty);

// lshr/ashr are undefined when the shift amount is equal to the vector
// element size.
if (ShiftAmt == EltSize) {
  if (usgn) {
    // Right-shifting an unsigned value by its size yields 0.
    return llvm::ConstantAggregateZero::get(VTy);
  } else {
    // Right-shifting a signed value by its size is equivalent
    // to a shift of size-1.
    --ShiftAmt;
    Shift = ConstantInt::get(VTy->getElementType(), ShiftAmt);
  }
}

Shift = EmitNeonShiftVector(Shift, Ty, false);
if (usgn)
  return Builder.CreateLShr(Vec, Shift, name);
else
  return Builder.CreateAShr(Vec, Shift, name);
3550}

3552enum {
AddRetType = (1 << 0),
Add1ArgType = (1 << 1),
Add2ArgTypes = (1 << 2),

VectorizeRetType = (1 << 3),
VectorizeArgTypes = (1 << 4),

InventFloatType = (1 << 5),
UnsignedAlts = (1 << 6),

Use64BitVectors = (1 << 7),
Use128BitVectors = (1 << 8),

Vectorize1ArgType = Add1ArgType | VectorizeArgTypes,
VectorRet = AddRetType | VectorizeRetType,
VectorRetGetArgs01 =
    AddRetType | Add2ArgTypes | VectorizeRetType | VectorizeArgTypes,
FpCmpzModifiers =
    AddRetType | VectorizeRetType | Add1ArgType | InventFloatType
3572};

3574namespace {
3575struct NeonIntrinsicInfo {
const char *NameHint;
unsigned BuiltinID;
unsigned LLVMIntrinsic;
unsigned AltLLVMIntrinsic;
unsigned TypeModifier;

bool operator<(unsigned RHSBuiltinID) const {
  return BuiltinID < RHSBuiltinID;
}
bool operator<(const NeonIntrinsicInfo &TE) const {
  return BuiltinID < TE.BuiltinID;
}
3588};
3589} // end anonymous namespace

3591#define NEONMAP0(NameBase) \
{ #NameBase, NEON::BI__builtin_neon_ ## NameBase, 0, 0, 0 }

3594#define NEONMAP1(NameBase, LLVMIntrinsic, TypeModifier) \
{ #NameBase, NEON:: BI__builtin_neon_ ## NameBase, \
    Intrinsic::LLVMIntrinsic, 0, TypeModifier }

3598#define NEONMAP2(NameBase, LLVMIntrinsic, AltLLVMIntrinsic, TypeModifier) \
{ #NameBase, NEON:: BI__builtin_neon_ ## NameBase, \
    Intrinsic::LLVMIntrinsic, Intrinsic::AltLLVMIntrinsic, \
    TypeModifier }

3603static const NeonIntrinsicInfo ARMSIMDIntrinsicMap [] = {
NEONMAP2(vabd_v, arm_neon_vabdu, arm_neon_vabds, Add1ArgType | UnsignedAlts),
NEONMAP2(vabdq_v, arm_neon_vabdu, arm_neon_vabds, Add1ArgType | UnsignedAlts),
NEONMAP1(vabs_v, arm_neon_vabs, 0),
NEONMAP1(vabsq_v, arm_neon_vabs, 0),
NEONMAP0(vaddhn_v),
NEONMAP1(vaesdq_v, arm_neon_aesd, 0),
NEONMAP1(vaeseq_v, arm_neon_aese, 0),
NEONMAP1(vaesimcq_v, arm_neon_aesimc, 0),
NEONMAP1(vaesmcq_v, arm_neon_aesmc, 0),
NEONMAP1(vbsl_v, arm_neon_vbsl, AddRetType),
NEONMAP1(vbslq_v, arm_neon_vbsl, AddRetType),
NEONMAP1(vcage_v, arm_neon_vacge, 0),
NEONMAP1(vcageq_v, arm_neon_vacge, 0),
NEONMAP1(vcagt_v, arm_neon_vacgt, 0),
NEONMAP1(vcagtq_v, arm_neon_vacgt, 0),
NEONMAP1(vcale_v, arm_neon_vacge, 0),
NEONMAP1(vcaleq_v, arm_neon_vacge, 0),
NEONMAP1(vcalt_v, arm_neon_vacgt, 0),
NEONMAP1(vcaltq_v, arm_neon_vacgt, 0),
NEONMAP1(vcls_v, arm_neon_vcls, Add1ArgType),
NEONMAP1(vclsq_v, arm_neon_vcls, Add1ArgType),
NEONMAP1(vclz_v, ctlz, Add1ArgType),
NEONMAP1(vclzq_v, ctlz, Add1ArgType),
NEONMAP1(vcnt_v, ctpop, Add1ArgType),
NEONMAP1(vcntq_v, ctpop, Add1ArgType),
NEONMAP1(vcvt_f16_f32, arm_neon_vcvtfp2hf, 0),
NEONMAP1(vcvt_f32_f16, arm_neon_vcvthf2fp, 0),
NEONMAP0(vcvt_f32_v),
NEONMAP2(vcvt_n_f16_v, arm_neon_vcvtfxu2fp, arm_neon_vcvtfxs2fp, 0),
NEONMAP2(vcvt_n_f32_v, arm_neon_vcvtfxu2fp, arm_neon_vcvtfxs2fp, 0),
NEONMAP1(vcvt_n_s16_v, arm_neon_vcvtfp2fxs, 0),
NEONMAP1(vcvt_n_s32_v, arm_neon_vcvtfp2fxs, 0),
NEONMAP1(vcvt_n_s64_v, arm_neon_vcvtfp2fxs, 0),
NEONMAP1(vcvt_n_u16_v, arm_neon_vcvtfp2fxu, 0),
NEONMAP1(vcvt_n_u32_v, arm_neon_vcvtfp2fxu, 0),
NEONMAP1(vcvt_n_u64_v, arm_neon_vcvtfp2fxu, 0),
NEONMAP0(vcvt_s16_v),
NEONMAP0(vcvt_s32_v),
NEONMAP0(vcvt_s64_v),
NEONMAP0(vcvt_u16_v),
NEONMAP0(vcvt_u32_v),
NEONMAP0(vcvt_u64_v),
NEONMAP1(vcvta_s16_v, arm_neon_vcvtas, 0),
NEONMAP1(vcvta_s32_v, arm_neon_vcvtas, 0),
NEONMAP1(vcvta_s64_v, arm_neon_vcvtas, 0),
NEONMAP1(vcvta_u32_v, arm_neon_vcvtau, 0),
NEONMAP1(vcvta_u64_v, arm_neon_vcvtau, 0),
NEONMAP1(vcvtaq_s16_v, arm_neon_vcvtas, 0),
NEONMAP1(vcvtaq_s32_v, arm_neon_vcvtas, 0),
NEONMAP1(vcvtaq_s64_v, arm_neon_vcvtas, 0),
NEONMAP1(vcvtaq_u16_v, arm_neon_vcvtau, 0),
NEONMAP1(vcvtaq_u32_v, arm_neon_vcvtau, 0),
NEONMAP1(vcvtaq_u64_v, arm_neon_vcvtau, 0),
NEONMAP1(vcvtm_s16_v, arm_neon_vcvtms, 0),
NEONMAP1(vcvtm_s32_v, arm_neon_vcvtms, 0),
NEONMAP1(vcvtm_s64_v, arm_neon_vcvtms, 0),
NEONMAP1(vcvtm_u16_v, arm_neon_vcvtmu, 0),
NEONMAP1(vcvtm_u32_v, arm_neon_vcvtmu, 0),
NEONMAP1(vcvtm_u64_v, arm_neon_vcvtmu, 0),
NEONMAP1(vcvtmq_s16_v, arm_neon_vcvtms, 0),
NEONMAP1(vcvtmq_s32_v, arm_neon_vcvtms, 0),
NEONMAP1(vcvtmq_s64_v, arm_neon_vcvtms, 0),
NEONMAP1(vcvtmq_u16_v, arm_neon_vcvtmu, 0),
NEONMAP1(vcvtmq_u32_v, arm_neon_vcvtmu, 0),
NEONMAP1(vcvtmq_u64_v, arm_neon_vcvtmu, 0),
NEONMAP1(vcvtn_s16_v, arm_neon_vcvtns, 0),
NEONMAP1(vcvtn_s32_v, arm_neon_vcvtns, 0),
NEONMAP1(vcvtn_s64_v, arm_neon_vcvtns, 0),
NEONMAP1(vcvtn_u16_v, arm_neon_vcvtnu, 0),
NEONMAP1(vcvtn_u32_v, arm_neon_vcvtnu, 0),
NEONMAP1(vcvtn_u64_v, arm_neon_vcvtnu, 0),
NEONMAP1(vcvtnq_s16_v, arm_neon_vcvtns, 0),
NEONMAP1(vcvtnq_s32_v, arm_neon_vcvtns, 0),
NEONMAP1(vcvtnq_s64_v, arm_neon_vcvtns, 0),
NEONMAP1(vcvtnq_u16_v, arm_neon_vcvtnu, 0),
NEONMAP1(vcvtnq_u32_v, arm_neon_vcvtnu, 0),
NEONMAP1(vcvtnq_u64_v, arm_neon_vcvtnu, 0),
NEONMAP1(vcvtp_s16_v, arm_neon_vcvtps, 0),
NEONMAP1(vcvtp_s32_v, arm_neon_vcvtps, 0),
NEONMAP1(vcvtp_s64_v, arm_neon_vcvtps, 0),
NEONMAP1(vcvtp_u16_v, arm_neon_vcvtpu, 0),
NEONMAP1(vcvtp_u32_v, arm_neon_vcvtpu, 0),
NEONMAP1(vcvtp_u64_v, arm_neon_vcvtpu, 0),
NEONMAP1(vcvtpq_s16_v, arm_neon_vcvtps, 0),
NEONMAP1(vcvtpq_s32_v, arm_neon_vcvtps, 0),
NEONMAP1(vcvtpq_s64_v, arm_neon_vcvtps, 0),
NEONMAP1(vcvtpq_u16_v, arm_neon_vcvtpu, 0),
NEONMAP1(vcvtpq_u32_v, arm_neon_vcvtpu, 0),
NEONMAP1(vcvtpq_u64_v, arm_neon_vcvtpu, 0),
NEONMAP0(vcvtq_f32_v),
NEONMAP2(vcvtq_n_f16_v, arm_neon_vcvtfxu2fp, arm_neon_vcvtfxs2fp, 0),
NEONMAP2(vcvtq_n_f32_v, arm_neon_vcvtfxu2fp, arm_neon_vcvtfxs2fp, 0),
NEONMAP1(vcvtq_n_s16_v, arm_neon_vcvtfp2fxs, 0),
NEONMAP1(vcvtq_n_s32_v, arm_neon_vcvtfp2fxs, 0),
NEONMAP1(vcvtq_n_s64_v, arm_neon_vcvtfp2fxs, 0),
NEONMAP1(vcvtq_n_u16_v, arm_neon_vcvtfp2fxu, 0),
NEONMAP1(vcvtq_n_u32_v, arm_neon_vcvtfp2fxu, 0),
NEONMAP1(vcvtq_n_u64_v, arm_neon_vcvtfp2fxu, 0),
NEONMAP0(vcvtq_s16_v),
NEONMAP0(vcvtq_s32_v),
NEONMAP0(vcvtq_s64_v),
NEONMAP0(vcvtq_u16_v),
NEONMAP0(vcvtq_u32_v),
NEONMAP0(vcvtq_u64_v),
NEONMAP0(vext_v),
NEONMAP0(vextq_v),
NEONMAP0(vfma_v),
NEONMAP0(vfmaq_v),
NEONMAP2(vhadd_v, arm_neon_vhaddu, arm_neon_vhadds, Add1ArgType | UnsignedAlts),
NEONMAP2(vhaddq_v, arm_neon_vhaddu, arm_neon_vhadds, Add1ArgType | UnsignedAlts),
NEONMAP2(vhsub_v, arm_neon_vhsubu, arm_neon_vhsubs, Add1ArgType | UnsignedAlts),
NEONMAP2(vhsubq_v, arm_neon_vhsubu, arm_neon_vhsubs, Add1ArgType | UnsignedAlts),
NEONMAP0(vld1_dup_v),
NEONMAP1(vld1_v, arm_neon_vld1, 0),
NEONMAP0(vld1q_dup_v),
NEONMAP1(vld1q_v, arm_neon_vld1, 0),
NEONMAP1(vld2_lane_v, arm_neon_vld2lane, 0),
NEONMAP1(vld2_v, arm_neon_vld2, 0),
NEONMAP1(vld2q_lane_v, arm_neon_vld2lane, 0),
NEONMAP1(vld2q_v, arm_neon_vld2, 0),
NEONMAP1(vld3_lane_v, arm_neon_vld3lane, 0),
NEONMAP1(vld3_v, arm_neon_vld3, 0),
NEONMAP1(vld3q_lane_v, arm_neon_vld3lane, 0),
NEONMAP1(vld3q_v, arm_neon_vld3, 0),
NEONMAP1(vld4_lane_v, arm_neon_vld4lane, 0),
NEONMAP1(vld4_v, arm_neon_vld4, 0),
NEONMAP1(vld4q_lane_v, arm_neon_vld4lane, 0),
NEONMAP1(vld4q_v, arm_neon_vld4, 0),
NEONMAP2(vmax_v, arm_neon_vmaxu, arm_neon_vmaxs, Add1ArgType | UnsignedAlts),
NEONMAP1(vmaxnm_v, arm_neon_vmaxnm, Add1ArgType),
NEONMAP1(vmaxnmq_v, arm_neon_vmaxnm, Add1ArgType),
NEONMAP2(vmaxq_v, arm_neon_vmaxu, arm_neon_vmaxs, Add1ArgType | UnsignedAlts),
NEONMAP2(vmin_v, arm_neon_vminu, arm_neon_vmins, Add1ArgType | UnsignedAlts),
NEONMAP1(vminnm_v, arm_neon_vminnm, Add1ArgType),
NEONMAP1(vminnmq_v, arm_neon_vminnm, Add1ArgType),
NEONMAP2(vminq_v, arm_neon_vminu, arm_neon_vmins, Add1ArgType | UnsignedAlts),
NEONMAP0(vmovl_v),
NEONMAP0(vmovn_v),
NEONMAP1(vmul_v, arm_neon_vmulp, Add1ArgType),
NEONMAP0(vmull_v),
NEONMAP1(vmulq_v, arm_neon_vmulp, Add1ArgType),
NEONMAP2(vpadal_v, arm_neon_vpadalu, arm_neon_vpadals, UnsignedAlts),
NEONMAP2(vpadalq_v, arm_neon_vpadalu, arm_neon_vpadals, UnsignedAlts),
NEONMAP1(vpadd_v, arm_neon_vpadd, Add1ArgType),
NEONMAP2(vpaddl_v, arm_neon_vpaddlu, arm_neon_vpaddls, UnsignedAlts),
NEONMAP2(vpaddlq_v, arm_neon_vpaddlu, arm_neon_vpaddls, UnsignedAlts),
NEONMAP1(vpaddq_v, arm_neon_vpadd, Add1ArgType),
NEONMAP2(vpmax_v, arm_neon_vpmaxu, arm_neon_vpmaxs, Add1ArgType | UnsignedAlts),
NEONMAP2(vpmin_v, arm_neon_vpminu, arm_neon_vpmins, Add1ArgType | UnsignedAlts),
NEONMAP1(vqabs_v, arm_neon_vqabs, Add1ArgType),
NEONMAP1(vqabsq_v, arm_neon_vqabs, Add1ArgType),
NEONMAP2(vqadd_v, arm_neon_vqaddu, arm_neon_vqadds, Add1ArgType | UnsignedAlts),
NEONMAP2(vqaddq_v, arm_neon_vqaddu, arm_neon_vqadds, Add1ArgType | UnsignedAlts),
NEONMAP2(vqdmlal_v, arm_neon_vqdmull, arm_neon_vqadds, 0),
NEONMAP2(vqdmlsl_v, arm_neon_vqdmull, arm_neon_vqsubs, 0),
NEONMAP1(vqdmulh_v, arm_neon_vqdmulh, Add1ArgType),
NEONMAP1(vqdmulhq_v, arm_neon_vqdmulh, Add1ArgType),
NEONMAP1(vqdmull_v, arm_neon_vqdmull, Add1ArgType),
NEONMAP2(vqmovn_v, arm_neon_vqmovnu, arm_neon_vqmovns, Add1ArgType | UnsignedAlts),
NEONMAP1(vqmovun_v, arm_neon_vqmovnsu, Add1ArgType),
NEONMAP1(vqneg_v, arm_neon_vqneg, Add1ArgType),
NEONMAP1(vqnegq_v, arm_neon_vqneg, Add1ArgType),
NEONMAP1(vqrdmulh_v, arm_neon_vqrdmulh, Add1ArgType),
NEONMAP1(vqrdmulhq_v, arm_neon_vqrdmulh, Add1ArgType),
NEONMAP2(vqrshl_v, arm_neon_vqrshiftu, arm_neon_vqrshifts, Add1ArgType | UnsignedAlts),
NEONMAP2(vqrshlq_v, arm_neon_vqrshiftu, arm_neon_vqrshifts, Add1ArgType | UnsignedAlts),
NEONMAP2(vqshl_n_v, arm_neon_vqshiftu, arm_neon_vqshifts, UnsignedAlts),
NEONMAP2(vqshl_v, arm_neon_vqshiftu, arm_neon_vqshifts, Add1ArgType | UnsignedAlts),
NEONMAP2(vqshlq_n_v, arm_neon_vqshiftu, arm_neon_vqshifts, UnsignedAlts),
NEONMAP2(vqshlq_v, arm_neon_vqshiftu, arm_neon_vqshifts, Add1ArgType | UnsignedAlts),
NEONMAP1(vqshlu_n_v, arm_neon_vqshiftsu, 0),
NEONMAP1(vqshluq_n_v, arm_neon_vqshiftsu, 0),
NEONMAP2(vqsub_v, arm_neon_vqsubu, arm_neon_vqsubs, Add1ArgType | UnsignedAlts),
NEONMAP2(vqsubq_v, arm_neon_vqsubu, arm_neon_vqsubs, Add1ArgType | UnsignedAlts),
NEONMAP1(vraddhn_v, arm_neon_vraddhn, Add1ArgType),
NEONMAP2(vrecpe_v, arm_neon_vrecpe, arm_neon_vrecpe, 0),
NEONMAP2(vrecpeq_v, arm_neon_vrecpe, arm_neon_vrecpe, 0),
NEONMAP1(vrecps_v, arm_neon_vrecps, Add1ArgType),
NEONMAP1(vrecpsq_v, arm_neon_vrecps, Add1ArgType),
NEONMAP2(vrhadd_v, arm_neon_vrhaddu, arm_neon_vrhadds, Add1ArgType | UnsignedAlts),
NEONMAP2(vrhaddq_v, arm_neon_vrhaddu, arm_neon_vrhadds, Add1ArgType | UnsignedAlts),
NEONMAP1(vrnd_v, arm_neon_vrintz, Add1ArgType),
NEONMAP1(vrnda_v, arm_neon_vrinta, Add1ArgType),
NEONMAP1(vrndaq_v, arm_neon_vrinta, Add1ArgType),
NEONMAP1(vrndm_v, arm_neon_vrintm, Add1ArgType),
NEONMAP1(vrndmq_v, arm_neon_vrintm, Add1ArgType),
NEONMAP1(vrndn_v, arm_neon_vrintn, Add1ArgType),
NEONMAP1(vrndnq_v, arm_neon_vrintn, Add1ArgType),
NEONMAP1(vrndp_v, arm_neon_vrintp, Add1ArgType),
NEONMAP1(vrndpq_v, arm_neon_vrintp, Add1ArgType),
NEONMAP1(vrndq_v, arm_neon_vrintz, Add1ArgType),
NEONMAP1(vrndx_v, arm_neon_vrintx, Add1ArgType),
NEONMAP1(vrndxq_v, arm_neon_vrintx, Add1ArgType),
NEONMAP2(vrshl_v, arm_neon_vrshiftu, arm_neon_vrshifts, Add1ArgType | UnsignedAlts),
NEONMAP2(vrshlq_v, arm_neon_vrshiftu, arm_neon_vrshifts, Add1ArgType | UnsignedAlts),
NEONMAP2(vrshr_n_v, arm_neon_vrshiftu, arm_neon_vrshifts, UnsignedAlts),
NEONMAP2(vrshrq_n_v, arm_neon_vrshiftu, arm_neon_vrshifts, UnsignedAlts),
NEONMAP2(vrsqrte_v, arm_neon_vrsqrte, arm_neon_vrsqrte, 0),
NEONMAP2(vrsqrteq_v, arm_neon_vrsqrte, arm_neon_vrsqrte, 0),
NEONMAP1(vrsqrts_v, arm_neon_vrsqrts, Add1ArgType),
NEONMAP1(vrsqrtsq_v, arm_neon_vrsqrts, Add1ArgType),
NEONMAP1(vrsubhn_v, arm_neon_vrsubhn, Add1ArgType),
NEONMAP1(vsha1su0q_v, arm_neon_sha1su0, 0),
NEONMAP1(vsha1su1q_v, arm_neon_sha1su1, 0),
NEONMAP1(vsha256h2q_v, arm_neon_sha256h2, 0),
NEONMAP1(vsha256hq_v, arm_neon_sha256h, 0),
NEONMAP1(vsha256su0q_v, arm_neon_sha256su0, 0),
NEONMAP1(vsha256su1q_v, arm_neon_sha256su1, 0),
NEONMAP0(vshl_n_v),
NEONMAP2(vshl_v, arm_neon_vshiftu, arm_neon_vshifts, Add1ArgType | UnsignedAlts),
NEONMAP0(vshll_n_v),
NEONMAP0(vshlq_n_v),
NEONMAP2(vshlq_v, arm_neon_vshiftu, arm_neon_vshifts, Add1ArgType | UnsignedAlts),
NEONMAP0(vshr_n_v),
NEONMAP0(vshrn_n_v),
NEONMAP0(vshrq_n_v),
NEONMAP1(vst1_v, arm_neon_vst1, 0),
NEONMAP1(vst1q_v, arm_neon_vst1, 0),
NEONMAP1(vst2_lane_v, arm_neon_vst2lane, 0),
NEONMAP1(vst2_v, arm_neon_vst2, 0),
NEONMAP1(vst2q_lane_v, arm_neon_vst2lane, 0),
NEONMAP1(vst2q_v, arm_neon_vst2, 0),
NEONMAP1(vst3_lane_v, arm_neon_vst3lane, 0),
NEONMAP1(vst3_v, arm_neon_vst3, 0),
NEONMAP1(vst3q_lane_v, arm_neon_vst3lane, 0),
NEONMAP1(vst3q_v, arm_neon_vst3, 0),
NEONMAP1(vst4_lane_v, arm_neon_vst4lane, 0),
NEONMAP1(vst4_v, arm_neon_vst4, 0),
NEONMAP1(vst4q_lane_v, arm_neon_vst4lane, 0),
NEONMAP1(vst4q_v, arm_neon_vst4, 0),
NEONMAP0(vsubhn_v),
NEONMAP0(vtrn_v),
NEONMAP0(vtrnq_v),
NEONMAP0(vtst_v),
NEONMAP0(vtstq_v),
NEONMAP0(vuzp_v),
NEONMAP0(vuzpq_v),
NEONMAP0(vzip_v),
NEONMAP0(vzipq_v)
3843};

3845static const NeonIntrinsicInfo AArch64SIMDIntrinsicMap[] = {
NEONMAP1(vabs_v, aarch64_neon_abs, 0),
NEONMAP1(vabsq_v, aarch64_neon_abs, 0),
NEONMAP0(vaddhn_v),
NEONMAP1(vaesdq_v, aarch64_crypto_aesd, 0),
NEONMAP1(vaeseq_v, aarch64_crypto_aese, 0),
NEONMAP1(vaesimcq_v, aarch64_crypto_aesimc, 0),
NEONMAP1(vaesmcq_v, aarch64_crypto_aesmc, 0),
NEONMAP1(vcage_v, aarch64_neon_facge, 0),
NEONMAP1(vcageq_v, aarch64_neon_facge, 0),
NEONMAP1(vcagt_v, aarch64_neon_facgt, 0),
NEONMAP1(vcagtq_v, aarch64_neon_facgt, 0),
NEONMAP1(vcale_v, aarch64_neon_facge, 0),
NEONMAP1(vcaleq_v, aarch64_neon_facge, 0),
NEONMAP1(vcalt_v, aarch64_neon_facgt, 0),
NEONMAP1(vcaltq_v, aarch64_neon_facgt, 0),
NEONMAP1(vcls_v, aarch64_neon_cls, Add1ArgType),
NEONMAP1(vclsq_v, aarch64_neon_cls, Add1ArgType),
NEONMAP1(vclz_v, ctlz, Add1ArgType),
NEONMAP1(vclzq_v, ctlz, Add1ArgType),
NEONMAP1(vcnt_v, ctpop, Add1ArgType),
NEONMAP1(vcntq_v, ctpop, Add1ArgType),
NEONMAP1(vcvt_f16_f32, aarch64_neon_vcvtfp2hf, 0),
NEONMAP0(vcvt_f16_v),
NEONMAP1(vcvt_f32_f16, aarch64_neon_vcvthf2fp, 0),
NEONMAP0(vcvt_f32_v),
NEONMAP2(vcvt_n_f16_v, aarch64_neon_vcvtfxu2fp, aarch64_neon_vcvtfxs2fp, 0),
NEONMAP2(vcvt_n_f32_v, aarch64_neon_vcvtfxu2fp, aarch64_neon_vcvtfxs2fp, 0),
NEONMAP2(vcvt_n_f64_v, aarch64_neon_vcvtfxu2fp, aarch64_neon_vcvtfxs2fp, 0),
NEONMAP1(vcvt_n_s16_v, aarch64_neon_vcvtfp2fxs, 0),
NEONMAP1(vcvt_n_s32_v, aarch64_neon_vcvtfp2fxs, 0),
NEONMAP1(vcvt_n_s64_v, aarch64_neon_vcvtfp2fxs, 0),
NEONMAP1(vcvt_n_u16_v, aarch64_neon_vcvtfp2fxu, 0),
NEONMAP1(vcvt_n_u32_v, aarch64_neon_vcvtfp2fxu, 0),
NEONMAP1(vcvt_n_u64_v, aarch64_neon_vcvtfp2fxu, 0),
NEONMAP0(vcvtq_f16_v),
NEONMAP0(vcvtq_f32_v),
NEONMAP2(vcvtq_n_f16_v, aarch64_neon_vcvtfxu2fp, aarch64_neon_vcvtfxs2fp, 0),
NEONMAP2(vcvtq_n_f32_v, aarch64_neon_vcvtfxu2fp, aarch64_neon_vcvtfxs2fp, 0),
NEONMAP2(vcvtq_n_f64_v, aarch64_neon_vcvtfxu2fp, aarch64_neon_vcvtfxs2fp, 0),
NEONMAP1(vcvtq_n_s16_v, aarch64_neon_vcvtfp2fxs, 0),
NEONMAP1(vcvtq_n_s32_v, aarch64_neon_vcvtfp2fxs, 0),
NEONMAP1(vcvtq_n_s64_v, aarch64_neon_vcvtfp2fxs, 0),
NEONMAP1(vcvtq_n_u16_v, aarch64_neon_vcvtfp2fxu, 0),
NEONMAP1(vcvtq_n_u32_v, aarch64_neon_vcvtfp2fxu, 0),
NEONMAP1(vcvtq_n_u64_v, aarch64_neon_vcvtfp2fxu, 0),
NEONMAP1(vcvtx_f32_v, aarch64_neon_fcvtxn, AddRetType | Add1ArgType),
NEONMAP0(vext_v),
NEONMAP0(vextq_v),
NEONMAP0(vfma_v),
NEONMAP0(vfmaq_v),
NEONMAP2(vhadd_v, aarch64_neon_uhadd, aarch64_neon_shadd, Add1ArgType | UnsignedAlts),
NEONMAP2(vhaddq_v, aarch64_neon_uhadd, aarch64_neon_shadd, Add1ArgType | UnsignedAlts),
NEONMAP2(vhsub_v, aarch64_neon_uhsub, aarch64_neon_shsub, Add1ArgType | UnsignedAlts),
NEONMAP2(vhsubq_v, aarch64_neon_uhsub, aarch64_neon_shsub, Add1ArgType | UnsignedAlts),
NEONMAP0(vmovl_v),
NEONMAP0(vmovn_v),
NEONMAP1(vmul_v, aarch64_neon_pmul, Add1ArgType),
NEONMAP1(vmulq_v, aarch64_neon_pmul, Add1ArgType),
NEONMAP1(vpadd_v, aarch64_neon_addp, Add1ArgType),
NEONMAP2(vpaddl_v, aarch64_neon_uaddlp, aarch64_neon_saddlp, UnsignedAlts),
NEONMAP2(vpaddlq_v, aarch64_neon_uaddlp, aarch64_neon_saddlp, UnsignedAlts),
NEONMAP1(vpaddq_v, aarch64_neon_addp, Add1ArgType),
NEONMAP1(vqabs_v, aarch64_neon_sqabs, Add1ArgType),
NEONMAP1(vqabsq_v, aarch64_neon_sqabs, Add1ArgType),
NEONMAP2(vqadd_v, aarch64_neon_uqadd, aarch64_neon_sqadd, Add1ArgType | UnsignedAlts),
NEONMAP2(vqaddq_v, aarch64_neon_uqadd, aarch64_neon_sqadd, Add1ArgType | UnsignedAlts),
NEONMAP2(vqdmlal_v, aarch64_neon_sqdmull, aarch64_neon_sqadd, 0),
NEONMAP2(vqdmlsl_v, aarch64_neon_sqdmull, aarch64_neon_sqsub, 0),
NEONMAP1(vqdmulh_v, aarch64_neon_sqdmulh, Add1ArgType),
NEONMAP1(vqdmulhq_v, aarch64_neon_sqdmulh, Add1ArgType),
NEONMAP1(vqdmull_v, aarch64_neon_sqdmull, Add1ArgType),
NEONMAP2(vqmovn_v, aarch64_neon_uqxtn, aarch64_neon_sqxtn, Add1ArgType | UnsignedAlts),
NEONMAP1(vqmovun_v, aarch64_neon_sqxtun, Add1ArgType),
NEONMAP1(vqneg_v, aarch64_neon_sqneg, Add1ArgType),
NEONMAP1(vqnegq_v, aarch64_neon_sqneg, Add1ArgType),
NEONMAP1(vqrdmulh_v, aarch64_neon_sqrdmulh, Add1ArgType),
NEONMAP1(vqrdmulhq_v, aarch64_neon_sqrdmulh, Add1ArgType),
NEONMAP2(vqrshl_v, aarch64_neon_uqrshl, aarch64_neon_sqrshl, Add1ArgType | UnsignedAlts),
NEONMAP2(vqrshlq_v, aarch64_neon_uqrshl, aarch64_neon_sqrshl, Add1ArgType | UnsignedAlts),
NEONMAP2(vqshl_n_v, aarch64_neon_uqshl, aarch64_neon_sqshl, UnsignedAlts),
NEONMAP2(vqshl_v, aarch64_neon_uqshl, aarch64_neon_sqshl, Add1ArgType | UnsignedAlts),
NEONMAP2(vqshlq_n_v, aarch64_neon_uqshl, aarch64_neon_sqshl,UnsignedAlts),
NEONMAP2(vqshlq_v, aarch64_neon_uqshl, aarch64_neon_sqshl, Add1ArgType | UnsignedAlts),
NEONMAP1(vqshlu_n_v, aarch64_neon_sqshlu, 0),
NEONMAP1(vqshluq_n_v, aarch64_neon_sqshlu, 0),
NEONMAP2(vqsub_v, aarch64_neon_uqsub, aarch64_neon_sqsub, Add1ArgType | UnsignedAlts),
NEONMAP2(vqsubq_v, aarch64_neon_uqsub, aarch64_neon_sqsub, Add1ArgType | UnsignedAlts),
NEONMAP1(vraddhn_v, aarch64_neon_raddhn, Add1ArgType),
NEONMAP2(vrecpe_v, aarch64_neon_frecpe, aarch64_neon_urecpe, 0),
NEONMAP2(vrecpeq_v, aarch64_neon_frecpe, aarch64_neon_urecpe, 0),
NEONMAP1(vrecps_v, aarch64_neon_frecps, Add1ArgType),
NEONMAP1(vrecpsq_v, aarch64_neon_frecps, Add1ArgType),
NEONMAP2(vrhadd_v, aarch64_neon_urhadd, aarch64_neon_srhadd, Add1ArgType | UnsignedAlts),
NEONMAP2(vrhaddq_v, aarch64_neon_urhadd, aarch64_neon_srhadd, Add1ArgType | UnsignedAlts),
NEONMAP2(vrshl_v, aarch64_neon_urshl, aarch64_neon_srshl, Add1ArgType | UnsignedAlts),
NEONMAP2(vrshlq_v, aarch64_neon_urshl, aarch64_neon_srshl, Add1ArgType | UnsignedAlts),
NEONMAP2(vrshr_n_v, aarch64_neon_urshl, aarch64_neon_srshl, UnsignedAlts),
NEONMAP2(vrshrq_n_v, aarch64_neon_urshl, aarch64_neon_srshl, UnsignedAlts),
NEONMAP2(vrsqrte_v, aarch64_neon_frsqrte, aarch64_neon_ursqrte, 0),
NEONMAP2(vrsqrteq_v, aarch64_neon_frsqrte, aarch64_neon_ursqrte, 0),
NEONMAP1(vrsqrts_v, aarch64_neon_frsqrts, Add1ArgType),
NEONMAP1(vrsqrtsq_v, aarch64_neon_frsqrts, Add1ArgType),
NEONMAP1(vrsubhn_v, aarch64_neon_rsubhn, Add1ArgType),
NEONMAP1(vsha1su0q_v, aarch64_crypto_sha1su0, 0),
NEONMAP1(vsha1su1q_v, aarch64_crypto_sha1su1, 0),
NEONMAP1(vsha256h2q_v, aarch64_crypto_sha256h2, 0),
NEONMAP1(vsha256hq_v, aarch64_crypto_sha256h, 0),
NEONMAP1(vsha256su0q_v, aarch64_crypto_sha256su0, 0),
NEONMAP1(vsha256su1q_v, aarch64_crypto_sha256su1, 0),
NEONMAP0(vshl_n_v),
NEONMAP2(vshl_v, aarch64_neon_ushl, aarch64_neon_sshl, Add1ArgType | UnsignedAlts),
NEONMAP0(vshll_n_v),
NEONMAP0(vshlq_n_v),
NEONMAP2(vshlq_v, aarch64_neon_ushl, aarch64_neon_sshl, Add1ArgType | UnsignedAlts),
NEONMAP0(vshr_n_v),
NEONMAP0(vshrn_n_v),
NEONMAP0(vshrq_n_v),
NEONMAP0(vsubhn_v),
NEONMAP0(vtst_v),
NEONMAP0(vtstq_v),
3966};

3968static const NeonIntrinsicInfo AArch64SISDIntrinsicMap[] = {
NEONMAP1(vabdd_f64, aarch64_sisd_fabd, Add1ArgType),
NEONMAP1(vabds_f32, aarch64_sisd_fabd, Add1ArgType),
NEONMAP1(vabsd_s64, aarch64_neon_abs, Add1ArgType),
NEONMAP1(vaddlv_s32, aarch64_neon_saddlv, AddRetType | Add1ArgType),
NEONMAP1(vaddlv_u32, aarch64_neon_uaddlv, AddRetType | Add1ArgType),
NEONMAP1(vaddlvq_s32, aarch64_neon_saddlv, AddRetType | Add1ArgType),
NEONMAP1(vaddlvq_u32, aarch64_neon_uaddlv, AddRetType | Add1ArgType),
NEONMAP1(vaddv_f32, aarch64_neon_faddv, AddRetType | Add1ArgType),
NEONMAP1(vaddv_s32, aarch64_neon_saddv, AddRetType | Add1ArgType),
NEONMAP1(vaddv_u32, aarch64_neon_uaddv, AddRetType | Add1ArgType),
NEONMAP1(vaddvq_f32, aarch64_neon_faddv, AddRetType | Add1ArgType),
NEONMAP1(vaddvq_f64, aarch64_neon_faddv, AddRetType | Add1ArgType),
NEONMAP1(vaddvq_s32, aarch64_neon_saddv, AddRetType | Add1ArgType),
NEONMAP1(vaddvq_s64, aarch64_neon_saddv, AddRetType | Add1ArgType),
NEONMAP1(vaddvq_u32, aarch64_neon_uaddv, AddRetType | Add1ArgType),
NEONMAP1(vaddvq_u64, aarch64_neon_uaddv, AddRetType | Add1ArgType),
NEONMAP1(vcaged_f64, aarch64_neon_facge, AddRetType | Add1ArgType),
NEONMAP1(vcages_f32, aarch64_neon_facge, AddRetType | Add1ArgType),
NEONMAP1(vcagtd_f64, aarch64_neon_facgt, AddRetType | Add1ArgType),
NEONMAP1(vcagts_f32, aarch64_neon_facgt, AddRetType | Add1ArgType),
NEONMAP1(vcaled_f64, aarch64_neon_facge, AddRetType | Add1ArgType),
NEONMAP1(vcales_f32, aarch64_neon_facge, AddRetType | Add1ArgType),
NEONMAP1(vcaltd_f64, aarch64_neon_facgt, AddRetType | Add1ArgType),
NEONMAP1(vcalts_f32, aarch64_neon_facgt, AddRetType | Add1ArgType),
NEONMAP1(vcvtad_s64_f64, aarch64_neon_fcvtas, AddRetType | Add1ArgType),
NEONMAP1(vcvtad_u64_f64, aarch64_neon_fcvtau, AddRetType | Add1ArgType),
NEONMAP1(vcvtas_s32_f32, aarch64_neon_fcvtas, AddRetType | Add1ArgType),
NEONMAP1(vcvtas_u32_f32, aarch64_neon_fcvtau, AddRetType | Add1ArgType),
NEONMAP1(vcvtd_n_f64_s64, aarch64_neon_vcvtfxs2fp, AddRetType | Add1ArgType),
NEONMAP1(vcvtd_n_f64_u64, aarch64_neon_vcvtfxu2fp, AddRetType | Add1ArgType),
NEONMAP1(vcvtd_n_s64_f64, aarch64_neon_vcvtfp2fxs, AddRetType | Add1ArgType),
NEONMAP1(vcvtd_n_u64_f64, aarch64_neon_vcvtfp2fxu, AddRetType | Add1ArgType),
NEONMAP1(vcvtmd_s64_f64, aarch64_neon_fcvtms, AddRetType | Add1ArgType),
NEONMAP1(vcvtmd_u64_f64, aarch64_neon_fcvtmu, AddRetType | Add1ArgType),
NEONMAP1(vcvtms_s32_f32, aarch64_neon_fcvtms, AddRetType | Add1ArgType),
NEONMAP1(vcvtms_u32_f32, aarch64_neon_fcvtmu, AddRetType | Add1ArgType),
NEONMAP1(vcvtnd_s64_f64, aarch64_neon_fcvtns, AddRetType | Add1ArgType),
NEONMAP1(vcvtnd_u64_f64, aarch64_neon_fcvtnu, AddRetType | Add1ArgType),
NEONMAP1(vcvtns_s32_f32, aarch64_neon_fcvtns, AddRetType | Add1ArgType),
NEONMAP1(vcvtns_u32_f32, aarch64_neon_fcvtnu, AddRetType | Add1ArgType),
NEONMAP1(vcvtpd_s64_f64, aarch64_neon_fcvtps, AddRetType | Add1ArgType),
NEONMAP1(vcvtpd_u64_f64, aarch64_neon_fcvtpu, AddRetType | Add1ArgType),
NEONMAP1(vcvtps_s32_f32, aarch64_neon_fcvtps, AddRetType | Add1ArgType),
NEONMAP1(vcvtps_u32_f32, aarch64_neon_fcvtpu, AddRetType | Add1ArgType),
NEONMAP1(vcvts_n_f32_s32, aarch64_neon_vcvtfxs2fp, AddRetType | Add1ArgType),
NEONMAP1(vcvts_n_f32_u32, aarch64_neon_vcvtfxu2fp, AddRetType | Add1ArgType),
NEONMAP1(vcvts_n_s32_f32, aarch64_neon_vcvtfp2fxs, AddRetType | Add1ArgType),
NEONMAP1(vcvts_n_u32_f32, aarch64_neon_vcvtfp2fxu, AddRetType | Add1ArgType),
NEONMAP1(vcvtxd_f32_f64, aarch64_sisd_fcvtxn, 0),
NEONMAP1(vmaxnmv_f32, aarch64_neon_fmaxnmv, AddRetType | Add1ArgType),
NEONMAP1(vmaxnmvq_f32, aarch64_neon_fmaxnmv, AddRetType | Add1ArgType),
NEONMAP1(vmaxnmvq_f64, aarch64_neon_fmaxnmv, AddRetType | Add1ArgType),
NEONMAP1(vmaxv_f32, aarch64_neon_fmaxv, AddRetType | Add1ArgType),
NEONMAP1(vmaxv_s32, aarch64_neon_smaxv, AddRetType | Add1ArgType),
NEONMAP1(vmaxv_u32, aarch64_neon_umaxv, AddRetType | Add1ArgType),
NEONMAP1(vmaxvq_f32, aarch64_neon_fmaxv, AddRetType | Add1ArgType),
NEONMAP1(vmaxvq_f64, aarch64_neon_fmaxv, AddRetType | Add1ArgType),
NEONMAP1(vmaxvq_s32, aarch64_neon_smaxv, AddRetType | Add1ArgType),
NEONMAP1(vmaxvq_u32, aarch64_neon_umaxv, AddRetType | Add1ArgType),
NEONMAP1(vminnmv_f32, aarch64_neon_fminnmv, AddRetType | Add1ArgType),
NEONMAP1(vminnmvq_f32, aarch64_neon_fminnmv, AddRetType | Add1ArgType),
NEONMAP1(vminnmvq_f64, aarch64_neon_fminnmv, AddRetType | Add1ArgType),
NEONMAP1(vminv_f32, aarch64_neon_fminv, AddRetType | Add1ArgType),
NEONMAP1(vminv_s32, aarch64_neon_sminv, AddRetType | Add1ArgType),
NEONMAP1(vminv_u32, aarch64_neon_uminv, AddRetType | Add1ArgType),
NEONMAP1(vminvq_f32, aarch64_neon_fminv, AddRetType | Add1ArgType),
NEONMAP1(vminvq_f64, aarch64_neon_fminv, AddRetType | Add1ArgType),
NEONMAP1(vminvq_s32, aarch64_neon_sminv, AddRetType | Add1ArgType),
NEONMAP1(vminvq_u32, aarch64_neon_uminv, AddRetType | Add1ArgType),
NEONMAP1(vmull_p64, aarch64_neon_pmull64, 0),
NEONMAP1(vmulxd_f64, aarch64_neon_fmulx, Add1ArgType),
NEONMAP1(vmulxs_f32, aarch64_neon_fmulx, Add1ArgType),
NEONMAP1(vpaddd_s64, aarch64_neon_uaddv, AddRetType | Add1ArgType),
NEONMAP1(vpaddd_u64, aarch64_neon_uaddv, AddRetType | Add1ArgType),
NEONMAP1(vpmaxnmqd_f64, aarch64_neon_fmaxnmv, AddRetType | Add1ArgType),
NEONMAP1(vpmaxnms_f32, aarch64_neon_fmaxnmv, AddRetType | Add1ArgType),
NEONMAP1(vpmaxqd_f64, aarch64_neon_fmaxv, AddRetType | Add1ArgType),
NEONMAP1(vpmaxs_f32, aarch64_neon_fmaxv, AddRetType | Add1ArgType),
NEONMAP1(vpminnmqd_f64, aarch64_neon_fminnmv, AddRetType | Add1ArgType),
NEONMAP1(vpminnms_f32, aarch64_neon_fminnmv, AddRetType | Add1ArgType),
NEONMAP1(vpminqd_f64, aarch64_neon_fminv, AddRetType | Add1ArgType),
NEONMAP1(vpmins_f32, aarch64_neon_fminv, AddRetType | Add1ArgType),
NEONMAP1(vqabsb_s8, aarch64_neon_sqabs, Vectorize1ArgType | Use64BitVectors),
NEONMAP1(vqabsd_s64, aarch64_neon_sqabs, Add1ArgType),
NEONMAP1(vqabsh_s16, aarch64_neon_sqabs, Vectorize1ArgType | Use64BitVectors),
NEONMAP1(vqabss_s32, aarch64_neon_sqabs, Add1ArgType),
NEONMAP1(vqaddb_s8, aarch64_neon_sqadd, Vectorize1ArgType | Use64BitVectors),
NEONMAP1(vqaddb_u8, aarch64_neon_uqadd, Vectorize1ArgType | Use64BitVectors),
NEONMAP1(vqaddd_s64, aarch64_neon_sqadd, Add1ArgType),
NEONMAP1(vqaddd_u64, aarch64_neon_uqadd, Add1ArgType),
NEONMAP1(vqaddh_s16, aarch64_neon_sqadd, Vectorize1ArgType | Use64BitVectors),
NEONMAP1(vqaddh_u16, aarch64_neon_uqadd, Vectorize1ArgType | Use64BitVectors),
NEONMAP1(vqadds_s32, aarch64_neon_sqadd, Add1ArgType),
NEONMAP1(vqadds_u32, aarch64_neon_uqadd, Add1ArgType),
NEONMAP1(vqdmulhh_s16, aarch64_neon_sqdmulh, Vectorize1ArgType | Use64BitVectors),
NEONMAP1(vqdmulhs_s32, aarch64_neon_sqdmulh, Add1ArgType),
NEONMAP1(vqdmullh_s16, aarch64_neon_sqdmull, VectorRet | Use128BitVectors),
NEONMAP1(vqdmulls_s32, aarch64_neon_sqdmulls_scalar, 0),
NEONMAP1(vqmovnd_s64, aarch64_neon_scalar_sqxtn, AddRetType | Add1ArgType),
NEONMAP1(vqmovnd_u64, aarch64_neon_scalar_uqxtn, AddRetType | Add1ArgType),
NEONMAP1(vqmovnh_s16, aarch64_neon_sqxtn, VectorRet | Use64BitVectors),
NEONMAP1(vqmovnh_u16, aarch64_neon_uqxtn, VectorRet | Use64BitVectors),
NEONMAP1(vqmovns_s32, aarch64_neon_sqxtn, VectorRet | Use64BitVectors),
NEONMAP1(vqmovns_u32, aarch64_neon_uqxtn, VectorRet | Use64BitVectors),
NEONMAP1(vqmovund_s64, aarch64_neon_scalar_sqxtun, AddRetType | Add1ArgType),
NEONMAP1(vqmovunh_s16, aarch64_neon_sqxtun, VectorRet | Use64BitVectors),
NEONMAP1(vqmovuns_s32, aarch64_neon_sqxtun, VectorRet | Use64BitVectors),
NEONMAP1(vqnegb_s8, aarch64_neon_sqneg, Vectorize1ArgType | Use64BitVectors),
NEONMAP1(vqnegd_s64, aarch64_neon_sqneg, Add1ArgType),
NEONMAP1(vqnegh_s16, aarch64_neon_sqneg, Vectorize1ArgType | Use64BitVectors),
NEONMAP1(vqnegs_s32, aarch64_neon_sqneg, Add1ArgType),
NEONMAP1(vqrdmulhh_s16, aarch64_neon_sqrdmulh, Vectorize1ArgType | Use64BitVectors),
NEONMAP1(vqrdmulhs_s32, aarch64_neon_sqrdmulh, Add1ArgType),
NEONMAP1(vqrshlb_s8, aarch64_neon_sqrshl, Vectorize1ArgType | Use64BitVectors),
NEONMAP1(vqrshlb_u8, aarch64_neon_uqrshl, Vectorize1ArgType | Use64BitVectors),
NEONMAP1(vqrshld_s64, aarch64_neon_sqrshl, Add1ArgType),
NEONMAP1(vqrshld_u64, aarch64_neon_uqrshl, Add1ArgType),
NEONMAP1(vqrshlh_s16, aarch64_neon_sqrshl, Vectorize1ArgType | Use64BitVectors),
NEONMAP1(vqrshlh_u16, aarch64_neon_uqrshl, Vectorize1ArgType | Use64BitVectors),
NEONMAP1(vqrshls_s32, aarch64_neon_sqrshl, Add1ArgType),
NEONMAP1(vqrshls_u32, aarch64_neon_uqrshl, Add1ArgType),
NEONMAP1(vqrshrnd_n_s64, aarch64_neon_sqrshrn, AddRetType),
NEONMAP1(vqrshrnd_n_u64, aarch64_neon_uqrshrn, AddRetType),
NEONMAP1(vqrshrnh_n_s16, aarch64_neon_sqrshrn, VectorRet | Use64BitVectors),
NEONMAP1(vqrshrnh_n_u16, aarch64_neon_uqrshrn, VectorRet | Use64BitVectors),
NEONMAP1(vqrshrns_n_s32, aarch64_neon_sqrshrn, VectorRet | Use64BitVectors),
NEONMAP1(vqrshrns_n_u32, aarch64_neon_uqrshrn, VectorRet | Use64BitVectors),
NEONMAP1(vqrshrund_n_s64, aarch64_neon_sqrshrun, AddRetType),
NEONMAP1(vqrshrunh_n_s16, aarch64_neon_sqrshrun, VectorRet | Use64BitVectors),
NEONMAP1(vqrshruns_n_s32, aarch64_neon_sqrshrun, VectorRet | Use64BitVectors),
NEONMAP1(vqshlb_n_s8, aarch64_neon_sqshl, Vectorize1ArgType | Use64BitVectors),
NEONMAP1(vqshlb_n_u8, aarch64_neon_uqshl, Vectorize1ArgType | Use64BitVectors),
NEONMAP1(vqshlb_s8, aarch64_neon_sqshl, Vectorize1ArgType | Use64BitVectors),
NEONMAP1(vqshlb_u8, aarch64_neon_uqshl, Vectorize1ArgType | Use64BitVectors),
NEONMAP1(vqshld_s64, aarch64_neon_sqshl, Add1ArgType),
NEONMAP1(vqshld_u64, aarch64_neon_uqshl, Add1ArgType),
NEONMAP1(vqshlh_n_s16, aarch64_neon_sqshl, Vectorize1ArgType | Use64BitVectors),
NEONMAP1(vqshlh_n_u16, aarch64_neon_uqshl, Vectorize1ArgType | Use64BitVectors),
NEONMAP1(vqshlh_s16, aarch64_neon_sqshl, Vectorize1ArgType | Use64BitVectors),
NEONMAP1(vqshlh_u16, aarch64_neon_uqshl, Vectorize1ArgType | Use64BitVectors),
NEONMAP1(vqshls_n_s32, aarch64_neon_sqshl, Add1ArgType),
NEONMAP1(vqshls_n_u32, aarch64_neon_uqshl, Add1ArgType),
NEONMAP1(vqshls_s32, aarch64_neon_sqshl, Add1ArgType),
NEONMAP1(vqshls_u32, aarch64_neon_uqshl, Add1ArgType),
NEONMAP1(vqshlub_n_s8, aarch64_neon_sqshlu, Vectorize1ArgType | Use64BitVectors),
NEONMAP1(vqshluh_n_s16, aarch64_neon_sqshlu, Vectorize1ArgType | Use64BitVectors),
NEONMAP1(vqshlus_n_s32, aarch64_neon_sqshlu, Add1ArgType),
NEONMAP1(vqshrnd_n_s64, aarch64_neon_sqshrn, AddRetType),
NEONMAP1(vqshrnd_n_u64, aarch64_neon_uqshrn, AddRetType),
NEONMAP1(vqshrnh_n_s16, aarch64_neon_sqshrn, VectorRet | Use64BitVectors),
NEONMAP1(vqshrnh_n_u16, aarch64_neon_uqshrn, VectorRet | Use64BitVectors),
NEONMAP1(vqshrns_n_s32, aarch64_neon_sqshrn, VectorRet | Use64BitVectors),
NEONMAP1(vqshrns_n_u32, aarch64_neon_uqshrn, VectorRet | Use64BitVectors),
NEONMAP1(vqshrund_n_s64, aarch64_neon_sqshrun, AddRetType),
NEONMAP1(vqshrunh_n_s16, aarch64_neon_sqshrun, VectorRet | Use64BitVectors),
NEONMAP1(vqshruns_n_s32, aarch64_neon_sqshrun, VectorRet | Use64BitVectors),
NEONMAP1(vqsubb_s8, aarch64_neon_sqsub, Vectorize1ArgType | Use64BitVectors),
NEONMAP1(vqsubb_u8, aarch64_neon_uqsub, Vectorize1ArgType | Use64BitVectors),
NEONMAP1(vqsubd_s64, aarch64_neon_sqsub, Add1ArgType),
NEONMAP1(vqsubd_u64, aarch64_neon_uqsub, Add1ArgType),
NEONMAP1(vqsubh_s16, aarch64_neon_sqsub, Vectorize1ArgType | Use64BitVectors),
NEONMAP1(vqsubh_u16, aarch64_neon_uqsub, Vectorize1ArgType | Use64BitVectors),
NEONMAP1(vqsubs_s32, aarch64_neon_sqsub, Add1ArgType),
NEONMAP1(vqsubs_u32, aarch64_neon_uqsub, Add1ArgType),
NEONMAP1(vrecped_f64, aarch64_neon_frecpe, Add1ArgType),
NEONMAP1(vrecpes_f32, aarch64_neon_frecpe, Add1ArgType),
NEONMAP1(vrecpxd_f64, aarch64_neon_frecpx, Add1ArgType),
NEONMAP1(vrecpxs_f32, aarch64_neon_frecpx, Add1ArgType),
NEONMAP1(vrshld_s64, aarch64_neon_srshl, Add1ArgType),
NEONMAP1(vrshld_u64, aarch64_neon_urshl, Add1ArgType),
NEONMAP1(vrsqrted_f64, aarch64_neon_frsqrte, Add1ArgType),
NEONMAP1(vrsqrtes_f32, aarch64_neon_frsqrte, Add1ArgType),
NEONMAP1(vrsqrtsd_f64, aarch64_neon_frsqrts, Add1ArgType),
NEONMAP1(vrsqrtss_f32, aarch64_neon_frsqrts, Add1ArgType),
NEONMAP1(vsha1cq_u32, aarch64_crypto_sha1c, 0),
NEONMAP1(vsha1h_u32, aarch64_crypto_sha1h, 0),
NEONMAP1(vsha1mq_u32, aarch64_crypto_sha1m, 0),
NEONMAP1(vsha1pq_u32, aarch64_crypto_sha1p, 0),
NEONMAP1(vshld_s64, aarch64_neon_sshl, Add1ArgType),
NEONMAP1(vshld_u64, aarch64_neon_ushl, Add1ArgType),
NEONMAP1(vslid_n_s64, aarch64_neon_vsli, Vectorize1ArgType),
NEONMAP1(vslid_n_u64, aarch64_neon_vsli, Vectorize1ArgType),
NEONMAP1(vsqaddb_u8, aarch64_neon_usqadd, Vectorize1ArgType | Use64BitVectors),
NEONMAP1(vsqaddd_u64, aarch64_neon_usqadd, Add1ArgType),
NEONMAP1(vsqaddh_u16, aarch64_neon_usqadd, Vectorize1ArgType | Use64BitVectors),
NEONMAP1(vsqadds_u32, aarch64_neon_usqadd, Add1ArgType),
NEONMAP1(vsrid_n_s64, aarch64_neon_vsri, Vectorize1ArgType),
NEONMAP1(vsrid_n_u64, aarch64_neon_vsri, Vectorize1ArgType),
NEONMAP1(vuqaddb_s8, aarch64_neon_suqadd, Vectorize1ArgType | Use64BitVectors),
NEONMAP1(vuqaddd_s64, aarch64_neon_suqadd, Add1ArgType),
NEONMAP1(vuqaddh_s16, aarch64_neon_suqadd, Vectorize1ArgType | Use64BitVectors),
NEONMAP1(vuqadds_s32, aarch64_neon_suqadd, Add1ArgType),
// FP16 scalar intrinisics go here.
NEONMAP1(vabdh_f16, aarch64_sisd_fabd, Add1ArgType),
NEONMAP1(vabsh_f16, aarch64_neon_abs, Add1ArgType),
NEONMAP1(vcageh_f16, aarch64_neon_facge, AddRetType | Add1ArgType),
NEONMAP1(vcagth_f16, aarch64_neon_facgt, AddRetType | Add1ArgType),
NEONMAP1(vcaleh_f16, aarch64_neon_facge, AddRetType | Add1ArgType),
NEONMAP1(vcalth_f16, aarch64_neon_facgt, AddRetType | Add1ArgType),
NEONMAP1(vcvtah_s16_f16, aarch64_neon_fcvtas, AddRetType | Add1ArgType),
NEONMAP1(vcvtah_s32_f16, aarch64_neon_fcvtas, AddRetType | Add1ArgType),
NEONMAP1(vcvtah_s64_f16, aarch64_neon_fcvtas, AddRetType | Add1ArgType),
NEONMAP1(vcvtah_u16_f16, aarch64_neon_fcvtau, AddRetType | Add1ArgType),
NEONMAP1(vcvtah_u32_f16, aarch64_neon_fcvtau, AddRetType | Add1ArgType),
NEONMAP1(vcvtah_u64_f16, aarch64_neon_fcvtau, AddRetType | Add1ArgType),
NEONMAP1(vcvth_n_f16_s16, aarch64_neon_vcvtfxs2fp, AddRetType | Add1ArgType),
NEONMAP1(vcvth_n_f16_s32, aarch64_neon_vcvtfxs2fp, AddRetType | Add1ArgType),
NEONMAP1(vcvth_n_f16_s64, aarch64_neon_vcvtfxs2fp, AddRetType | Add1ArgType),
NEONMAP1(vcvth_n_f16_u16, aarch64_neon_vcvtfxu2fp, AddRetType | Add1ArgType),
NEONMAP1(vcvth_n_f16_u32, aarch64_neon_vcvtfxu2fp, AddRetType | Add1ArgType),
NEONMAP1(vcvth_n_f16_u64, aarch64_neon_vcvtfxu2fp, AddRetType | Add1ArgType),
NEONMAP1(vcvth_n_s16_f16, aarch64_neon_vcvtfp2fxs, AddRetType | Add1ArgType),
NEONMAP1(vcvth_n_s32_f16, aarch64_neon_vcvtfp2fxs, AddRetType | Add1ArgType),
NEONMAP1(vcvth_n_s64_f16, aarch64_neon_vcvtfp2fxs, AddRetType | Add1ArgType),
NEONMAP1(vcvth_n_u16_f16, aarch64_neon_vcvtfp2fxu, AddRetType | Add1ArgType),
NEONMAP1(vcvth_n_u32_f16, aarch64_neon_vcvtfp2fxu, AddRetType | Add1ArgType),
NEONMAP1(vcvth_n_u64_f16, aarch64_neon_vcvtfp2fxu, AddRetType | Add1ArgType),
NEONMAP1(vcvtmh_s16_f16, aarch64_neon_fcvtms, AddRetType | Add1ArgType),
NEONMAP1(vcvtmh_s32_f16, aarch64_neon_fcvtms, AddRetType | Add1ArgType),
NEONMAP1(vcvtmh_s64_f16, aarch64_neon_fcvtms, AddRetType | Add1ArgType),
NEONMAP1(vcvtmh_u16_f16, aarch64_neon_fcvtmu, AddRetType | Add1ArgType),
NEONMAP1(vcvtmh_u32_f16, aarch64_neon_fcvtmu, AddRetType | Add1ArgType),
NEONMAP1(vcvtmh_u64_f16, aarch64_neon_fcvtmu, AddRetType | Add1ArgType),
NEONMAP1(vcvtnh_s16_f16, aarch64_neon_fcvtns, AddRetType | Add1ArgType),
NEONMAP1(vcvtnh_s32_f16, aarch64_neon_fcvtns, AddRetType | Add1ArgType),
NEONMAP1(vcvtnh_s64_f16, aarch64_neon_fcvtns, AddRetType | Add1ArgType),
NEONMAP1(vcvtnh_u16_f16, aarch64_neon_fcvtnu, AddRetType | Add1ArgType),
NEONMAP1(vcvtnh_u32_f16, aarch64_neon_fcvtnu, AddRetType | Add1ArgType),
NEONMAP1(vcvtnh_u64_f16, aarch64_neon_fcvtnu, AddRetType | Add1ArgType),
NEONMAP1(vcvtph_s16_f16, aarch64_neon_fcvtps, AddRetType | Add1ArgType),
NEONMAP1(vcvtph_s32_f16, aarch64_neon_fcvtps, AddRetType | Add1ArgType),
NEONMAP1(vcvtph_s64_f16, aarch64_neon_fcvtps, AddRetType | Add1ArgType),
NEONMAP1(vcvtph_u16_f16, aarch64_neon_fcvtpu, AddRetType | Add1ArgType),
NEONMAP1(vcvtph_u32_f16, aarch64_neon_fcvtpu, AddRetType | Add1ArgType),
NEONMAP1(vcvtph_u64_f16, aarch64_neon_fcvtpu, AddRetType | Add1ArgType),
NEONMAP1(vmulxh_f16, aarch64_neon_fmulx, Add1ArgType),
NEONMAP1(vrecpeh_f16, aarch64_neon_frecpe, Add1ArgType),
NEONMAP1(vrecpxh_f16, aarch64_neon_frecpx, Add1ArgType),
NEONMAP1(vrsqrteh_f16, aarch64_neon_frsqrte, Add1ArgType),
NEONMAP1(vrsqrtsh_f16, aarch64_neon_frsqrts, Add1ArgType),
4209};

4211#undef NEONMAP0
4212#undef NEONMAP1
4213#undef NEONMAP2

4215static bool NEONSIMDIntrinsicsProvenSorted = false;

4217static bool AArch64SIMDIntrinsicsProvenSorted = false;
4218static bool AArch64SISDIntrinsicsProvenSorted = false;


4221static const NeonIntrinsicInfo *
4222findNeonIntrinsicInMap(ArrayRef<NeonIntrinsicInfo> IntrinsicMap,
                     unsigned BuiltinID, bool &MapProvenSorted) {

4225#ifndef NDEBUG
if (!MapProvenSorted) {
  assert(std::is_sorted(std::begin(IntrinsicMap), std::end(IntrinsicMap)))(static_cast <bool> (std::is_sorted(std::begin(IntrinsicMap
), std::end(IntrinsicMap))) ? void (0) : __assert_fail ("std::is_sorted(std::begin(IntrinsicMap), std::end(IntrinsicMap))"
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 4227, __extension__ __PRETTY_FUNCTION__));
  MapProvenSorted = true;
}
4230#endif

const NeonIntrinsicInfo *Builtin =
    std::lower_bound(IntrinsicMap.begin(), IntrinsicMap.end(), BuiltinID);

if (Builtin != IntrinsicMap.end() && Builtin->BuiltinID == BuiltinID)
  return Builtin;

return nullptr;
4239}

4241Function *CodeGenFunction::LookupNeonLLVMIntrinsic(unsigned IntrinsicID,
                                                 unsigned Modifier,
                                                 llvm::Type *ArgType,
                                                 const CallExpr *E) {
int VectorSize = 0;
if (Modifier & Use64BitVectors)
  VectorSize = 64;
else if (Modifier & Use128BitVectors)
  VectorSize = 128;

// Return type.
SmallVector<llvm::Type *, 3> Tys;
if (Modifier & AddRetType) {
  llvm::Type *Ty = ConvertType(E->getCallReturnType(getContext()));
  if (Modifier & VectorizeRetType)
    Ty = llvm::VectorType::get(
        Ty, VectorSize ? VectorSize / Ty->getPrimitiveSizeInBits() : 1);

  Tys.push_back(Ty);
}

// Arguments.
if (Modifier & VectorizeArgTypes) {
  int Elts = VectorSize ? VectorSize / ArgType->getPrimitiveSizeInBits() : 1;
  ArgType = llvm::VectorType::get(ArgType, Elts);
}

if (Modifier & (Add1ArgType | Add2ArgTypes))
  Tys.push_back(ArgType);

if (Modifier & Add2ArgTypes)
  Tys.push_back(ArgType);

if (Modifier & InventFloatType)
  Tys.push_back(FloatTy);

return CGM.getIntrinsic(IntrinsicID, Tys);
4278}

4280static Value *EmitCommonNeonSISDBuiltinExpr(CodeGenFunction &CGF,
                                          const NeonIntrinsicInfo &SISDInfo,
                                          SmallVectorImpl<Value *> &Ops,
                                          const CallExpr *E) {
unsigned BuiltinID = SISDInfo.BuiltinID;
unsigned int Int = SISDInfo.LLVMIntrinsic;
unsigned Modifier = SISDInfo.TypeModifier;
const char *s = SISDInfo.NameHint;

switch (BuiltinID) {
case NEON::BI__builtin_neon_vcled_s64:
case NEON::BI__builtin_neon_vcled_u64:
case NEON::BI__builtin_neon_vcles_f32:
case NEON::BI__builtin_neon_vcled_f64:
case NEON::BI__builtin_neon_vcltd_s64:
case NEON::BI__builtin_neon_vcltd_u64:
case NEON::BI__builtin_neon_vclts_f32:
case NEON::BI__builtin_neon_vcltd_f64:
case NEON::BI__builtin_neon_vcales_f32:
case NEON::BI__builtin_neon_vcaled_f64:
case NEON::BI__builtin_neon_vcalts_f32:
case NEON::BI__builtin_neon_vcaltd_f64:
  // Only one direction of comparisons actually exist, cmle is actually a cmge
  // with swapped operands. The table gives us the right intrinsic but we
  // still need to do the swap.
  std::swap(Ops[0], Ops[1]);
  break;
}

assert(Int && "Generic code assumes a valid intrinsic")(static_cast <bool> (Int && "Generic code assumes a valid intrinsic"
) ? void (0) : __assert_fail ("Int && \"Generic code assumes a valid intrinsic\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 4309, __extension__ __PRETTY_FUNCTION__));

// Determine the type(s) of this overloaded AArch64 intrinsic.
const Expr *Arg = E->getArg(0);
llvm::Type *ArgTy = CGF.ConvertType(Arg->getType());
Function *F = CGF.LookupNeonLLVMIntrinsic(Int, Modifier, ArgTy, E);

int j = 0;
ConstantInt *C0 = ConstantInt::get(CGF.SizeTy, 0);
for (Function::const_arg_iterator ai = F->arg_begin(), ae = F->arg_end();
     ai != ae; ++ai, ++j) {
  llvm::Type *ArgTy = ai->getType();
  if (Ops[j]->getType()->getPrimitiveSizeInBits() ==
           ArgTy->getPrimitiveSizeInBits())
    continue;

  assert(ArgTy->isVectorTy() && !Ops[j]->getType()->isVectorTy())(static_cast <bool> (ArgTy->isVectorTy() && !
Ops[j]->getType()->isVectorTy()) ? void (0) : __assert_fail
 ("ArgTy->isVectorTy() && !Ops[j]->getType()->isVectorTy()"
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 4325, __extension__ __PRETTY_FUNCTION__));
  // The constant argument to an _n_ intrinsic always has Int32Ty, so truncate
  // it before inserting.
  Ops[j] =
      CGF.Builder.CreateTruncOrBitCast(Ops[j], ArgTy->getVectorElementType());
  Ops[j] =
      CGF.Builder.CreateInsertElement(UndefValue::get(ArgTy), Ops[j], C0);
}

Value *Result = CGF.EmitNeonCall(F, Ops, s);
llvm::Type *ResultType = CGF.ConvertType(E->getType());
if (ResultType->getPrimitiveSizeInBits() <
    Result->getType()->getPrimitiveSizeInBits())
  return CGF.Builder.CreateExtractElement(Result, C0);

return CGF.Builder.CreateBitCast(Result, ResultType, s);
4341}

4343Value *CodeGenFunction::EmitCommonNeonBuiltinExpr(
  unsigned BuiltinID, unsigned LLVMIntrinsic, unsigned AltLLVMIntrinsic,
  const char *NameHint, unsigned Modifier, const CallExpr *E,
  SmallVectorImpl<llvm::Value *> &Ops, Address PtrOp0, Address PtrOp1,
  llvm::Triple::ArchType Arch) {
// Get the last argument, which specifies the vector type.
llvm::APSInt NeonTypeConst;
const Expr *Arg = E->getArg(E->getNumArgs() - 1);
if (!Arg->isIntegerConstantExpr(NeonTypeConst, getContext()))
  return nullptr;

// Determine the type of this overloaded NEON intrinsic.
NeonTypeFlags Type(NeonTypeConst.getZExtValue());
bool Usgn = Type.isUnsigned();
bool Quad = Type.isQuad();

llvm::VectorType *VTy = GetNeonType(this, Type, Arch);
llvm::Type *Ty = VTy;
if (!Ty)
  return nullptr;

auto getAlignmentValue32 = [&](Address addr) -> Value* {
  return Builder.getInt32(addr.getAlignment().getQuantity());
};

unsigned Int = LLVMIntrinsic;
if ((Modifier & UnsignedAlts) && !Usgn)
  Int = AltLLVMIntrinsic;

switch (BuiltinID) {
default: break;
case NEON::BI__builtin_neon_vabs_v:
case NEON::BI__builtin_neon_vabsq_v:
  if (VTy->getElementType()->isFloatingPointTy())
    return EmitNeonCall(CGM.getIntrinsic(Intrinsic::fabs, Ty), Ops, "vabs");
  return EmitNeonCall(CGM.getIntrinsic(LLVMIntrinsic, Ty), Ops, "vabs");
case NEON::BI__builtin_neon_vaddhn_v: {
  llvm::VectorType *SrcTy =
      llvm::VectorType::getExtendedElementVectorType(VTy);

  // %sum = add <4 x i32> %lhs, %rhs
  Ops[0] = Builder.CreateBitCast(Ops[0], SrcTy);
  Ops[1] = Builder.CreateBitCast(Ops[1], SrcTy);
  Ops[0] = Builder.CreateAdd(Ops[0], Ops[1], "vaddhn");

  // %high = lshr <4 x i32> %sum, <i32 16, i32 16, i32 16, i32 16>
  Constant *ShiftAmt =
      ConstantInt::get(SrcTy, SrcTy->getScalarSizeInBits() / 2);
  Ops[0] = Builder.CreateLShr(Ops[0], ShiftAmt, "vaddhn");

  // %res = trunc <4 x i32> %high to <4 x i16>
  return Builder.CreateTrunc(Ops[0], VTy, "vaddhn");
}
case NEON::BI__builtin_neon_vcale_v:
case NEON::BI__builtin_neon_vcaleq_v:
case NEON::BI__builtin_neon_vcalt_v:
case NEON::BI__builtin_neon_vcaltq_v:
  std::swap(Ops[0], Ops[1]);
  LLVM_FALLTHROUGH[[clang::fallthrough]];
case NEON::BI__builtin_neon_vcage_v:
case NEON::BI__builtin_neon_vcageq_v:
case NEON::BI__builtin_neon_vcagt_v:
case NEON::BI__builtin_neon_vcagtq_v: {
  llvm::Type *Ty;
  switch (VTy->getScalarSizeInBits()) {
  default: llvm_unreachable("unexpected type")::llvm::llvm_unreachable_internal("unexpected type", "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 4408);
  case 32:
    Ty = FloatTy;
    break;
  case 64:
    Ty = DoubleTy;
    break;
  case 16:
    Ty = HalfTy;
    break;
  }
  llvm::Type *VecFlt = llvm::VectorType::get(Ty, VTy->getNumElements());
  llvm::Type *Tys[] = { VTy, VecFlt };
  Function *F = CGM.getIntrinsic(LLVMIntrinsic, Tys);
  return EmitNeonCall(F, Ops, NameHint);
}
case NEON::BI__builtin_neon_vclz_v:
case NEON::BI__builtin_neon_vclzq_v:
  // We generate target-independent intrinsic, which needs a second argument
  // for whether or not clz of zero is undefined; on ARM it isn't.
  Ops.push_back(Builder.getInt1(getTarget().isCLZForZeroUndef()));
  break;
case NEON::BI__builtin_neon_vcvt_f32_v:
case NEON::BI__builtin_neon_vcvtq_f32_v:
  Ops[0] = Builder.CreateBitCast(Ops[0], Ty);
  Ty = GetNeonType(this, NeonTypeFlags(NeonTypeFlags::Float32, false, Quad), Arch);
  return Usgn ? Builder.CreateUIToFP(Ops[0], Ty, "vcvt")
              : Builder.CreateSIToFP(Ops[0], Ty, "vcvt");
case NEON::BI__builtin_neon_vcvt_f16_v:
case NEON::BI__builtin_neon_vcvtq_f16_v:
  Ops[0] = Builder.CreateBitCast(Ops[0], Ty);
  Ty = GetNeonType(this, NeonTypeFlags(NeonTypeFlags::Float16, false, Quad), Arch);
  return Usgn ? Builder.CreateUIToFP(Ops[0], Ty, "vcvt")
              : Builder.CreateSIToFP(Ops[0], Ty, "vcvt");
case NEON::BI__builtin_neon_vcvt_n_f16_v:
case NEON::BI__builtin_neon_vcvt_n_f32_v:
case NEON::BI__builtin_neon_vcvt_n_f64_v:
case NEON::BI__builtin_neon_vcvtq_n_f16_v:
case NEON::BI__builtin_neon_vcvtq_n_f32_v:
case NEON::BI__builtin_neon_vcvtq_n_f64_v: {
  llvm::Type *Tys[2] = { GetFloatNeonType(this, Type), Ty };
  Int = Usgn ? LLVMIntrinsic : AltLLVMIntrinsic;
  Function *F = CGM.getIntrinsic(Int, Tys);
  return EmitNeonCall(F, Ops, "vcvt_n");
}
case NEON::BI__builtin_neon_vcvt_n_s16_v:
case NEON::BI__builtin_neon_vcvt_n_s32_v:
case NEON::BI__builtin_neon_vcvt_n_u16_v:
case NEON::BI__builtin_neon_vcvt_n_u32_v:
case NEON::BI__builtin_neon_vcvt_n_s64_v:
case NEON::BI__builtin_neon_vcvt_n_u64_v:
case NEON::BI__builtin_neon_vcvtq_n_s16_v:
case NEON::BI__builtin_neon_vcvtq_n_s32_v:
case NEON::BI__builtin_neon_vcvtq_n_u16_v:
case NEON::BI__builtin_neon_vcvtq_n_u32_v:
case NEON::BI__builtin_neon_vcvtq_n_s64_v:
case NEON::BI__builtin_neon_vcvtq_n_u64_v: {
  llvm::Type *Tys[2] = { Ty, GetFloatNeonType(this, Type) };
  Function *F = CGM.getIntrinsic(LLVMIntrinsic, Tys);
  return EmitNeonCall(F, Ops, "vcvt_n");
}
case NEON::BI__builtin_neon_vcvt_s32_v:
case NEON::BI__builtin_neon_vcvt_u32_v:
case NEON::BI__builtin_neon_vcvt_s64_v:
case NEON::BI__builtin_neon_vcvt_u64_v:
case NEON::BI__builtin_neon_vcvt_s16_v:
case NEON::BI__builtin_neon_vcvt_u16_v:
case NEON::BI__builtin_neon_vcvtq_s32_v:
case NEON::BI__builtin_neon_vcvtq_u32_v:
case NEON::BI__builtin_neon_vcvtq_s64_v:
case NEON::BI__builtin_neon_vcvtq_u64_v:
case NEON::BI__builtin_neon_vcvtq_s16_v:
case NEON::BI__builtin_neon_vcvtq_u16_v: {
  Ops[0] = Builder.CreateBitCast(Ops[0], GetFloatNeonType(this, Type));
  return Usgn ? Builder.CreateFPToUI(Ops[0], Ty, "vcvt")
              : Builder.CreateFPToSI(Ops[0], Ty, "vcvt");
}
case NEON::BI__builtin_neon_vcvta_s16_v:
case NEON::BI__builtin_neon_vcvta_s32_v:
case NEON::BI__builtin_neon_vcvta_s64_v:
case NEON::BI__builtin_neon_vcvta_u32_v:
case NEON::BI__builtin_neon_vcvta_u64_v:
case NEON::BI__builtin_neon_vcvtaq_s16_v:
case NEON::BI__builtin_neon_vcvtaq_s32_v:
case NEON::BI__builtin_neon_vcvtaq_s64_v:
case NEON::BI__builtin_neon_vcvtaq_u16_v:
case NEON::BI__builtin_neon_vcvtaq_u32_v:
case NEON::BI__builtin_neon_vcvtaq_u64_v:
case NEON::BI__builtin_neon_vcvtn_s16_v:
case NEON::BI__builtin_neon_vcvtn_s32_v:
case NEON::BI__builtin_neon_vcvtn_s64_v:
case NEON::BI__builtin_neon_vcvtn_u16_v:
case NEON::BI__builtin_neon_vcvtn_u32_v:
case NEON::BI__builtin_neon_vcvtn_u64_v:
case NEON::BI__builtin_neon_vcvtnq_s16_v:
case NEON::BI__builtin_neon_vcvtnq_s32_v:
case NEON::BI__builtin_neon_vcvtnq_s64_v:
case NEON::BI__builtin_neon_vcvtnq_u16_v:
case NEON::BI__builtin_neon_vcvtnq_u32_v:
case NEON::BI__builtin_neon_vcvtnq_u64_v:
case NEON::BI__builtin_neon_vcvtp_s16_v:
case NEON::BI__builtin_neon_vcvtp_s32_v:
case NEON::BI__builtin_neon_vcvtp_s64_v:
case NEON::BI__builtin_neon_vcvtp_u16_v:
case NEON::BI__builtin_neon_vcvtp_u32_v:
case NEON::BI__builtin_neon_vcvtp_u64_v:
case NEON::BI__builtin_neon_vcvtpq_s16_v:
case NEON::BI__builtin_neon_vcvtpq_s32_v:
case NEON::BI__builtin_neon_vcvtpq_s64_v:
case NEON::BI__builtin_neon_vcvtpq_u16_v:
case NEON::BI__builtin_neon_vcvtpq_u32_v:
case NEON::BI__builtin_neon_vcvtpq_u64_v:
case NEON::BI__builtin_neon_vcvtm_s16_v:
case NEON::BI__builtin_neon_vcvtm_s32_v:
case NEON::BI__builtin_neon_vcvtm_s64_v:
case NEON::BI__builtin_neon_vcvtm_u16_v:
case NEON::BI__builtin_neon_vcvtm_u32_v:
case NEON::BI__builtin_neon_vcvtm_u64_v:
case NEON::BI__builtin_neon_vcvtmq_s16_v:
case NEON::BI__builtin_neon_vcvtmq_s32_v:
case NEON::BI__builtin_neon_vcvtmq_s64_v:
case NEON::BI__builtin_neon_vcvtmq_u16_v:
case NEON::BI__builtin_neon_vcvtmq_u32_v:
case NEON::BI__builtin_neon_vcvtmq_u64_v: {
  llvm::Type *Tys[2] = { Ty, GetFloatNeonType(this, Type) };
  return EmitNeonCall(CGM.getIntrinsic(LLVMIntrinsic, Tys), Ops, NameHint);
}
case NEON::BI__builtin_neon_vext_v:
case NEON::BI__builtin_neon_vextq_v: {
  int CV = cast<ConstantInt>(Ops[2])->getSExtValue();
  SmallVector<uint32_t, 16> Indices;
  for (unsigned i = 0, e = VTy->getNumElements(); i != e; ++i)
    Indices.push_back(i+CV);

  Ops[0] = Builder.CreateBitCast(Ops[0], Ty);
  Ops[1] = Builder.CreateBitCast(Ops[1], Ty);
  return Builder.CreateShuffleVector(Ops[0], Ops[1], Indices, "vext");
}
case NEON::BI__builtin_neon_vfma_v:
case NEON::BI__builtin_neon_vfmaq_v: {
  Value *F = CGM.getIntrinsic(Intrinsic::fma, Ty);
  Ops[0] = Builder.CreateBitCast(Ops[0], Ty);
  Ops[1] = Builder.CreateBitCast(Ops[1], Ty);
  Ops[2] = Builder.CreateBitCast(Ops[2], Ty);

  // NEON intrinsic puts accumulator first, unlike the LLVM fma.
  return Builder.CreateCall(F, {Ops[1], Ops[2], Ops[0]});
}
case NEON::BI__builtin_neon_vld1_v:
case NEON::BI__builtin_neon_vld1q_v: {
  llvm::Type *Tys[] = {Ty, Int8PtrTy};
  Ops.push_back(getAlignmentValue32(PtrOp0));
  return EmitNeonCall(CGM.getIntrinsic(LLVMIntrinsic, Tys), Ops, "vld1");
}
case NEON::BI__builtin_neon_vld2_v:
case NEON::BI__builtin_neon_vld2q_v:
case NEON::BI__builtin_neon_vld3_v:
case NEON::BI__builtin_neon_vld3q_v:
case NEON::BI__builtin_neon_vld4_v:
case NEON::BI__builtin_neon_vld4q_v: {
  llvm::Type *Tys[] = {Ty, Int8PtrTy};
  Function *F = CGM.getIntrinsic(LLVMIntrinsic, Tys);
  Value *Align = getAlignmentValue32(PtrOp1);
  Ops[1] = Builder.CreateCall(F, {Ops[1], Align}, NameHint);
  Ty = llvm::PointerType::getUnqual(Ops[1]->getType());
  Ops[0] = Builder.CreateBitCast(Ops[0], Ty);
  return Builder.CreateDefaultAlignedStore(Ops[1], Ops[0]);
}
case NEON::BI__builtin_neon_vld1_dup_v:
case NEON::BI__builtin_neon_vld1q_dup_v: {
  Value *V = UndefValue::get(Ty);
  Ty = llvm::PointerType::getUnqual(VTy->getElementType());
  PtrOp0 = Builder.CreateBitCast(PtrOp0, Ty);
  LoadInst *Ld = Builder.CreateLoad(PtrOp0);
  llvm::Constant *CI = ConstantInt::get(SizeTy, 0);
  Ops[0] = Builder.CreateInsertElement(V, Ld, CI);
  return EmitNeonSplat(Ops[0], CI);
}
case NEON::BI__builtin_neon_vld2_lane_v:
case NEON::BI__builtin_neon_vld2q_lane_v:
case NEON::BI__builtin_neon_vld3_lane_v:
case NEON::BI__builtin_neon_vld3q_lane_v:
case NEON::BI__builtin_neon_vld4_lane_v:
case NEON::BI__builtin_neon_vld4q_lane_v: {
  llvm::Type *Tys[] = {Ty, Int8PtrTy};
  Function *F = CGM.getIntrinsic(LLVMIntrinsic, Tys);
  for (unsigned I = 2; I < Ops.size() - 1; ++I)
    Ops[I] = Builder.CreateBitCast(Ops[I], Ty);
  Ops.push_back(getAlignmentValue32(PtrOp1));
  Ops[1] = Builder.CreateCall(F, makeArrayRef(Ops).slice(1), NameHint);
  Ty = llvm::PointerType::getUnqual(Ops[1]->getType());
  Ops[0] = Builder.CreateBitCast(Ops[0], Ty);
  return Builder.CreateDefaultAlignedStore(Ops[1], Ops[0]);
}
case NEON::BI__builtin_neon_vmovl_v: {
  llvm::Type *DTy =llvm::VectorType::getTruncatedElementVectorType(VTy);
  Ops[0] = Builder.CreateBitCast(Ops[0], DTy);
  if (Usgn)
    return Builder.CreateZExt(Ops[0], Ty, "vmovl");
  return Builder.CreateSExt(Ops[0], Ty, "vmovl");
}
case NEON::BI__builtin_neon_vmovn_v: {
  llvm::Type *QTy = llvm::VectorType::getExtendedElementVectorType(VTy);
  Ops[0] = Builder.CreateBitCast(Ops[0], QTy);
  return Builder.CreateTrunc(Ops[0], Ty, "vmovn");
}
case NEON::BI__builtin_neon_vmull_v:
  // FIXME: the integer vmull operations could be emitted in terms of pure
  // LLVM IR (2 exts followed by a mul). Unfortunately LLVM has a habit of
  // hoisting the exts outside loops. Until global ISel comes along that can
  // see through such movement this leads to bad CodeGen. So we need an
  // intrinsic for now.
  Int = Usgn ? Intrinsic::arm_neon_vmullu : Intrinsic::arm_neon_vmulls;
  Int = Type.isPoly() ? (unsigned)Intrinsic::arm_neon_vmullp : Int;
  return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vmull");
case NEON::BI__builtin_neon_vpadal_v:
case NEON::BI__builtin_neon_vpadalq_v: {
  // The source operand type has twice as many elements of half the size.
  unsigned EltBits = VTy->getElementType()->getPrimitiveSizeInBits();
  llvm::Type *EltTy =
    llvm::IntegerType::get(getLLVMContext(), EltBits / 2);
  llvm::Type *NarrowTy =
    llvm::VectorType::get(EltTy, VTy->getNumElements() * 2);
  llvm::Type *Tys[2] = { Ty, NarrowTy };
  return EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, NameHint);
}
case NEON::BI__builtin_neon_vpaddl_v:
case NEON::BI__builtin_neon_vpaddlq_v: {
  // The source operand type has twice as many elements of half the size.
  unsigned EltBits = VTy->getElementType()->getPrimitiveSizeInBits();
  llvm::Type *EltTy = llvm::IntegerType::get(getLLVMContext(), EltBits / 2);
  llvm::Type *NarrowTy =
    llvm::VectorType::get(EltTy, VTy->getNumElements() * 2);
  llvm::Type *Tys[2] = { Ty, NarrowTy };
  return EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vpaddl");
}
case NEON::BI__builtin_neon_vqdmlal_v:
case NEON::BI__builtin_neon_vqdmlsl_v: {
  SmallVector<Value *, 2> MulOps(Ops.begin() + 1, Ops.end());
  Ops[1] =
      EmitNeonCall(CGM.getIntrinsic(LLVMIntrinsic, Ty), MulOps, "vqdmlal");
  Ops.resize(2);
  return EmitNeonCall(CGM.getIntrinsic(AltLLVMIntrinsic, Ty), Ops, NameHint);
}
case NEON::BI__builtin_neon_vqshl_n_v:
case NEON::BI__builtin_neon_vqshlq_n_v:
  return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vqshl_n",
                      1, false);
case NEON::BI__builtin_neon_vqshlu_n_v:
case NEON::BI__builtin_neon_vqshluq_n_v:
  return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vqshlu_n",
                      1, false);
case NEON::BI__builtin_neon_vrecpe_v:
case NEON::BI__builtin_neon_vrecpeq_v:
case NEON::BI__builtin_neon_vrsqrte_v:
case NEON::BI__builtin_neon_vrsqrteq_v:
  Int = Ty->isFPOrFPVectorTy() ? LLVMIntrinsic : AltLLVMIntrinsic;
  return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, NameHint);

case NEON::BI__builtin_neon_vrshr_n_v:
case NEON::BI__builtin_neon_vrshrq_n_v:
  return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vrshr_n",
                      1, true);
case NEON::BI__builtin_neon_vshl_n_v:
case NEON::BI__builtin_neon_vshlq_n_v:
  Ops[1] = EmitNeonShiftVector(Ops[1], Ty, false);
  return Builder.CreateShl(Builder.CreateBitCast(Ops[0],Ty), Ops[1],
                           "vshl_n");
case NEON::BI__builtin_neon_vshll_n_v: {
  llvm::Type *SrcTy = llvm::VectorType::getTruncatedElementVectorType(VTy);
  Ops[0] = Builder.CreateBitCast(Ops[0], SrcTy);
  if (Usgn)
    Ops[0] = Builder.CreateZExt(Ops[0], VTy);
  else
    Ops[0] = Builder.CreateSExt(Ops[0], VTy);
  Ops[1] = EmitNeonShiftVector(Ops[1], VTy, false);
  return Builder.CreateShl(Ops[0], Ops[1], "vshll_n");
}
case NEON::BI__builtin_neon_vshrn_n_v: {
  llvm::Type *SrcTy = llvm::VectorType::getExtendedElementVectorType(VTy);
  Ops[0] = Builder.CreateBitCast(Ops[0], SrcTy);
  Ops[1] = EmitNeonShiftVector(Ops[1], SrcTy, false);
  if (Usgn)
    Ops[0] = Builder.CreateLShr(Ops[0], Ops[1]);
  else
    Ops[0] = Builder.CreateAShr(Ops[0], Ops[1]);
  return Builder.CreateTrunc(Ops[0], Ty, "vshrn_n");
}
case NEON::BI__builtin_neon_vshr_n_v:
case NEON::BI__builtin_neon_vshrq_n_v:
  return EmitNeonRShiftImm(Ops[0], Ops[1], Ty, Usgn, "vshr_n");
case NEON::BI__builtin_neon_vst1_v:
case NEON::BI__builtin_neon_vst1q_v:
case NEON::BI__builtin_neon_vst2_v:
case NEON::BI__builtin_neon_vst2q_v:
case NEON::BI__builtin_neon_vst3_v:
case NEON::BI__builtin_neon_vst3q_v:
case NEON::BI__builtin_neon_vst4_v:
case NEON::BI__builtin_neon_vst4q_v:
case NEON::BI__builtin_neon_vst2_lane_v:
case NEON::BI__builtin_neon_vst2q_lane_v:
case NEON::BI__builtin_neon_vst3_lane_v:
case NEON::BI__builtin_neon_vst3q_lane_v:
case NEON::BI__builtin_neon_vst4_lane_v:
case NEON::BI__builtin_neon_vst4q_lane_v: {
  llvm::Type *Tys[] = {Int8PtrTy, Ty};
  Ops.push_back(getAlignmentValue32(PtrOp0));
  return EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "");
}
case NEON::BI__builtin_neon_vsubhn_v: {
  llvm::VectorType *SrcTy =
      llvm::VectorType::getExtendedElementVectorType(VTy);

  // %sum = add <4 x i32> %lhs, %rhs
  Ops[0] = Builder.CreateBitCast(Ops[0], SrcTy);
  Ops[1] = Builder.CreateBitCast(Ops[1], SrcTy);
  Ops[0] = Builder.CreateSub(Ops[0], Ops[1], "vsubhn");

  // %high = lshr <4 x i32> %sum, <i32 16, i32 16, i32 16, i32 16>
  Constant *ShiftAmt =
      ConstantInt::get(SrcTy, SrcTy->getScalarSizeInBits() / 2);
  Ops[0] = Builder.CreateLShr(Ops[0], ShiftAmt, "vsubhn");

  // %res = trunc <4 x i32> %high to <4 x i16>
  return Builder.CreateTrunc(Ops[0], VTy, "vsubhn");
}
case NEON::BI__builtin_neon_vtrn_v:
case NEON::BI__builtin_neon_vtrnq_v: {
  Ops[0] = Builder.CreateBitCast(Ops[0], llvm::PointerType::getUnqual(Ty));
  Ops[1] = Builder.CreateBitCast(Ops[1], Ty);
  Ops[2] = Builder.CreateBitCast(Ops[2], Ty);
  Value *SV = nullptr;

  for (unsigned vi = 0; vi != 2; ++vi) {
    SmallVector<uint32_t, 16> Indices;
    for (unsigned i = 0, e = VTy->getNumElements(); i != e; i += 2) {
      Indices.push_back(i+vi);
      Indices.push_back(i+e+vi);
    }
    Value *Addr = Builder.CreateConstInBoundsGEP1_32(Ty, Ops[0], vi);
    SV = Builder.CreateShuffleVector(Ops[1], Ops[2], Indices, "vtrn");
    SV = Builder.CreateDefaultAlignedStore(SV, Addr);
  }
  return SV;
}
case NEON::BI__builtin_neon_vtst_v:
case NEON::BI__builtin_neon_vtstq_v: {
  Ops[0] = Builder.CreateBitCast(Ops[0], Ty);
  Ops[1] = Builder.CreateBitCast(Ops[1], Ty);
  Ops[0] = Builder.CreateAnd(Ops[0], Ops[1]);
  Ops[0] = Builder.CreateICmp(ICmpInst::ICMP_NE, Ops[0],
                              ConstantAggregateZero::get(Ty));
  return Builder.CreateSExt(Ops[0], Ty, "vtst");
}
case NEON::BI__builtin_neon_vuzp_v:
case NEON::BI__builtin_neon_vuzpq_v: {
  Ops[0] = Builder.CreateBitCast(Ops[0], llvm::PointerType::getUnqual(Ty));
  Ops[1] = Builder.CreateBitCast(Ops[1], Ty);
  Ops[2] = Builder.CreateBitCast(Ops[2], Ty);
  Value *SV = nullptr;

  for (unsigned vi = 0; vi != 2; ++vi) {
    SmallVector<uint32_t, 16> Indices;
    for (unsigned i = 0, e = VTy->getNumElements(); i != e; ++i)
      Indices.push_back(2*i+vi);

    Value *Addr = Builder.CreateConstInBoundsGEP1_32(Ty, Ops[0], vi);
    SV = Builder.CreateShuffleVector(Ops[1], Ops[2], Indices, "vuzp");
    SV = Builder.CreateDefaultAlignedStore(SV, Addr);
  }
  return SV;
}
case NEON::BI__builtin_neon_vzip_v:
case NEON::BI__builtin_neon_vzipq_v: {
  Ops[0] = Builder.CreateBitCast(Ops[0], llvm::PointerType::getUnqual(Ty));
  Ops[1] = Builder.CreateBitCast(Ops[1], Ty);
  Ops[2] = Builder.CreateBitCast(Ops[2], Ty);
  Value *SV = nullptr;

  for (unsigned vi = 0; vi != 2; ++vi) {
    SmallVector<uint32_t, 16> Indices;
    for (unsigned i = 0, e = VTy->getNumElements(); i != e; i += 2) {
      Indices.push_back((i + vi*e) >> 1);
      Indices.push_back(((i + vi*e) >> 1)+e);
    }
    Value *Addr = Builder.CreateConstInBoundsGEP1_32(Ty, Ops[0], vi);
    SV = Builder.CreateShuffleVector(Ops[1], Ops[2], Indices, "vzip");
    SV = Builder.CreateDefaultAlignedStore(SV, Addr);
  }
  return SV;
}
}

assert(Int && "Expected valid intrinsic number")(static_cast <bool> (Int && "Expected valid intrinsic number"
) ? void (0) : __assert_fail ("Int && \"Expected valid intrinsic number\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 4801, __extension__ __PRETTY_FUNCTION__));

// Determine the type(s) of this overloaded AArch64 intrinsic.
Function *F = LookupNeonLLVMIntrinsic(Int, Modifier, Ty, E);

Value *Result = EmitNeonCall(F, Ops, NameHint);
llvm::Type *ResultType = ConvertType(E->getType());
// AArch64 intrinsic one-element vector type cast to
// scalar type expected by the builtin
return Builder.CreateBitCast(Result, ResultType, NameHint);
4811}

4813Value *CodeGenFunction::EmitAArch64CompareBuiltinExpr(
  Value *Op, llvm::Type *Ty, const CmpInst::Predicate Fp,
  const CmpInst::Predicate Ip, const Twine &Name) {
llvm::Type *OTy = Op->getType();

// FIXME: this is utterly horrific. We should not be looking at previous
// codegen context to find out what needs doing. Unfortunately TableGen
// currently gives us exactly the same calls for vceqz_f32 and vceqz_s32
// (etc).
if (BitCastInst *BI = dyn_cast<BitCastInst>(Op))
  OTy = BI->getOperand(0)->getType();

Op = Builder.CreateBitCast(Op, OTy);
if (OTy->getScalarType()->isFloatingPointTy()) {
  Op = Builder.CreateFCmp(Fp, Op, Constant::getNullValue(OTy));
} else {
  Op = Builder.CreateICmp(Ip, Op, Constant::getNullValue(OTy));
}
return Builder.CreateSExt(Op, Ty, Name);
4832}

4834static Value *packTBLDVectorList(CodeGenFunction &CGF, ArrayRef<Value *> Ops,
                               Value *ExtOp, Value *IndexOp,
                               llvm::Type *ResTy, unsigned IntID,
                               const char *Name) {
SmallVector<Value *, 2> TblOps;
if (ExtOp)
  TblOps.push_back(ExtOp);

// Build a vector containing sequential number like (0, 1, 2, ..., 15)
SmallVector<uint32_t, 16> Indices;
llvm::VectorType *TblTy = cast<llvm::VectorType>(Ops[0]->getType());
for (unsigned i = 0, e = TblTy->getNumElements(); i != e; ++i) {
  Indices.push_back(2*i);
  Indices.push_back(2*i+1);
}

int PairPos = 0, End = Ops.size() - 1;
while (PairPos < End) {
  TblOps.push_back(CGF.Builder.CreateShuffleVector(Ops[PairPos],
                                                   Ops[PairPos+1], Indices,
                                                   Name));
  PairPos += 2;
}

// If there's an odd number of 64-bit lookup table, fill the high 64-bit
// of the 128-bit lookup table with zero.
if (PairPos == End) {
  Value *ZeroTbl = ConstantAggregateZero::get(TblTy);
  TblOps.push_back(CGF.Builder.CreateShuffleVector(Ops[PairPos],
                                                   ZeroTbl, Indices, Name));
}

Function *TblF;
TblOps.push_back(IndexOp);
TblF = CGF.CGM.getIntrinsic(IntID, ResTy);

return CGF.EmitNeonCall(TblF, TblOps, Name);
4871}

4873Value *CodeGenFunction::GetValueForARMHint(unsigned BuiltinID) {
unsigned Value;
switch (BuiltinID) {
default:
  return nullptr;
case ARM::BI__builtin_arm_nop:
  Value = 0;
  break;
case ARM::BI__builtin_arm_yield:
case ARM::BI__yield:
  Value = 1;
  break;
case ARM::BI__builtin_arm_wfe:
case ARM::BI__wfe:
  Value = 2;
  break;
case ARM::BI__builtin_arm_wfi:
case ARM::BI__wfi:
  Value = 3;
  break;
case ARM::BI__builtin_arm_sev:
case ARM::BI__sev:
  Value = 4;
  break;
case ARM::BI__builtin_arm_sevl:
case ARM::BI__sevl:
  Value = 5;
  break;
}

return Builder.CreateCall(CGM.getIntrinsic(Intrinsic::arm_hint),
                          llvm::ConstantInt::get(Int32Ty, Value));
4905}

4907// Generates the IR for the read/write special register builtin,
4908// ValueType is the type of the value that is to be written or read,
4909// RegisterType is the type of the register being written to or read from.
4910static Value *EmitSpecialRegisterBuiltin(CodeGenFunction &CGF,
                                       const CallExpr *E,
                                       llvm::Type *RegisterType,
                                       llvm::Type *ValueType,
                                       bool IsRead,
                                       StringRef SysReg = "") {
// write and register intrinsics only support 32 and 64 bit operations.
assert((RegisterType->isIntegerTy(32) || RegisterType->isIntegerTy(64))(static_cast <bool> ((RegisterType->isIntegerTy(32) ||
 RegisterType->isIntegerTy(64)) && "Unsupported size for register."
) ? void (0) : __assert_fail ("(RegisterType->isIntegerTy(32) || RegisterType->isIntegerTy(64)) && \"Unsupported size for register.\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 4918, __extension__ __PRETTY_FUNCTION__))
        && "Unsupported size for register.")(static_cast <bool> ((RegisterType->isIntegerTy(32) ||
 RegisterType->isIntegerTy(64)) && "Unsupported size for register."
) ? void (0) : __assert_fail ("(RegisterType->isIntegerTy(32) || RegisterType->isIntegerTy(64)) && \"Unsupported size for register.\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 4918, __extension__ __PRETTY_FUNCTION__));

CodeGen::CGBuilderTy &Builder = CGF.Builder;
CodeGen::CodeGenModule &CGM = CGF.CGM;
LLVMContext &Context = CGM.getLLVMContext();

if (SysReg.empty()) {
  const Expr *SysRegStrExpr = E->getArg(0)->IgnoreParenCasts();
  SysReg = cast<clang::StringLiteral>(SysRegStrExpr)->getString();
}

llvm::Metadata *Ops[] = { llvm::MDString::get(Context, SysReg) };
llvm::MDNode *RegName = llvm::MDNode::get(Context, Ops);
llvm::Value *Metadata = llvm::MetadataAsValue::get(Context, RegName);

llvm::Type *Types[] = { RegisterType };

bool MixedTypes = RegisterType->isIntegerTy(64) && ValueType->isIntegerTy(32);
assert(!(RegisterType->isIntegerTy(32) && ValueType->isIntegerTy(64))(static_cast <bool> (!(RegisterType->isIntegerTy(32)
 && ValueType->isIntegerTy(64)) && "Can't fit 64-bit value in 32-bit register"
) ? void (0) : __assert_fail ("!(RegisterType->isIntegerTy(32) && ValueType->isIntegerTy(64)) && \"Can't fit 64-bit value in 32-bit register\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 4937, __extension__ __PRETTY_FUNCTION__))
          && "Can't fit 64-bit value in 32-bit register")(static_cast <bool> (!(RegisterType->isIntegerTy(32)
 && ValueType->isIntegerTy(64)) && "Can't fit 64-bit value in 32-bit register"
) ? void (0) : __assert_fail ("!(RegisterType->isIntegerTy(32) && ValueType->isIntegerTy(64)) && \"Can't fit 64-bit value in 32-bit register\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 4937, __extension__ __PRETTY_FUNCTION__));

if (IsRead) {
  llvm::Value *F = CGM.getIntrinsic(llvm::Intrinsic::read_register, Types);
  llvm::Value *Call = Builder.CreateCall(F, Metadata);

  if (MixedTypes)
    // Read into 64 bit register and then truncate result to 32 bit.
    return Builder.CreateTrunc(Call, ValueType);

  if (ValueType->isPointerTy())
    // Have i32/i64 result (Call) but want to return a VoidPtrTy (i8*).
    return Builder.CreateIntToPtr(Call, ValueType);

  return Call;
}

llvm::Value *F = CGM.getIntrinsic(llvm::Intrinsic::write_register, Types);
llvm::Value *ArgValue = CGF.EmitScalarExpr(E->getArg(1));
if (MixedTypes) {
  // Extend 32 bit write value to 64 bit to pass to write.
  ArgValue = Builder.CreateZExt(ArgValue, RegisterType);
  return Builder.CreateCall(F, { Metadata, ArgValue });
}

if (ValueType->isPointerTy()) {
  // Have VoidPtrTy ArgValue but want to return an i32/i64.
  ArgValue = Builder.CreatePtrToInt(ArgValue, RegisterType);
  return Builder.CreateCall(F, { Metadata, ArgValue });
}

return Builder.CreateCall(F, { Metadata, ArgValue });
4969}

4971/// Return true if BuiltinID is an overloaded Neon intrinsic with an extra
4972/// argument that specifies the vector type.
4973static bool HasExtraNeonArgument(unsigned BuiltinID) {
switch (BuiltinID) {
default: break;
case NEON::BI__builtin_neon_vget_lane_i8:
case NEON::BI__builtin_neon_vget_lane_i16:
case NEON::BI__builtin_neon_vget_lane_i32:
case NEON::BI__builtin_neon_vget_lane_i64:
case NEON::BI__builtin_neon_vget_lane_f32:
case NEON::BI__builtin_neon_vgetq_lane_i8:
case NEON::BI__builtin_neon_vgetq_lane_i16:
case NEON::BI__builtin_neon_vgetq_lane_i32:
case NEON::BI__builtin_neon_vgetq_lane_i64:
case NEON::BI__builtin_neon_vgetq_lane_f32:
case NEON::BI__builtin_neon_vset_lane_i8:
case NEON::BI__builtin_neon_vset_lane_i16:
case NEON::BI__builtin_neon_vset_lane_i32:
case NEON::BI__builtin_neon_vset_lane_i64:
case NEON::BI__builtin_neon_vset_lane_f32:
case NEON::BI__builtin_neon_vsetq_lane_i8:
case NEON::BI__builtin_neon_vsetq_lane_i16:
case NEON::BI__builtin_neon_vsetq_lane_i32:
case NEON::BI__builtin_neon_vsetq_lane_i64:
case NEON::BI__builtin_neon_vsetq_lane_f32:
case NEON::BI__builtin_neon_vsha1h_u32:
case NEON::BI__builtin_neon_vsha1cq_u32:
case NEON::BI__builtin_neon_vsha1pq_u32:
case NEON::BI__builtin_neon_vsha1mq_u32:
case clang::ARM::BI_MoveToCoprocessor:
case clang::ARM::BI_MoveToCoprocessor2:
  return false;
}
return true;
5005}

5007Value *CodeGenFunction::EmitARMBuiltinExpr(unsigned BuiltinID,
                                         const CallExpr *E,
                                         llvm::Triple::ArchType Arch) {
if (auto Hint = GetValueForARMHint(BuiltinID))
  return Hint;

if (BuiltinID == ARM::BI__emit) {
  bool IsThumb = getTarget().getTriple().getArch() == llvm::Triple::thumb;
  llvm::FunctionType *FTy =
      llvm::FunctionType::get(VoidTy, /*Variadic=*/false);

  APSInt Value;
  if (!E->getArg(0)->EvaluateAsInt(Value, CGM.getContext()))
    llvm_unreachable("Sema will ensure that the parameter is constant")::llvm::llvm_unreachable_internal("Sema will ensure that the parameter is constant"
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 5020);

  uint64_t ZExtValue = Value.zextOrTrunc(IsThumb ? 16 : 32).getZExtValue();

  llvm::InlineAsm *Emit =
      IsThumb ? InlineAsm::get(FTy, ".inst.n 0x" + utohexstr(ZExtValue), "",
                               /*SideEffects=*/true)
              : InlineAsm::get(FTy, ".inst 0x" + utohexstr(ZExtValue), "",
                               /*SideEffects=*/true);

  return Builder.CreateCall(Emit);
}

if (BuiltinID == ARM::BI__builtin_arm_dbg) {
  Value *Option = EmitScalarExpr(E->getArg(0));
  return Builder.CreateCall(CGM.getIntrinsic(Intrinsic::arm_dbg), Option);
}

if (BuiltinID == ARM::BI__builtin_arm_prefetch) {
  Value *Address = EmitScalarExpr(E->getArg(0));
  Value *RW      = EmitScalarExpr(E->getArg(1));
  Value *IsData  = EmitScalarExpr(E->getArg(2));

  // Locality is not supported on ARM target
  Value *Locality = llvm::ConstantInt::get(Int32Ty, 3);

  Value *F = CGM.getIntrinsic(Intrinsic::prefetch);
  return Builder.CreateCall(F, {Address, RW, Locality, IsData});
}

if (BuiltinID == ARM::BI__builtin_arm_rbit) {
  llvm::Value *Arg = EmitScalarExpr(E->getArg(0));
  return Builder.CreateCall(
      CGM.getIntrinsic(Intrinsic::bitreverse, Arg->getType()), Arg, "rbit");
}

if (BuiltinID == ARM::BI__clear_cache) {
  assert(E->getNumArgs() == 2 && "__clear_cache takes 2 arguments")(static_cast <bool> (E->getNumArgs() == 2 &&
 "__clear_cache takes 2 arguments") ? void (0) : __assert_fail
 ("E->getNumArgs() == 2 && \"__clear_cache takes 2 arguments\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 5057, __extension__ __PRETTY_FUNCTION__));
  const FunctionDecl *FD = E->getDirectCallee();
  Value *Ops[2];
  for (unsigned i = 0; i < 2; i++)
    Ops[i] = EmitScalarExpr(E->getArg(i));
  llvm::Type *Ty = CGM.getTypes().ConvertType(FD->getType());
  llvm::FunctionType *FTy = cast<llvm::FunctionType>(Ty);
  StringRef Name = FD->getName();
  return EmitNounwindRuntimeCall(CGM.CreateRuntimeFunction(FTy, Name), Ops);
}

if (BuiltinID == ARM::BI__builtin_arm_mcrr ||
    BuiltinID == ARM::BI__builtin_arm_mcrr2) {
  Function *F;

  switch (BuiltinID) {
  default: llvm_unreachable("unexpected builtin")::llvm::llvm_unreachable_internal("unexpected builtin", "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 5073);
  case ARM::BI__builtin_arm_mcrr:
    F = CGM.getIntrinsic(Intrinsic::arm_mcrr);
    break;
  case ARM::BI__builtin_arm_mcrr2:
    F = CGM.getIntrinsic(Intrinsic::arm_mcrr2);
    break;
  }

  // MCRR{2} instruction has 5 operands but
  // the intrinsic has 4 because Rt and Rt2
  // are represented as a single unsigned 64
  // bit integer in the intrinsic definition
  // but internally it's represented as 2 32
  // bit integers.

  Value *Coproc = EmitScalarExpr(E->getArg(0));
  Value *Opc1 = EmitScalarExpr(E->getArg(1));
  Value *RtAndRt2 = EmitScalarExpr(E->getArg(2));
  Value *CRm = EmitScalarExpr(E->getArg(3));

  Value *C1 = llvm::ConstantInt::get(Int64Ty, 32);
  Value *Rt = Builder.CreateTruncOrBitCast(RtAndRt2, Int32Ty);
  Value *Rt2 = Builder.CreateLShr(RtAndRt2, C1);
  Rt2 = Builder.CreateTruncOrBitCast(Rt2, Int32Ty);

  return Builder.CreateCall(F, {Coproc, Opc1, Rt, Rt2, CRm});
}

if (BuiltinID == ARM::BI__builtin_arm_mrrc ||
    BuiltinID == ARM::BI__builtin_arm_mrrc2) {
  Function *F;

  switch (BuiltinID) {
  default: llvm_unreachable("unexpected builtin")::llvm::llvm_unreachable_internal("unexpected builtin", "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 5107);
  case ARM::BI__builtin_arm_mrrc:
    F = CGM.getIntrinsic(Intrinsic::arm_mrrc);
    break;
  case ARM::BI__builtin_arm_mrrc2:
    F = CGM.getIntrinsic(Intrinsic::arm_mrrc2);
    break;
  }

  Value *Coproc = EmitScalarExpr(E->getArg(0));
  Value *Opc1 = EmitScalarExpr(E->getArg(1));
  Value *CRm  = EmitScalarExpr(E->getArg(2));
  Value *RtAndRt2 = Builder.CreateCall(F, {Coproc, Opc1, CRm});

  // Returns an unsigned 64 bit integer, represented
  // as two 32 bit integers.

  Value *Rt = Builder.CreateExtractValue(RtAndRt2, 1);
  Value *Rt1 = Builder.CreateExtractValue(RtAndRt2, 0);
  Rt = Builder.CreateZExt(Rt, Int64Ty);
  Rt1 = Builder.CreateZExt(Rt1, Int64Ty);

  Value *ShiftCast = llvm::ConstantInt::get(Int64Ty, 32);
  RtAndRt2 = Builder.CreateShl(Rt, ShiftCast, "shl", true);
  RtAndRt2 = Builder.CreateOr(RtAndRt2, Rt1);

  return Builder.CreateBitCast(RtAndRt2, ConvertType(E->getType()));
}

if (BuiltinID == ARM::BI__builtin_arm_ldrexd ||
    ((BuiltinID == ARM::BI__builtin_arm_ldrex ||
      BuiltinID == ARM::BI__builtin_arm_ldaex) &&
     getContext().getTypeSize(E->getType()) == 64) ||
    BuiltinID == ARM::BI__ldrexd) {
  Function *F;

  switch (BuiltinID) {
  default: llvm_unreachable("unexpected builtin")::llvm::llvm_unreachable_internal("unexpected builtin", "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 5144);
  case ARM::BI__builtin_arm_ldaex:
    F = CGM.getIntrinsic(Intrinsic::arm_ldaexd);
    break;
  case ARM::BI__builtin_arm_ldrexd:
  case ARM::BI__builtin_arm_ldrex:
  case ARM::BI__ldrexd:
    F = CGM.getIntrinsic(Intrinsic::arm_ldrexd);
    break;
  }

  Value *LdPtr = EmitScalarExpr(E->getArg(0));
  Value *Val = Builder.CreateCall(F, Builder.CreateBitCast(LdPtr, Int8PtrTy),
                                  "ldrexd");

  Value *Val0 = Builder.CreateExtractValue(Val, 1);
  Value *Val1 = Builder.CreateExtractValue(Val, 0);
  Val0 = Builder.CreateZExt(Val0, Int64Ty);
  Val1 = Builder.CreateZExt(Val1, Int64Ty);

  Value *ShiftCst = llvm::ConstantInt::get(Int64Ty, 32);
  Val = Builder.CreateShl(Val0, ShiftCst, "shl", true /* nuw */);
  Val = Builder.CreateOr(Val, Val1);
  return Builder.CreateBitCast(Val, ConvertType(E->getType()));
}

if (BuiltinID == ARM::BI__builtin_arm_ldrex ||
    BuiltinID == ARM::BI__builtin_arm_ldaex) {
  Value *LoadAddr = EmitScalarExpr(E->getArg(0));

  QualType Ty = E->getType();
  llvm::Type *RealResTy = ConvertType(Ty);
  llvm::Type *PtrTy = llvm::IntegerType::get(
      getLLVMContext(), getContext().getTypeSize(Ty))->getPointerTo();
  LoadAddr = Builder.CreateBitCast(LoadAddr, PtrTy);

  Function *F = CGM.getIntrinsic(BuiltinID == ARM::BI__builtin_arm_ldaex
                                     ? Intrinsic::arm_ldaex
                                     : Intrinsic::arm_ldrex,
                                 PtrTy);
  Value *Val = Builder.CreateCall(F, LoadAddr, "ldrex");

  if (RealResTy->isPointerTy())
    return Builder.CreateIntToPtr(Val, RealResTy);
  else {
    llvm::Type *IntResTy = llvm::IntegerType::get(
        getLLVMContext(), CGM.getDataLayout().getTypeSizeInBits(RealResTy));
    Val = Builder.CreateTruncOrBitCast(Val, IntResTy);
    return Builder.CreateBitCast(Val, RealResTy);
  }
}

if (BuiltinID == ARM::BI__builtin_arm_strexd ||
    ((BuiltinID == ARM::BI__builtin_arm_stlex ||
      BuiltinID == ARM::BI__builtin_arm_strex) &&
     getContext().getTypeSize(E->getArg(0)->getType()) == 64)) {
  Function *F = CGM.getIntrinsic(BuiltinID == ARM::BI__builtin_arm_stlex
                                     ? Intrinsic::arm_stlexd
                                     : Intrinsic::arm_strexd);
  llvm::Type *STy = llvm::StructType::get(Int32Ty, Int32Ty);

  Address Tmp = CreateMemTemp(E->getArg(0)->getType());
  Value *Val = EmitScalarExpr(E->getArg(0));
  Builder.CreateStore(Val, Tmp);

  Address LdPtr = Builder.CreateBitCast(Tmp,llvm::PointerType::getUnqual(STy));
  Val = Builder.CreateLoad(LdPtr);

  Value *Arg0 = Builder.CreateExtractValue(Val, 0);
  Value *Arg1 = Builder.CreateExtractValue(Val, 1);
  Value *StPtr = Builder.CreateBitCast(EmitScalarExpr(E->getArg(1)), Int8PtrTy);
  return Builder.CreateCall(F, {Arg0, Arg1, StPtr}, "strexd");
}

if (BuiltinID == ARM::BI__builtin_arm_strex ||
    BuiltinID == ARM::BI__builtin_arm_stlex) {
  Value *StoreVal = EmitScalarExpr(E->getArg(0));
  Value *StoreAddr = EmitScalarExpr(E->getArg(1));

  QualType Ty = E->getArg(0)->getType();
  llvm::Type *StoreTy = llvm::IntegerType::get(getLLVMContext(),
                                               getContext().getTypeSize(Ty));
  StoreAddr = Builder.CreateBitCast(StoreAddr, StoreTy->getPointerTo());

  if (StoreVal->getType()->isPointerTy())
    StoreVal = Builder.CreatePtrToInt(StoreVal, Int32Ty);
  else {
    llvm::Type *IntTy = llvm::IntegerType::get(
        getLLVMContext(),
        CGM.getDataLayout().getTypeSizeInBits(StoreVal->getType()));
    StoreVal = Builder.CreateBitCast(StoreVal, IntTy);
    StoreVal = Builder.CreateZExtOrBitCast(StoreVal, Int32Ty);
  }

  Function *F = CGM.getIntrinsic(BuiltinID == ARM::BI__builtin_arm_stlex
                                     ? Intrinsic::arm_stlex
                                     : Intrinsic::arm_strex,
                                 StoreAddr->getType());
  return Builder.CreateCall(F, {StoreVal, StoreAddr}, "strex");
}

switch (BuiltinID) {
case ARM::BI__iso_volatile_load8:
case ARM::BI__iso_volatile_load16:
case ARM::BI__iso_volatile_load32:
case ARM::BI__iso_volatile_load64: {
  Value *Ptr = EmitScalarExpr(E->getArg(0));
  QualType ElTy = E->getArg(0)->getType()->getPointeeType();
  CharUnits LoadSize = getContext().getTypeSizeInChars(ElTy);
  llvm::Type *ITy = llvm::IntegerType::get(getLLVMContext(),
                                           LoadSize.getQuantity() * 8);
  Ptr = Builder.CreateBitCast(Ptr, ITy->getPointerTo());
  llvm::LoadInst *Load =
    Builder.CreateAlignedLoad(Ptr, LoadSize);
  Load->setVolatile(true);
  return Load;
}
case ARM::BI__iso_volatile_store8:
case ARM::BI__iso_volatile_store16:
case ARM::BI__iso_volatile_store32:
case ARM::BI__iso_volatile_store64: {
  Value *Ptr = EmitScalarExpr(E->getArg(0));
  Value *Value = EmitScalarExpr(E->getArg(1));
  QualType ElTy = E->getArg(0)->getType()->getPointeeType();
  CharUnits StoreSize = getContext().getTypeSizeInChars(ElTy);
  llvm::Type *ITy = llvm::IntegerType::get(getLLVMContext(),
                                           StoreSize.getQuantity() * 8);
  Ptr = Builder.CreateBitCast(Ptr, ITy->getPointerTo());
  llvm::StoreInst *Store =
    Builder.CreateAlignedStore(Value, Ptr,
                               StoreSize);
  Store->setVolatile(true);
  return Store;
}
}

if (BuiltinID == ARM::BI__builtin_arm_clrex) {
  Function *F = CGM.getIntrinsic(Intrinsic::arm_clrex);
  return Builder.CreateCall(F);
}

// CRC32
Intrinsic::ID CRCIntrinsicID = Intrinsic::not_intrinsic;
switch (BuiltinID) {
case ARM::BI__builtin_arm_crc32b:
  CRCIntrinsicID = Intrinsic::arm_crc32b; break;
case ARM::BI__builtin_arm_crc32cb:
  CRCIntrinsicID = Intrinsic::arm_crc32cb; break;
case ARM::BI__builtin_arm_crc32h:
  CRCIntrinsicID = Intrinsic::arm_crc32h; break;
case ARM::BI__builtin_arm_crc32ch:
  CRCIntrinsicID = Intrinsic::arm_crc32ch; break;
case ARM::BI__builtin_arm_crc32w:
case ARM::BI__builtin_arm_crc32d:
  CRCIntrinsicID = Intrinsic::arm_crc32w; break;
case ARM::BI__builtin_arm_crc32cw:
case ARM::BI__builtin_arm_crc32cd:
  CRCIntrinsicID = Intrinsic::arm_crc32cw; break;
}

if (CRCIntrinsicID != Intrinsic::not_intrinsic) {
  Value *Arg0 = EmitScalarExpr(E->getArg(0));
  Value *Arg1 = EmitScalarExpr(E->getArg(1));

  // crc32{c,}d intrinsics are implemnted as two calls to crc32{c,}w
  // intrinsics, hence we need different codegen for these cases.
  if (BuiltinID == ARM::BI__builtin_arm_crc32d ||
      BuiltinID == ARM::BI__builtin_arm_crc32cd) {
    Value *C1 = llvm::ConstantInt::get(Int64Ty, 32);
    Value *Arg1a = Builder.CreateTruncOrBitCast(Arg1, Int32Ty);
    Value *Arg1b = Builder.CreateLShr(Arg1, C1);
    Arg1b = Builder.CreateTruncOrBitCast(Arg1b, Int32Ty);

    Function *F = CGM.getIntrinsic(CRCIntrinsicID);
    Value *Res = Builder.CreateCall(F, {Arg0, Arg1a});
    return Builder.CreateCall(F, {Res, Arg1b});
  } else {
    Arg1 = Builder.CreateZExtOrBitCast(Arg1, Int32Ty);

    Function *F = CGM.getIntrinsic(CRCIntrinsicID);
    return Builder.CreateCall(F, {Arg0, Arg1});
  }
}

if (BuiltinID == ARM::BI__builtin_arm_rsr ||
    BuiltinID == ARM::BI__builtin_arm_rsr64 ||
    BuiltinID == ARM::BI__builtin_arm_rsrp ||
    BuiltinID == ARM::BI__builtin_arm_wsr ||
    BuiltinID == ARM::BI__builtin_arm_wsr64 ||
    BuiltinID == ARM::BI__builtin_arm_wsrp) {

  bool IsRead = BuiltinID == ARM::BI__builtin_arm_rsr ||
                BuiltinID == ARM::BI__builtin_arm_rsr64 ||
                BuiltinID == ARM::BI__builtin_arm_rsrp;

  bool IsPointerBuiltin = BuiltinID == ARM::BI__builtin_arm_rsrp ||
                          BuiltinID == ARM::BI__builtin_arm_wsrp;

  bool Is64Bit = BuiltinID == ARM::BI__builtin_arm_rsr64 ||
                 BuiltinID == ARM::BI__builtin_arm_wsr64;

  llvm::Type *ValueType;
  llvm::Type *RegisterType;
  if (IsPointerBuiltin) {
    ValueType = VoidPtrTy;
    RegisterType = Int32Ty;
  } else if (Is64Bit) {
    ValueType = RegisterType = Int64Ty;
  } else {
    ValueType = RegisterType = Int32Ty;
  }

  return EmitSpecialRegisterBuiltin(*this, E, RegisterType, ValueType, IsRead);
}

// Find out if any arguments are required to be integer constant
// expressions.
unsigned ICEArguments = 0;
ASTContext::GetBuiltinTypeError Error;
getContext().GetBuiltinType(BuiltinID, Error, &ICEArguments);
assert(Error == ASTContext::GE_None && "Should not codegen an error")(static_cast <bool> (Error == ASTContext::GE_None &&
 "Should not codegen an error") ? void (0) : __assert_fail ("Error == ASTContext::GE_None && \"Should not codegen an error\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 5364, __extension__ __PRETTY_FUNCTION__));

auto getAlignmentValue32 = [&](Address addr) -> Value* {
  return Builder.getInt32(addr.getAlignment().getQuantity());
};

Address PtrOp0 = Address::invalid();
Address PtrOp1 = Address::invalid();
SmallVector<Value*, 4> Ops;
bool HasExtraArg = HasExtraNeonArgument(BuiltinID);
unsigned NumArgs = E->getNumArgs() - (HasExtraArg ? 1 : 0);
for (unsigned i = 0, e = NumArgs; i != e; i++) {
  if (i == 0) {
    switch (BuiltinID) {
    case NEON::BI__builtin_neon_vld1_v:
    case NEON::BI__builtin_neon_vld1q_v:
    case NEON::BI__builtin_neon_vld1q_lane_v:
    case NEON::BI__builtin_neon_vld1_lane_v:
    case NEON::BI__builtin_neon_vld1_dup_v:
    case NEON::BI__builtin_neon_vld1q_dup_v:
    case NEON::BI__builtin_neon_vst1_v:
    case NEON::BI__builtin_neon_vst1q_v:
    case NEON::BI__builtin_neon_vst1q_lane_v:
    case NEON::BI__builtin_neon_vst1_lane_v:
    case NEON::BI__builtin_neon_vst2_v:
    case NEON::BI__builtin_neon_vst2q_v:
    case NEON::BI__builtin_neon_vst2_lane_v:
    case NEON::BI__builtin_neon_vst2q_lane_v:
    case NEON::BI__builtin_neon_vst3_v:
    case NEON::BI__builtin_neon_vst3q_v:
    case NEON::BI__builtin_neon_vst3_lane_v:
    case NEON::BI__builtin_neon_vst3q_lane_v:
    case NEON::BI__builtin_neon_vst4_v:
    case NEON::BI__builtin_neon_vst4q_v:
    case NEON::BI__builtin_neon_vst4_lane_v:
    case NEON::BI__builtin_neon_vst4q_lane_v:
      // Get the alignment for the argument in addition to the value;
      // we'll use it later.
      PtrOp0 = EmitPointerWithAlignment(E->getArg(0));
      Ops.push_back(PtrOp0.getPointer());
      continue;
    }
  }
  if (i == 1) {
    switch (BuiltinID) {
    case NEON::BI__builtin_neon_vld2_v:
    case NEON::BI__builtin_neon_vld2q_v:
    case NEON::BI__builtin_neon_vld3_v:
    case NEON::BI__builtin_neon_vld3q_v:
    case NEON::BI__builtin_neon_vld4_v:
    case NEON::BI__builtin_neon_vld4q_v:
    case NEON::BI__builtin_neon_vld2_lane_v:
    case NEON::BI__builtin_neon_vld2q_lane_v:
    case NEON::BI__builtin_neon_vld3_lane_v:
    case NEON::BI__builtin_neon_vld3q_lane_v:
    case NEON::BI__builtin_neon_vld4_lane_v:
    case NEON::BI__builtin_neon_vld4q_lane_v:
    case NEON::BI__builtin_neon_vld2_dup_v:
    case NEON::BI__builtin_neon_vld3_dup_v:
    case NEON::BI__builtin_neon_vld4_dup_v:
      // Get the alignment for the argument in addition to the value;
      // we'll use it later.
      PtrOp1 = EmitPointerWithAlignment(E->getArg(1));
      Ops.push_back(PtrOp1.getPointer());
      continue;
    }
  }

  if ((ICEArguments & (1 << i)) == 0) {
    Ops.push_back(EmitScalarExpr(E->getArg(i)));
  } else {
    // If this is required to be a constant, constant fold it so that we know
    // that the generated intrinsic gets a ConstantInt.
    llvm::APSInt Result;
    bool IsConst = E->getArg(i)->isIntegerConstantExpr(Result, getContext());
    assert(IsConst && "Constant arg isn't actually constant?")(static_cast <bool> (IsConst && "Constant arg isn't actually constant?"
) ? void (0) : __assert_fail ("IsConst && \"Constant arg isn't actually constant?\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 5439, __extension__ __PRETTY_FUNCTION__)); (void)IsConst;
    Ops.push_back(llvm::ConstantInt::get(getLLVMContext(), Result));
  }
}

switch (BuiltinID) {
default: break;

case NEON::BI__builtin_neon_vget_lane_i8:
case NEON::BI__builtin_neon_vget_lane_i16:
case NEON::BI__builtin_neon_vget_lane_i32:
case NEON::BI__builtin_neon_vget_lane_i64:
case NEON::BI__builtin_neon_vget_lane_f32:
case NEON::BI__builtin_neon_vgetq_lane_i8:
case NEON::BI__builtin_neon_vgetq_lane_i16:
case NEON::BI__builtin_neon_vgetq_lane_i32:
case NEON::BI__builtin_neon_vgetq_lane_i64:
case NEON::BI__builtin_neon_vgetq_lane_f32:
  return Builder.CreateExtractElement(Ops[0], Ops[1], "vget_lane");

case NEON::BI__builtin_neon_vset_lane_i8:
case NEON::BI__builtin_neon_vset_lane_i16:
case NEON::BI__builtin_neon_vset_lane_i32:
case NEON::BI__builtin_neon_vset_lane_i64:
case NEON::BI__builtin_neon_vset_lane_f32:
case NEON::BI__builtin_neon_vsetq_lane_i8:
case NEON::BI__builtin_neon_vsetq_lane_i16:
case NEON::BI__builtin_neon_vsetq_lane_i32:
case NEON::BI__builtin_neon_vsetq_lane_i64:
case NEON::BI__builtin_neon_vsetq_lane_f32:
  return Builder.CreateInsertElement(Ops[1], Ops[0], Ops[2], "vset_lane");

case NEON::BI__builtin_neon_vsha1h_u32:
  return EmitNeonCall(CGM.getIntrinsic(Intrinsic::arm_neon_sha1h), Ops,
                      "vsha1h");
case NEON::BI__builtin_neon_vsha1cq_u32:
  return EmitNeonCall(CGM.getIntrinsic(Intrinsic::arm_neon_sha1c), Ops,
                      "vsha1h");
case NEON::BI__builtin_neon_vsha1pq_u32:
  return EmitNeonCall(CGM.getIntrinsic(Intrinsic::arm_neon_sha1p), Ops,
                      "vsha1h");
case NEON::BI__builtin_neon_vsha1mq_u32:
  return EmitNeonCall(CGM.getIntrinsic(Intrinsic::arm_neon_sha1m), Ops,
                      "vsha1h");

// The ARM _MoveToCoprocessor builtins put the input register value as
// the first argument, but the LLVM intrinsic expects it as the third one.
case ARM::BI_MoveToCoprocessor:
case ARM::BI_MoveToCoprocessor2: {
  Function *F = CGM.getIntrinsic(BuiltinID == ARM::BI_MoveToCoprocessor ?
                                 Intrinsic::arm_mcr : Intrinsic::arm_mcr2);
  return Builder.CreateCall(F, {Ops[1], Ops[2], Ops[0],
                                Ops[3], Ops[4], Ops[5]});
}
case ARM::BI_BitScanForward:
case ARM::BI_BitScanForward64:
  return EmitMSVCBuiltinExpr(MSVCIntrin::_BitScanForward, E);
case ARM::BI_BitScanReverse:
case ARM::BI_BitScanReverse64:
  return EmitMSVCBuiltinExpr(MSVCIntrin::_BitScanReverse, E);

case ARM::BI_InterlockedAnd64:
  return EmitMSVCBuiltinExpr(MSVCIntrin::_InterlockedAnd, E);
case ARM::BI_InterlockedExchange64:
  return EmitMSVCBuiltinExpr(MSVCIntrin::_InterlockedExchange, E);
case ARM::BI_InterlockedExchangeAdd64:
  return EmitMSVCBuiltinExpr(MSVCIntrin::_InterlockedExchangeAdd, E);
case ARM::BI_InterlockedExchangeSub64:
  return EmitMSVCBuiltinExpr(MSVCIntrin::_InterlockedExchangeSub, E);
case ARM::BI_InterlockedOr64:
  return EmitMSVCBuiltinExpr(MSVCIntrin::_InterlockedOr, E);
case ARM::BI_InterlockedXor64:
  return EmitMSVCBuiltinExpr(MSVCIntrin::_InterlockedXor, E);
case ARM::BI_InterlockedDecrement64:
  return EmitMSVCBuiltinExpr(MSVCIntrin::_InterlockedDecrement, E);
case ARM::BI_InterlockedIncrement64:
  return EmitMSVCBuiltinExpr(MSVCIntrin::_InterlockedIncrement, E);
}

// Get the last argument, which specifies the vector type.
assert(HasExtraArg)(static_cast <bool> (HasExtraArg) ? void (0) : __assert_fail
 ("HasExtraArg", "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 5519, __extension__ __PRETTY_FUNCTION__));
llvm::APSInt Result;
const Expr *Arg = E->getArg(E->getNumArgs()-1);
if (!Arg->isIntegerConstantExpr(Result, getContext()))
  return nullptr;

if (BuiltinID == ARM::BI__builtin_arm_vcvtr_f ||
    BuiltinID == ARM::BI__builtin_arm_vcvtr_d) {
  // Determine the overloaded type of this builtin.
  llvm::Type *Ty;
  if (BuiltinID == ARM::BI__builtin_arm_vcvtr_f)
    Ty = FloatTy;
  else
    Ty = DoubleTy;

  // Determine whether this is an unsigned conversion or not.
  bool usgn = Result.getZExtValue() == 1;
  unsigned Int = usgn ? Intrinsic::arm_vcvtru : Intrinsic::arm_vcvtr;

  // Call the appropriate intrinsic.
  Function *F = CGM.getIntrinsic(Int, Ty);
  return Builder.CreateCall(F, Ops, "vcvtr");
}

// Determine the type of this overloaded NEON intrinsic.
NeonTypeFlags Type(Result.getZExtValue());
bool usgn = Type.isUnsigned();
bool rightShift = false;

llvm::VectorType *VTy = GetNeonType(this, Type, Arch);
llvm::Type *Ty = VTy;
if (!Ty)
  return nullptr;

// Many NEON builtins have identical semantics and uses in ARM and
// AArch64. Emit these in a single function.
auto IntrinsicMap = makeArrayRef(ARMSIMDIntrinsicMap);
const NeonIntrinsicInfo *Builtin = findNeonIntrinsicInMap(
    IntrinsicMap, BuiltinID, NEONSIMDIntrinsicsProvenSorted);
if (Builtin)
  return EmitCommonNeonBuiltinExpr(
      Builtin->BuiltinID, Builtin->LLVMIntrinsic, Builtin->AltLLVMIntrinsic,
      Builtin->NameHint, Builtin->TypeModifier, E, Ops, PtrOp0, PtrOp1, Arch);

unsigned Int;
switch (BuiltinID) {
default: return nullptr;
case NEON::BI__builtin_neon_vld1q_lane_v:
  // Handle 64-bit integer elements as a special case.  Use shuffles of
  // one-element vectors to avoid poor code for i64 in the backend.
  if (VTy->getElementType()->isIntegerTy(64)) {
    // Extract the other lane.
    Ops[1] = Builder.CreateBitCast(Ops[1], Ty);
    uint32_t Lane = cast<ConstantInt>(Ops[2])->getZExtValue();
    Value *SV = llvm::ConstantVector::get(ConstantInt::get(Int32Ty, 1-Lane));
    Ops[1] = Builder.CreateShuffleVector(Ops[1], Ops[1], SV);
    // Load the value as a one-element vector.
    Ty = llvm::VectorType::get(VTy->getElementType(), 1);
    llvm::Type *Tys[] = {Ty, Int8PtrTy};
    Function *F = CGM.getIntrinsic(Intrinsic::arm_neon_vld1, Tys);
    Value *Align = getAlignmentValue32(PtrOp0);
    Value *Ld = Builder.CreateCall(F, {Ops[0], Align});
    // Combine them.
    uint32_t Indices[] = {1 - Lane, Lane};
    SV = llvm::ConstantDataVector::get(getLLVMContext(), Indices);
    return Builder.CreateShuffleVector(Ops[1], Ld, SV, "vld1q_lane");
  }
  LLVM_FALLTHROUGH[[clang::fallthrough]];
case NEON::BI__builtin_neon_vld1_lane_v: {
  Ops[1] = Builder.CreateBitCast(Ops[1], Ty);
  PtrOp0 = Builder.CreateElementBitCast(PtrOp0, VTy->getElementType());
  Value *Ld = Builder.CreateLoad(PtrOp0);
  return Builder.CreateInsertElement(Ops[1], Ld, Ops[2], "vld1_lane");
}
case NEON::BI__builtin_neon_vld2_dup_v:
case NEON::BI__builtin_neon_vld3_dup_v:
case NEON::BI__builtin_neon_vld4_dup_v: {
  // Handle 64-bit elements as a special-case.  There is no "dup" needed.
  if (VTy->getElementType()->getPrimitiveSizeInBits() == 64) {
    switch (BuiltinID) {
    case NEON::BI__builtin_neon_vld2_dup_v:
      Int = Intrinsic::arm_neon_vld2;
      break;
    case NEON::BI__builtin_neon_vld3_dup_v:
      Int = Intrinsic::arm_neon_vld3;
      break;
    case NEON::BI__builtin_neon_vld4_dup_v:
      Int = Intrinsic::arm_neon_vld4;
      break;
    default: llvm_unreachable("unknown vld_dup intrinsic?")::llvm::llvm_unreachable_internal("unknown vld_dup intrinsic?"
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 5608);
    }
    llvm::Type *Tys[] = {Ty, Int8PtrTy};
    Function *F = CGM.getIntrinsic(Int, Tys);
    llvm::Value *Align = getAlignmentValue32(PtrOp1);
    Ops[1] = Builder.CreateCall(F, {Ops[1], Align}, "vld_dup");
    Ty = llvm::PointerType::getUnqual(Ops[1]->getType());
    Ops[0] = Builder.CreateBitCast(Ops[0], Ty);
    return Builder.CreateDefaultAlignedStore(Ops[1], Ops[0]);
  }
  switch (BuiltinID) {
  case NEON::BI__builtin_neon_vld2_dup_v:
    Int = Intrinsic::arm_neon_vld2lane;
    break;
  case NEON::BI__builtin_neon_vld3_dup_v:
    Int = Intrinsic::arm_neon_vld3lane;
    break;
  case NEON::BI__builtin_neon_vld4_dup_v:
    Int = Intrinsic::arm_neon_vld4lane;
    break;
  default: llvm_unreachable("unknown vld_dup intrinsic?")::llvm::llvm_unreachable_internal("unknown vld_dup intrinsic?"
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 5628);
  }
  llvm::Type *Tys[] = {Ty, Int8PtrTy};
  Function *F = CGM.getIntrinsic(Int, Tys);
  llvm::StructType *STy = cast<llvm::StructType>(F->getReturnType());

  SmallVector<Value*, 6> Args;
  Args.push_back(Ops[1]);
  Args.append(STy->getNumElements(), UndefValue::get(Ty));

  llvm::Constant *CI = ConstantInt::get(Int32Ty, 0);
  Args.push_back(CI);
  Args.push_back(getAlignmentValue32(PtrOp1));

  Ops[1] = Builder.CreateCall(F, Args, "vld_dup");
  // splat lane 0 to all elts in each vector of the result.
  for (unsigned i = 0, e = STy->getNumElements(); i != e; ++i) {
    Value *Val = Builder.CreateExtractValue(Ops[1], i);
    Value *Elt = Builder.CreateBitCast(Val, Ty);
    Elt = EmitNeonSplat(Elt, CI);
    Elt = Builder.CreateBitCast(Elt, Val->getType());
    Ops[1] = Builder.CreateInsertValue(Ops[1], Elt, i);
  }
  Ty = llvm::PointerType::getUnqual(Ops[1]->getType());
  Ops[0] = Builder.CreateBitCast(Ops[0], Ty);
  return Builder.CreateDefaultAlignedStore(Ops[1], Ops[0]);
}
case NEON::BI__builtin_neon_vqrshrn_n_v:
  Int =
    usgn ? Intrinsic::arm_neon_vqrshiftnu : Intrinsic::arm_neon_vqrshiftns;
  return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vqrshrn_n",
                      1, true);
case NEON::BI__builtin_neon_vqrshrun_n_v:
  return EmitNeonCall(CGM.getIntrinsic(Intrinsic::arm_neon_vqrshiftnsu, Ty),
                      Ops, "vqrshrun_n", 1, true);
case NEON::BI__builtin_neon_vqshrn_n_v:
  Int = usgn ? Intrinsic::arm_neon_vqshiftnu : Intrinsic::arm_neon_vqshiftns;
  return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vqshrn_n",
                      1, true);
case NEON::BI__builtin_neon_vqshrun_n_v:
  return EmitNeonCall(CGM.getIntrinsic(Intrinsic::arm_neon_vqshiftnsu, Ty),
                      Ops, "vqshrun_n", 1, true);
case NEON::BI__builtin_neon_vrecpe_v:
case NEON::BI__builtin_neon_vrecpeq_v:
  return EmitNeonCall(CGM.getIntrinsic(Intrinsic::arm_neon_vrecpe, Ty),
                      Ops, "vrecpe");
case NEON::BI__builtin_neon_vrshrn_n_v:
  return EmitNeonCall(CGM.getIntrinsic(Intrinsic::arm_neon_vrshiftn, Ty),
                      Ops, "vrshrn_n", 1, true);
case NEON::BI__builtin_neon_vrsra_n_v:
case NEON::BI__builtin_neon_vrsraq_n_v:
  Ops[0] = Builder.CreateBitCast(Ops[0], Ty);
  Ops[1] = Builder.CreateBitCast(Ops[1], Ty);
  Ops[2] = EmitNeonShiftVector(Ops[2], Ty, true);
  Int = usgn ? Intrinsic::arm_neon_vrshiftu : Intrinsic::arm_neon_vrshifts;
  Ops[1] = Builder.CreateCall(CGM.getIntrinsic(Int, Ty), {Ops[1], Ops[2]});
  return Builder.CreateAdd(Ops[0], Ops[1], "vrsra_n");
case NEON::BI__builtin_neon_vsri_n_v:
case NEON::BI__builtin_neon_vsriq_n_v:
  rightShift = true;
  LLVM_FALLTHROUGH[[clang::fallthrough]];
case NEON::BI__builtin_neon_vsli_n_v:
case NEON::BI__builtin_neon_vsliq_n_v:
  Ops[2] = EmitNeonShiftVector(Ops[2], Ty, rightShift);
  return EmitNeonCall(CGM.getIntrinsic(Intrinsic::arm_neon_vshiftins, Ty),
                      Ops, "vsli_n");
case NEON::BI__builtin_neon_vsra_n_v:
case NEON::BI__builtin_neon_vsraq_n_v:
  Ops[0] = Builder.CreateBitCast(Ops[0], Ty);
  Ops[1] = EmitNeonRShiftImm(Ops[1], Ops[2], Ty, usgn, "vsra_n");
  return Builder.CreateAdd(Ops[0], Ops[1]);
case NEON::BI__builtin_neon_vst1q_lane_v:
  // Handle 64-bit integer elements as a special case.  Use a shuffle to get
  // a one-element vector and avoid poor code for i64 in the backend.
  if (VTy->getElementType()->isIntegerTy(64)) {
    Ops[1] = Builder.CreateBitCast(Ops[1], Ty);
    Value *SV = llvm::ConstantVector::get(cast<llvm::Constant>(Ops[2]));
    Ops[1] = Builder.CreateShuffleVector(Ops[1], Ops[1], SV);
    Ops[2] = getAlignmentValue32(PtrOp0);
    llvm::Type *Tys[] = {Int8PtrTy, Ops[1]->getType()};
    return Builder.CreateCall(CGM.getIntrinsic(Intrinsic::arm_neon_vst1,
                                               Tys), Ops);
  }
  LLVM_FALLTHROUGH[[clang::fallthrough]];
case NEON::BI__builtin_neon_vst1_lane_v: {
  Ops[1] = Builder.CreateBitCast(Ops[1], Ty);
  Ops[1] = Builder.CreateExtractElement(Ops[1], Ops[2]);
  Ty = llvm::PointerType::getUnqual(Ops[1]->getType());
  auto St = Builder.CreateStore(Ops[1], Builder.CreateBitCast(PtrOp0, Ty));
  return St;
}
case NEON::BI__builtin_neon_vtbl1_v:
  return EmitNeonCall(CGM.getIntrinsic(Intrinsic::arm_neon_vtbl1),
                      Ops, "vtbl1");
case NEON::BI__builtin_neon_vtbl2_v:
  return EmitNeonCall(CGM.getIntrinsic(Intrinsic::arm_neon_vtbl2),
                      Ops, "vtbl2");
case NEON::BI__builtin_neon_vtbl3_v:
  return EmitNeonCall(CGM.getIntrinsic(Intrinsic::arm_neon_vtbl3),
                      Ops, "vtbl3");
case NEON::BI__builtin_neon_vtbl4_v:
  return EmitNeonCall(CGM.getIntrinsic(Intrinsic::arm_neon_vtbl4),
                      Ops, "vtbl4");
case NEON::BI__builtin_neon_vtbx1_v:
  return EmitNeonCall(CGM.getIntrinsic(Intrinsic::arm_neon_vtbx1),
                      Ops, "vtbx1");
case NEON::BI__builtin_neon_vtbx2_v:
  return EmitNeonCall(CGM.getIntrinsic(Intrinsic::arm_neon_vtbx2),
                      Ops, "vtbx2");
case NEON::BI__builtin_neon_vtbx3_v:
  return EmitNeonCall(CGM.getIntrinsic(Intrinsic::arm_neon_vtbx3),
                      Ops, "vtbx3");
case NEON::BI__builtin_neon_vtbx4_v:
  return EmitNeonCall(CGM.getIntrinsic(Intrinsic::arm_neon_vtbx4),
                      Ops, "vtbx4");
}
5744}

5746static Value *EmitAArch64TblBuiltinExpr(CodeGenFunction &CGF, unsigned BuiltinID,
                                    const CallExpr *E,
                                    SmallVectorImpl<Value *> &Ops,
                                    llvm::Triple::ArchType Arch) {
unsigned int Int = 0;
const char *s = nullptr;

switch (BuiltinID) {
default:
  return nullptr;
case NEON::BI__builtin_neon_vtbl1_v:
case NEON::BI__builtin_neon_vqtbl1_v:
case NEON::BI__builtin_neon_vqtbl1q_v:
case NEON::BI__builtin_neon_vtbl2_v:
case NEON::BI__builtin_neon_vqtbl2_v:
case NEON::BI__builtin_neon_vqtbl2q_v:
case NEON::BI__builtin_neon_vtbl3_v:
case NEON::BI__builtin_neon_vqtbl3_v:
case NEON::BI__builtin_neon_vqtbl3q_v:
case NEON::BI__builtin_neon_vtbl4_v:
case NEON::BI__builtin_neon_vqtbl4_v:
case NEON::BI__builtin_neon_vqtbl4q_v:
  break;
case NEON::BI__builtin_neon_vtbx1_v:
case NEON::BI__builtin_neon_vqtbx1_v:
case NEON::BI__builtin_neon_vqtbx1q_v:
case NEON::BI__builtin_neon_vtbx2_v:
case NEON::BI__builtin_neon_vqtbx2_v:
case NEON::BI__builtin_neon_vqtbx2q_v:
case NEON::BI__builtin_neon_vtbx3_v:
case NEON::BI__builtin_neon_vqtbx3_v:
case NEON::BI__builtin_neon_vqtbx3q_v:
case NEON::BI__builtin_neon_vtbx4_v:
case NEON::BI__builtin_neon_vqtbx4_v:
case NEON::BI__builtin_neon_vqtbx4q_v:
  break;
}

assert(E->getNumArgs() >= 3)(static_cast <bool> (E->getNumArgs() >= 3) ? void
 (0) : __assert_fail ("E->getNumArgs() >= 3", "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 5784, __extension__ __PRETTY_FUNCTION__));

// Get the last argument, which specifies the vector type.
llvm::APSInt Result;
const Expr *Arg = E->getArg(E->getNumArgs() - 1);
if (!Arg->isIntegerConstantExpr(Result, CGF.getContext()))
  return nullptr;

// Determine the type of this overloaded NEON intrinsic.
NeonTypeFlags Type(Result.getZExtValue());
llvm::VectorType *Ty = GetNeonType(&CGF, Type, Arch);
if (!Ty)
  return nullptr;

CodeGen::CGBuilderTy &Builder = CGF.Builder;

// AArch64 scalar builtins are not overloaded, they do not have an extra
// argument that specifies the vector type, need to handle each case.
switch (BuiltinID) {
case NEON::BI__builtin_neon_vtbl1_v: {
  return packTBLDVectorList(CGF, makeArrayRef(Ops).slice(0, 1), nullptr,
                            Ops[1], Ty, Intrinsic::aarch64_neon_tbl1,
                            "vtbl1");
}
case NEON::BI__builtin_neon_vtbl2_v: {
  return packTBLDVectorList(CGF, makeArrayRef(Ops).slice(0, 2), nullptr,
                            Ops[2], Ty, Intrinsic::aarch64_neon_tbl1,
                            "vtbl1");
}
case NEON::BI__builtin_neon_vtbl3_v: {
  return packTBLDVectorList(CGF, makeArrayRef(Ops).slice(0, 3), nullptr,
                            Ops[3], Ty, Intrinsic::aarch64_neon_tbl2,
                            "vtbl2");
}
case NEON::BI__builtin_neon_vtbl4_v: {
  return packTBLDVectorList(CGF, makeArrayRef(Ops).slice(0, 4), nullptr,
                            Ops[4], Ty, Intrinsic::aarch64_neon_tbl2,
                            "vtbl2");
}
case NEON::BI__builtin_neon_vtbx1_v: {
  Value *TblRes =
      packTBLDVectorList(CGF, makeArrayRef(Ops).slice(1, 1), nullptr, Ops[2],
                         Ty, Intrinsic::aarch64_neon_tbl1, "vtbl1");

  llvm::Constant *EightV = ConstantInt::get(Ty, 8);
  Value *CmpRes = Builder.CreateICmp(ICmpInst::ICMP_UGE, Ops[2], EightV);
  CmpRes = Builder.CreateSExt(CmpRes, Ty);

  Value *EltsFromInput = Builder.CreateAnd(CmpRes, Ops[0]);
  Value *EltsFromTbl = Builder.CreateAnd(Builder.CreateNot(CmpRes), TblRes);
  return Builder.CreateOr(EltsFromInput, EltsFromTbl, "vtbx");
}
case NEON::BI__builtin_neon_vtbx2_v: {
  return packTBLDVectorList(CGF, makeArrayRef(Ops).slice(1, 2), Ops[0],
                            Ops[3], Ty, Intrinsic::aarch64_neon_tbx1,
                            "vtbx1");
}
case NEON::BI__builtin_neon_vtbx3_v: {
  Value *TblRes =
      packTBLDVectorList(CGF, makeArrayRef(Ops).slice(1, 3), nullptr, Ops[4],
                         Ty, Intrinsic::aarch64_neon_tbl2, "vtbl2");

  llvm::Constant *TwentyFourV = ConstantInt::get(Ty, 24);
  Value *CmpRes = Builder.CreateICmp(ICmpInst::ICMP_UGE, Ops[4],
                                         TwentyFourV);
  CmpRes = Builder.CreateSExt(CmpRes, Ty);

  Value *EltsFromInput = Builder.CreateAnd(CmpRes, Ops[0]);
  Value *EltsFromTbl = Builder.CreateAnd(Builder.CreateNot(CmpRes), TblRes);
  return Builder.CreateOr(EltsFromInput, EltsFromTbl, "vtbx");
}
case NEON::BI__builtin_neon_vtbx4_v: {
  return packTBLDVectorList(CGF, makeArrayRef(Ops).slice(1, 4), Ops[0],
                            Ops[5], Ty, Intrinsic::aarch64_neon_tbx2,
                            "vtbx2");
}
case NEON::BI__builtin_neon_vqtbl1_v:
case NEON::BI__builtin_neon_vqtbl1q_v:
  Int = Intrinsic::aarch64_neon_tbl1; s = "vtbl1"; break;
case NEON::BI__builtin_neon_vqtbl2_v:
case NEON::BI__builtin_neon_vqtbl2q_v: {
  Int = Intrinsic::aarch64_neon_tbl2; s = "vtbl2"; break;
case NEON::BI__builtin_neon_vqtbl3_v:
case NEON::BI__builtin_neon_vqtbl3q_v:
  Int = Intrinsic::aarch64_neon_tbl3; s = "vtbl3"; break;
case NEON::BI__builtin_neon_vqtbl4_v:
case NEON::BI__builtin_neon_vqtbl4q_v:
  Int = Intrinsic::aarch64_neon_tbl4; s = "vtbl4"; break;
case NEON::BI__builtin_neon_vqtbx1_v:
case NEON::BI__builtin_neon_vqtbx1q_v:
  Int = Intrinsic::aarch64_neon_tbx1; s = "vtbx1"; break;
case NEON::BI__builtin_neon_vqtbx2_v:
case NEON::BI__builtin_neon_vqtbx2q_v:
  Int = Intrinsic::aarch64_neon_tbx2; s = "vtbx2"; break;
case NEON::BI__builtin_neon_vqtbx3_v:
case NEON::BI__builtin_neon_vqtbx3q_v:
  Int = Intrinsic::aarch64_neon_tbx3; s = "vtbx3"; break;
case NEON::BI__builtin_neon_vqtbx4_v:
case NEON::BI__builtin_neon_vqtbx4q_v:
  Int = Intrinsic::aarch64_neon_tbx4; s = "vtbx4"; break;
}
}

if (!Int)
  return nullptr;

Function *F = CGF.CGM.getIntrinsic(Int, Ty);
return CGF.EmitNeonCall(F, Ops, s);
5892}

5894Value *CodeGenFunction::vectorWrapScalar16(Value *Op) {
llvm::Type *VTy = llvm::VectorType::get(Int16Ty, 4);
Op = Builder.CreateBitCast(Op, Int16Ty);
Value *V = UndefValue::get(VTy);
llvm::Constant *CI = ConstantInt::get(SizeTy, 0);
Op = Builder.CreateInsertElement(V, Op, CI);
return Op;
5901}

5903Value *CodeGenFunction::EmitAArch64BuiltinExpr(unsigned BuiltinID,
                                             const CallExpr *E,
                                             llvm::Triple::ArchType Arch) {
unsigned HintID = static_cast<unsigned>(-1);
switch (BuiltinID) {
default: break;
case AArch64::BI__builtin_arm_nop:
  HintID = 0;
  break;
case AArch64::BI__builtin_arm_yield:
  HintID = 1;
  break;
case AArch64::BI__builtin_arm_wfe:
  HintID = 2;
  break;
case AArch64::BI__builtin_arm_wfi:
  HintID = 3;
  break;
case AArch64::BI__builtin_arm_sev:
  HintID = 4;
  break;
case AArch64::BI__builtin_arm_sevl:
  HintID = 5;
  break;
}

if (HintID != static_cast<unsigned>(-1)) {
  Function *F = CGM.getIntrinsic(Intrinsic::aarch64_hint);
  return Builder.CreateCall(F, llvm::ConstantInt::get(Int32Ty, HintID));
}

if (BuiltinID == AArch64::BI__builtin_arm_prefetch) {
  Value *Address         = EmitScalarExpr(E->getArg(0));
  Value *RW              = EmitScalarExpr(E->getArg(1));
  Value *CacheLevel      = EmitScalarExpr(E->getArg(2));
  Value *RetentionPolicy = EmitScalarExpr(E->getArg(3));
  Value *IsData          = EmitScalarExpr(E->getArg(4));

  Value *Locality = nullptr;
  if (cast<llvm::ConstantInt>(RetentionPolicy)->isZero()) {
    // Temporal fetch, needs to convert cache level to locality.
    Locality = llvm::ConstantInt::get(Int32Ty,
      -cast<llvm::ConstantInt>(CacheLevel)->getValue() + 3);
  } else {
    // Streaming fetch.
    Locality = llvm::ConstantInt::get(Int32Ty, 0);
  }

  // FIXME: We need AArch64 specific LLVM intrinsic if we want to specify
  // PLDL3STRM or PLDL2STRM.
  Value *F = CGM.getIntrinsic(Intrinsic::prefetch);
  return Builder.CreateCall(F, {Address, RW, Locality, IsData});
}

if (BuiltinID == AArch64::BI__builtin_arm_rbit) {
  assert((getContext().getTypeSize(E->getType()) == 32) &&(static_cast <bool> ((getContext().getTypeSize(E->getType
()) == 32) && "rbit of unusual size!") ? void (0) : __assert_fail
 ("(getContext().getTypeSize(E->getType()) == 32) && \"rbit of unusual size!\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 5959, __extension__ __PRETTY_FUNCTION__))
         "rbit of unusual size!")(static_cast <bool> ((getContext().getTypeSize(E->getType
()) == 32) && "rbit of unusual size!") ? void (0) : __assert_fail
 ("(getContext().getTypeSize(E->getType()) == 32) && \"rbit of unusual size!\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 5959, __extension__ __PRETTY_FUNCTION__));
  llvm::Value *Arg = EmitScalarExpr(E->getArg(0));
  return Builder.CreateCall(
      CGM.getIntrinsic(Intrinsic::bitreverse, Arg->getType()), Arg, "rbit");
}
if (BuiltinID == AArch64::BI__builtin_arm_rbit64) {
  assert((getContext().getTypeSize(E->getType()) == 64) &&(static_cast <bool> ((getContext().getTypeSize(E->getType
()) == 64) && "rbit of unusual size!") ? void (0) : __assert_fail
 ("(getContext().getTypeSize(E->getType()) == 64) && \"rbit of unusual size!\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 5966, __extension__ __PRETTY_FUNCTION__))
         "rbit of unusual size!")(static_cast <bool> ((getContext().getTypeSize(E->getType
()) == 64) && "rbit of unusual size!") ? void (0) : __assert_fail
 ("(getContext().getTypeSize(E->getType()) == 64) && \"rbit of unusual size!\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 5966, __extension__ __PRETTY_FUNCTION__));
  llvm::Value *Arg = EmitScalarExpr(E->getArg(0));
  return Builder.CreateCall(
      CGM.getIntrinsic(Intrinsic::bitreverse, Arg->getType()), Arg, "rbit");
}

if (BuiltinID == AArch64::BI__clear_cache) {
  assert(E->getNumArgs() == 2 && "__clear_cache takes 2 arguments")(static_cast <bool> (E->getNumArgs() == 2 &&
 "__clear_cache takes 2 arguments") ? void (0) : __assert_fail
 ("E->getNumArgs() == 2 && \"__clear_cache takes 2 arguments\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 5973, __extension__ __PRETTY_FUNCTION__));
  const FunctionDecl *FD = E->getDirectCallee();
  Value *Ops[2];
  for (unsigned i = 0; i < 2; i++)
    Ops[i] = EmitScalarExpr(E->getArg(i));
  llvm::Type *Ty = CGM.getTypes().ConvertType(FD->getType());
  llvm::FunctionType *FTy = cast<llvm::FunctionType>(Ty);
  StringRef Name = FD->getName();
  return EmitNounwindRuntimeCall(CGM.CreateRuntimeFunction(FTy, Name), Ops);
}

if ((BuiltinID == AArch64::BI__builtin_arm_ldrex ||
    BuiltinID == AArch64::BI__builtin_arm_ldaex) &&
    getContext().getTypeSize(E->getType()) == 128) {
  Function *F = CGM.getIntrinsic(BuiltinID == AArch64::BI__builtin_arm_ldaex
                                     ? Intrinsic::aarch64_ldaxp
                                     : Intrinsic::aarch64_ldxp);

  Value *LdPtr = EmitScalarExpr(E->getArg(0));
  Value *Val = Builder.CreateCall(F, Builder.CreateBitCast(LdPtr, Int8PtrTy),
                                  "ldxp");

  Value *Val0 = Builder.CreateExtractValue(Val, 1);
  Value *Val1 = Builder.CreateExtractValue(Val, 0);
  llvm::Type *Int128Ty = llvm::IntegerType::get(getLLVMContext(), 128);
  Val0 = Builder.CreateZExt(Val0, Int128Ty);
  Val1 = Builder.CreateZExt(Val1, Int128Ty);

  Value *ShiftCst = llvm::ConstantInt::get(Int128Ty, 64);
  Val = Builder.CreateShl(Val0, ShiftCst, "shl", true /* nuw */);
  Val = Builder.CreateOr(Val, Val1);
  return Builder.CreateBitCast(Val, ConvertType(E->getType()));
} else if (BuiltinID == AArch64::BI__builtin_arm_ldrex ||
           BuiltinID == AArch64::BI__builtin_arm_ldaex) {
  Value *LoadAddr = EmitScalarExpr(E->getArg(0));

  QualType Ty = E->getType();
  llvm::Type *RealResTy = ConvertType(Ty);
  llvm::Type *PtrTy = llvm::IntegerType::get(
      getLLVMContext(), getContext().getTypeSize(Ty))->getPointerTo();
  LoadAddr = Builder.CreateBitCast(LoadAddr, PtrTy);

  Function *F = CGM.getIntrinsic(BuiltinID == AArch64::BI__builtin_arm_ldaex
                                     ? Intrinsic::aarch64_ldaxr
                                     : Intrinsic::aarch64_ldxr,
                                 PtrTy);
  Value *Val = Builder.CreateCall(F, LoadAddr, "ldxr");

  if (RealResTy->isPointerTy())
    return Builder.CreateIntToPtr(Val, RealResTy);

  llvm::Type *IntResTy = llvm::IntegerType::get(
      getLLVMContext(), CGM.getDataLayout().getTypeSizeInBits(RealResTy));
  Val = Builder.CreateTruncOrBitCast(Val, IntResTy);
  return Builder.CreateBitCast(Val, RealResTy);
}

if ((BuiltinID == AArch64::BI__builtin_arm_strex ||
     BuiltinID == AArch64::BI__builtin_arm_stlex) &&
    getContext().getTypeSize(E->getArg(0)->getType()) == 128) {
  Function *F = CGM.getIntrinsic(BuiltinID == AArch64::BI__builtin_arm_stlex
                                     ? Intrinsic::aarch64_stlxp
                                     : Intrinsic::aarch64_stxp);
  llvm::Type *STy = llvm::StructType::get(Int64Ty, Int64Ty);

  Address Tmp = CreateMemTemp(E->getArg(0)->getType());
  EmitAnyExprToMem(E->getArg(0), Tmp, Qualifiers(), /*init*/ true);

  Tmp = Builder.CreateBitCast(Tmp, llvm::PointerType::getUnqual(STy));
  llvm::Value *Val = Builder.CreateLoad(Tmp);

  Value *Arg0 = Builder.CreateExtractValue(Val, 0);
  Value *Arg1 = Builder.CreateExtractValue(Val, 1);
  Value *StPtr = Builder.CreateBitCast(EmitScalarExpr(E->getArg(1)),
                                       Int8PtrTy);
  return Builder.CreateCall(F, {Arg0, Arg1, StPtr}, "stxp");
}

if (BuiltinID == AArch64::BI__builtin_arm_strex ||
    BuiltinID == AArch64::BI__builtin_arm_stlex) {
  Value *StoreVal = EmitScalarExpr(E->getArg(0));
  Value *StoreAddr = EmitScalarExpr(E->getArg(1));

  QualType Ty = E->getArg(0)->getType();
  llvm::Type *StoreTy = llvm::IntegerType::get(getLLVMContext(),
                                               getContext().getTypeSize(Ty));
  StoreAddr = Builder.CreateBitCast(StoreAddr, StoreTy->getPointerTo());

  if (StoreVal->getType()->isPointerTy())
    StoreVal = Builder.CreatePtrToInt(StoreVal, Int64Ty);
  else {
    llvm::Type *IntTy = llvm::IntegerType::get(
        getLLVMContext(),
        CGM.getDataLayout().getTypeSizeInBits(StoreVal->getType()));
    StoreVal = Builder.CreateBitCast(StoreVal, IntTy);
    StoreVal = Builder.CreateZExtOrBitCast(StoreVal, Int64Ty);
  }

  Function *F = CGM.getIntrinsic(BuiltinID == AArch64::BI__builtin_arm_stlex
                                     ? Intrinsic::aarch64_stlxr
                                     : Intrinsic::aarch64_stxr,
                                 StoreAddr->getType());
  return Builder.CreateCall(F, {StoreVal, StoreAddr}, "stxr");
}

if (BuiltinID == AArch64::BI__builtin_arm_clrex) {
  Function *F = CGM.getIntrinsic(Intrinsic::aarch64_clrex);
  return Builder.CreateCall(F);
}

// CRC32
Intrinsic::ID CRCIntrinsicID = Intrinsic::not_intrinsic;
switch (BuiltinID) {
case AArch64::BI__builtin_arm_crc32b:
  CRCIntrinsicID = Intrinsic::aarch64_crc32b; break;
case AArch64::BI__builtin_arm_crc32cb:
  CRCIntrinsicID = Intrinsic::aarch64_crc32cb; break;
case AArch64::BI__builtin_arm_crc32h:
  CRCIntrinsicID = Intrinsic::aarch64_crc32h; break;
case AArch64::BI__builtin_arm_crc32ch:
  CRCIntrinsicID = Intrinsic::aarch64_crc32ch; break;
case AArch64::BI__builtin_arm_crc32w:
  CRCIntrinsicID = Intrinsic::aarch64_crc32w; break;
case AArch64::BI__builtin_arm_crc32cw:
  CRCIntrinsicID = Intrinsic::aarch64_crc32cw; break;
case AArch64::BI__builtin_arm_crc32d:
  CRCIntrinsicID = Intrinsic::aarch64_crc32x; break;
case AArch64::BI__builtin_arm_crc32cd:
  CRCIntrinsicID = Intrinsic::aarch64_crc32cx; break;
}

if (CRCIntrinsicID != Intrinsic::not_intrinsic) {
  Value *Arg0 = EmitScalarExpr(E->getArg(0));
  Value *Arg1 = EmitScalarExpr(E->getArg(1));
  Function *F = CGM.getIntrinsic(CRCIntrinsicID);

  llvm::Type *DataTy = F->getFunctionType()->getParamType(1);
  Arg1 = Builder.CreateZExtOrBitCast(Arg1, DataTy);

  return Builder.CreateCall(F, {Arg0, Arg1});
}

if (BuiltinID == AArch64::BI__builtin_arm_rsr ||
    BuiltinID == AArch64::BI__builtin_arm_rsr64 ||
    BuiltinID == AArch64::BI__builtin_arm_rsrp ||
    BuiltinID == AArch64::BI__builtin_arm_wsr ||
    BuiltinID == AArch64::BI__builtin_arm_wsr64 ||
    BuiltinID == AArch64::BI__builtin_arm_wsrp) {

  bool IsRead = BuiltinID == AArch64::BI__builtin_arm_rsr ||
                BuiltinID == AArch64::BI__builtin_arm_rsr64 ||
                BuiltinID == AArch64::BI__builtin_arm_rsrp;

  bool IsPointerBuiltin = BuiltinID == AArch64::BI__builtin_arm_rsrp ||
                          BuiltinID == AArch64::BI__builtin_arm_wsrp;

  bool Is64Bit = BuiltinID != AArch64::BI__builtin_arm_rsr &&
                 BuiltinID != AArch64::BI__builtin_arm_wsr;

  llvm::Type *ValueType;
  llvm::Type *RegisterType = Int64Ty;
  if (IsPointerBuiltin) {
    ValueType = VoidPtrTy;
  } else if (Is64Bit) {
    ValueType = Int64Ty;
  } else {
    ValueType = Int32Ty;
  }

  return EmitSpecialRegisterBuiltin(*this, E, RegisterType, ValueType, IsRead);
}

// Find out if any arguments are required to be integer constant
// expressions.
unsigned ICEArguments = 0;
ASTContext::GetBuiltinTypeError Error;
getContext().GetBuiltinType(BuiltinID, Error, &ICEArguments);
assert(Error == ASTContext::GE_None && "Should not codegen an error")(static_cast <bool> (Error == ASTContext::GE_None &&
 "Should not codegen an error") ? void (0) : __assert_fail ("Error == ASTContext::GE_None && \"Should not codegen an error\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 6150, __extension__ __PRETTY_FUNCTION__));

llvm::SmallVector<Value*, 4> Ops;
for (unsigned i = 0, e = E->getNumArgs() - 1; i != e; i++) {
  if ((ICEArguments & (1 << i)) == 0) {
    Ops.push_back(EmitScalarExpr(E->getArg(i)));
  } else {
    // If this is required to be a constant, constant fold it so that we know
    // that the generated intrinsic gets a ConstantInt.
    llvm::APSInt Result;
    bool IsConst = E->getArg(i)->isIntegerConstantExpr(Result, getContext());
    assert(IsConst && "Constant arg isn't actually constant?")(static_cast <bool> (IsConst && "Constant arg isn't actually constant?"
) ? void (0) : __assert_fail ("IsConst && \"Constant arg isn't actually constant?\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 6161, __extension__ __PRETTY_FUNCTION__));
    (void)IsConst;
    Ops.push_back(llvm::ConstantInt::get(getLLVMContext(), Result));
  }
}

auto SISDMap = makeArrayRef(AArch64SISDIntrinsicMap);
const NeonIntrinsicInfo *Builtin = findNeonIntrinsicInMap(
    SISDMap, BuiltinID, AArch64SISDIntrinsicsProvenSorted);

if (Builtin) {
  Ops.push_back(EmitScalarExpr(E->getArg(E->getNumArgs() - 1)));
  Value *Result = EmitCommonNeonSISDBuiltinExpr(*this, *Builtin, Ops, E);
  assert(Result && "SISD intrinsic should have been handled")(static_cast <bool> (Result && "SISD intrinsic should have been handled"
) ? void (0) : __assert_fail ("Result && \"SISD intrinsic should have been handled\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 6174, __extension__ __PRETTY_FUNCTION__));
  return Result;
}

llvm::APSInt Result;
const Expr *Arg = E->getArg(E->getNumArgs()-1);
NeonTypeFlags Type(0);
if (Arg->isIntegerConstantExpr(Result, getContext()))
  // Determine the type of this overloaded NEON intrinsic.
  Type = NeonTypeFlags(Result.getZExtValue());

bool usgn = Type.isUnsigned();
bool quad = Type.isQuad();

// Handle non-overloaded intrinsics first.
switch (BuiltinID) {
default: break;
case NEON::BI__builtin_neon_vldrq_p128: {
  llvm::Type *Int128Ty = llvm::Type::getIntNTy(getLLVMContext(), 128);
  llvm::Type *Int128PTy = llvm::PointerType::get(Int128Ty, 0);
  Value *Ptr = Builder.CreateBitCast(EmitScalarExpr(E->getArg(0)), Int128PTy);
  return Builder.CreateAlignedLoad(Int128Ty, Ptr,
                                   CharUnits::fromQuantity(16));
}
case NEON::BI__builtin_neon_vstrq_p128: {
  llvm::Type *Int128PTy = llvm::Type::getIntNPtrTy(getLLVMContext(), 128);
  Value *Ptr = Builder.CreateBitCast(Ops[0], Int128PTy);
  return Builder.CreateDefaultAlignedStore(EmitScalarExpr(E->getArg(1)), Ptr);
}
case NEON::BI__builtin_neon_vcvts_u32_f32:
case NEON::BI__builtin_neon_vcvtd_u64_f64:
  usgn = true;
  LLVM_FALLTHROUGH[[clang::fallthrough]];
case NEON::BI__builtin_neon_vcvts_s32_f32:
case NEON::BI__builtin_neon_vcvtd_s64_f64: {
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  bool Is64 = Ops[0]->getType()->getPrimitiveSizeInBits() == 64;
  llvm::Type *InTy = Is64 ? Int64Ty : Int32Ty;
  llvm::Type *FTy = Is64 ? DoubleTy : FloatTy;
  Ops[0] = Builder.CreateBitCast(Ops[0], FTy);
  if (usgn)
    return Builder.CreateFPToUI(Ops[0], InTy);
  return Builder.CreateFPToSI(Ops[0], InTy);
}
case NEON::BI__builtin_neon_vcvts_f32_u32:
case NEON::BI__builtin_neon_vcvtd_f64_u64:
  usgn = true;
  LLVM_FALLTHROUGH[[clang::fallthrough]];
case NEON::BI__builtin_neon_vcvts_f32_s32:
case NEON::BI__builtin_neon_vcvtd_f64_s64: {
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  bool Is64 = Ops[0]->getType()->getPrimitiveSizeInBits() == 64;
  llvm::Type *InTy = Is64 ? Int64Ty : Int32Ty;
  llvm::Type *FTy = Is64 ? DoubleTy : FloatTy;
  Ops[0] = Builder.CreateBitCast(Ops[0], InTy);
  if (usgn)
    return Builder.CreateUIToFP(Ops[0], FTy);
  return Builder.CreateSIToFP(Ops[0], FTy);
}
case NEON::BI__builtin_neon_vcvth_f16_u16:
case NEON::BI__builtin_neon_vcvth_f16_u32:
case NEON::BI__builtin_neon_vcvth_f16_u64:
  usgn = true;
  // FALL THROUGH
case NEON::BI__builtin_neon_vcvth_f16_s16:
case NEON::BI__builtin_neon_vcvth_f16_s32:
case NEON::BI__builtin_neon_vcvth_f16_s64: {
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  llvm::Type *FTy = HalfTy;
  llvm::Type *InTy;
  if (Ops[0]->getType()->getPrimitiveSizeInBits() == 64)
    InTy = Int64Ty;
  else if (Ops[0]->getType()->getPrimitiveSizeInBits() == 32)
    InTy = Int32Ty;
  else
    InTy = Int16Ty;
  Ops[0] = Builder.CreateBitCast(Ops[0], InTy);
  if (usgn)
    return Builder.CreateUIToFP(Ops[0], FTy);
  return Builder.CreateSIToFP(Ops[0], FTy);
}
case NEON::BI__builtin_neon_vcvth_u16_f16:
  usgn = true;
  // FALL THROUGH
case NEON::BI__builtin_neon_vcvth_s16_f16: {
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Ops[0] = Builder.CreateBitCast(Ops[0], HalfTy);
  if (usgn)
    return Builder.CreateFPToUI(Ops[0], Int16Ty);
  return Builder.CreateFPToSI(Ops[0], Int16Ty);
}
case NEON::BI__builtin_neon_vcvth_u32_f16:
  usgn = true;
  // FALL THROUGH
case NEON::BI__builtin_neon_vcvth_s32_f16: {
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Ops[0] = Builder.CreateBitCast(Ops[0], HalfTy);
  if (usgn)
    return Builder.CreateFPToUI(Ops[0], Int32Ty);
  return Builder.CreateFPToSI(Ops[0], Int32Ty);
}
case NEON::BI__builtin_neon_vcvth_u64_f16:
  usgn = true;
  // FALL THROUGH
case NEON::BI__builtin_neon_vcvth_s64_f16: {
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Ops[0] = Builder.CreateBitCast(Ops[0], HalfTy);
  if (usgn)
    return Builder.CreateFPToUI(Ops[0], Int64Ty);
  return Builder.CreateFPToSI(Ops[0], Int64Ty);
}
case NEON::BI__builtin_neon_vpaddd_s64: {
  llvm::Type *Ty = llvm::VectorType::get(Int64Ty, 2);
  Value *Vec = EmitScalarExpr(E->getArg(0));
  // The vector is v2f64, so make sure it's bitcast to that.
  Vec = Builder.CreateBitCast(Vec, Ty, "v2i64");
  llvm::Value *Idx0 = llvm::ConstantInt::get(SizeTy, 0);
  llvm::Value *Idx1 = llvm::ConstantInt::get(SizeTy, 1);
  Value *Op0 = Builder.CreateExtractElement(Vec, Idx0, "lane0");
  Value *Op1 = Builder.CreateExtractElement(Vec, Idx1, "lane1");
  // Pairwise addition of a v2f64 into a scalar f64.
  return Builder.CreateAdd(Op0, Op1, "vpaddd");
}
case NEON::BI__builtin_neon_vpaddd_f64: {
  llvm::Type *Ty =
    llvm::VectorType::get(DoubleTy, 2);
  Value *Vec = EmitScalarExpr(E->getArg(0));
  // The vector is v2f64, so make sure it's bitcast to that.
  Vec = Builder.CreateBitCast(Vec, Ty, "v2f64");
  llvm::Value *Idx0 = llvm::ConstantInt::get(SizeTy, 0);
  llvm::Value *Idx1 = llvm::ConstantInt::get(SizeTy, 1);
  Value *Op0 = Builder.CreateExtractElement(Vec, Idx0, "lane0");
  Value *Op1 = Builder.CreateExtractElement(Vec, Idx1, "lane1");
  // Pairwise addition of a v2f64 into a scalar f64.
  return Builder.CreateFAdd(Op0, Op1, "vpaddd");
}
case NEON::BI__builtin_neon_vpadds_f32: {
  llvm::Type *Ty =
    llvm::VectorType::get(FloatTy, 2);
  Value *Vec = EmitScalarExpr(E->getArg(0));
  // The vector is v2f32, so make sure it's bitcast to that.
  Vec = Builder.CreateBitCast(Vec, Ty, "v2f32");
  llvm::Value *Idx0 = llvm::ConstantInt::get(SizeTy, 0);
  llvm::Value *Idx1 = llvm::ConstantInt::get(SizeTy, 1);
  Value *Op0 = Builder.CreateExtractElement(Vec, Idx0, "lane0");
  Value *Op1 = Builder.CreateExtractElement(Vec, Idx1, "lane1");
  // Pairwise addition of a v2f32 into a scalar f32.
  return Builder.CreateFAdd(Op0, Op1, "vpaddd");
}
case NEON::BI__builtin_neon_vceqzd_s64:
case NEON::BI__builtin_neon_vceqzd_f64:
case NEON::BI__builtin_neon_vceqzs_f32:
case NEON::BI__builtin_neon_vceqzh_f16:
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  return EmitAArch64CompareBuiltinExpr(
      Ops[0], ConvertType(E->getCallReturnType(getContext())),
      ICmpInst::FCMP_OEQ, ICmpInst::ICMP_EQ, "vceqz");
case NEON::BI__builtin_neon_vcgezd_s64:
case NEON::BI__builtin_neon_vcgezd_f64:
case NEON::BI__builtin_neon_vcgezs_f32:
case NEON::BI__builtin_neon_vcgezh_f16:
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  return EmitAArch64CompareBuiltinExpr(
      Ops[0], ConvertType(E->getCallReturnType(getContext())),
      ICmpInst::FCMP_OGE, ICmpInst::ICMP_SGE, "vcgez");
case NEON::BI__builtin_neon_vclezd_s64:
case NEON::BI__builtin_neon_vclezd_f64:
case NEON::BI__builtin_neon_vclezs_f32:
case NEON::BI__builtin_neon_vclezh_f16:
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  return EmitAArch64CompareBuiltinExpr(
      Ops[0], ConvertType(E->getCallReturnType(getContext())),
      ICmpInst::FCMP_OLE, ICmpInst::ICMP_SLE, "vclez");
case NEON::BI__builtin_neon_vcgtzd_s64:
case NEON::BI__builtin_neon_vcgtzd_f64:
case NEON::BI__builtin_neon_vcgtzs_f32:
case NEON::BI__builtin_neon_vcgtzh_f16:
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  return EmitAArch64CompareBuiltinExpr(
      Ops[0], ConvertType(E->getCallReturnType(getContext())),
      ICmpInst::FCMP_OGT, ICmpInst::ICMP_SGT, "vcgtz");
case NEON::BI__builtin_neon_vcltzd_s64:
case NEON::BI__builtin_neon_vcltzd_f64:
case NEON::BI__builtin_neon_vcltzs_f32:
case NEON::BI__builtin_neon_vcltzh_f16:
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  return EmitAArch64CompareBuiltinExpr(
      Ops[0], ConvertType(E->getCallReturnType(getContext())),
      ICmpInst::FCMP_OLT, ICmpInst::ICMP_SLT, "vcltz");

case NEON::BI__builtin_neon_vceqzd_u64: {
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Ops[0] = Builder.CreateBitCast(Ops[0], Int64Ty);
  Ops[0] =
      Builder.CreateICmpEQ(Ops[0], llvm::Constant::getNullValue(Int64Ty));
  return Builder.CreateSExt(Ops[0], Int64Ty, "vceqzd");
}
case NEON::BI__builtin_neon_vceqd_f64:
case NEON::BI__builtin_neon_vcled_f64:
case NEON::BI__builtin_neon_vcltd_f64:
case NEON::BI__builtin_neon_vcged_f64:
case NEON::BI__builtin_neon_vcgtd_f64: {
  llvm::CmpInst::Predicate P;
  switch (BuiltinID) {
  default: llvm_unreachable("missing builtin ID in switch!")::llvm::llvm_unreachable_internal("missing builtin ID in switch!"
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 6378);
  case NEON::BI__builtin_neon_vceqd_f64: P = llvm::FCmpInst::FCMP_OEQ; break;
  case NEON::BI__builtin_neon_vcled_f64: P = llvm::FCmpInst::FCMP_OLE; break;
  case NEON::BI__builtin_neon_vcltd_f64: P = llvm::FCmpInst::FCMP_OLT; break;
  case NEON::BI__builtin_neon_vcged_f64: P = llvm::FCmpInst::FCMP_OGE; break;
  case NEON::BI__builtin_neon_vcgtd_f64: P = llvm::FCmpInst::FCMP_OGT; break;
  }
  Ops.push_back(EmitScalarExpr(E->getArg(1)));
  Ops[0] = Builder.CreateBitCast(Ops[0], DoubleTy);
  Ops[1] = Builder.CreateBitCast(Ops[1], DoubleTy);
  Ops[0] = Builder.CreateFCmp(P, Ops[0], Ops[1]);
  return Builder.CreateSExt(Ops[0], Int64Ty, "vcmpd");
}
case NEON::BI__builtin_neon_vceqs_f32:
case NEON::BI__builtin_neon_vcles_f32:
case NEON::BI__builtin_neon_vclts_f32:
case NEON::BI__builtin_neon_vcges_f32:
case NEON::BI__builtin_neon_vcgts_f32: {
  llvm::CmpInst::Predicate P;
  switch (BuiltinID) {
  default: llvm_unreachable("missing builtin ID in switch!")::llvm::llvm_unreachable_internal("missing builtin ID in switch!"
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 6398);
  case NEON::BI__builtin_neon_vceqs_f32: P = llvm::FCmpInst::FCMP_OEQ; break;
  case NEON::BI__builtin_neon_vcles_f32: P = llvm::FCmpInst::FCMP_OLE; break;
  case NEON::BI__builtin_neon_vclts_f32: P = llvm::FCmpInst::FCMP_OLT; break;
  case NEON::BI__builtin_neon_vcges_f32: P = llvm::FCmpInst::FCMP_OGE; break;
  case NEON::BI__builtin_neon_vcgts_f32: P = llvm::FCmpInst::FCMP_OGT; break;
  }
  Ops.push_back(EmitScalarExpr(E->getArg(1)));
  Ops[0] = Builder.CreateBitCast(Ops[0], FloatTy);
  Ops[1] = Builder.CreateBitCast(Ops[1], FloatTy);
  Ops[0] = Builder.CreateFCmp(P, Ops[0], Ops[1]);
  return Builder.CreateSExt(Ops[0], Int32Ty, "vcmpd");
}
case NEON::BI__builtin_neon_vceqh_f16:
case NEON::BI__builtin_neon_vcleh_f16:
case NEON::BI__builtin_neon_vclth_f16:
case NEON::BI__builtin_neon_vcgeh_f16:
case NEON::BI__builtin_neon_vcgth_f16: {
  llvm::CmpInst::Predicate P;
  switch (BuiltinID) {
  default: llvm_unreachable("missing builtin ID in switch!")::llvm::llvm_unreachable_internal("missing builtin ID in switch!"
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 6418);
  case NEON::BI__builtin_neon_vceqh_f16: P = llvm::FCmpInst::FCMP_OEQ; break;
  case NEON::BI__builtin_neon_vcleh_f16: P = llvm::FCmpInst::FCMP_OLE; break;
  case NEON::BI__builtin_neon_vclth_f16: P = llvm::FCmpInst::FCMP_OLT; break;
  case NEON::BI__builtin_neon_vcgeh_f16: P = llvm::FCmpInst::FCMP_OGE; break;
  case NEON::BI__builtin_neon_vcgth_f16: P = llvm::FCmpInst::FCMP_OGT; break;
  }
  Ops.push_back(EmitScalarExpr(E->getArg(1)));
  Ops[0] = Builder.CreateBitCast(Ops[0], HalfTy);
  Ops[1] = Builder.CreateBitCast(Ops[1], HalfTy);
  Ops[0] = Builder.CreateFCmp(P, Ops[0], Ops[1]);
  return Builder.CreateSExt(Ops[0], Int16Ty, "vcmpd");
}
case NEON::BI__builtin_neon_vceqd_s64:
case NEON::BI__builtin_neon_vceqd_u64:
case NEON::BI__builtin_neon_vcgtd_s64:
case NEON::BI__builtin_neon_vcgtd_u64:
case NEON::BI__builtin_neon_vcltd_s64:
case NEON::BI__builtin_neon_vcltd_u64:
case NEON::BI__builtin_neon_vcged_u64:
case NEON::BI__builtin_neon_vcged_s64:
case NEON::BI__builtin_neon_vcled_u64:
case NEON::BI__builtin_neon_vcled_s64: {
  llvm::CmpInst::Predicate P;
  switch (BuiltinID) {
  default: llvm_unreachable("missing builtin ID in switch!")::llvm::llvm_unreachable_internal("missing builtin ID in switch!"
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 6443);
  case NEON::BI__builtin_neon_vceqd_s64:
  case NEON::BI__builtin_neon_vceqd_u64:P = llvm::ICmpInst::ICMP_EQ;break;
  case NEON::BI__builtin_neon_vcgtd_s64:P = llvm::ICmpInst::ICMP_SGT;break;
  case NEON::BI__builtin_neon_vcgtd_u64:P = llvm::ICmpInst::ICMP_UGT;break;
  case NEON::BI__builtin_neon_vcltd_s64:P = llvm::ICmpInst::ICMP_SLT;break;
  case NEON::BI__builtin_neon_vcltd_u64:P = llvm::ICmpInst::ICMP_ULT;break;
  case NEON::BI__builtin_neon_vcged_u64:P = llvm::ICmpInst::ICMP_UGE;break;
  case NEON::BI__builtin_neon_vcged_s64:P = llvm::ICmpInst::ICMP_SGE;break;
  case NEON::BI__builtin_neon_vcled_u64:P = llvm::ICmpInst::ICMP_ULE;break;
  case NEON::BI__builtin_neon_vcled_s64:P = llvm::ICmpInst::ICMP_SLE;break;
  }
  Ops.push_back(EmitScalarExpr(E->getArg(1)));
  Ops[0] = Builder.CreateBitCast(Ops[0], Int64Ty);
  Ops[1] = Builder.CreateBitCast(Ops[1], Int64Ty);
  Ops[0] = Builder.CreateICmp(P, Ops[0], Ops[1]);
  return Builder.CreateSExt(Ops[0], Int64Ty, "vceqd");
}
case NEON::BI__builtin_neon_vtstd_s64:
case NEON::BI__builtin_neon_vtstd_u64: {
  Ops.push_back(EmitScalarExpr(E->getArg(1)));
  Ops[0] = Builder.CreateBitCast(Ops[0], Int64Ty);
  Ops[1] = Builder.CreateBitCast(Ops[1], Int64Ty);
  Ops[0] = Builder.CreateAnd(Ops[0], Ops[1]);
  Ops[0] = Builder.CreateICmp(ICmpInst::ICMP_NE, Ops[0],
                              llvm::Constant::getNullValue(Int64Ty));
  return Builder.CreateSExt(Ops[0], Int64Ty, "vtstd");
}
case NEON::BI__builtin_neon_vset_lane_i8:
case NEON::BI__builtin_neon_vset_lane_i16:
case NEON::BI__builtin_neon_vset_lane_i32:
case NEON::BI__builtin_neon_vset_lane_i64:
case NEON::BI__builtin_neon_vset_lane_f32:
case NEON::BI__builtin_neon_vsetq_lane_i8:
case NEON::BI__builtin_neon_vsetq_lane_i16:
case NEON::BI__builtin_neon_vsetq_lane_i32:
case NEON::BI__builtin_neon_vsetq_lane_i64:
case NEON::BI__builtin_neon_vsetq_lane_f32:
  Ops.push_back(EmitScalarExpr(E->getArg(2)));
  return Builder.CreateInsertElement(Ops[1], Ops[0], Ops[2], "vset_lane");
case NEON::BI__builtin_neon_vset_lane_f64:
  // The vector type needs a cast for the v1f64 variant.
  Ops[1] = Builder.CreateBitCast(Ops[1],
                                 llvm::VectorType::get(DoubleTy, 1));
  Ops.push_back(EmitScalarExpr(E->getArg(2)));
  return Builder.CreateInsertElement(Ops[1], Ops[0], Ops[2], "vset_lane");
case NEON::BI__builtin_neon_vsetq_lane_f64:
  // The vector type needs a cast for the v2f64 variant.
  Ops[1] = Builder.CreateBitCast(Ops[1],
      llvm::VectorType::get(DoubleTy, 2));
  Ops.push_back(EmitScalarExpr(E->getArg(2)));
  return Builder.CreateInsertElement(Ops[1], Ops[0], Ops[2], "vset_lane");

case NEON::BI__builtin_neon_vget_lane_i8:
case NEON::BI__builtin_neon_vdupb_lane_i8:
  Ops[0] = Builder.CreateBitCast(Ops[0], llvm::VectorType::get(Int8Ty, 8));
  return Builder.CreateExtractElement(Ops[0], EmitScalarExpr(E->getArg(1)),
                                      "vget_lane");
case NEON::BI__builtin_neon_vgetq_lane_i8:
case NEON::BI__builtin_neon_vdupb_laneq_i8:
  Ops[0] = Builder.CreateBitCast(Ops[0], llvm::VectorType::get(Int8Ty, 16));
  return Builder.CreateExtractElement(Ops[0], EmitScalarExpr(E->getArg(1)),
                                      "vgetq_lane");
case NEON::BI__builtin_neon_vget_lane_i16:
case NEON::BI__builtin_neon_vduph_lane_i16:
  Ops[0] = Builder.CreateBitCast(Ops[0], llvm::VectorType::get(Int16Ty, 4));
  return Builder.CreateExtractElement(Ops[0], EmitScalarExpr(E->getArg(1)),
                                      "vget_lane");
case NEON::BI__builtin_neon_vgetq_lane_i16:
case NEON::BI__builtin_neon_vduph_laneq_i16:
  Ops[0] = Builder.CreateBitCast(Ops[0], llvm::VectorType::get(Int16Ty, 8));
  return Builder.CreateExtractElement(Ops[0], EmitScalarExpr(E->getArg(1)),
                                      "vgetq_lane");
case NEON::BI__builtin_neon_vget_lane_i32:
case NEON::BI__builtin_neon_vdups_lane_i32:
  Ops[0] = Builder.CreateBitCast(Ops[0], llvm::VectorType::get(Int32Ty, 2));
  return Builder.CreateExtractElement(Ops[0], EmitScalarExpr(E->getArg(1)),
                                      "vget_lane");
case NEON::BI__builtin_neon_vdups_lane_f32:
  Ops[0] = Builder.CreateBitCast(Ops[0],
      llvm::VectorType::get(FloatTy, 2));
  return Builder.CreateExtractElement(Ops[0], EmitScalarExpr(E->getArg(1)),
                                      "vdups_lane");
case NEON::BI__builtin_neon_vgetq_lane_i32:
case NEON::BI__builtin_neon_vdups_laneq_i32:
  Ops[0] = Builder.CreateBitCast(Ops[0], llvm::VectorType::get(Int32Ty, 4));
  return Builder.CreateExtractElement(Ops[0], EmitScalarExpr(E->getArg(1)),
                                      "vgetq_lane");
case NEON::BI__builtin_neon_vget_lane_i64:
case NEON::BI__builtin_neon_vdupd_lane_i64:
  Ops[0] = Builder.CreateBitCast(Ops[0], llvm::VectorType::get(Int64Ty, 1));
  return Builder.CreateExtractElement(Ops[0], EmitScalarExpr(E->getArg(1)),
                                      "vget_lane");
case NEON::BI__builtin_neon_vdupd_lane_f64:
  Ops[0] = Builder.CreateBitCast(Ops[0],
      llvm::VectorType::get(DoubleTy, 1));
  return Builder.CreateExtractElement(Ops[0], EmitScalarExpr(E->getArg(1)),
                                      "vdupd_lane");
case NEON::BI__builtin_neon_vgetq_lane_i64:
case NEON::BI__builtin_neon_vdupd_laneq_i64:
  Ops[0] = Builder.CreateBitCast(Ops[0], llvm::VectorType::get(Int64Ty, 2));
  return Builder.CreateExtractElement(Ops[0], EmitScalarExpr(E->getArg(1)),
                                      "vgetq_lane");
case NEON::BI__builtin_neon_vget_lane_f32:
  Ops[0] = Builder.CreateBitCast(Ops[0],
      llvm::VectorType::get(FloatTy, 2));
  return Builder.CreateExtractElement(Ops[0], EmitScalarExpr(E->getArg(1)),
                                      "vget_lane");
case NEON::BI__builtin_neon_vget_lane_f64:
  Ops[0] = Builder.CreateBitCast(Ops[0],
      llvm::VectorType::get(DoubleTy, 1));
  return Builder.CreateExtractElement(Ops[0], EmitScalarExpr(E->getArg(1)),
                                      "vget_lane");
case NEON::BI__builtin_neon_vgetq_lane_f32:
case NEON::BI__builtin_neon_vdups_laneq_f32:
  Ops[0] = Builder.CreateBitCast(Ops[0],
      llvm::VectorType::get(FloatTy, 4));
  return Builder.CreateExtractElement(Ops[0], EmitScalarExpr(E->getArg(1)),
                                      "vgetq_lane");
case NEON::BI__builtin_neon_vgetq_lane_f64:
case NEON::BI__builtin_neon_vdupd_laneq_f64:
  Ops[0] = Builder.CreateBitCast(Ops[0],
      llvm::VectorType::get(DoubleTy, 2));
  return Builder.CreateExtractElement(Ops[0], EmitScalarExpr(E->getArg(1)),
                                      "vgetq_lane");
case NEON::BI__builtin_neon_vaddh_f16:
  Ops.push_back(EmitScalarExpr(E->getArg(1)));
  return Builder.CreateFAdd(Ops[0], Ops[1], "vaddh");
case NEON::BI__builtin_neon_vsubh_f16:
  Ops.push_back(EmitScalarExpr(E->getArg(1)));
  return Builder.CreateFSub(Ops[0], Ops[1], "vsubh");
case NEON::BI__builtin_neon_vmulh_f16:
  Ops.push_back(EmitScalarExpr(E->getArg(1)));
  return Builder.CreateFMul(Ops[0], Ops[1], "vmulh");
case NEON::BI__builtin_neon_vdivh_f16:
  Ops.push_back(EmitScalarExpr(E->getArg(1)));
  return Builder.CreateFDiv(Ops[0], Ops[1], "vdivh");
case NEON::BI__builtin_neon_vfmah_f16: {
  Value *F = CGM.getIntrinsic(Intrinsic::fma, HalfTy);
  // NEON intrinsic puts accumulator first, unlike the LLVM fma.
  return Builder.CreateCall(F,
    {EmitScalarExpr(E->getArg(1)), EmitScalarExpr(E->getArg(2)), Ops[0]});
}
case NEON::BI__builtin_neon_vfmsh_f16: {
  Value *F = CGM.getIntrinsic(Intrinsic::fma, HalfTy);
  Value *Zero = llvm::ConstantFP::getZeroValueForNegation(HalfTy);
  Value* Sub = Builder.CreateFSub(Zero, EmitScalarExpr(E->getArg(1)), "vsubh");
  // NEON intrinsic puts accumulator first, unlike the LLVM fma.
  return Builder.CreateCall(F, {Sub, EmitScalarExpr(E->getArg(2)), Ops[0]});
}
case NEON::BI__builtin_neon_vaddd_s64:
case NEON::BI__builtin_neon_vaddd_u64:
  return Builder.CreateAdd(Ops[0], EmitScalarExpr(E->getArg(1)), "vaddd");
case NEON::BI__builtin_neon_vsubd_s64:
case NEON::BI__builtin_neon_vsubd_u64:
  return Builder.CreateSub(Ops[0], EmitScalarExpr(E->getArg(1)), "vsubd");
case NEON::BI__builtin_neon_vqdmlalh_s16:
case NEON::BI__builtin_neon_vqdmlslh_s16: {
  SmallVector<Value *, 2> ProductOps;
  ProductOps.push_back(vectorWrapScalar16(Ops[1]));
  ProductOps.push_back(vectorWrapScalar16(EmitScalarExpr(E->getArg(2))));
  llvm::Type *VTy = llvm::VectorType::get(Int32Ty, 4);
  Ops[1] = EmitNeonCall(CGM.getIntrinsic(Intrinsic::aarch64_neon_sqdmull, VTy),
                        ProductOps, "vqdmlXl");
  Constant *CI = ConstantInt::get(SizeTy, 0);
  Ops[1] = Builder.CreateExtractElement(Ops[1], CI, "lane0");

  unsigned AccumInt = BuiltinID == NEON::BI__builtin_neon_vqdmlalh_s16
                                      ? Intrinsic::aarch64_neon_sqadd
                                      : Intrinsic::aarch64_neon_sqsub;
  return EmitNeonCall(CGM.getIntrinsic(AccumInt, Int32Ty), Ops, "vqdmlXl");
}
case NEON::BI__builtin_neon_vqshlud_n_s64: {
  Ops.push_back(EmitScalarExpr(E->getArg(1)));
  Ops[1] = Builder.CreateZExt(Ops[1], Int64Ty);
  return EmitNeonCall(CGM.getIntrinsic(Intrinsic::aarch64_neon_sqshlu, Int64Ty),
                      Ops, "vqshlu_n");
}
case NEON::BI__builtin_neon_vqshld_n_u64:
case NEON::BI__builtin_neon_vqshld_n_s64: {
  unsigned Int = BuiltinID == NEON::BI__builtin_neon_vqshld_n_u64
                                 ? Intrinsic::aarch64_neon_uqshl
                                 : Intrinsic::aarch64_neon_sqshl;
  Ops.push_back(EmitScalarExpr(E->getArg(1)));
  Ops[1] = Builder.CreateZExt(Ops[1], Int64Ty);
  return EmitNeonCall(CGM.getIntrinsic(Int, Int64Ty), Ops, "vqshl_n");
}
case NEON::BI__builtin_neon_vrshrd_n_u64:
case NEON::BI__builtin_neon_vrshrd_n_s64: {
  unsigned Int = BuiltinID == NEON::BI__builtin_neon_vrshrd_n_u64
                                 ? Intrinsic::aarch64_neon_urshl
                                 : Intrinsic::aarch64_neon_srshl;
  Ops.push_back(EmitScalarExpr(E->getArg(1)));
  int SV = cast<ConstantInt>(Ops[1])->getSExtValue();
  Ops[1] = ConstantInt::get(Int64Ty, -SV);
  return EmitNeonCall(CGM.getIntrinsic(Int, Int64Ty), Ops, "vrshr_n");
}
case NEON::BI__builtin_neon_vrsrad_n_u64:
case NEON::BI__builtin_neon_vrsrad_n_s64: {
  unsigned Int = BuiltinID == NEON::BI__builtin_neon_vrsrad_n_u64
                                 ? Intrinsic::aarch64_neon_urshl
                                 : Intrinsic::aarch64_neon_srshl;
  Ops[1] = Builder.CreateBitCast(Ops[1], Int64Ty);
  Ops.push_back(Builder.CreateNeg(EmitScalarExpr(E->getArg(2))));
  Ops[1] = Builder.CreateCall(CGM.getIntrinsic(Int, Int64Ty),
                              {Ops[1], Builder.CreateSExt(Ops[2], Int64Ty)});
  return Builder.CreateAdd(Ops[0], Builder.CreateBitCast(Ops[1], Int64Ty));
}
case NEON::BI__builtin_neon_vshld_n_s64:
case NEON::BI__builtin_neon_vshld_n_u64: {
  llvm::ConstantInt *Amt = cast<ConstantInt>(EmitScalarExpr(E->getArg(1)));
  return Builder.CreateShl(
      Ops[0], ConstantInt::get(Int64Ty, Amt->getZExtValue()), "shld_n");
}
case NEON::BI__builtin_neon_vshrd_n_s64: {
  llvm::ConstantInt *Amt = cast<ConstantInt>(EmitScalarExpr(E->getArg(1)));
  return Builder.CreateAShr(
      Ops[0], ConstantInt::get(Int64Ty, std::min(static_cast<uint64_t>(63),
                                                 Amt->getZExtValue())),
      "shrd_n");
}
case NEON::BI__builtin_neon_vshrd_n_u64: {
  llvm::ConstantInt *Amt = cast<ConstantInt>(EmitScalarExpr(E->getArg(1)));
  uint64_t ShiftAmt = Amt->getZExtValue();
  // Right-shifting an unsigned value by its size yields 0.
  if (ShiftAmt == 64)
    return ConstantInt::get(Int64Ty, 0);
  return Builder.CreateLShr(Ops[0], ConstantInt::get(Int64Ty, ShiftAmt),
                            "shrd_n");
}
case NEON::BI__builtin_neon_vsrad_n_s64: {
  llvm::ConstantInt *Amt = cast<ConstantInt>(EmitScalarExpr(E->getArg(2)));
  Ops[1] = Builder.CreateAShr(
      Ops[1], ConstantInt::get(Int64Ty, std::min(static_cast<uint64_t>(63),
                                                 Amt->getZExtValue())),
      "shrd_n");
  return Builder.CreateAdd(Ops[0], Ops[1]);
}
case NEON::BI__builtin_neon_vsrad_n_u64: {
  llvm::ConstantInt *Amt = cast<ConstantInt>(EmitScalarExpr(E->getArg(2)));
  uint64_t ShiftAmt = Amt->getZExtValue();
  // Right-shifting an unsigned value by its size yields 0.
  // As Op + 0 = Op, return Ops[0] directly.
  if (ShiftAmt == 64)
    return Ops[0];
  Ops[1] = Builder.CreateLShr(Ops[1], ConstantInt::get(Int64Ty, ShiftAmt),
                              "shrd_n");
  return Builder.CreateAdd(Ops[0], Ops[1]);
}
case NEON::BI__builtin_neon_vqdmlalh_lane_s16:
case NEON::BI__builtin_neon_vqdmlalh_laneq_s16:
case NEON::BI__builtin_neon_vqdmlslh_lane_s16:
case NEON::BI__builtin_neon_vqdmlslh_laneq_s16: {
  Ops[2] = Builder.CreateExtractElement(Ops[2], EmitScalarExpr(E->getArg(3)),
                                        "lane");
  SmallVector<Value *, 2> ProductOps;
  ProductOps.push_back(vectorWrapScalar16(Ops[1]));
  ProductOps.push_back(vectorWrapScalar16(Ops[2]));
  llvm::Type *VTy = llvm::VectorType::get(Int32Ty, 4);
  Ops[1] = EmitNeonCall(CGM.getIntrinsic(Intrinsic::aarch64_neon_sqdmull, VTy),
                        ProductOps, "vqdmlXl");
  Constant *CI = ConstantInt::get(SizeTy, 0);
  Ops[1] = Builder.CreateExtractElement(Ops[1], CI, "lane0");
  Ops.pop_back();

  unsigned AccInt = (BuiltinID == NEON::BI__builtin_neon_vqdmlalh_lane_s16 ||
                     BuiltinID == NEON::BI__builtin_neon_vqdmlalh_laneq_s16)
                        ? Intrinsic::aarch64_neon_sqadd
                        : Intrinsic::aarch64_neon_sqsub;
  return EmitNeonCall(CGM.getIntrinsic(AccInt, Int32Ty), Ops, "vqdmlXl");
}
case NEON::BI__builtin_neon_vqdmlals_s32:
case NEON::BI__builtin_neon_vqdmlsls_s32: {
  SmallVector<Value *, 2> ProductOps;
  ProductOps.push_back(Ops[1]);
  ProductOps.push_back(EmitScalarExpr(E->getArg(2)));
  Ops[1] =
      EmitNeonCall(CGM.getIntrinsic(Intrinsic::aarch64_neon_sqdmulls_scalar),
                   ProductOps, "vqdmlXl");

  unsigned AccumInt = BuiltinID == NEON::BI__builtin_neon_vqdmlals_s32
                                      ? Intrinsic::aarch64_neon_sqadd
                                      : Intrinsic::aarch64_neon_sqsub;
  return EmitNeonCall(CGM.getIntrinsic(AccumInt, Int64Ty), Ops, "vqdmlXl");
}
case NEON::BI__builtin_neon_vqdmlals_lane_s32:
case NEON::BI__builtin_neon_vqdmlals_laneq_s32:
case NEON::BI__builtin_neon_vqdmlsls_lane_s32:
case NEON::BI__builtin_neon_vqdmlsls_laneq_s32: {
  Ops[2] = Builder.CreateExtractElement(Ops[2], EmitScalarExpr(E->getArg(3)),
                                        "lane");
  SmallVector<Value *, 2> ProductOps;
  ProductOps.push_back(Ops[1]);
  ProductOps.push_back(Ops[2]);
  Ops[1] =
      EmitNeonCall(CGM.getIntrinsic(Intrinsic::aarch64_neon_sqdmulls_scalar),
                   ProductOps, "vqdmlXl");
  Ops.pop_back();

  unsigned AccInt = (BuiltinID == NEON::BI__builtin_neon_vqdmlals_lane_s32 ||
                     BuiltinID == NEON::BI__builtin_neon_vqdmlals_laneq_s32)
                        ? Intrinsic::aarch64_neon_sqadd
                        : Intrinsic::aarch64_neon_sqsub;
  return EmitNeonCall(CGM.getIntrinsic(AccInt, Int64Ty), Ops, "vqdmlXl");
}
}

llvm::VectorType *VTy = GetNeonType(this, Type, Arch);
llvm::Type *Ty = VTy;
if (!Ty)
  return nullptr;

// Not all intrinsics handled by the common case work for AArch64 yet, so only
// defer to common code if it's been added to our special map.
Builtin = findNeonIntrinsicInMap(AArch64SIMDIntrinsicMap, BuiltinID,
                                 AArch64SIMDIntrinsicsProvenSorted);

if (Builtin)
  return EmitCommonNeonBuiltinExpr(
      Builtin->BuiltinID, Builtin->LLVMIntrinsic, Builtin->AltLLVMIntrinsic,
      Builtin->NameHint, Builtin->TypeModifier, E, Ops,
      /*never use addresses*/ Address::invalid(), Address::invalid(), Arch);

if (Value *V = EmitAArch64TblBuiltinExpr(*this, BuiltinID, E, Ops, Arch))
  return V;

unsigned Int;
switch (BuiltinID) {
default: return nullptr;
case NEON::BI__builtin_neon_vbsl_v:
case NEON::BI__builtin_neon_vbslq_v: {
  llvm::Type *BitTy = llvm::VectorType::getInteger(VTy);
  Ops[0] = Builder.CreateBitCast(Ops[0], BitTy, "vbsl");
  Ops[1] = Builder.CreateBitCast(Ops[1], BitTy, "vbsl");
  Ops[2] = Builder.CreateBitCast(Ops[2], BitTy, "vbsl");

  Ops[1] = Builder.CreateAnd(Ops[0], Ops[1], "vbsl");
  Ops[2] = Builder.CreateAnd(Builder.CreateNot(Ops[0]), Ops[2], "vbsl");
  Ops[0] = Builder.CreateOr(Ops[1], Ops[2], "vbsl");
  return Builder.CreateBitCast(Ops[0], Ty);
}
case NEON::BI__builtin_neon_vfma_lane_v:
case NEON::BI__builtin_neon_vfmaq_lane_v: { // Only used for FP types
  // The ARM builtins (and instructions) have the addend as the first
  // operand, but the 'fma' intrinsics have it last. Swap it around here.
  Value *Addend = Ops[0];
  Value *Multiplicand = Ops[1];
  Value *LaneSource = Ops[2];
  Ops[0] = Multiplicand;
  Ops[1] = LaneSource;
  Ops[2] = Addend;

  // Now adjust things to handle the lane access.
  llvm::Type *SourceTy = BuiltinID == NEON::BI__builtin_neon_vfmaq_lane_v ?
    llvm::VectorType::get(VTy->getElementType(), VTy->getNumElements() / 2) :
    VTy;
  llvm::Constant *cst = cast<Constant>(Ops[3]);
  Value *SV = llvm::ConstantVector::getSplat(VTy->getNumElements(), cst);
  Ops[1] = Builder.CreateBitCast(Ops[1], SourceTy);
  Ops[1] = Builder.CreateShuffleVector(Ops[1], Ops[1], SV, "lane");

  Ops.pop_back();
  Int = Intrinsic::fma;
  return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "fmla");
}
case NEON::BI__builtin_neon_vfma_laneq_v: {
  llvm::VectorType *VTy = cast<llvm::VectorType>(Ty);
  // v1f64 fma should be mapped to Neon scalar f64 fma
  if (VTy && VTy->getElementType() == DoubleTy) {
    Ops[0] = Builder.CreateBitCast(Ops[0], DoubleTy);
    Ops[1] = Builder.CreateBitCast(Ops[1], DoubleTy);
    llvm::Type *VTy = GetNeonType(this,
      NeonTypeFlags(NeonTypeFlags::Float64, false, true), Arch);
    Ops[2] = Builder.CreateBitCast(Ops[2], VTy);
    Ops[2] = Builder.CreateExtractElement(Ops[2], Ops[3], "extract");
    Value *F = CGM.getIntrinsic(Intrinsic::fma, DoubleTy);
    Value *Result = Builder.CreateCall(F, {Ops[1], Ops[2], Ops[0]});
    return Builder.CreateBitCast(Result, Ty);
  }
  Value *F = CGM.getIntrinsic(Intrinsic::fma, Ty);
  Ops[0] = Builder.CreateBitCast(Ops[0], Ty);
  Ops[1] = Builder.CreateBitCast(Ops[1], Ty);

  llvm::Type *STy = llvm::VectorType::get(VTy->getElementType(),
                                          VTy->getNumElements() * 2);
  Ops[2] = Builder.CreateBitCast(Ops[2], STy);
  Value* SV = llvm::ConstantVector::getSplat(VTy->getNumElements(),
                                             cast<ConstantInt>(Ops[3]));
  Ops[2] = Builder.CreateShuffleVector(Ops[2], Ops[2], SV, "lane");

  return Builder.CreateCall(F, {Ops[2], Ops[1], Ops[0]});
}
case NEON::BI__builtin_neon_vfmaq_laneq_v: {
  Value *F = CGM.getIntrinsic(Intrinsic::fma, Ty);
  Ops[0] = Builder.CreateBitCast(Ops[0], Ty);
  Ops[1] = Builder.CreateBitCast(Ops[1], Ty);

  Ops[2] = Builder.CreateBitCast(Ops[2], Ty);
  Ops[2] = EmitNeonSplat(Ops[2], cast<ConstantInt>(Ops[3]));
  return Builder.CreateCall(F, {Ops[2], Ops[1], Ops[0]});
}
case NEON::BI__builtin_neon_vfmah_lane_f16:
case NEON::BI__builtin_neon_vfmas_lane_f32:
case NEON::BI__builtin_neon_vfmah_laneq_f16:
case NEON::BI__builtin_neon_vfmas_laneq_f32:
case NEON::BI__builtin_neon_vfmad_lane_f64:
case NEON::BI__builtin_neon_vfmad_laneq_f64: {
  Ops.push_back(EmitScalarExpr(E->getArg(3)));
  llvm::Type *Ty = ConvertType(E->getCallReturnType(getContext()));
  Value *F = CGM.getIntrinsic(Intrinsic::fma, Ty);
  Ops[2] = Builder.CreateExtractElement(Ops[2], Ops[3], "extract");
  return Builder.CreateCall(F, {Ops[1], Ops[2], Ops[0]});
}
case NEON::BI__builtin_neon_vmull_v:
  // FIXME: improve sharing scheme to cope with 3 alternative LLVM intrinsics.
  Int = usgn ? Intrinsic::aarch64_neon_umull : Intrinsic::aarch64_neon_smull;
  if (Type.isPoly()) Int = Intrinsic::aarch64_neon_pmull;
  return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vmull");
case NEON::BI__builtin_neon_vmax_v:
case NEON::BI__builtin_neon_vmaxq_v:
  // FIXME: improve sharing scheme to cope with 3 alternative LLVM intrinsics.
  Int = usgn ? Intrinsic::aarch64_neon_umax : Intrinsic::aarch64_neon_smax;
  if (Ty->isFPOrFPVectorTy()) Int = Intrinsic::aarch64_neon_fmax;
  return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vmax");
case NEON::BI__builtin_neon_vmaxh_f16: {
  Ops.push_back(EmitScalarExpr(E->getArg(1)));
  Int = Intrinsic::aarch64_neon_fmax;
  return EmitNeonCall(CGM.getIntrinsic(Int, HalfTy), Ops, "vmax");
}
case NEON::BI__builtin_neon_vmin_v:
case NEON::BI__builtin_neon_vminq_v:
  // FIXME: improve sharing scheme to cope with 3 alternative LLVM intrinsics.
  Int = usgn ? Intrinsic::aarch64_neon_umin : Intrinsic::aarch64_neon_smin;
  if (Ty->isFPOrFPVectorTy()) Int = Intrinsic::aarch64_neon_fmin;
  return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vmin");
case NEON::BI__builtin_neon_vminh_f16: {
  Ops.push_back(EmitScalarExpr(E->getArg(1)));
  Int = Intrinsic::aarch64_neon_fmin;
  return EmitNeonCall(CGM.getIntrinsic(Int, HalfTy), Ops, "vmin");
}
case NEON::BI__builtin_neon_vabd_v:
case NEON::BI__builtin_neon_vabdq_v:
  // FIXME: improve sharing scheme to cope with 3 alternative LLVM intrinsics.
  Int = usgn ? Intrinsic::aarch64_neon_uabd : Intrinsic::aarch64_neon_sabd;
  if (Ty->isFPOrFPVectorTy()) Int = Intrinsic::aarch64_neon_fabd;
  return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vabd");
case NEON::BI__builtin_neon_vpadal_v:
case NEON::BI__builtin_neon_vpadalq_v: {
  unsigned ArgElts = VTy->getNumElements();
  llvm::IntegerType *EltTy = cast<IntegerType>(VTy->getElementType());
  unsigned BitWidth = EltTy->getBitWidth();
  llvm::Type *ArgTy = llvm::VectorType::get(
      llvm::IntegerType::get(getLLVMContext(), BitWidth/2), 2*ArgElts);
  llvm::Type* Tys[2] = { VTy, ArgTy };
  Int = usgn ? Intrinsic::aarch64_neon_uaddlp : Intrinsic::aarch64_neon_saddlp;
  SmallVector<llvm::Value*, 1> TmpOps;
  TmpOps.push_back(Ops[1]);
  Function *F = CGM.getIntrinsic(Int, Tys);
  llvm::Value *tmp = EmitNeonCall(F, TmpOps, "vpadal");
  llvm::Value *addend = Builder.CreateBitCast(Ops[0], tmp->getType());
  return Builder.CreateAdd(tmp, addend);
}
case NEON::BI__builtin_neon_vpmin_v:
case NEON::BI__builtin_neon_vpminq_v:
  // FIXME: improve sharing scheme to cope with 3 alternative LLVM intrinsics.
  Int = usgn ? Intrinsic::aarch64_neon_uminp : Intrinsic::aarch64_neon_sminp;
  if (Ty->isFPOrFPVectorTy()) Int = Intrinsic::aarch64_neon_fminp;
  return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vpmin");
case NEON::BI__builtin_neon_vpmax_v:
case NEON::BI__builtin_neon_vpmaxq_v:
  // FIXME: improve sharing scheme to cope with 3 alternative LLVM intrinsics.
  Int = usgn ? Intrinsic::aarch64_neon_umaxp : Intrinsic::aarch64_neon_smaxp;
  if (Ty->isFPOrFPVectorTy()) Int = Intrinsic::aarch64_neon_fmaxp;
  return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vpmax");
case NEON::BI__builtin_neon_vminnm_v:
case NEON::BI__builtin_neon_vminnmq_v:
  Int = Intrinsic::aarch64_neon_fminnm;
  return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vminnm");
case NEON::BI__builtin_neon_vminnmh_f16:
  Ops.push_back(EmitScalarExpr(E->getArg(1)));
  Int = Intrinsic::aarch64_neon_fminnm;
  return EmitNeonCall(CGM.getIntrinsic(Int, HalfTy), Ops, "vminnm");
case NEON::BI__builtin_neon_vmaxnm_v:
case NEON::BI__builtin_neon_vmaxnmq_v:
  Int = Intrinsic::aarch64_neon_fmaxnm;
  return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vmaxnm");
case NEON::BI__builtin_neon_vmaxnmh_f16:
  Ops.push_back(EmitScalarExpr(E->getArg(1)));
  Int = Intrinsic::aarch64_neon_fmaxnm;
  return EmitNeonCall(CGM.getIntrinsic(Int, HalfTy), Ops, "vmaxnm");
case NEON::BI__builtin_neon_vrecpss_f32: {
  Ops.push_back(EmitScalarExpr(E->getArg(1)));
  return EmitNeonCall(CGM.getIntrinsic(Intrinsic::aarch64_neon_frecps, FloatTy),
                      Ops, "vrecps");
}
case NEON::BI__builtin_neon_vrecpsd_f64:
  Ops.push_back(EmitScalarExpr(E->getArg(1)));
  return EmitNeonCall(CGM.getIntrinsic(Intrinsic::aarch64_neon_frecps, DoubleTy),
                      Ops, "vrecps");
case NEON::BI__builtin_neon_vrecpsh_f16:
  Ops.push_back(EmitScalarExpr(E->getArg(1)));
  return EmitNeonCall(CGM.getIntrinsic(Intrinsic::aarch64_neon_frecps, HalfTy),
                      Ops, "vrecps");
case NEON::BI__builtin_neon_vqshrun_n_v:
  Int = Intrinsic::aarch64_neon_sqshrun;
  return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vqshrun_n");
case NEON::BI__builtin_neon_vqrshrun_n_v:
  Int = Intrinsic::aarch64_neon_sqrshrun;
  return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vqrshrun_n");
case NEON::BI__builtin_neon_vqshrn_n_v:
  Int = usgn ? Intrinsic::aarch64_neon_uqshrn : Intrinsic::aarch64_neon_sqshrn;
  return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vqshrn_n");
case NEON::BI__builtin_neon_vrshrn_n_v:
  Int = Intrinsic::aarch64_neon_rshrn;
  return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vrshrn_n");
case NEON::BI__builtin_neon_vqrshrn_n_v:
  Int = usgn ? Intrinsic::aarch64_neon_uqrshrn : Intrinsic::aarch64_neon_sqrshrn;
  return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vqrshrn_n");
case NEON::BI__builtin_neon_vrndah_f16: {
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Int = Intrinsic::round;
  return EmitNeonCall(CGM.getIntrinsic(Int, HalfTy), Ops, "vrnda");
}
case NEON::BI__builtin_neon_vrnda_v:
case NEON::BI__builtin_neon_vrndaq_v: {
  Int = Intrinsic::round;
  return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vrnda");
}
case NEON::BI__builtin_neon_vrndih_f16: {
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Int = Intrinsic::nearbyint;
  return EmitNeonCall(CGM.getIntrinsic(Int, HalfTy), Ops, "vrndi");
}
case NEON::BI__builtin_neon_vrndi_v:
case NEON::BI__builtin_neon_vrndiq_v: {
  Int = Intrinsic::nearbyint;
  return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vrndi");
}
case NEON::BI__builtin_neon_vrndmh_f16: {
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Int = Intrinsic::floor;
  return EmitNeonCall(CGM.getIntrinsic(Int, HalfTy), Ops, "vrndm");
}
case NEON::BI__builtin_neon_vrndm_v:
case NEON::BI__builtin_neon_vrndmq_v: {
  Int = Intrinsic::floor;
  return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vrndm");
}
case NEON::BI__builtin_neon_vrndnh_f16: {
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Int = Intrinsic::aarch64_neon_frintn;
  return EmitNeonCall(CGM.getIntrinsic(Int, HalfTy), Ops, "vrndn");
}
case NEON::BI__builtin_neon_vrndn_v:
case NEON::BI__builtin_neon_vrndnq_v: {
  Int = Intrinsic::aarch64_neon_frintn;
  return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vrndn");
}
case NEON::BI__builtin_neon_vrndph_f16: {
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Int = Intrinsic::ceil;
  return EmitNeonCall(CGM.getIntrinsic(Int, HalfTy), Ops, "vrndp");
}
case NEON::BI__builtin_neon_vrndp_v:
case NEON::BI__builtin_neon_vrndpq_v: {
  Int = Intrinsic::ceil;
  return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vrndp");
}
case NEON::BI__builtin_neon_vrndxh_f16: {
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Int = Intrinsic::rint;
  return EmitNeonCall(CGM.getIntrinsic(Int, HalfTy), Ops, "vrndx");
}
case NEON::BI__builtin_neon_vrndx_v:
case NEON::BI__builtin_neon_vrndxq_v: {
  Int = Intrinsic::rint;
  return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vrndx");
}
case NEON::BI__builtin_neon_vrndh_f16: {
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Int = Intrinsic::trunc;
  return EmitNeonCall(CGM.getIntrinsic(Int, HalfTy), Ops, "vrndz");
}
case NEON::BI__builtin_neon_vrnd_v:
case NEON::BI__builtin_neon_vrndq_v: {
  Int = Intrinsic::trunc;
  return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vrndz");
}
case NEON::BI__builtin_neon_vceqz_v:
case NEON::BI__builtin_neon_vceqzq_v:
  return EmitAArch64CompareBuiltinExpr(Ops[0], Ty, ICmpInst::FCMP_OEQ,
                                       ICmpInst::ICMP_EQ, "vceqz");
case NEON::BI__builtin_neon_vcgez_v:
case NEON::BI__builtin_neon_vcgezq_v:
  return EmitAArch64CompareBuiltinExpr(Ops[0], Ty, ICmpInst::FCMP_OGE,
                                       ICmpInst::ICMP_SGE, "vcgez");
case NEON::BI__builtin_neon_vclez_v:
case NEON::BI__builtin_neon_vclezq_v:
  return EmitAArch64CompareBuiltinExpr(Ops[0], Ty, ICmpInst::FCMP_OLE,
                                       ICmpInst::ICMP_SLE, "vclez");
case NEON::BI__builtin_neon_vcgtz_v:
case NEON::BI__builtin_neon_vcgtzq_v:
  return EmitAArch64CompareBuiltinExpr(Ops[0], Ty, ICmpInst::FCMP_OGT,
                                       ICmpInst::ICMP_SGT, "vcgtz");
case NEON::BI__builtin_neon_vcltz_v:
case NEON::BI__builtin_neon_vcltzq_v:
  return EmitAArch64CompareBuiltinExpr(Ops[0], Ty, ICmpInst::FCMP_OLT,
                                       ICmpInst::ICMP_SLT, "vcltz");
case NEON::BI__builtin_neon_vcvt_f64_v:
case NEON::BI__builtin_neon_vcvtq_f64_v:
  Ops[0] = Builder.CreateBitCast(Ops[0], Ty);
  Ty = GetNeonType(this, NeonTypeFlags(NeonTypeFlags::Float64, false, quad), Arch);
  return usgn ? Builder.CreateUIToFP(Ops[0], Ty, "vcvt")
              : Builder.CreateSIToFP(Ops[0], Ty, "vcvt");
case NEON::BI__builtin_neon_vcvt_f64_f32: {
  assert(Type.getEltType() == NeonTypeFlags::Float64 && quad &&(static_cast <bool> (Type.getEltType() == NeonTypeFlags
::Float64 && quad && "unexpected vcvt_f64_f32 builtin"
) ? void (0) : __assert_fail ("Type.getEltType() == NeonTypeFlags::Float64 && quad && \"unexpected vcvt_f64_f32 builtin\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 7059, __extension__ __PRETTY_FUNCTION__))
         "unexpected vcvt_f64_f32 builtin")(static_cast <bool> (Type.getEltType() == NeonTypeFlags
::Float64 && quad && "unexpected vcvt_f64_f32 builtin"
) ? void (0) : __assert_fail ("Type.getEltType() == NeonTypeFlags::Float64 && quad && \"unexpected vcvt_f64_f32 builtin\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 7059, __extension__ __PRETTY_FUNCTION__));
  NeonTypeFlags SrcFlag = NeonTypeFlags(NeonTypeFlags::Float32, false, false);
  Ops[0] = Builder.CreateBitCast(Ops[0], GetNeonType(this, SrcFlag, Arch));

  return Builder.CreateFPExt(Ops[0], Ty, "vcvt");
}
case NEON::BI__builtin_neon_vcvt_f32_f64: {
  assert(Type.getEltType() == NeonTypeFlags::Float32 &&(static_cast <bool> (Type.getEltType() == NeonTypeFlags
::Float32 && "unexpected vcvt_f32_f64 builtin") ? void
 (0) : __assert_fail ("Type.getEltType() == NeonTypeFlags::Float32 && \"unexpected vcvt_f32_f64 builtin\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 7067, __extension__ __PRETTY_FUNCTION__))
         "unexpected vcvt_f32_f64 builtin")(static_cast <bool> (Type.getEltType() == NeonTypeFlags
::Float32 && "unexpected vcvt_f32_f64 builtin") ? void
 (0) : __assert_fail ("Type.getEltType() == NeonTypeFlags::Float32 && \"unexpected vcvt_f32_f64 builtin\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 7067, __extension__ __PRETTY_FUNCTION__));
  NeonTypeFlags SrcFlag = NeonTypeFlags(NeonTypeFlags::Float64, false, true);
  Ops[0] = Builder.CreateBitCast(Ops[0], GetNeonType(this, SrcFlag, Arch));

  return Builder.CreateFPTrunc(Ops[0], Ty, "vcvt");
}
case NEON::BI__builtin_neon_vcvt_s32_v:
case NEON::BI__builtin_neon_vcvt_u32_v:
case NEON::BI__builtin_neon_vcvt_s64_v:
case NEON::BI__builtin_neon_vcvt_u64_v:
case NEON::BI__builtin_neon_vcvt_s16_v:
case NEON::BI__builtin_neon_vcvt_u16_v:
case NEON::BI__builtin_neon_vcvtq_s32_v:
case NEON::BI__builtin_neon_vcvtq_u32_v:
case NEON::BI__builtin_neon_vcvtq_s64_v:
case NEON::BI__builtin_neon_vcvtq_u64_v:
case NEON::BI__builtin_neon_vcvtq_s16_v:
case NEON::BI__builtin_neon_vcvtq_u16_v: {
  Ops[0] = Builder.CreateBitCast(Ops[0], GetFloatNeonType(this, Type));
  if (usgn)
    return Builder.CreateFPToUI(Ops[0], Ty);
  return Builder.CreateFPToSI(Ops[0], Ty);
}
case NEON::BI__builtin_neon_vcvta_s16_v:
case NEON::BI__builtin_neon_vcvta_s32_v:
case NEON::BI__builtin_neon_vcvtaq_s16_v:
case NEON::BI__builtin_neon_vcvtaq_s32_v:
case NEON::BI__builtin_neon_vcvta_u32_v:
case NEON::BI__builtin_neon_vcvtaq_u16_v:
case NEON::BI__builtin_neon_vcvtaq_u32_v:
case NEON::BI__builtin_neon_vcvta_s64_v:
case NEON::BI__builtin_neon_vcvtaq_s64_v:
case NEON::BI__builtin_neon_vcvta_u64_v:
case NEON::BI__builtin_neon_vcvtaq_u64_v: {
  Int = usgn ? Intrinsic::aarch64_neon_fcvtau : Intrinsic::aarch64_neon_fcvtas;
  llvm::Type *Tys[2] = { Ty, GetFloatNeonType(this, Type) };
  return EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vcvta");
}
case NEON::BI__builtin_neon_vcvtm_s16_v:
case NEON::BI__builtin_neon_vcvtm_s32_v:
case NEON::BI__builtin_neon_vcvtmq_s16_v:
case NEON::BI__builtin_neon_vcvtmq_s32_v:
case NEON::BI__builtin_neon_vcvtm_u16_v:
case NEON::BI__builtin_neon_vcvtm_u32_v:
case NEON::BI__builtin_neon_vcvtmq_u16_v:
case NEON::BI__builtin_neon_vcvtmq_u32_v:
case NEON::BI__builtin_neon_vcvtm_s64_v:
case NEON::BI__builtin_neon_vcvtmq_s64_v:
case NEON::BI__builtin_neon_vcvtm_u64_v:
case NEON::BI__builtin_neon_vcvtmq_u64_v: {
  Int = usgn ? Intrinsic::aarch64_neon_fcvtmu : Intrinsic::aarch64_neon_fcvtms;
  llvm::Type *Tys[2] = { Ty, GetFloatNeonType(this, Type) };
  return EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vcvtm");
}
case NEON::BI__builtin_neon_vcvtn_s16_v:
case NEON::BI__builtin_neon_vcvtn_s32_v:
case NEON::BI__builtin_neon_vcvtnq_s16_v:
case NEON::BI__builtin_neon_vcvtnq_s32_v:
case NEON::BI__builtin_neon_vcvtn_u16_v:
case NEON::BI__builtin_neon_vcvtn_u32_v:
case NEON::BI__builtin_neon_vcvtnq_u16_v:
case NEON::BI__builtin_neon_vcvtnq_u32_v:
case NEON::BI__builtin_neon_vcvtn_s64_v:
case NEON::BI__builtin_neon_vcvtnq_s64_v:
case NEON::BI__builtin_neon_vcvtn_u64_v:
case NEON::BI__builtin_neon_vcvtnq_u64_v: {
  Int = usgn ? Intrinsic::aarch64_neon_fcvtnu : Intrinsic::aarch64_neon_fcvtns;
  llvm::Type *Tys[2] = { Ty, GetFloatNeonType(this, Type) };
  return EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vcvtn");
}
case NEON::BI__builtin_neon_vcvtp_s16_v:
case NEON::BI__builtin_neon_vcvtp_s32_v:
case NEON::BI__builtin_neon_vcvtpq_s16_v:
case NEON::BI__builtin_neon_vcvtpq_s32_v:
case NEON::BI__builtin_neon_vcvtp_u16_v:
case NEON::BI__builtin_neon_vcvtp_u32_v:
case NEON::BI__builtin_neon_vcvtpq_u16_v:
case NEON::BI__builtin_neon_vcvtpq_u32_v:
case NEON::BI__builtin_neon_vcvtp_s64_v:
case NEON::BI__builtin_neon_vcvtpq_s64_v:
case NEON::BI__builtin_neon_vcvtp_u64_v:
case NEON::BI__builtin_neon_vcvtpq_u64_v: {
  Int = usgn ? Intrinsic::aarch64_neon_fcvtpu : Intrinsic::aarch64_neon_fcvtps;
  llvm::Type *Tys[2] = { Ty, GetFloatNeonType(this, Type) };
  return EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vcvtp");
}
case NEON::BI__builtin_neon_vmulx_v:
case NEON::BI__builtin_neon_vmulxq_v: {
  Int = Intrinsic::aarch64_neon_fmulx;
  return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vmulx");
}
case NEON::BI__builtin_neon_vmul_lane_v:
case NEON::BI__builtin_neon_vmul_laneq_v: {
  // v1f64 vmul_lane should be mapped to Neon scalar mul lane
  bool Quad = false;
  if (BuiltinID == NEON::BI__builtin_neon_vmul_laneq_v)
    Quad = true;
  Ops[0] = Builder.CreateBitCast(Ops[0], DoubleTy);
  llvm::Type *VTy = GetNeonType(this,
    NeonTypeFlags(NeonTypeFlags::Float64, false, Quad), Arch);
  Ops[1] = Builder.CreateBitCast(Ops[1], VTy);
  Ops[1] = Builder.CreateExtractElement(Ops[1], Ops[2], "extract");
  Value *Result = Builder.CreateFMul(Ops[0], Ops[1]);
  return Builder.CreateBitCast(Result, Ty);
}
case NEON::BI__builtin_neon_vnegd_s64:
  return Builder.CreateNeg(EmitScalarExpr(E->getArg(0)), "vnegd");
case NEON::BI__builtin_neon_vnegh_f16:
  return Builder.CreateFNeg(EmitScalarExpr(E->getArg(0)), "vnegh");
case NEON::BI__builtin_neon_vpmaxnm_v:
case NEON::BI__builtin_neon_vpmaxnmq_v: {
  Int = Intrinsic::aarch64_neon_fmaxnmp;
  return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vpmaxnm");
}
case NEON::BI__builtin_neon_vpminnm_v:
case NEON::BI__builtin_neon_vpminnmq_v: {
  Int = Intrinsic::aarch64_neon_fminnmp;
  return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vpminnm");
}
case NEON::BI__builtin_neon_vsqrth_f16: {
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Int = Intrinsic::sqrt;
  return EmitNeonCall(CGM.getIntrinsic(Int, HalfTy), Ops, "vsqrt");
}
case NEON::BI__builtin_neon_vsqrt_v:
case NEON::BI__builtin_neon_vsqrtq_v: {
  Int = Intrinsic::sqrt;
  Ops[0] = Builder.CreateBitCast(Ops[0], Ty);
  return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vsqrt");
}
case NEON::BI__builtin_neon_vrbit_v:
case NEON::BI__builtin_neon_vrbitq_v: {
  Int = Intrinsic::aarch64_neon_rbit;
  return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vrbit");
}
case NEON::BI__builtin_neon_vaddv_u8:
  // FIXME: These are handled by the AArch64 scalar code.
  usgn = true;
  LLVM_FALLTHROUGH[[clang::fallthrough]];
case NEON::BI__builtin_neon_vaddv_s8: {
  Int = usgn ? Intrinsic::aarch64_neon_uaddv : Intrinsic::aarch64_neon_saddv;
  Ty = Int32Ty;
  VTy = llvm::VectorType::get(Int8Ty, 8);
  llvm::Type *Tys[2] = { Ty, VTy };
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vaddv");
  return Builder.CreateTrunc(Ops[0], Int8Ty);
}
case NEON::BI__builtin_neon_vaddv_u16:
  usgn = true;
  LLVM_FALLTHROUGH[[clang::fallthrough]];
case NEON::BI__builtin_neon_vaddv_s16: {
  Int = usgn ? Intrinsic::aarch64_neon_uaddv : Intrinsic::aarch64_neon_saddv;
  Ty = Int32Ty;
  VTy = llvm::VectorType::get(Int16Ty, 4);
  llvm::Type *Tys[2] = { Ty, VTy };
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vaddv");
  return Builder.CreateTrunc(Ops[0], Int16Ty);
}
case NEON::BI__builtin_neon_vaddvq_u8:
  usgn = true;
  LLVM_FALLTHROUGH[[clang::fallthrough]];
case NEON::BI__builtin_neon_vaddvq_s8: {
  Int = usgn ? Intrinsic::aarch64_neon_uaddv : Intrinsic::aarch64_neon_saddv;
  Ty = Int32Ty;
  VTy = llvm::VectorType::get(Int8Ty, 16);
  llvm::Type *Tys[2] = { Ty, VTy };
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vaddv");
  return Builder.CreateTrunc(Ops[0], Int8Ty);
}
case NEON::BI__builtin_neon_vaddvq_u16:
  usgn = true;
  LLVM_FALLTHROUGH[[clang::fallthrough]];
case NEON::BI__builtin_neon_vaddvq_s16: {
  Int = usgn ? Intrinsic::aarch64_neon_uaddv : Intrinsic::aarch64_neon_saddv;
  Ty = Int32Ty;
  VTy = llvm::VectorType::get(Int16Ty, 8);
  llvm::Type *Tys[2] = { Ty, VTy };
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vaddv");
  return Builder.CreateTrunc(Ops[0], Int16Ty);
}
case NEON::BI__builtin_neon_vmaxv_u8: {
  Int = Intrinsic::aarch64_neon_umaxv;
  Ty = Int32Ty;
  VTy = llvm::VectorType::get(Int8Ty, 8);
  llvm::Type *Tys[2] = { Ty, VTy };
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vmaxv");
  return Builder.CreateTrunc(Ops[0], Int8Ty);
}
case NEON::BI__builtin_neon_vmaxv_u16: {
  Int = Intrinsic::aarch64_neon_umaxv;
  Ty = Int32Ty;
  VTy = llvm::VectorType::get(Int16Ty, 4);
  llvm::Type *Tys[2] = { Ty, VTy };
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vmaxv");
  return Builder.CreateTrunc(Ops[0], Int16Ty);
}
case NEON::BI__builtin_neon_vmaxvq_u8: {
  Int = Intrinsic::aarch64_neon_umaxv;
  Ty = Int32Ty;
  VTy = llvm::VectorType::get(Int8Ty, 16);
  llvm::Type *Tys[2] = { Ty, VTy };
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vmaxv");
  return Builder.CreateTrunc(Ops[0], Int8Ty);
}
case NEON::BI__builtin_neon_vmaxvq_u16: {
  Int = Intrinsic::aarch64_neon_umaxv;
  Ty = Int32Ty;
  VTy = llvm::VectorType::get(Int16Ty, 8);
  llvm::Type *Tys[2] = { Ty, VTy };
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vmaxv");
  return Builder.CreateTrunc(Ops[0], Int16Ty);
}
case NEON::BI__builtin_neon_vmaxv_s8: {
  Int = Intrinsic::aarch64_neon_smaxv;
  Ty = Int32Ty;
  VTy = llvm::VectorType::get(Int8Ty, 8);
  llvm::Type *Tys[2] = { Ty, VTy };
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vmaxv");
  return Builder.CreateTrunc(Ops[0], Int8Ty);
}
case NEON::BI__builtin_neon_vmaxv_s16: {
  Int = Intrinsic::aarch64_neon_smaxv;
  Ty = Int32Ty;
  VTy = llvm::VectorType::get(Int16Ty, 4);
  llvm::Type *Tys[2] = { Ty, VTy };
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vmaxv");
  return Builder.CreateTrunc(Ops[0], Int16Ty);
}
case NEON::BI__builtin_neon_vmaxvq_s8: {
  Int = Intrinsic::aarch64_neon_smaxv;
  Ty = Int32Ty;
  VTy = llvm::VectorType::get(Int8Ty, 16);
  llvm::Type *Tys[2] = { Ty, VTy };
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vmaxv");
  return Builder.CreateTrunc(Ops[0], Int8Ty);
}
case NEON::BI__builtin_neon_vmaxvq_s16: {
  Int = Intrinsic::aarch64_neon_smaxv;
  Ty = Int32Ty;
  VTy = llvm::VectorType::get(Int16Ty, 8);
  llvm::Type *Tys[2] = { Ty, VTy };
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vmaxv");
  return Builder.CreateTrunc(Ops[0], Int16Ty);
}
case NEON::BI__builtin_neon_vmaxv_f16: {
  Int = Intrinsic::aarch64_neon_fmaxv;
  Ty = HalfTy;
  VTy = llvm::VectorType::get(HalfTy, 4);
  llvm::Type *Tys[2] = { Ty, VTy };
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vmaxv");
  return Builder.CreateTrunc(Ops[0], HalfTy);
}
case NEON::BI__builtin_neon_vmaxvq_f16: {
  Int = Intrinsic::aarch64_neon_fmaxv;
  Ty = HalfTy;
  VTy = llvm::VectorType::get(HalfTy, 8);
  llvm::Type *Tys[2] = { Ty, VTy };
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vmaxv");
  return Builder.CreateTrunc(Ops[0], HalfTy);
}
case NEON::BI__builtin_neon_vminv_u8: {
  Int = Intrinsic::aarch64_neon_uminv;
  Ty = Int32Ty;
  VTy = llvm::VectorType::get(Int8Ty, 8);
  llvm::Type *Tys[2] = { Ty, VTy };
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vminv");
  return Builder.CreateTrunc(Ops[0], Int8Ty);
}
case NEON::BI__builtin_neon_vminv_u16: {
  Int = Intrinsic::aarch64_neon_uminv;
  Ty = Int32Ty;
  VTy = llvm::VectorType::get(Int16Ty, 4);
  llvm::Type *Tys[2] = { Ty, VTy };
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vminv");
  return Builder.CreateTrunc(Ops[0], Int16Ty);
}
case NEON::BI__builtin_neon_vminvq_u8: {
  Int = Intrinsic::aarch64_neon_uminv;
  Ty = Int32Ty;
  VTy = llvm::VectorType::get(Int8Ty, 16);
  llvm::Type *Tys[2] = { Ty, VTy };
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vminv");
  return Builder.CreateTrunc(Ops[0], Int8Ty);
}
case NEON::BI__builtin_neon_vminvq_u16: {
  Int = Intrinsic::aarch64_neon_uminv;
  Ty = Int32Ty;
  VTy = llvm::VectorType::get(Int16Ty, 8);
  llvm::Type *Tys[2] = { Ty, VTy };
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vminv");
  return Builder.CreateTrunc(Ops[0], Int16Ty);
}
case NEON::BI__builtin_neon_vminv_s8: {
  Int = Intrinsic::aarch64_neon_sminv;
  Ty = Int32Ty;
  VTy = llvm::VectorType::get(Int8Ty, 8);
  llvm::Type *Tys[2] = { Ty, VTy };
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vminv");
  return Builder.CreateTrunc(Ops[0], Int8Ty);
}
case NEON::BI__builtin_neon_vminv_s16: {
  Int = Intrinsic::aarch64_neon_sminv;
  Ty = Int32Ty;
  VTy = llvm::VectorType::get(Int16Ty, 4);
  llvm::Type *Tys[2] = { Ty, VTy };
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vminv");
  return Builder.CreateTrunc(Ops[0], Int16Ty);
}
case NEON::BI__builtin_neon_vminvq_s8: {
  Int = Intrinsic::aarch64_neon_sminv;
  Ty = Int32Ty;
  VTy = llvm::VectorType::get(Int8Ty, 16);
  llvm::Type *Tys[2] = { Ty, VTy };
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vminv");
  return Builder.CreateTrunc(Ops[0], Int8Ty);
}
case NEON::BI__builtin_neon_vminvq_s16: {
  Int = Intrinsic::aarch64_neon_sminv;
  Ty = Int32Ty;
  VTy = llvm::VectorType::get(Int16Ty, 8);
  llvm::Type *Tys[2] = { Ty, VTy };
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vminv");
  return Builder.CreateTrunc(Ops[0], Int16Ty);
}
case NEON::BI__builtin_neon_vminv_f16: {
  Int = Intrinsic::aarch64_neon_fminv;
  Ty = HalfTy;
  VTy = llvm::VectorType::get(HalfTy, 4);
  llvm::Type *Tys[2] = { Ty, VTy };
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vminv");
  return Builder.CreateTrunc(Ops[0], HalfTy);
}
case NEON::BI__builtin_neon_vminvq_f16: {
  Int = Intrinsic::aarch64_neon_fminv;
  Ty = HalfTy;
  VTy = llvm::VectorType::get(HalfTy, 8);
  llvm::Type *Tys[2] = { Ty, VTy };
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vminv");
  return Builder.CreateTrunc(Ops[0], HalfTy);
}
case NEON::BI__builtin_neon_vmaxnmv_f16: {
  Int = Intrinsic::aarch64_neon_fmaxnmv;
  Ty = HalfTy;
  VTy = llvm::VectorType::get(HalfTy, 4);
  llvm::Type *Tys[2] = { Ty, VTy };
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vmaxnmv");
  return Builder.CreateTrunc(Ops[0], HalfTy);
}
case NEON::BI__builtin_neon_vmaxnmvq_f16: {
  Int = Intrinsic::aarch64_neon_fmaxnmv;
  Ty = HalfTy;
  VTy = llvm::VectorType::get(HalfTy, 8);
  llvm::Type *Tys[2] = { Ty, VTy };
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vmaxnmv");
  return Builder.CreateTrunc(Ops[0], HalfTy);
}
case NEON::BI__builtin_neon_vminnmv_f16: {
  Int = Intrinsic::aarch64_neon_fminnmv;
  Ty = HalfTy;
  VTy = llvm::VectorType::get(HalfTy, 4);
  llvm::Type *Tys[2] = { Ty, VTy };
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vminnmv");
  return Builder.CreateTrunc(Ops[0], HalfTy);
}
case NEON::BI__builtin_neon_vminnmvq_f16: {
  Int = Intrinsic::aarch64_neon_fminnmv;
  Ty = HalfTy;
  VTy = llvm::VectorType::get(HalfTy, 8);
  llvm::Type *Tys[2] = { Ty, VTy };
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vminnmv");
  return Builder.CreateTrunc(Ops[0], HalfTy);
}
case NEON::BI__builtin_neon_vmul_n_f64: {
  Ops[0] = Builder.CreateBitCast(Ops[0], DoubleTy);
  Value *RHS = Builder.CreateBitCast(EmitScalarExpr(E->getArg(1)), DoubleTy);
  return Builder.CreateFMul(Ops[0], RHS);
}
case NEON::BI__builtin_neon_vaddlv_u8: {
  Int = Intrinsic::aarch64_neon_uaddlv;
  Ty = Int32Ty;
  VTy = llvm::VectorType::get(Int8Ty, 8);
  llvm::Type *Tys[2] = { Ty, VTy };
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vaddlv");
  return Builder.CreateTrunc(Ops[0], Int16Ty);
}
case NEON::BI__builtin_neon_vaddlv_u16: {
  Int = Intrinsic::aarch64_neon_uaddlv;
  Ty = Int32Ty;
  VTy = llvm::VectorType::get(Int16Ty, 4);
  llvm::Type *Tys[2] = { Ty, VTy };
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  return EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vaddlv");
}
case NEON::BI__builtin_neon_vaddlvq_u8: {
  Int = Intrinsic::aarch64_neon_uaddlv;
  Ty = Int32Ty;
  VTy = llvm::VectorType::get(Int8Ty, 16);
  llvm::Type *Tys[2] = { Ty, VTy };
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vaddlv");
  return Builder.CreateTrunc(Ops[0], Int16Ty);
}
case NEON::BI__builtin_neon_vaddlvq_u16: {
  Int = Intrinsic::aarch64_neon_uaddlv;
  Ty = Int32Ty;
  VTy = llvm::VectorType::get(Int16Ty, 8);
  llvm::Type *Tys[2] = { Ty, VTy };
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  return EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vaddlv");
}
case NEON::BI__builtin_neon_vaddlv_s8: {
  Int = Intrinsic::aarch64_neon_saddlv;
  Ty = Int32Ty;
  VTy = llvm::VectorType::get(Int8Ty, 8);
  llvm::Type *Tys[2] = { Ty, VTy };
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vaddlv");
  return Builder.CreateTrunc(Ops[0], Int16Ty);
}
case NEON::BI__builtin_neon_vaddlv_s16: {
  Int = Intrinsic::aarch64_neon_saddlv;
  Ty = Int32Ty;
  VTy = llvm::VectorType::get(Int16Ty, 4);
  llvm::Type *Tys[2] = { Ty, VTy };
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  return EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vaddlv");
}
case NEON::BI__builtin_neon_vaddlvq_s8: {
  Int = Intrinsic::aarch64_neon_saddlv;
  Ty = Int32Ty;
  VTy = llvm::VectorType::get(Int8Ty, 16);
  llvm::Type *Tys[2] = { Ty, VTy };
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vaddlv");
  return Builder.CreateTrunc(Ops[0], Int16Ty);
}
case NEON::BI__builtin_neon_vaddlvq_s16: {
  Int = Intrinsic::aarch64_neon_saddlv;
  Ty = Int32Ty;
  VTy = llvm::VectorType::get(Int16Ty, 8);
  llvm::Type *Tys[2] = { Ty, VTy };
  Ops.push_back(EmitScalarExpr(E->getArg(0)));
  return EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vaddlv");
}
case NEON::BI__builtin_neon_vsri_n_v:
case NEON::BI__builtin_neon_vsriq_n_v: {
  Int = Intrinsic::aarch64_neon_vsri;
  llvm::Function *Intrin = CGM.getIntrinsic(Int, Ty);
  return EmitNeonCall(Intrin, Ops, "vsri_n");
}
case NEON::BI__builtin_neon_vsli_n_v:
case NEON::BI__builtin_neon_vsliq_n_v: {
  Int = Intrinsic::aarch64_neon_vsli;
  llvm::Function *Intrin = CGM.getIntrinsic(Int, Ty);
  return EmitNeonCall(Intrin, Ops, "vsli_n");
}
case NEON::BI__builtin_neon_vsra_n_v:
case NEON::BI__builtin_neon_vsraq_n_v:
  Ops[0] = Builder.CreateBitCast(Ops[0], Ty);
  Ops[1] = EmitNeonRShiftImm(Ops[1], Ops[2], Ty, usgn, "vsra_n");
  return Builder.CreateAdd(Ops[0], Ops[1]);
case NEON::BI__builtin_neon_vrsra_n_v:
case NEON::BI__builtin_neon_vrsraq_n_v: {
  Int = usgn ? Intrinsic::aarch64_neon_urshl : Intrinsic::aarch64_neon_srshl;
  SmallVector<llvm::Value*,2> TmpOps;
  TmpOps.push_back(Ops[1]);
  TmpOps.push_back(Ops[2]);
  Function* F = CGM.getIntrinsic(Int, Ty);
  llvm::Value *tmp = EmitNeonCall(F, TmpOps, "vrshr_n", 1, true);
  Ops[0] = Builder.CreateBitCast(Ops[0], VTy);
  return Builder.CreateAdd(Ops[0], tmp);
}
  // FIXME: Sharing loads & stores with 32-bit is complicated by the absence
  // of an Align parameter here.
case NEON::BI__builtin_neon_vld1_x2_v:
case NEON::BI__builtin_neon_vld1q_x2_v:
case NEON::BI__builtin_neon_vld1_x3_v:
case NEON::BI__builtin_neon_vld1q_x3_v:
case NEON::BI__builtin_neon_vld1_x4_v:
case NEON::BI__builtin_neon_vld1q_x4_v: {
  llvm::Type *PTy = llvm::PointerType::getUnqual(VTy->getVectorElementType());
  Ops[1] = Builder.CreateBitCast(Ops[1], PTy);
  llvm::Type *Tys[2] = { VTy, PTy };
  unsigned Int;
  switch (BuiltinID) {
  case NEON::BI__builtin_neon_vld1_x2_v:
  case NEON::BI__builtin_neon_vld1q_x2_v:
    Int = Intrinsic::aarch64_neon_ld1x2;
    break;
  case NEON::BI__builtin_neon_vld1_x3_v:
  case NEON::BI__builtin_neon_vld1q_x3_v:
    Int = Intrinsic::aarch64_neon_ld1x3;
    break;
  case NEON::BI__builtin_neon_vld1_x4_v:
  case NEON::BI__builtin_neon_vld1q_x4_v:
    Int = Intrinsic::aarch64_neon_ld1x4;
    break;
  }
  Function *F = CGM.getIntrinsic(Int, Tys);
  Ops[1] = Builder.CreateCall(F, Ops[1], "vld1xN");
  Ty = llvm::PointerType::getUnqual(Ops[1]->getType());
  Ops[0] = Builder.CreateBitCast(Ops[0], Ty);
  return Builder.CreateDefaultAlignedStore(Ops[1], Ops[0]);
}
case NEON::BI__builtin_neon_vst1_x2_v:
case NEON::BI__builtin_neon_vst1q_x2_v:
case NEON::BI__builtin_neon_vst1_x3_v:
case NEON::BI__builtin_neon_vst1q_x3_v:
case NEON::BI__builtin_neon_vst1_x4_v:
case NEON::BI__builtin_neon_vst1q_x4_v: {
  llvm::Type *PTy = llvm::PointerType::getUnqual(VTy->getVectorElementType());
  llvm::Type *Tys[2] = { VTy, PTy };
  unsigned Int;
  switch (BuiltinID) {
  case NEON::BI__builtin_neon_vst1_x2_v:
  case NEON::BI__builtin_neon_vst1q_x2_v:
    Int = Intrinsic::aarch64_neon_st1x2;
    break;
  case NEON::BI__builtin_neon_vst1_x3_v:
  case NEON::BI__builtin_neon_vst1q_x3_v:
    Int = Intrinsic::aarch64_neon_st1x3;
    break;
  case NEON::BI__builtin_neon_vst1_x4_v:
  case NEON::BI__builtin_neon_vst1q_x4_v:
    Int = Intrinsic::aarch64_neon_st1x4;
    break;
  }
  std::rotate(Ops.begin(), Ops.begin() + 1, Ops.end());
  return EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "");
}
case NEON::BI__builtin_neon_vld1_v:
case NEON::BI__builtin_neon_vld1q_v: {
  Ops[0] = Builder.CreateBitCast(Ops[0], llvm::PointerType::getUnqual(VTy));
  auto Alignment = CharUnits::fromQuantity(
      BuiltinID == NEON::BI__builtin_neon_vld1_v ? 8 : 16);
  return Builder.CreateAlignedLoad(VTy, Ops[0], Alignment);
}
case NEON::BI__builtin_neon_vst1_v:
case NEON::BI__builtin_neon_vst1q_v:
  Ops[0] = Builder.CreateBitCast(Ops[0], llvm::PointerType::getUnqual(VTy));
  Ops[1] = Builder.CreateBitCast(Ops[1], VTy);
  return Builder.CreateDefaultAlignedStore(Ops[1], Ops[0]);
case NEON::BI__builtin_neon_vld1_lane_v:
case NEON::BI__builtin_neon_vld1q_lane_v: {
  Ops[1] = Builder.CreateBitCast(Ops[1], Ty);
  Ty = llvm::PointerType::getUnqual(VTy->getElementType());
  Ops[0] = Builder.CreateBitCast(Ops[0], Ty);
  auto Alignment = CharUnits::fromQuantity(
      BuiltinID == NEON::BI__builtin_neon_vld1_lane_v ? 8 : 16);
  Ops[0] =
      Builder.CreateAlignedLoad(VTy->getElementType(), Ops[0], Alignment);
  return Builder.CreateInsertElement(Ops[1], Ops[0], Ops[2], "vld1_lane");
}
case NEON::BI__builtin_neon_vld1_dup_v:
case NEON::BI__builtin_neon_vld1q_dup_v: {
  Value *V = UndefValue::get(Ty);
  Ty = llvm::PointerType::getUnqual(VTy->getElementType());
  Ops[0] = Builder.CreateBitCast(Ops[0], Ty);
  auto Alignment = CharUnits::fromQuantity(
      BuiltinID == NEON::BI__builtin_neon_vld1_dup_v ? 8 : 16);
  Ops[0] =
      Builder.CreateAlignedLoad(VTy->getElementType(), Ops[0], Alignment);
  llvm::Constant *CI = ConstantInt::get(Int32Ty, 0);
  Ops[0] = Builder.CreateInsertElement(V, Ops[0], CI);
  return EmitNeonSplat(Ops[0], CI);
}
case NEON::BI__builtin_neon_vst1_lane_v:
case NEON::BI__builtin_neon_vst1q_lane_v:
  Ops[1] = Builder.CreateBitCast(Ops[1], Ty);
  Ops[1] = Builder.CreateExtractElement(Ops[1], Ops[2]);
  Ty = llvm::PointerType::getUnqual(Ops[1]->getType());
  return Builder.CreateDefaultAlignedStore(Ops[1],
                                           Builder.CreateBitCast(Ops[0], Ty));
case NEON::BI__builtin_neon_vld2_v:
case NEON::BI__builtin_neon_vld2q_v: {
  llvm::Type *PTy = llvm::PointerType::getUnqual(VTy);
  Ops[1] = Builder.CreateBitCast(Ops[1], PTy);
  llvm::Type *Tys[2] = { VTy, PTy };
  Function *F = CGM.getIntrinsic(Intrinsic::aarch64_neon_ld2, Tys);
  Ops[1] = Builder.CreateCall(F, Ops[1], "vld2");
  Ops[0] = Builder.CreateBitCast(Ops[0],
              llvm::PointerType::getUnqual(Ops[1]->getType()));
  return Builder.CreateDefaultAlignedStore(Ops[1], Ops[0]);
}
case NEON::BI__builtin_neon_vld3_v:
case NEON::BI__builtin_neon_vld3q_v: {
  llvm::Type *PTy = llvm::PointerType::getUnqual(VTy);
  Ops[1] = Builder.CreateBitCast(Ops[1], PTy);
  llvm::Type *Tys[2] = { VTy, PTy };
  Function *F = CGM.getIntrinsic(Intrinsic::aarch64_neon_ld3, Tys);
  Ops[1] = Builder.CreateCall(F, Ops[1], "vld3");
  Ops[0] = Builder.CreateBitCast(Ops[0],
              llvm::PointerType::getUnqual(Ops[1]->getType()));
  return Builder.CreateDefaultAlignedStore(Ops[1], Ops[0]);
}
case NEON::BI__builtin_neon_vld4_v:
case NEON::BI__builtin_neon_vld4q_v: {
  llvm::Type *PTy = llvm::PointerType::getUnqual(VTy);
  Ops[1] = Builder.CreateBitCast(Ops[1], PTy);
  llvm::Type *Tys[2] = { VTy, PTy };
  Function *F = CGM.getIntrinsic(Intrinsic::aarch64_neon_ld4, Tys);
  Ops[1] = Builder.CreateCall(F, Ops[1], "vld4");
  Ops[0] = Builder.CreateBitCast(Ops[0],
              llvm::PointerType::getUnqual(Ops[1]->getType()));
  return Builder.CreateDefaultAlignedStore(Ops[1], Ops[0]);
}
case NEON::BI__builtin_neon_vld2_dup_v:
case NEON::BI__builtin_neon_vld2q_dup_v: {
  llvm::Type *PTy =
    llvm::PointerType::getUnqual(VTy->getElementType());
  Ops[1] = Builder.CreateBitCast(Ops[1], PTy);
  llvm::Type *Tys[2] = { VTy, PTy };
  Function *F = CGM.getIntrinsic(Intrinsic::aarch64_neon_ld2r, Tys);
  Ops[1] = Builder.CreateCall(F, Ops[1], "vld2");
  Ops[0] = Builder.CreateBitCast(Ops[0],
              llvm::PointerType::getUnqual(Ops[1]->getType()));
  return Builder.CreateDefaultAlignedStore(Ops[1], Ops[0]);
}
case NEON::BI__builtin_neon_vld3_dup_v:
case NEON::BI__builtin_neon_vld3q_dup_v: {
  llvm::Type *PTy =
    llvm::PointerType::getUnqual(VTy->getElementType());
  Ops[1] = Builder.CreateBitCast(Ops[1], PTy);
  llvm::Type *Tys[2] = { VTy, PTy };
  Function *F = CGM.getIntrinsic(Intrinsic::aarch64_neon_ld3r, Tys);
  Ops[1] = Builder.CreateCall(F, Ops[1], "vld3");
  Ops[0] = Builder.CreateBitCast(Ops[0],
              llvm::PointerType::getUnqual(Ops[1]->getType()));
  return Builder.CreateDefaultAlignedStore(Ops[1], Ops[0]);
}
case NEON::BI__builtin_neon_vld4_dup_v:
case NEON::BI__builtin_neon_vld4q_dup_v: {
  llvm::Type *PTy =
    llvm::PointerType::getUnqual(VTy->getElementType());
  Ops[1] = Builder.CreateBitCast(Ops[1], PTy);
  llvm::Type *Tys[2] = { VTy, PTy };
  Function *F = CGM.getIntrinsic(Intrinsic::aarch64_neon_ld4r, Tys);
  Ops[1] = Builder.CreateCall(F, Ops[1], "vld4");
  Ops[0] = Builder.CreateBitCast(Ops[0],
              llvm::PointerType::getUnqual(Ops[1]->getType()));
  return Builder.CreateDefaultAlignedStore(Ops[1], Ops[0]);
}
case NEON::BI__builtin_neon_vld2_lane_v:
case NEON::BI__builtin_neon_vld2q_lane_v: {
  llvm::Type *Tys[2] = { VTy, Ops[1]->getType() };
  Function *F = CGM.getIntrinsic(Intrinsic::aarch64_neon_ld2lane, Tys);
  Ops.push_back(Ops[1]);
  Ops.erase(Ops.begin()+1);
  Ops[1] = Builder.CreateBitCast(Ops[1], Ty);
  Ops[2] = Builder.CreateBitCast(Ops[2], Ty);
  Ops[3] = Builder.CreateZExt(Ops[3], Int64Ty);
  Ops[1] = Builder.CreateCall(F, makeArrayRef(Ops).slice(1), "vld2_lane");
  Ty = llvm::PointerType::getUnqual(Ops[1]->getType());
  Ops[0] = Builder.CreateBitCast(Ops[0], Ty);
  return Builder.CreateDefaultAlignedStore(Ops[1], Ops[0]);
}
case NEON::BI__builtin_neon_vld3_lane_v:
case NEON::BI__builtin_neon_vld3q_lane_v: {
  llvm::Type *Tys[2] = { VTy, Ops[1]->getType() };
  Function *F = CGM.getIntrinsic(Intrinsic::aarch64_neon_ld3lane, Tys);
  Ops.push_back(Ops[1]);
  Ops.erase(Ops.begin()+1);
  Ops[1] = Builder.CreateBitCast(Ops[1], Ty);
  Ops[2] = Builder.CreateBitCast(Ops[2], Ty);
  Ops[3] = Builder.CreateBitCast(Ops[3], Ty);
  Ops[4] = Builder.CreateZExt(Ops[4], Int64Ty);
  Ops[1] = Builder.CreateCall(F, makeArrayRef(Ops).slice(1), "vld3_lane");
  Ty = llvm::PointerType::getUnqual(Ops[1]->getType());
  Ops[0] = Builder.CreateBitCast(Ops[0], Ty);
  return Builder.CreateDefaultAlignedStore(Ops[1], Ops[0]);
}
case NEON::BI__builtin_neon_vld4_lane_v:
case NEON::BI__builtin_neon_vld4q_lane_v: {
  llvm::Type *Tys[2] = { VTy, Ops[1]->getType() };
  Function *F = CGM.getIntrinsic(Intrinsic::aarch64_neon_ld4lane, Tys);
  Ops.push_back(Ops[1]);
  Ops.erase(Ops.begin()+1);
  Ops[1] = Builder.CreateBitCast(Ops[1], Ty);
  Ops[2] = Builder.CreateBitCast(Ops[2], Ty);
  Ops[3] = Builder.CreateBitCast(Ops[3], Ty);
  Ops[4] = Builder.CreateBitCast(Ops[4], Ty);
  Ops[5] = Builder.CreateZExt(Ops[5], Int64Ty);
  Ops[1] = Builder.CreateCall(F, makeArrayRef(Ops).slice(1), "vld4_lane");
  Ty = llvm::PointerType::getUnqual(Ops[1]->getType());
  Ops[0] = Builder.CreateBitCast(Ops[0], Ty);
  return Builder.CreateDefaultAlignedStore(Ops[1], Ops[0]);
}
case NEON::BI__builtin_neon_vst2_v:
case NEON::BI__builtin_neon_vst2q_v: {
  Ops.push_back(Ops[0]);
  Ops.erase(Ops.begin());
  llvm::Type *Tys[2] = { VTy, Ops[2]->getType() };
  return EmitNeonCall(CGM.getIntrinsic(Intrinsic::aarch64_neon_st2, Tys),
                      Ops, "");
}
case NEON::BI__builtin_neon_vst2_lane_v:
case NEON::BI__builtin_neon_vst2q_lane_v: {
  Ops.push_back(Ops[0]);
  Ops.erase(Ops.begin());
  Ops[2] = Builder.CreateZExt(Ops[2], Int64Ty);
  llvm::Type *Tys[2] = { VTy, Ops[3]->getType() };
  return EmitNeonCall(CGM.getIntrinsic(Intrinsic::aarch64_neon_st2lane, Tys),
                      Ops, "");
}
case NEON::BI__builtin_neon_vst3_v:
case NEON::BI__builtin_neon_vst3q_v: {
  Ops.push_back(Ops[0]);
  Ops.erase(Ops.begin());
  llvm::Type *Tys[2] = { VTy, Ops[3]->getType() };
  return EmitNeonCall(CGM.getIntrinsic(Intrinsic::aarch64_neon_st3, Tys),
                      Ops, "");
}
case NEON::BI__builtin_neon_vst3_lane_v:
case NEON::BI__builtin_neon_vst3q_lane_v: {
  Ops.push_back(Ops[0]);
  Ops.erase(Ops.begin());
  Ops[3] = Builder.CreateZExt(Ops[3], Int64Ty);
  llvm::Type *Tys[2] = { VTy, Ops[4]->getType() };
  return EmitNeonCall(CGM.getIntrinsic(Intrinsic::aarch64_neon_st3lane, Tys),
                      Ops, "");
}
case NEON::BI__builtin_neon_vst4_v:
case NEON::BI__builtin_neon_vst4q_v: {
  Ops.push_back(Ops[0]);
  Ops.erase(Ops.begin());
  llvm::Type *Tys[2] = { VTy, Ops[4]->getType() };
  return EmitNeonCall(CGM.getIntrinsic(Intrinsic::aarch64_neon_st4, Tys),
                      Ops, "");
}
case NEON::BI__builtin_neon_vst4_lane_v:
case NEON::BI__builtin_neon_vst4q_lane_v: {
  Ops.push_back(Ops[0]);
  Ops.erase(Ops.begin());
  Ops[4] = Builder.CreateZExt(Ops[4], Int64Ty);
  llvm::Type *Tys[2] = { VTy, Ops[5]->getType() };
  return EmitNeonCall(CGM.getIntrinsic(Intrinsic::aarch64_neon_st4lane, Tys),
                      Ops, "");
}
case NEON::BI__builtin_neon_vtrn_v:
case NEON::BI__builtin_neon_vtrnq_v: {
  Ops[0] = Builder.CreateBitCast(Ops[0], llvm::PointerType::getUnqual(Ty));
  Ops[1] = Builder.CreateBitCast(Ops[1], Ty);
  Ops[2] = Builder.CreateBitCast(Ops[2], Ty);
  Value *SV = nullptr;

  for (unsigned vi = 0; vi != 2; ++vi) {
    SmallVector<uint32_t, 16> Indices;
    for (unsigned i = 0, e = VTy->getNumElements(); i != e; i += 2) {
      Indices.push_back(i+vi);
      Indices.push_back(i+e+vi);
    }
    Value *Addr = Builder.CreateConstInBoundsGEP1_32(Ty, Ops[0], vi);
    SV = Builder.CreateShuffleVector(Ops[1], Ops[2], Indices, "vtrn");
    SV = Builder.CreateDefaultAlignedStore(SV, Addr);
  }
  return SV;
}
case NEON::BI__builtin_neon_vuzp_v:
case NEON::BI__builtin_neon_vuzpq_v: {
  Ops[0] = Builder.CreateBitCast(Ops[0], llvm::PointerType::getUnqual(Ty));
  Ops[1] = Builder.CreateBitCast(Ops[1], Ty);
  Ops[2] = Builder.CreateBitCast(Ops[2], Ty);
  Value *SV = nullptr;

  for (unsigned vi = 0; vi != 2; ++vi) {
    SmallVector<uint32_t, 16> Indices;
    for (unsigned i = 0, e = VTy->getNumElements(); i != e; ++i)
      Indices.push_back(2*i+vi);

    Value *Addr = Builder.CreateConstInBoundsGEP1_32(Ty, Ops[0], vi);
    SV = Builder.CreateShuffleVector(Ops[1], Ops[2], Indices, "vuzp");
    SV = Builder.CreateDefaultAlignedStore(SV, Addr);
  }
  return SV;
}
case NEON::BI__builtin_neon_vzip_v:
case NEON::BI__builtin_neon_vzipq_v: {
  Ops[0] = Builder.CreateBitCast(Ops[0], llvm::PointerType::getUnqual(Ty));
  Ops[1] = Builder.CreateBitCast(Ops[1], Ty);
  Ops[2] = Builder.CreateBitCast(Ops[2], Ty);
  Value *SV = nullptr;

  for (unsigned vi = 0; vi != 2; ++vi) {
    SmallVector<uint32_t, 16> Indices;
    for (unsigned i = 0, e = VTy->getNumElements(); i != e; i += 2) {
      Indices.push_back((i + vi*e) >> 1);
      Indices.push_back(((i + vi*e) >> 1)+e);
    }
    Value *Addr = Builder.CreateConstInBoundsGEP1_32(Ty, Ops[0], vi);
    SV = Builder.CreateShuffleVector(Ops[1], Ops[2], Indices, "vzip");
    SV = Builder.CreateDefaultAlignedStore(SV, Addr);
  }
  return SV;
}
case NEON::BI__builtin_neon_vqtbl1q_v: {
  return EmitNeonCall(CGM.getIntrinsic(Intrinsic::aarch64_neon_tbl1, Ty),
                      Ops, "vtbl1");
}
case NEON::BI__builtin_neon_vqtbl2q_v: {
  return EmitNeonCall(CGM.getIntrinsic(Intrinsic::aarch64_neon_tbl2, Ty),
                      Ops, "vtbl2");
}
case NEON::BI__builtin_neon_vqtbl3q_v: {
  return EmitNeonCall(CGM.getIntrinsic(Intrinsic::aarch64_neon_tbl3, Ty),
                      Ops, "vtbl3");
}
case NEON::BI__builtin_neon_vqtbl4q_v: {
  return EmitNeonCall(CGM.getIntrinsic(Intrinsic::aarch64_neon_tbl4, Ty),
                      Ops, "vtbl4");
}
case NEON::BI__builtin_neon_vqtbx1q_v: {
  return EmitNeonCall(CGM.getIntrinsic(Intrinsic::aarch64_neon_tbx1, Ty),
                      Ops, "vtbx1");
}
case NEON::BI__builtin_neon_vqtbx2q_v: {
  return EmitNeonCall(CGM.getIntrinsic(Intrinsic::aarch64_neon_tbx2, Ty),
                      Ops, "vtbx2");
}
case NEON::BI__builtin_neon_vqtbx3q_v: {
  return EmitNeonCall(CGM.getIntrinsic(Intrinsic::aarch64_neon_tbx3, Ty),
                      Ops, "vtbx3");
}
case NEON::BI__builtin_neon_vqtbx4q_v: {
  return EmitNeonCall(CGM.getIntrinsic(Intrinsic::aarch64_neon_tbx4, Ty),
                      Ops, "vtbx4");
}
case NEON::BI__builtin_neon_vsqadd_v:
case NEON::BI__builtin_neon_vsqaddq_v: {
  Int = Intrinsic::aarch64_neon_usqadd;
  return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vsqadd");
}
case NEON::BI__builtin_neon_vuqadd_v:
case NEON::BI__builtin_neon_vuqaddq_v: {
  Int = Intrinsic::aarch64_neon_suqadd;
  return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vuqadd");
}
}
7933}

7935llvm::Value *CodeGenFunction::
7936BuildVector(ArrayRef<llvm::Value*> Ops) {
assert((Ops.size() & (Ops.size() - 1)) == 0 &&(static_cast <bool> ((Ops.size() & (Ops.size() - 1)
) == 0 && "Not a power-of-two sized vector!") ? void (
0) : __assert_fail ("(Ops.size() & (Ops.size() - 1)) == 0 && \"Not a power-of-two sized vector!\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 7938, __extension__ __PRETTY_FUNCTION__))
       "Not a power-of-two sized vector!")(static_cast <bool> ((Ops.size() & (Ops.size() - 1)
) == 0 && "Not a power-of-two sized vector!") ? void (
0) : __assert_fail ("(Ops.size() & (Ops.size() - 1)) == 0 && \"Not a power-of-two sized vector!\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 7938, __extension__ __PRETTY_FUNCTION__));
bool AllConstants = true;
for (unsigned i = 0, e = Ops.size(); i != e && AllConstants; ++i)
  AllConstants &= isa<Constant>(Ops[i]);

// If this is a constant vector, create a ConstantVector.
if (AllConstants) {
  SmallVector<llvm::Constant*, 16> CstOps;
  for (unsigned i = 0, e = Ops.size(); i != e; ++i)
    CstOps.push_back(cast<Constant>(Ops[i]));
  return llvm::ConstantVector::get(CstOps);
}

// Otherwise, insertelement the values to build the vector.
Value *Result =
  llvm::UndefValue::get(llvm::VectorType::get(Ops[0]->getType(), Ops.size()));

for (unsigned i = 0, e = Ops.size(); i != e; ++i)
  Result = Builder.CreateInsertElement(Result, Ops[i], Builder.getInt32(i));

return Result;
7959}

7961// Convert the mask from an integer type to a vector of i1.
7962static Value *getMaskVecValue(CodeGenFunction &CGF, Value *Mask,
                            unsigned NumElts) {

llvm::VectorType *MaskTy = llvm::VectorType::get(CGF.Builder.getInt1Ty(),
                       cast<IntegerType>(Mask->getType())->getBitWidth());
Value *MaskVec = CGF.Builder.CreateBitCast(Mask, MaskTy);

// If we have less than 8 elements, then the starting mask was an i8 and
// we need to extract down to the right number of elements.
if (NumElts < 8) {
  uint32_t Indices[4];
  for (unsigned i = 0; i != NumElts; ++i)
    Indices[i] = i;
  MaskVec = CGF.Builder.CreateShuffleVector(MaskVec, MaskVec,
                                           makeArrayRef(Indices, NumElts),
                                           "extract");
}
return MaskVec;
7980}

7982static Value *EmitX86MaskedStore(CodeGenFunction &CGF,
                               SmallVectorImpl<Value *> &Ops,
                               unsigned Align) {
// Cast the pointer to right type.
Ops[0] = CGF.Builder.CreateBitCast(Ops[0],
                             llvm::PointerType::getUnqual(Ops[1]->getType()));

// If the mask is all ones just emit a regular store.
if (const auto *C = dyn_cast<Constant>(Ops[2]))
  if (C->isAllOnesValue())
    return CGF.Builder.CreateAlignedStore(Ops[1], Ops[0], Align);

Value *MaskVec = getMaskVecValue(CGF, Ops[2],
                                 Ops[1]->getType()->getVectorNumElements());

return CGF.Builder.CreateMaskedStore(Ops[1], Ops[0], Align, MaskVec);
7998}

8000static Value *EmitX86MaskedLoad(CodeGenFunction &CGF,
                              SmallVectorImpl<Value *> &Ops, unsigned Align) {
// Cast the pointer to right type.
Ops[0] = CGF.Builder.CreateBitCast(Ops[0],
                             llvm::PointerType::getUnqual(Ops[1]->getType()));

// If the mask is all ones just emit a regular store.
if (const auto *C = dyn_cast<Constant>(Ops[2]))
  if (C->isAllOnesValue())
    return CGF.Builder.CreateAlignedLoad(Ops[0], Align);

Value *MaskVec = getMaskVecValue(CGF, Ops[2],
                                 Ops[1]->getType()->getVectorNumElements());

return CGF.Builder.CreateMaskedLoad(Ops[0], Align, MaskVec, Ops[1]);
8015}

8017static Value *EmitX86MaskLogic(CodeGenFunction &CGF, Instruction::BinaryOps Opc,
                            unsigned NumElts, SmallVectorImpl<Value *> &Ops,
                            bool InvertLHS = false) {
Value *LHS = getMaskVecValue(CGF, Ops[0], NumElts);
Value *RHS = getMaskVecValue(CGF, Ops[1], NumElts);

if (InvertLHS)
  LHS = CGF.Builder.CreateNot(LHS);

return CGF.Builder.CreateBitCast(CGF.Builder.CreateBinOp(Opc, LHS, RHS),
                                CGF.Builder.getIntNTy(std::max(NumElts, 8U)));
8028}

8030static Value *EmitX86SubVectorBroadcast(CodeGenFunction &CGF,
                                      SmallVectorImpl<Value *> &Ops,
                                      llvm::Type *DstTy,
                                      unsigned SrcSizeInBits,
                                      unsigned Align) {
// Load the subvector.
Ops[0] = CGF.Builder.CreateAlignedLoad(Ops[0], Align);

// Create broadcast mask.
unsigned NumDstElts = DstTy->getVectorNumElements();
unsigned NumSrcElts = SrcSizeInBits / DstTy->getScalarSizeInBits();

SmallVector<uint32_t, 8> Mask;
for (unsigned i = 0; i != NumDstElts; i += NumSrcElts)
  for (unsigned j = 0; j != NumSrcElts; ++j)
    Mask.push_back(j);

return CGF.Builder.CreateShuffleVector(Ops[0], Ops[0], Mask, "subvecbcst");
8048}

8050static Value *EmitX86Select(CodeGenFunction &CGF,
                          Value *Mask, Value *Op0, Value *Op1) {

// If the mask is all ones just return first argument.
if (const auto *C = dyn_cast<Constant>(Mask))
  if (C->isAllOnesValue())
    return Op0;

Mask = getMaskVecValue(CGF, Mask, Op0->getType()->getVectorNumElements());

return CGF.Builder.CreateSelect(Mask, Op0, Op1);
8061}

8063static Value *EmitX86MaskedCompare(CodeGenFunction &CGF, unsigned CC,
                                 bool Signed, ArrayRef<Value *> Ops) {
assert((Ops.size() == 2 || Ops.size() == 4) &&(static_cast <bool> ((Ops.size() == 2 || Ops.size() == 4
) && "Unexpected number of arguments") ? void (0) : __assert_fail
 ("(Ops.size() == 2 || Ops.size() == 4) && \"Unexpected number of arguments\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 8066, __extension__ __PRETTY_FUNCTION__))
       "Unexpected number of arguments")(static_cast <bool> ((Ops.size() == 2 || Ops.size() == 4
) && "Unexpected number of arguments") ? void (0) : __assert_fail
 ("(Ops.size() == 2 || Ops.size() == 4) && \"Unexpected number of arguments\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 8066, __extension__ __PRETTY_FUNCTION__));
unsigned NumElts = Ops[0]->getType()->getVectorNumElements();
2
←
Calling 'Type::getVectorNumElements'→
28
←
Returning from 'Type::getVectorNumElements'→
29
←
'NumElts' initialized here→
Value *Cmp;

if (CC == 3) {
30
←
Taking false branch→
  Cmp = Constant::getNullValue(
                     llvm::VectorType::get(CGF.Builder.getInt1Ty(), NumElts));
} else if (CC == 7) {
31
←
Taking false branch→
  Cmp = Constant::getAllOnesValue(
                     llvm::VectorType::get(CGF.Builder.getInt1Ty(), NumElts));
} else {
  ICmpInst::Predicate Pred;
  switch (CC) {
32
←
Control jumps to 'case 1:'  at line 8081→
  default: llvm_unreachable("Unknown condition code")::llvm::llvm_unreachable_internal("Unknown condition code", "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 8079);
  case 0: Pred = ICmpInst::ICMP_EQ;  break;
  case 1: Pred = Signed ? ICmpInst::ICMP_SLT : ICmpInst::ICMP_ULT; break;
33
←
'?' condition is true→
34
←
 Execution continues on line 8087→
  case 2: Pred = Signed ? ICmpInst::ICMP_SLE : ICmpInst::ICMP_ULE; break;
  case 4: Pred = ICmpInst::ICMP_NE;  break;
  case 5: Pred = Signed ? ICmpInst::ICMP_SGE : ICmpInst::ICMP_UGE; break;
  case 6: Pred = Signed ? ICmpInst::ICMP_SGT : ICmpInst::ICMP_UGT; break;
  }
  Cmp = CGF.Builder.CreateICmp(Pred, Ops[0], Ops[1]);
}

if (Ops.size() == 4) {
35
←
Assuming the condition is false→
36
←
Taking false branch→
  const auto *C = dyn_cast<Constant>(Ops[3]);
  if (!C || !C->isAllOnesValue())
    Cmp = CGF.Builder.CreateAnd(Cmp, getMaskVecValue(CGF, Ops[3], NumElts));
}

if (NumElts < 8) {
37
←
Assuming 'NumElts' is < 8→
38
←
Taking true branch→
  uint32_t Indices[8];
  for (unsigned i = 0; i != NumElts; ++i)
39
←
Assuming 'i' is equal to 'NumElts'→
40
←
Loop condition is false. Execution continues on line 8100→
    Indices[i] = i;
  for (unsigned i = NumElts; i != 8; ++i)
41
←
Loop condition is true.  Entering loop body→
    Indices[i] = i % NumElts + NumElts;
42
←
Division by zero
  Cmp = CGF.Builder.CreateShuffleVector(
      Cmp, llvm::Constant::getNullValue(Cmp->getType()), Indices);
}
return CGF.Builder.CreateBitCast(Cmp,
                                 IntegerType::get(CGF.getLLVMContext(),
                                                  std::max(NumElts, 8U)));
8108}

8110static Value *EmitX86ConvertToMask(CodeGenFunction &CGF, Value *In) {
Value *Zero = Constant::getNullValue(In->getType());
return EmitX86MaskedCompare(CGF, 1, true, { In, Zero });
1
Calling 'EmitX86MaskedCompare'→
8113}

8115static Value *EmitX86Abs(CodeGenFunction &CGF, ArrayRef<Value *> Ops) {

llvm::Type *Ty = Ops[0]->getType();
Value *Zero = llvm::Constant::getNullValue(Ty);
Value *Sub = CGF.Builder.CreateSub(Zero, Ops[0]);
Value *Cmp = CGF.Builder.CreateICmp(ICmpInst::ICMP_SGT, Ops[0], Zero);
Value *Res = CGF.Builder.CreateSelect(Cmp, Ops[0], Sub);
if (Ops.size() == 1)
  return Res;
return EmitX86Select(CGF, Ops[2], Res, Ops[1]);
8125}

8127static Value *EmitX86MinMax(CodeGenFunction &CGF, ICmpInst::Predicate Pred,
                          ArrayRef<Value *> Ops) {
Value *Cmp = CGF.Builder.CreateICmp(Pred, Ops[0], Ops[1]);
Value *Res = CGF.Builder.CreateSelect(Cmp, Ops[0], Ops[1]);

if (Ops.size() == 2)
  return Res;

assert(Ops.size() == 4)(static_cast <bool> (Ops.size() == 4) ? void (0) : __assert_fail
 ("Ops.size() == 4", "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 8135, __extension__ __PRETTY_FUNCTION__));
return EmitX86Select(CGF, Ops[3], Res, Ops[2]);
8137}

8139static Value *EmitX86SExtMask(CodeGenFunction &CGF, Value *Op, 
                            llvm::Type *DstTy) {
unsigned NumberOfElements = DstTy->getVectorNumElements();
Value *Mask = getMaskVecValue(CGF, Op, NumberOfElements);
return CGF.Builder.CreateSExt(Mask, DstTy, "vpmovm2");
8144}

8146Value *CodeGenFunction::EmitX86CpuIs(const CallExpr *E) {
const Expr *CPUExpr = E->getArg(0)->IgnoreParenCasts();
StringRef CPUStr = cast<clang::StringLiteral>(CPUExpr)->getString();
return EmitX86CpuIs(CPUStr);
8150}

8152Value *CodeGenFunction::EmitX86CpuIs(StringRef CPUStr) {

llvm::Type *Int32Ty = Builder.getInt32Ty();

// Matching the struct layout from the compiler-rt/libgcc structure that is
// filled in:
// unsigned int __cpu_vendor;
// unsigned int __cpu_type;
// unsigned int __cpu_subtype;
// unsigned int __cpu_features[1];
llvm::Type *STy = llvm::StructType::get(Int32Ty, Int32Ty, Int32Ty,
                                        llvm::ArrayType::get(Int32Ty, 1));

// Grab the global __cpu_model.
llvm::Constant *CpuModel = CGM.CreateRuntimeVariable(STy, "__cpu_model");

// Calculate the index needed to access the correct field based on the
// range. Also adjust the expected value.
unsigned Index;
unsigned Value;
std::tie(Index, Value) = StringSwitch<std::pair<unsigned, unsigned>>(CPUStr)
8173#define X86_VENDOR(ENUM, STRING)                                               \
.Case(STRING, {0u, static_cast<unsigned>(llvm::X86::ENUM)})
8175#define X86_CPU_TYPE_COMPAT_WITH_ALIAS(ARCHNAME, ENUM, STR, ALIAS)             \
.Cases(STR, ALIAS, {1u, static_cast<unsigned>(llvm::X86::ENUM)})
8177#define X86_CPU_TYPE_COMPAT(ARCHNAME, ENUM, STR)                               \
.Case(STR, {1u, static_cast<unsigned>(llvm::X86::ENUM)})
8179#define X86_CPU_SUBTYPE_COMPAT(ARCHNAME, ENUM, STR)                            \
.Case(STR, {2u, static_cast<unsigned>(llvm::X86::ENUM)})
8181#include "llvm/Support/X86TargetParser.def"
                             .Default({0, 0});
assert(Value != 0 && "Invalid CPUStr passed to CpuIs")(static_cast <bool> (Value != 0 && "Invalid CPUStr passed to CpuIs"
) ? void (0) : __assert_fail ("Value != 0 && \"Invalid CPUStr passed to CpuIs\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 8183, __extension__ __PRETTY_FUNCTION__));

// Grab the appropriate field from __cpu_model.
llvm::Value *Idxs[] = {ConstantInt::get(Int32Ty, 0),
                       ConstantInt::get(Int32Ty, Index)};
llvm::Value *CpuValue = Builder.CreateGEP(STy, CpuModel, Idxs);
CpuValue = Builder.CreateAlignedLoad(CpuValue, CharUnits::fromQuantity(4));

// Check the value of the field against the requested value.
return Builder.CreateICmpEQ(CpuValue,
                                llvm::ConstantInt::get(Int32Ty, Value));
8194}

8196Value *CodeGenFunction::EmitX86CpuSupports(const CallExpr *E) {
const Expr *FeatureExpr = E->getArg(0)->IgnoreParenCasts();
StringRef FeatureStr = cast<StringLiteral>(FeatureExpr)->getString();
return EmitX86CpuSupports(FeatureStr);
8200}

8202Value *CodeGenFunction::EmitX86CpuSupports(ArrayRef<StringRef> FeatureStrs) {
// Processor features and mapping to processor feature value.

uint32_t FeaturesMask = 0;

for (const StringRef &FeatureStr : FeatureStrs) {
  unsigned Feature =
      StringSwitch<unsigned>(FeatureStr)
8210#define X86_FEATURE_COMPAT(VAL, ENUM, STR) .Case(STR, VAL)
8211#include "llvm/Support/X86TargetParser.def"
      ;
  FeaturesMask |= (1U << Feature);
}

// Matching the struct layout from the compiler-rt/libgcc structure that is
// filled in:
// unsigned int __cpu_vendor;
// unsigned int __cpu_type;
// unsigned int __cpu_subtype;
// unsigned int __cpu_features[1];
llvm::Type *STy = llvm::StructType::get(Int32Ty, Int32Ty, Int32Ty,
                                        llvm::ArrayType::get(Int32Ty, 1));

// Grab the global __cpu_model.
llvm::Constant *CpuModel = CGM.CreateRuntimeVariable(STy, "__cpu_model");

// Grab the first (0th) element from the field __cpu_features off of the
// global in the struct STy.
Value *Idxs[] = {ConstantInt::get(Int32Ty, 0), ConstantInt::get(Int32Ty, 3),
                 ConstantInt::get(Int32Ty, 0)};
Value *CpuFeatures = Builder.CreateGEP(STy, CpuModel, Idxs);
Value *Features =
    Builder.CreateAlignedLoad(CpuFeatures, CharUnits::fromQuantity(4));

// Check the value of the bit corresponding to the feature requested.
Value *Bitset = Builder.CreateAnd(
    Features, llvm::ConstantInt::get(Int32Ty, FeaturesMask));
return Builder.CreateICmpNE(Bitset, llvm::ConstantInt::get(Int32Ty, 0));
8240}

8242Value *CodeGenFunction::EmitX86CpuInit() {
llvm::FunctionType *FTy = llvm::FunctionType::get(VoidTy,
                                                  /*Variadic*/ false);
llvm::Constant *Func = CGM.CreateRuntimeFunction(FTy, "__cpu_indicator_init");
return Builder.CreateCall(Func);
8247}

8249Value *CodeGenFunction::EmitX86BuiltinExpr(unsigned BuiltinID,
                                         const CallExpr *E) {
if (BuiltinID == X86::BI__builtin_cpu_is)
  return EmitX86CpuIs(E);
if (BuiltinID == X86::BI__builtin_cpu_supports)
  return EmitX86CpuSupports(E);
if (BuiltinID == X86::BI__builtin_cpu_init)
  return EmitX86CpuInit();

SmallVector<Value*, 4> Ops;

// Find out if any arguments are required to be integer constant expressions.
unsigned ICEArguments = 0;
ASTContext::GetBuiltinTypeError Error;
getContext().GetBuiltinType(BuiltinID, Error, &ICEArguments);
assert(Error == ASTContext::GE_None && "Should not codegen an error")(static_cast <bool> (Error == ASTContext::GE_None &&
 "Should not codegen an error") ? void (0) : __assert_fail ("Error == ASTContext::GE_None && \"Should not codegen an error\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 8264, __extension__ __PRETTY_FUNCTION__));

for (unsigned i = 0, e = E->getNumArgs(); i != e; i++) {
  // If this is a normal argument, just emit it as a scalar.
  if ((ICEArguments & (1 << i)) == 0) {
    Ops.push_back(EmitScalarExpr(E->getArg(i)));
    continue;
  }

  // If this is required to be a constant, constant fold it so that we know
  // that the generated intrinsic gets a ConstantInt.
  llvm::APSInt Result;
  bool IsConst = E->getArg(i)->isIntegerConstantExpr(Result, getContext());
  assert(IsConst && "Constant arg isn't actually constant?")(static_cast <bool> (IsConst && "Constant arg isn't actually constant?"
) ? void (0) : __assert_fail ("IsConst && \"Constant arg isn't actually constant?\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 8277, __extension__ __PRETTY_FUNCTION__)); (void)IsConst;
  Ops.push_back(llvm::ConstantInt::get(getLLVMContext(), Result));
}

// These exist so that the builtin that takes an immediate can be bounds
// checked by clang to avoid passing bad immediates to the backend. Since
// AVX has a larger immediate than SSE we would need separate builtins to
// do the different bounds checking. Rather than create a clang specific
// SSE only builtin, this implements eight separate builtins to match gcc
// implementation.
auto getCmpIntrinsicCall = [this, &Ops](Intrinsic::ID ID, unsigned Imm) {
  Ops.push_back(llvm::ConstantInt::get(Int8Ty, Imm));
  llvm::Function *F = CGM.getIntrinsic(ID);
  return Builder.CreateCall(F, Ops);
};

// For the vector forms of FP comparisons, translate the builtins directly to
// IR.
// TODO: The builtins could be removed if the SSE header files used vector
// extension comparisons directly (vector ordered/unordered may need
// additional support via __builtin_isnan()).
auto getVectorFCmpIR = [this, &Ops](CmpInst::Predicate Pred) {
  Value *Cmp = Builder.CreateFCmp(Pred, Ops[0], Ops[1]);
  llvm::VectorType *FPVecTy = cast<llvm::VectorType>(Ops[0]->getType());
  llvm::VectorType *IntVecTy = llvm::VectorType::getInteger(FPVecTy);
  Value *Sext = Builder.CreateSExt(Cmp, IntVecTy);
  return Builder.CreateBitCast(Sext, FPVecTy);
};

switch (BuiltinID) {
default: return nullptr;
case X86::BI_mm_prefetch: {
  Value *Address = Ops[0];
  ConstantInt *C = cast<ConstantInt>(Ops[1]);
  Value *RW = ConstantInt::get(Int32Ty, (C->getZExtValue() >> 2) & 0x1);
  Value *Locality = ConstantInt::get(Int32Ty, C->getZExtValue() & 0x3);
  Value *Data = ConstantInt::get(Int32Ty, 1);
  Value *F = CGM.getIntrinsic(Intrinsic::prefetch);
  return Builder.CreateCall(F, {Address, RW, Locality, Data});
}
case X86::BI_mm_clflush: {
  return Builder.CreateCall(CGM.getIntrinsic(Intrinsic::x86_sse2_clflush),
                            Ops[0]);
}
case X86::BI_mm_lfence: {
  return Builder.CreateCall(CGM.getIntrinsic(Intrinsic::x86_sse2_lfence));
}
case X86::BI_mm_mfence: {
  return Builder.CreateCall(CGM.getIntrinsic(Intrinsic::x86_sse2_mfence));
}
case X86::BI_mm_sfence: {
  return Builder.CreateCall(CGM.getIntrinsic(Intrinsic::x86_sse_sfence));
}
case X86::BI_mm_pause: {
  return Builder.CreateCall(CGM.getIntrinsic(Intrinsic::x86_sse2_pause));
}
case X86::BI__rdtsc: {
  return Builder.CreateCall(CGM.getIntrinsic(Intrinsic::x86_rdtsc));
}
case X86::BI__builtin_ia32_undef128:
case X86::BI__builtin_ia32_undef256:
case X86::BI__builtin_ia32_undef512:
  // The x86 definition of "undef" is not the same as the LLVM definition
  // (PR32176). We leave optimizing away an unnecessary zero constant to the
  // IR optimizer and backend.
  // TODO: If we had a "freeze" IR instruction to generate a fixed undef
  // value, we should use that here instead of a zero.
  return llvm::Constant::getNullValue(ConvertType(E->getType()));
case X86::BI__builtin_ia32_vec_init_v8qi:
case X86::BI__builtin_ia32_vec_init_v4hi:
case X86::BI__builtin_ia32_vec_init_v2si:
  return Builder.CreateBitCast(BuildVector(Ops),
                               llvm::Type::getX86_MMXTy(getLLVMContext()));
case X86::BI__builtin_ia32_vec_ext_v2si:
  return Builder.CreateExtractElement(Ops[0],
                                llvm::ConstantInt::get(Ops[1]->getType(), 0));
case X86::BI_mm_setcsr:
case X86::BI__builtin_ia32_ldmxcsr: {
  Address Tmp = CreateMemTemp(E->getArg(0)->getType());
  Builder.CreateStore(Ops[0], Tmp);
  return Builder.CreateCall(CGM.getIntrinsic(Intrinsic::x86_sse_ldmxcsr),
                        Builder.CreateBitCast(Tmp.getPointer(), Int8PtrTy));
}
case X86::BI_mm_getcsr:
case X86::BI__builtin_ia32_stmxcsr: {
  Address Tmp = CreateMemTemp(E->getType());
  Builder.CreateCall(CGM.getIntrinsic(Intrinsic::x86_sse_stmxcsr),
                     Builder.CreateBitCast(Tmp.getPointer(), Int8PtrTy));
  return Builder.CreateLoad(Tmp, "stmxcsr");
}
case X86::BI__builtin_ia32_xsave:
case X86::BI__builtin_ia32_xsave64:
case X86::BI__builtin_ia32_xrstor:
case X86::BI__builtin_ia32_xrstor64:
case X86::BI__builtin_ia32_xsaveopt:
case X86::BI__builtin_ia32_xsaveopt64:
case X86::BI__builtin_ia32_xrstors:
case X86::BI__builtin_ia32_xrstors64:
case X86::BI__builtin_ia32_xsavec:
case X86::BI__builtin_ia32_xsavec64:
case X86::BI__builtin_ia32_xsaves:
case X86::BI__builtin_ia32_xsaves64: {
  Intrinsic::ID ID;
8380#define INTRINSIC_X86_XSAVE_ID(NAME) \
  case X86::BI__builtin_ia32_##NAME: \
    ID = Intrinsic::x86_##NAME; \
    break
  switch (BuiltinID) {
  default: llvm_unreachable("Unsupported intrinsic!")::llvm::llvm_unreachable_internal("Unsupported intrinsic!", "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 8385);
  INTRINSIC_X86_XSAVE_ID(xsave);
  INTRINSIC_X86_XSAVE_ID(xsave64);
  INTRINSIC_X86_XSAVE_ID(xrstor);
  INTRINSIC_X86_XSAVE_ID(xrstor64);
  INTRINSIC_X86_XSAVE_ID(xsaveopt);
  INTRINSIC_X86_XSAVE_ID(xsaveopt64);
  INTRINSIC_X86_XSAVE_ID(xrstors);
  INTRINSIC_X86_XSAVE_ID(xrstors64);
  INTRINSIC_X86_XSAVE_ID(xsavec);
  INTRINSIC_X86_XSAVE_ID(xsavec64);
  INTRINSIC_X86_XSAVE_ID(xsaves);
  INTRINSIC_X86_XSAVE_ID(xsaves64);
  }
8399#undef INTRINSIC_X86_XSAVE_ID
  Value *Mhi = Builder.CreateTrunc(
    Builder.CreateLShr(Ops[1], ConstantInt::get(Int64Ty, 32)), Int32Ty);
  Value *Mlo = Builder.CreateTrunc(Ops[1], Int32Ty);
  Ops[1] = Mhi;
  Ops.push_back(Mlo);
  return Builder.CreateCall(CGM.getIntrinsic(ID), Ops);
}
case X86::BI__builtin_ia32_storedqudi128_mask:
case X86::BI__builtin_ia32_storedqusi128_mask:
case X86::BI__builtin_ia32_storedquhi128_mask:
case X86::BI__builtin_ia32_storedquqi128_mask:
case X86::BI__builtin_ia32_storeupd128_mask:
case X86::BI__builtin_ia32_storeups128_mask:
case X86::BI__builtin_ia32_storedqudi256_mask:
case X86::BI__builtin_ia32_storedqusi256_mask:
case X86::BI__builtin_ia32_storedquhi256_mask:
case X86::BI__builtin_ia32_storedquqi256_mask:
case X86::BI__builtin_ia32_storeupd256_mask:
case X86::BI__builtin_ia32_storeups256_mask:
case X86::BI__builtin_ia32_storedqudi512_mask:
case X86::BI__builtin_ia32_storedqusi512_mask:
case X86::BI__builtin_ia32_storedquhi512_mask:
case X86::BI__builtin_ia32_storedquqi512_mask:
case X86::BI__builtin_ia32_storeupd512_mask:
case X86::BI__builtin_ia32_storeups512_mask:
  return EmitX86MaskedStore(*this, Ops, 1);

case X86::BI__builtin_ia32_storess128_mask:
case X86::BI__builtin_ia32_storesd128_mask: {
  return EmitX86MaskedStore(*this, Ops, 16);
}
case X86::BI__builtin_ia32_vpopcntb_128:
case X86::BI__builtin_ia32_vpopcntd_128:
case X86::BI__builtin_ia32_vpopcntq_128:
case X86::BI__builtin_ia32_vpopcntw_128:
case X86::BI__builtin_ia32_vpopcntb_256:
case X86::BI__builtin_ia32_vpopcntd_256:
case X86::BI__builtin_ia32_vpopcntq_256:
case X86::BI__builtin_ia32_vpopcntw_256:
case X86::BI__builtin_ia32_vpopcntb_512:
case X86::BI__builtin_ia32_vpopcntd_512:
case X86::BI__builtin_ia32_vpopcntq_512:
case X86::BI__builtin_ia32_vpopcntw_512: {
  llvm::Type *ResultType = ConvertType(E->getType());
  llvm::Function *F = CGM.getIntrinsic(Intrinsic::ctpop, ResultType);
  return Builder.CreateCall(F, Ops);
}
case X86::BI__builtin_ia32_cvtmask2b128:
case X86::BI__builtin_ia32_cvtmask2b256:
case X86::BI__builtin_ia32_cvtmask2b512:
case X86::BI__builtin_ia32_cvtmask2w128:
case X86::BI__builtin_ia32_cvtmask2w256:
case X86::BI__builtin_ia32_cvtmask2w512:
case X86::BI__builtin_ia32_cvtmask2d128:
case X86::BI__builtin_ia32_cvtmask2d256:
case X86::BI__builtin_ia32_cvtmask2d512:
case X86::BI__builtin_ia32_cvtmask2q128:
case X86::BI__builtin_ia32_cvtmask2q256:
case X86::BI__builtin_ia32_cvtmask2q512:
  return EmitX86SExtMask(*this, Ops[0], ConvertType(E->getType()));

case X86::BI__builtin_ia32_cvtb2mask128:
case X86::BI__builtin_ia32_cvtb2mask256:
case X86::BI__builtin_ia32_cvtb2mask512:
case X86::BI__builtin_ia32_cvtw2mask128:
case X86::BI__builtin_ia32_cvtw2mask256:
case X86::BI__builtin_ia32_cvtw2mask512:
case X86::BI__builtin_ia32_cvtd2mask128:
case X86::BI__builtin_ia32_cvtd2mask256:
case X86::BI__builtin_ia32_cvtd2mask512:
case X86::BI__builtin_ia32_cvtq2mask128:
case X86::BI__builtin_ia32_cvtq2mask256:
case X86::BI__builtin_ia32_cvtq2mask512:
  return EmitX86ConvertToMask(*this, Ops[0]);

case X86::BI__builtin_ia32_movdqa32store128_mask:
case X86::BI__builtin_ia32_movdqa64store128_mask:
case X86::BI__builtin_ia32_storeaps128_mask:
case X86::BI__builtin_ia32_storeapd128_mask:
case X86::BI__builtin_ia32_movdqa32store256_mask:
case X86::BI__builtin_ia32_movdqa64store256_mask:
case X86::BI__builtin_ia32_storeaps256_mask:
case X86::BI__builtin_ia32_storeapd256_mask:
case X86::BI__builtin_ia32_movdqa32store512_mask:
case X86::BI__builtin_ia32_movdqa64store512_mask:
case X86::BI__builtin_ia32_storeaps512_mask:
case X86::BI__builtin_ia32_storeapd512_mask: {
  unsigned Align =
    getContext().getTypeAlignInChars(E->getArg(1)->getType()).getQuantity();
  return EmitX86MaskedStore(*this, Ops, Align);
}
case X86::BI__builtin_ia32_loadups128_mask:
case X86::BI__builtin_ia32_loadups256_mask:
case X86::BI__builtin_ia32_loadups512_mask:
case X86::BI__builtin_ia32_loadupd128_mask:
case X86::BI__builtin_ia32_loadupd256_mask:
case X86::BI__builtin_ia32_loadupd512_mask:
case X86::BI__builtin_ia32_loaddquqi128_mask:
case X86::BI__builtin_ia32_loaddquqi256_mask:
case X86::BI__builtin_ia32_loaddquqi512_mask:
case X86::BI__builtin_ia32_loaddquhi128_mask:
case X86::BI__builtin_ia32_loaddquhi256_mask:
case X86::BI__builtin_ia32_loaddquhi512_mask:
case X86::BI__builtin_ia32_loaddqusi128_mask:
case X86::BI__builtin_ia32_loaddqusi256_mask:
case X86::BI__builtin_ia32_loaddqusi512_mask:
case X86::BI__builtin_ia32_loaddqudi128_mask:
case X86::BI__builtin_ia32_loaddqudi256_mask:
case X86::BI__builtin_ia32_loaddqudi512_mask:
  return EmitX86MaskedLoad(*this, Ops, 1);

case X86::BI__builtin_ia32_loadss128_mask:
case X86::BI__builtin_ia32_loadsd128_mask:
  return EmitX86MaskedLoad(*this, Ops, 16);

case X86::BI__builtin_ia32_loadaps128_mask:
case X86::BI__builtin_ia32_loadaps256_mask:
case X86::BI__builtin_ia32_loadaps512_mask:
case X86::BI__builtin_ia32_loadapd128_mask:
case X86::BI__builtin_ia32_loadapd256_mask:
case X86::BI__builtin_ia32_loadapd512_mask:
case X86::BI__builtin_ia32_movdqa32load128_mask:
case X86::BI__builtin_ia32_movdqa32load256_mask:
case X86::BI__builtin_ia32_movdqa32load512_mask:
case X86::BI__builtin_ia32_movdqa64load128_mask:
case X86::BI__builtin_ia32_movdqa64load256_mask:
case X86::BI__builtin_ia32_movdqa64load512_mask: {
  unsigned Align =
    getContext().getTypeAlignInChars(E->getArg(1)->getType()).getQuantity();
  return EmitX86MaskedLoad(*this, Ops, Align);
}

case X86::BI__builtin_ia32_vbroadcastf128_pd256:
case X86::BI__builtin_ia32_vbroadcastf128_ps256: {
  llvm::Type *DstTy = ConvertType(E->getType());
  return EmitX86SubVectorBroadcast(*this, Ops, DstTy, 128, 1);
}

case X86::BI__builtin_ia32_storehps:
case X86::BI__builtin_ia32_storelps: {
  llvm::Type *PtrTy = llvm::PointerType::getUnqual(Int64Ty);
  llvm::Type *VecTy = llvm::VectorType::get(Int64Ty, 2);

  // cast val v2i64
  Ops[1] = Builder.CreateBitCast(Ops[1], VecTy, "cast");

  // extract (0, 1)
  unsigned Index = BuiltinID == X86::BI__builtin_ia32_storelps ? 0 : 1;
  llvm::Value *Idx = llvm::ConstantInt::get(SizeTy, Index);
  Ops[1] = Builder.CreateExtractElement(Ops[1], Idx, "extract");

  // cast pointer to i64 & store
  Ops[0] = Builder.CreateBitCast(Ops[0], PtrTy);
  return Builder.CreateDefaultAlignedStore(Ops[1], Ops[0]);
}
case X86::BI__builtin_ia32_palignr128:
case X86::BI__builtin_ia32_palignr256:
case X86::BI__builtin_ia32_palignr512_mask: {
  unsigned ShiftVal = cast<llvm::ConstantInt>(Ops[2])->getZExtValue();

  unsigned NumElts = Ops[0]->getType()->getVectorNumElements();
  assert(NumElts % 16 == 0)(static_cast <bool> (NumElts % 16 == 0) ? void (0) : __assert_fail
 ("NumElts % 16 == 0", "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 8561, __extension__ __PRETTY_FUNCTION__));

  // If palignr is shifting the pair of vectors more than the size of two
  // lanes, emit zero.
  if (ShiftVal >= 32)
    return llvm::Constant::getNullValue(ConvertType(E->getType()));

  // If palignr is shifting the pair of input vectors more than one lane,
  // but less than two lanes, convert to shifting in zeroes.
  if (ShiftVal > 16) {
    ShiftVal -= 16;
    Ops[1] = Ops[0];
    Ops[0] = llvm::Constant::getNullValue(Ops[0]->getType());
  }

  uint32_t Indices[64];
  // 256-bit palignr operates on 128-bit lanes so we need to handle that
  for (unsigned l = 0; l != NumElts; l += 16) {
    for (unsigned i = 0; i != 16; ++i) {
      unsigned Idx = ShiftVal + i;
      if (Idx >= 16)
        Idx += NumElts - 16; // End of lane, switch operand.
      Indices[l + i] = Idx + l;
    }
  }

  Value *Align = Builder.CreateShuffleVector(Ops[1], Ops[0],
                                             makeArrayRef(Indices, NumElts),
                                             "palignr");

  // If this isn't a masked builtin, just return the align operation.
  if (Ops.size() == 3)
    return Align;

  return EmitX86Select(*this, Ops[4], Align, Ops[3]);
}

case X86::BI__builtin_ia32_vperm2f128_pd256:
case X86::BI__builtin_ia32_vperm2f128_ps256:
case X86::BI__builtin_ia32_vperm2f128_si256:
case X86::BI__builtin_ia32_permti256: {
  unsigned Imm = cast<llvm::ConstantInt>(Ops[2])->getZExtValue();
  unsigned NumElts = Ops[0]->getType()->getVectorNumElements();

  // This takes a very simple approach since there are two lanes and a
  // shuffle can have 2 inputs. So we reserve the first input for the first
  // lane and the second input for the second lane. This may result in
  // duplicate sources, but this can be dealt with in the backend.

  Value *OutOps[2];
  uint32_t Indices[8];
  for (unsigned l = 0; l != 2; ++l) {
    // Determine the source for this lane.
    if (Imm & (1 << ((l * 4) + 3)))
      OutOps[l] = llvm::ConstantAggregateZero::get(Ops[0]->getType());
    else if (Imm & (1 << ((l * 4) + 1)))
      OutOps[l] = Ops[1];
    else
      OutOps[l] = Ops[0];

    for (unsigned i = 0; i != NumElts/2; ++i) {
      // Start with ith element of the source for this lane.
      unsigned Idx = (l * NumElts) + i;
      // If bit 0 of the immediate half is set, switch to the high half of
      // the source.
      if (Imm & (1 << (l * 4)))
        Idx += NumElts/2;
      Indices[(l * (NumElts/2)) + i] = Idx;
    }
  }

  return Builder.CreateShuffleVector(OutOps[0], OutOps[1],
                                     makeArrayRef(Indices, NumElts),
                                     "vperm");
}

case X86::BI__builtin_ia32_movnti:
case X86::BI__builtin_ia32_movnti64:
case X86::BI__builtin_ia32_movntsd:
case X86::BI__builtin_ia32_movntss: {
  llvm::MDNode *Node = llvm::MDNode::get(
      getLLVMContext(), llvm::ConstantAsMetadata::get(Builder.getInt32(1)));

  Value *Ptr = Ops[0];
  Value *Src = Ops[1];

  // Extract the 0'th element of the source vector.
  if (BuiltinID == X86::BI__builtin_ia32_movntsd ||
      BuiltinID == X86::BI__builtin_ia32_movntss)
    Src = Builder.CreateExtractElement(Src, (uint64_t)0, "extract");

  // Convert the type of the pointer to a pointer to the stored type.
  Value *BC = Builder.CreateBitCast(
      Ptr, llvm::PointerType::getUnqual(Src->getType()), "cast");

  // Unaligned nontemporal store of the scalar value.
  StoreInst *SI = Builder.CreateDefaultAlignedStore(Src, BC);
  SI->setMetadata(CGM.getModule().getMDKindID("nontemporal"), Node);
  SI->setAlignment(1);
  return SI;
}

case X86::BI__builtin_ia32_selectb_128:
case X86::BI__builtin_ia32_selectb_256:
case X86::BI__builtin_ia32_selectb_512:
case X86::BI__builtin_ia32_selectw_128:
case X86::BI__builtin_ia32_selectw_256:
case X86::BI__builtin_ia32_selectw_512:
case X86::BI__builtin_ia32_selectd_128:
case X86::BI__builtin_ia32_selectd_256:
case X86::BI__builtin_ia32_selectd_512:
case X86::BI__builtin_ia32_selectq_128:
case X86::BI__builtin_ia32_selectq_256:
case X86::BI__builtin_ia32_selectq_512:
case X86::BI__builtin_ia32_selectps_128:
case X86::BI__builtin_ia32_selectps_256:
case X86::BI__builtin_ia32_selectps_512:
case X86::BI__builtin_ia32_selectpd_128:
case X86::BI__builtin_ia32_selectpd_256:
case X86::BI__builtin_ia32_selectpd_512:
  return EmitX86Select(*this, Ops[0], Ops[1], Ops[2]);
case X86::BI__builtin_ia32_cmpb128_mask:
case X86::BI__builtin_ia32_cmpb256_mask:
case X86::BI__builtin_ia32_cmpb512_mask:
case X86::BI__builtin_ia32_cmpw128_mask:
case X86::BI__builtin_ia32_cmpw256_mask:
case X86::BI__builtin_ia32_cmpw512_mask:
case X86::BI__builtin_ia32_cmpd128_mask:
case X86::BI__builtin_ia32_cmpd256_mask:
case X86::BI__builtin_ia32_cmpd512_mask:
case X86::BI__builtin_ia32_cmpq128_mask:
case X86::BI__builtin_ia32_cmpq256_mask:
case X86::BI__builtin_ia32_cmpq512_mask: {
  unsigned CC = cast<llvm::ConstantInt>(Ops[2])->getZExtValue() & 0x7;
  return EmitX86MaskedCompare(*this, CC, true, Ops);
}
case X86::BI__builtin_ia32_ucmpb128_mask:
case X86::BI__builtin_ia32_ucmpb256_mask:
case X86::BI__builtin_ia32_ucmpb512_mask:
case X86::BI__builtin_ia32_ucmpw128_mask:
case X86::BI__builtin_ia32_ucmpw256_mask:
case X86::BI__builtin_ia32_ucmpw512_mask:
case X86::BI__builtin_ia32_ucmpd128_mask:
case X86::BI__builtin_ia32_ucmpd256_mask:
case X86::BI__builtin_ia32_ucmpd512_mask:
case X86::BI__builtin_ia32_ucmpq128_mask:
case X86::BI__builtin_ia32_ucmpq256_mask:
case X86::BI__builtin_ia32_ucmpq512_mask: {
  unsigned CC = cast<llvm::ConstantInt>(Ops[2])->getZExtValue() & 0x7;
  return EmitX86MaskedCompare(*this, CC, false, Ops);
}

case X86::BI__builtin_ia32_kortestchi:
case X86::BI__builtin_ia32_kortestzhi: {
  Value *Or = EmitX86MaskLogic(*this, Instruction::Or, 16, Ops);
  Value *C;
  if (BuiltinID == X86::BI__builtin_ia32_kortestchi)
    C = llvm::Constant::getAllOnesValue(Builder.getInt16Ty());
  else
    C = llvm::Constant::getNullValue(Builder.getInt16Ty());
  Value *Cmp = Builder.CreateICmpEQ(Or, C);
  return Builder.CreateZExt(Cmp, ConvertType(E->getType()));
}

case X86::BI__builtin_ia32_kandhi:
  return EmitX86MaskLogic(*this, Instruction::And, 16, Ops);
case X86::BI__builtin_ia32_kandnhi:
  return EmitX86MaskLogic(*this, Instruction::And, 16, Ops, true);
case X86::BI__builtin_ia32_korhi:
  return EmitX86MaskLogic(*this, Instruction::Or, 16, Ops);
case X86::BI__builtin_ia32_kxnorhi:
  return EmitX86MaskLogic(*this, Instruction::Xor, 16, Ops, true);
case X86::BI__builtin_ia32_kxorhi:
  return EmitX86MaskLogic(*this, Instruction::Xor, 16, Ops);
case X86::BI__builtin_ia32_knothi: {
  Ops[0] = getMaskVecValue(*this, Ops[0], 16);
  return Builder.CreateBitCast(Builder.CreateNot(Ops[0]),
                               Builder.getInt16Ty());
}

case X86::BI__builtin_ia32_kunpckdi:
case X86::BI__builtin_ia32_kunpcksi:
case X86::BI__builtin_ia32_kunpckhi: {
  unsigned NumElts = Ops[0]->getType()->getScalarSizeInBits();
  Value *LHS = getMaskVecValue(*this, Ops[0], NumElts);
  Value *RHS = getMaskVecValue(*this, Ops[1], NumElts);
  uint32_t Indices[64];
  for (unsigned i = 0; i != NumElts; ++i)
    Indices[i] = i;

  // First extract half of each vector. This gives better codegen than
  // doing it in a single shuffle.
  LHS = Builder.CreateShuffleVector(LHS, LHS,
                                    makeArrayRef(Indices, NumElts / 2));
  RHS = Builder.CreateShuffleVector(RHS, RHS,
                                    makeArrayRef(Indices, NumElts / 2));
  // Concat the vectors.
  Value *Res = Builder.CreateShuffleVector(LHS, RHS,
                                           makeArrayRef(Indices, NumElts));
  return Builder.CreateBitCast(Res, Ops[0]->getType());
}

case X86::BI__builtin_ia32_vplzcntd_128_mask:
case X86::BI__builtin_ia32_vplzcntd_256_mask:
case X86::BI__builtin_ia32_vplzcntd_512_mask:
case X86::BI__builtin_ia32_vplzcntq_128_mask:
case X86::BI__builtin_ia32_vplzcntq_256_mask:
case X86::BI__builtin_ia32_vplzcntq_512_mask: {
  Function *F = CGM.getIntrinsic(Intrinsic::ctlz, Ops[0]->getType());
  return EmitX86Select(*this, Ops[2],
                       Builder.CreateCall(F, {Ops[0],Builder.getInt1(false)}),
                       Ops[1]);
}

case X86::BI__builtin_ia32_pabsb128:
case X86::BI__builtin_ia32_pabsw128:
case X86::BI__builtin_ia32_pabsd128:
case X86::BI__builtin_ia32_pabsb256:
case X86::BI__builtin_ia32_pabsw256:
case X86::BI__builtin_ia32_pabsd256:
case X86::BI__builtin_ia32_pabsq128_mask:
case X86::BI__builtin_ia32_pabsq256_mask:
case X86::BI__builtin_ia32_pabsb512_mask:
case X86::BI__builtin_ia32_pabsw512_mask:
case X86::BI__builtin_ia32_pabsd512_mask:
case X86::BI__builtin_ia32_pabsq512_mask:
  return EmitX86Abs(*this, Ops);

case X86::BI__builtin_ia32_pmaxsb128:
case X86::BI__builtin_ia32_pmaxsw128:
case X86::BI__builtin_ia32_pmaxsd128:
case X86::BI__builtin_ia32_pmaxsq128_mask:
case X86::BI__builtin_ia32_pmaxsb256:
case X86::BI__builtin_ia32_pmaxsw256:
case X86::BI__builtin_ia32_pmaxsd256:
case X86::BI__builtin_ia32_pmaxsq256_mask:
case X86::BI__builtin_ia32_pmaxsb512_mask:
case X86::BI__builtin_ia32_pmaxsw512_mask:
case X86::BI__builtin_ia32_pmaxsd512_mask:
case X86::BI__builtin_ia32_pmaxsq512_mask:
  return EmitX86MinMax(*this, ICmpInst::ICMP_SGT, Ops);
case X86::BI__builtin_ia32_pmaxub128:
case X86::BI__builtin_ia32_pmaxuw128:
case X86::BI__builtin_ia32_pmaxud128:
case X86::BI__builtin_ia32_pmaxuq128_mask:
case X86::BI__builtin_ia32_pmaxub256:
case X86::BI__builtin_ia32_pmaxuw256:
case X86::BI__builtin_ia32_pmaxud256:
case X86::BI__builtin_ia32_pmaxuq256_mask:
case X86::BI__builtin_ia32_pmaxub512_mask:
case X86::BI__builtin_ia32_pmaxuw512_mask:
case X86::BI__builtin_ia32_pmaxud512_mask:
case X86::BI__builtin_ia32_pmaxuq512_mask:
  return EmitX86MinMax(*this, ICmpInst::ICMP_UGT, Ops);
case X86::BI__builtin_ia32_pminsb128:
case X86::BI__builtin_ia32_pminsw128:
case X86::BI__builtin_ia32_pminsd128:
case X86::BI__builtin_ia32_pminsq128_mask:
case X86::BI__builtin_ia32_pminsb256:
case X86::BI__builtin_ia32_pminsw256:
case X86::BI__builtin_ia32_pminsd256:
case X86::BI__builtin_ia32_pminsq256_mask:
case X86::BI__builtin_ia32_pminsb512_mask:
case X86::BI__builtin_ia32_pminsw512_mask:
case X86::BI__builtin_ia32_pminsd512_mask:
case X86::BI__builtin_ia32_pminsq512_mask:
  return EmitX86MinMax(*this, ICmpInst::ICMP_SLT, Ops);
case X86::BI__builtin_ia32_pminub128:
case X86::BI__builtin_ia32_pminuw128:
case X86::BI__builtin_ia32_pminud128:
case X86::BI__builtin_ia32_pminuq128_mask:
case X86::BI__builtin_ia32_pminub256:
case X86::BI__builtin_ia32_pminuw256:
case X86::BI__builtin_ia32_pminud256:
case X86::BI__builtin_ia32_pminuq256_mask:
case X86::BI__builtin_ia32_pminub512_mask:
case X86::BI__builtin_ia32_pminuw512_mask:
case X86::BI__builtin_ia32_pminud512_mask:
case X86::BI__builtin_ia32_pminuq512_mask:
  return EmitX86MinMax(*this, ICmpInst::ICMP_ULT, Ops);

// 3DNow!
case X86::BI__builtin_ia32_pswapdsf:
case X86::BI__builtin_ia32_pswapdsi: {
  llvm::Type *MMXTy = llvm::Type::getX86_MMXTy(getLLVMContext());
  Ops[0] = Builder.CreateBitCast(Ops[0], MMXTy, "cast");
  llvm::Function *F = CGM.getIntrinsic(Intrinsic::x86_3dnowa_pswapd);
  return Builder.CreateCall(F, Ops, "pswapd");
}
case X86::BI__builtin_ia32_rdrand16_step:
case X86::BI__builtin_ia32_rdrand32_step:
case X86::BI__builtin_ia32_rdrand64_step:
case X86::BI__builtin_ia32_rdseed16_step:
case X86::BI__builtin_ia32_rdseed32_step:
case X86::BI__builtin_ia32_rdseed64_step: {
  Intrinsic::ID ID;
  switch (BuiltinID) {
  default: llvm_unreachable("Unsupported intrinsic!")::llvm::llvm_unreachable_internal("Unsupported intrinsic!", "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 8858);
  case X86::BI__builtin_ia32_rdrand16_step:
    ID = Intrinsic::x86_rdrand_16;
    break;
  case X86::BI__builtin_ia32_rdrand32_step:
    ID = Intrinsic::x86_rdrand_32;
    break;
  case X86::BI__builtin_ia32_rdrand64_step:
    ID = Intrinsic::x86_rdrand_64;
    break;
  case X86::BI__builtin_ia32_rdseed16_step:
    ID = Intrinsic::x86_rdseed_16;
    break;
  case X86::BI__builtin_ia32_rdseed32_step:
    ID = Intrinsic::x86_rdseed_32;
    break;
  case X86::BI__builtin_ia32_rdseed64_step:
    ID = Intrinsic::x86_rdseed_64;
    break;
  }

  Value *Call = Builder.CreateCall(CGM.getIntrinsic(ID));
  Builder.CreateDefaultAlignedStore(Builder.CreateExtractValue(Call, 0),
                                    Ops[0]);
  return Builder.CreateExtractValue(Call, 1);
}

// SSE packed comparison intrinsics
case X86::BI__builtin_ia32_cmpeqps:
case X86::BI__builtin_ia32_cmpeqpd:
  return getVectorFCmpIR(CmpInst::FCMP_OEQ);
case X86::BI__builtin_ia32_cmpltps:
case X86::BI__builtin_ia32_cmpltpd:
  return getVectorFCmpIR(CmpInst::FCMP_OLT);
case X86::BI__builtin_ia32_cmpleps:
case X86::BI__builtin_ia32_cmplepd:
  return getVectorFCmpIR(CmpInst::FCMP_OLE);
case X86::BI__builtin_ia32_cmpunordps:
case X86::BI__builtin_ia32_cmpunordpd:
  return getVectorFCmpIR(CmpInst::FCMP_UNO);
case X86::BI__builtin_ia32_cmpneqps:
case X86::BI__builtin_ia32_cmpneqpd:
  return getVectorFCmpIR(CmpInst::FCMP_UNE);
case X86::BI__builtin_ia32_cmpnltps:
case X86::BI__builtin_ia32_cmpnltpd:
  return getVectorFCmpIR(CmpInst::FCMP_UGE);
case X86::BI__builtin_ia32_cmpnleps:
case X86::BI__builtin_ia32_cmpnlepd:
  return getVectorFCmpIR(CmpInst::FCMP_UGT);
case X86::BI__builtin_ia32_cmpordps:
case X86::BI__builtin_ia32_cmpordpd:
  return getVectorFCmpIR(CmpInst::FCMP_ORD);
case X86::BI__builtin_ia32_cmpps:
case X86::BI__builtin_ia32_cmpps256:
case X86::BI__builtin_ia32_cmppd:
case X86::BI__builtin_ia32_cmppd256: {
  unsigned CC = cast<llvm::ConstantInt>(Ops[2])->getZExtValue();
  // If this one of the SSE immediates, we can use native IR.
  if (CC < 8) {
    FCmpInst::Predicate Pred;
    switch (CC) {
    case 0: Pred = FCmpInst::FCMP_OEQ; break;
    case 1: Pred = FCmpInst::FCMP_OLT; break;
    case 2: Pred = FCmpInst::FCMP_OLE; break;
    case 3: Pred = FCmpInst::FCMP_UNO; break;
    case 4: Pred = FCmpInst::FCMP_UNE; break;
    case 5: Pred = FCmpInst::FCMP_UGE; break;
    case 6: Pred = FCmpInst::FCMP_UGT; break;
    case 7: Pred = FCmpInst::FCMP_ORD; break;
    }
    return getVectorFCmpIR(Pred);
  }

  // We can't handle 8-31 immediates with native IR, use the intrinsic.
  // Except for predicates that create constants.
  Intrinsic::ID ID;
  switch (BuiltinID) {
  default: llvm_unreachable("Unsupported intrinsic!")::llvm::llvm_unreachable_internal("Unsupported intrinsic!", "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 8935);
  case X86::BI__builtin_ia32_cmpps:
    ID = Intrinsic::x86_sse_cmp_ps;
    break;
  case X86::BI__builtin_ia32_cmpps256:
    // _CMP_TRUE_UQ, _CMP_TRUE_US produce -1,-1... vector
    // on any input and _CMP_FALSE_OQ, _CMP_FALSE_OS produce 0, 0...
    if (CC == 0xf || CC == 0xb || CC == 0x1b || CC == 0x1f) {
       Value *Constant = (CC == 0xf || CC == 0x1f) ?
              llvm::Constant::getAllOnesValue(Builder.getInt32Ty()) :
              llvm::Constant::getNullValue(Builder.getInt32Ty());
       Value *Vec = Builder.CreateVectorSplat(
                      Ops[0]->getType()->getVectorNumElements(), Constant);
       return Builder.CreateBitCast(Vec, Ops[0]->getType());
    }
    ID = Intrinsic::x86_avx_cmp_ps_256;
    break;
  case X86::BI__builtin_ia32_cmppd:
    ID = Intrinsic::x86_sse2_cmp_pd;
    break;
  case X86::BI__builtin_ia32_cmppd256:
    // _CMP_TRUE_UQ, _CMP_TRUE_US produce -1,-1... vector
    // on any input and _CMP_FALSE_OQ, _CMP_FALSE_OS produce 0, 0...
    if (CC == 0xf || CC == 0xb || CC == 0x1b || CC == 0x1f) {
       Value *Constant = (CC == 0xf || CC == 0x1f) ?
              llvm::Constant::getAllOnesValue(Builder.getInt64Ty()) :
              llvm::Constant::getNullValue(Builder.getInt64Ty());
       Value *Vec = Builder.CreateVectorSplat(
                      Ops[0]->getType()->getVectorNumElements(), Constant);
       return Builder.CreateBitCast(Vec, Ops[0]->getType());
    }
    ID = Intrinsic::x86_avx_cmp_pd_256;
    break;
  }

  return Builder.CreateCall(CGM.getIntrinsic(ID), Ops);
}

// SSE scalar comparison intrinsics
case X86::BI__builtin_ia32_cmpeqss:
  return getCmpIntrinsicCall(Intrinsic::x86_sse_cmp_ss, 0);
case X86::BI__builtin_ia32_cmpltss:
  return getCmpIntrinsicCall(Intrinsic::x86_sse_cmp_ss, 1);
case X86::BI__builtin_ia32_cmpless:
  return getCmpIntrinsicCall(Intrinsic::x86_sse_cmp_ss, 2);
case X86::BI__builtin_ia32_cmpunordss:
  return getCmpIntrinsicCall(Intrinsic::x86_sse_cmp_ss, 3);
case X86::BI__builtin_ia32_cmpneqss:
  return getCmpIntrinsicCall(Intrinsic::x86_sse_cmp_ss, 4);
case X86::BI__builtin_ia32_cmpnltss:
  return getCmpIntrinsicCall(Intrinsic::x86_sse_cmp_ss, 5);
case X86::BI__builtin_ia32_cmpnless:
  return getCmpIntrinsicCall(Intrinsic::x86_sse_cmp_ss, 6);
case X86::BI__builtin_ia32_cmpordss:
  return getCmpIntrinsicCall(Intrinsic::x86_sse_cmp_ss, 7);
case X86::BI__builtin_ia32_cmpeqsd:
  return getCmpIntrinsicCall(Intrinsic::x86_sse2_cmp_sd, 0);
case X86::BI__builtin_ia32_cmpltsd:
  return getCmpIntrinsicCall(Intrinsic::x86_sse2_cmp_sd, 1);
case X86::BI__builtin_ia32_cmplesd:
  return getCmpIntrinsicCall(Intrinsic::x86_sse2_cmp_sd, 2);
case X86::BI__builtin_ia32_cmpunordsd:
  return getCmpIntrinsicCall(Intrinsic::x86_sse2_cmp_sd, 3);
case X86::BI__builtin_ia32_cmpneqsd:
  return getCmpIntrinsicCall(Intrinsic::x86_sse2_cmp_sd, 4);
case X86::BI__builtin_ia32_cmpnltsd:
  return getCmpIntrinsicCall(Intrinsic::x86_sse2_cmp_sd, 5);
case X86::BI__builtin_ia32_cmpnlesd:
  return getCmpIntrinsicCall(Intrinsic::x86_sse2_cmp_sd, 6);
case X86::BI__builtin_ia32_cmpordsd:
  return getCmpIntrinsicCall(Intrinsic::x86_sse2_cmp_sd, 7);

case X86::BI__emul:
case X86::BI__emulu: {
  llvm::Type *Int64Ty = llvm::IntegerType::get(getLLVMContext(), 64);
  bool isSigned = (BuiltinID == X86::BI__emul);
  Value *LHS = Builder.CreateIntCast(Ops[0], Int64Ty, isSigned);
  Value *RHS = Builder.CreateIntCast(Ops[1], Int64Ty, isSigned);
  return Builder.CreateMul(LHS, RHS, "", !isSigned, isSigned);
}
case X86::BI__mulh:
case X86::BI__umulh:
case X86::BI_mul128:
case X86::BI_umul128: {
  llvm::Type *ResType = ConvertType(E->getType());
  llvm::Type *Int128Ty = llvm::IntegerType::get(getLLVMContext(), 128);

  bool IsSigned = (BuiltinID == X86::BI__mulh || BuiltinID == X86::BI_mul128);
  Value *LHS = Builder.CreateIntCast(Ops[0], Int128Ty, IsSigned);
  Value *RHS = Builder.CreateIntCast(Ops[1], Int128Ty, IsSigned);

  Value *MulResult, *HigherBits;
  if (IsSigned) {
    MulResult = Builder.CreateNSWMul(LHS, RHS);
    HigherBits = Builder.CreateAShr(MulResult, 64);
  } else {
    MulResult = Builder.CreateNUWMul(LHS, RHS);
    HigherBits = Builder.CreateLShr(MulResult, 64);
  }
  HigherBits = Builder.CreateIntCast(HigherBits, ResType, IsSigned);

  if (BuiltinID == X86::BI__mulh || BuiltinID == X86::BI__umulh)
    return HigherBits;

  Address HighBitsAddress = EmitPointerWithAlignment(E->getArg(2));
  Builder.CreateStore(HigherBits, HighBitsAddress);
  return Builder.CreateIntCast(MulResult, ResType, IsSigned);
}

case X86::BI__faststorefence: {
  return Builder.CreateFence(llvm::AtomicOrdering::SequentiallyConsistent,
                             llvm::SyncScope::System);
}
case X86::BI_ReadWriteBarrier:
case X86::BI_ReadBarrier:
case X86::BI_WriteBarrier: {
  return Builder.CreateFence(llvm::AtomicOrdering::SequentiallyConsistent,
                             llvm::SyncScope::SingleThread);
}
case X86::BI_BitScanForward:
case X86::BI_BitScanForward64:
  return EmitMSVCBuiltinExpr(MSVCIntrin::_BitScanForward, E);
case X86::BI_BitScanReverse:
case X86::BI_BitScanReverse64:
  return EmitMSVCBuiltinExpr(MSVCIntrin::_BitScanReverse, E);

case X86::BI_InterlockedAnd64:
  return EmitMSVCBuiltinExpr(MSVCIntrin::_InterlockedAnd, E);
case X86::BI_InterlockedExchange64:
  return EmitMSVCBuiltinExpr(MSVCIntrin::_InterlockedExchange, E);
case X86::BI_InterlockedExchangeAdd64:
  return EmitMSVCBuiltinExpr(MSVCIntrin::_InterlockedExchangeAdd, E);
case X86::BI_InterlockedExchangeSub64:
  return EmitMSVCBuiltinExpr(MSVCIntrin::_InterlockedExchangeSub, E);
case X86::BI_InterlockedOr64:
  return EmitMSVCBuiltinExpr(MSVCIntrin::_InterlockedOr, E);
case X86::BI_InterlockedXor64:
  return EmitMSVCBuiltinExpr(MSVCIntrin::_InterlockedXor, E);
case X86::BI_InterlockedDecrement64:
  return EmitMSVCBuiltinExpr(MSVCIntrin::_InterlockedDecrement, E);
case X86::BI_InterlockedIncrement64:
  return EmitMSVCBuiltinExpr(MSVCIntrin::_InterlockedIncrement, E);
case X86::BI_InterlockedCompareExchange128: {
  // InterlockedCompareExchange128 doesn't directly refer to 128bit ints,
  // instead it takes pointers to 64bit ints for Destination and
  // ComparandResult, and exchange is taken as two 64bit ints (high & low).
  // The previous value is written to ComparandResult, and success is
  // returned.

  llvm::Type *Int128Ty = Builder.getInt128Ty();
  llvm::Type *Int128PtrTy = Int128Ty->getPointerTo();

  Value *Destination =
      Builder.CreateBitCast(EmitScalarExpr(E->getArg(0)), Int128PtrTy);
  Value *ExchangeHigh128 =
      Builder.CreateZExt(EmitScalarExpr(E->getArg(1)), Int128Ty);
  Value *ExchangeLow128 =
      Builder.CreateZExt(EmitScalarExpr(E->getArg(2)), Int128Ty);
  Address ComparandResult(
      Builder.CreateBitCast(EmitScalarExpr(E->getArg(3)), Int128PtrTy),
      getContext().toCharUnitsFromBits(128));

  Value *Exchange = Builder.CreateOr(
      Builder.CreateShl(ExchangeHigh128, 64, "", false, false),
      ExchangeLow128);

  Value *Comparand = Builder.CreateLoad(ComparandResult);

  AtomicCmpXchgInst *CXI =
      Builder.CreateAtomicCmpXchg(Destination, Comparand, Exchange,
                                  AtomicOrdering::SequentiallyConsistent,
                                  AtomicOrdering::SequentiallyConsistent);
  CXI->setVolatile(true);

  // Write the result back to the inout pointer.
  Builder.CreateStore(Builder.CreateExtractValue(CXI, 0), ComparandResult);

  // Get the success boolean and zero extend it to i8.
  Value *Success = Builder.CreateExtractValue(CXI, 1);
  return Builder.CreateZExt(Success, ConvertType(E->getType()));
}

case X86::BI_AddressOfReturnAddress: {
  Value *F = CGM.getIntrinsic(Intrinsic::addressofreturnaddress);
  return Builder.CreateCall(F);
}
case X86::BI__stosb: {
  // We treat __stosb as a volatile memset - it may not generate "rep stosb"
  // instruction, but it will create a memset that won't be optimized away.
  return Builder.CreateMemSet(Ops[0], Ops[1], Ops[2], 1, true);
}
case X86::BI__ud2:
  // llvm.trap makes a ud2a instruction on x86.
  return EmitTrapCall(Intrinsic::trap);
case X86::BI__int2c: {
  // This syscall signals a driver assertion failure in x86 NT kernels.
  llvm::FunctionType *FTy = llvm::FunctionType::get(VoidTy, false);
  llvm::InlineAsm *IA =
      llvm::InlineAsm::get(FTy, "int $$0x2c", "", /*SideEffects=*/true);
  llvm::AttributeList NoReturnAttr = llvm::AttributeList::get(
      getLLVMContext(), llvm::AttributeList::FunctionIndex,
      llvm::Attribute::NoReturn);
  CallSite CS = Builder.CreateCall(IA);
  CS.setAttributes(NoReturnAttr);
  return CS.getInstruction();
}
case X86::BI__readfsbyte:
case X86::BI__readfsword:
case X86::BI__readfsdword:
case X86::BI__readfsqword: {
  llvm::Type *IntTy = ConvertType(E->getType());
  Value *Ptr = Builder.CreateIntToPtr(EmitScalarExpr(E->getArg(0)),
                                      llvm::PointerType::get(IntTy, 257));
  LoadInst *Load = Builder.CreateAlignedLoad(
      IntTy, Ptr, getContext().getTypeAlignInChars(E->getType()));
  Load->setVolatile(true);
  return Load;
}
case X86::BI__readgsbyte:
case X86::BI__readgsword:
case X86::BI__readgsdword:
case X86::BI__readgsqword: {
  llvm::Type *IntTy = ConvertType(E->getType());
  Value *Ptr = Builder.CreateIntToPtr(EmitScalarExpr(E->getArg(0)),
                                      llvm::PointerType::get(IntTy, 256));
  LoadInst *Load = Builder.CreateAlignedLoad(
      IntTy, Ptr, getContext().getTypeAlignInChars(E->getType()));
  Load->setVolatile(true);
  return Load;
}
}
9166}


9169Value *CodeGenFunction::EmitPPCBuiltinExpr(unsigned BuiltinID,
                                         const CallExpr *E) {
SmallVector<Value*, 4> Ops;

for (unsigned i = 0, e = E->getNumArgs(); i != e; i++)
  Ops.push_back(EmitScalarExpr(E->getArg(i)));

Intrinsic::ID ID = Intrinsic::not_intrinsic;

switch (BuiltinID) {
default: return nullptr;

// __builtin_ppc_get_timebase is GCC 4.8+'s PowerPC-specific name for what we
// call __builtin_readcyclecounter.
case PPC::BI__builtin_ppc_get_timebase:
  return Builder.CreateCall(CGM.getIntrinsic(Intrinsic::readcyclecounter));

// vec_ld, vec_xl_be, vec_lvsl, vec_lvsr
case PPC::BI__builtin_altivec_lvx:
case PPC::BI__builtin_altivec_lvxl:
case PPC::BI__builtin_altivec_lvebx:
case PPC::BI__builtin_altivec_lvehx:
case PPC::BI__builtin_altivec_lvewx:
case PPC::BI__builtin_altivec_lvsl:
case PPC::BI__builtin_altivec_lvsr:
case PPC::BI__builtin_vsx_lxvd2x:
case PPC::BI__builtin_vsx_lxvw4x:
case PPC::BI__builtin_vsx_lxvd2x_be:
case PPC::BI__builtin_vsx_lxvw4x_be:
case PPC::BI__builtin_vsx_lxvl:
case PPC::BI__builtin_vsx_lxvll:
{
  if(BuiltinID == PPC::BI__builtin_vsx_lxvl ||
     BuiltinID == PPC::BI__builtin_vsx_lxvll){
    Ops[0] = Builder.CreateBitCast(Ops[0], Int8PtrTy);
  }else {
    Ops[1] = Builder.CreateBitCast(Ops[1], Int8PtrTy);
    Ops[0] = Builder.CreateGEP(Ops[1], Ops[0]);
    Ops.pop_back();
  }

  switch (BuiltinID) {
  default: llvm_unreachable("Unsupported ld/lvsl/lvsr intrinsic!")::llvm::llvm_unreachable_internal("Unsupported ld/lvsl/lvsr intrinsic!"
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 9211);
  case PPC::BI__builtin_altivec_lvx:
    ID = Intrinsic::ppc_altivec_lvx;
    break;
  case PPC::BI__builtin_altivec_lvxl:
    ID = Intrinsic::ppc_altivec_lvxl;
    break;
  case PPC::BI__builtin_altivec_lvebx:
    ID = Intrinsic::ppc_altivec_lvebx;
    break;
  case PPC::BI__builtin_altivec_lvehx:
    ID = Intrinsic::ppc_altivec_lvehx;
    break;
  case PPC::BI__builtin_altivec_lvewx:
    ID = Intrinsic::ppc_altivec_lvewx;
    break;
  case PPC::BI__builtin_altivec_lvsl:
    ID = Intrinsic::ppc_altivec_lvsl;
    break;
  case PPC::BI__builtin_altivec_lvsr:
    ID = Intrinsic::ppc_altivec_lvsr;
    break;
  case PPC::BI__builtin_vsx_lxvd2x:
    ID = Intrinsic::ppc_vsx_lxvd2x;
    break;
  case PPC::BI__builtin_vsx_lxvw4x:
    ID = Intrinsic::ppc_vsx_lxvw4x;
    break;
  case PPC::BI__builtin_vsx_lxvd2x_be:
    ID = Intrinsic::ppc_vsx_lxvd2x_be;
    break;
  case PPC::BI__builtin_vsx_lxvw4x_be:
    ID = Intrinsic::ppc_vsx_lxvw4x_be;
    break;
  case PPC::BI__builtin_vsx_lxvl:
    ID = Intrinsic::ppc_vsx_lxvl;
    break;
  case PPC::BI__builtin_vsx_lxvll:
    ID = Intrinsic::ppc_vsx_lxvll;
    break;
  }
  llvm::Function *F = CGM.getIntrinsic(ID);
  return Builder.CreateCall(F, Ops, "");
}

// vec_st, vec_xst_be
case PPC::BI__builtin_altivec_stvx:
case PPC::BI__builtin_altivec_stvxl:
case PPC::BI__builtin_altivec_stvebx:
case PPC::BI__builtin_altivec_stvehx:
case PPC::BI__builtin_altivec_stvewx:
case PPC::BI__builtin_vsx_stxvd2x:
case PPC::BI__builtin_vsx_stxvw4x:
case PPC::BI__builtin_vsx_stxvd2x_be:
case PPC::BI__builtin_vsx_stxvw4x_be:
case PPC::BI__builtin_vsx_stxvl:
case PPC::BI__builtin_vsx_stxvll:
{
  if(BuiltinID == PPC::BI__builtin_vsx_stxvl ||
    BuiltinID == PPC::BI__builtin_vsx_stxvll ){
    Ops[1] = Builder.CreateBitCast(Ops[1], Int8PtrTy);
  }else {
    Ops[2] = Builder.CreateBitCast(Ops[2], Int8PtrTy);
    Ops[1] = Builder.CreateGEP(Ops[2], Ops[1]);
    Ops.pop_back();
  }

  switch (BuiltinID) {
  default: llvm_unreachable("Unsupported st intrinsic!")::llvm::llvm_unreachable_internal("Unsupported st intrinsic!"
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 9279);
  case PPC::BI__builtin_altivec_stvx:
    ID = Intrinsic::ppc_altivec_stvx;
    break;
  case PPC::BI__builtin_altivec_stvxl:
    ID = Intrinsic::ppc_altivec_stvxl;
    break;
  case PPC::BI__builtin_altivec_stvebx:
    ID = Intrinsic::ppc_altivec_stvebx;
    break;
  case PPC::BI__builtin_altivec_stvehx:
    ID = Intrinsic::ppc_altivec_stvehx;
    break;
  case PPC::BI__builtin_altivec_stvewx:
    ID = Intrinsic::ppc_altivec_stvewx;
    break;
  case PPC::BI__builtin_vsx_stxvd2x:
    ID = Intrinsic::ppc_vsx_stxvd2x;
    break;
  case PPC::BI__builtin_vsx_stxvw4x:
    ID = Intrinsic::ppc_vsx_stxvw4x;
    break;
  case PPC::BI__builtin_vsx_stxvd2x_be:
    ID = Intrinsic::ppc_vsx_stxvd2x_be;
    break;
  case PPC::BI__builtin_vsx_stxvw4x_be:
    ID = Intrinsic::ppc_vsx_stxvw4x_be;
    break;
  case PPC::BI__builtin_vsx_stxvl:
    ID = Intrinsic::ppc_vsx_stxvl;
    break;
  case PPC::BI__builtin_vsx_stxvll:
    ID = Intrinsic::ppc_vsx_stxvll;
    break;
  }
  llvm::Function *F = CGM.getIntrinsic(ID);
  return Builder.CreateCall(F, Ops, "");
}
// Square root
case PPC::BI__builtin_vsx_xvsqrtsp:
case PPC::BI__builtin_vsx_xvsqrtdp: {
  llvm::Type *ResultType = ConvertType(E->getType());
  Value *X = EmitScalarExpr(E->getArg(0));
  ID = Intrinsic::sqrt;
  llvm::Function *F = CGM.getIntrinsic(ID, ResultType);
  return Builder.CreateCall(F, X);
}
// Count leading zeros
case PPC::BI__builtin_altivec_vclzb:
case PPC::BI__builtin_altivec_vclzh:
case PPC::BI__builtin_altivec_vclzw:
case PPC::BI__builtin_altivec_vclzd: {
  llvm::Type *ResultType = ConvertType(E->getType());
  Value *X = EmitScalarExpr(E->getArg(0));
  Value *Undef = ConstantInt::get(Builder.getInt1Ty(), false);
  Function *F = CGM.getIntrinsic(Intrinsic::ctlz, ResultType);
  return Builder.CreateCall(F, {X, Undef});
}
case PPC::BI__builtin_altivec_vctzb:
case PPC::BI__builtin_altivec_vctzh:
case PPC::BI__builtin_altivec_vctzw:
case PPC::BI__builtin_altivec_vctzd: {
  llvm::Type *ResultType = ConvertType(E->getType());
  Value *X = EmitScalarExpr(E->getArg(0));
  Value *Undef = ConstantInt::get(Builder.getInt1Ty(), false);
  Function *F = CGM.getIntrinsic(Intrinsic::cttz, ResultType);
  return Builder.CreateCall(F, {X, Undef});
}
case PPC::BI__builtin_altivec_vpopcntb:
case PPC::BI__builtin_altivec_vpopcnth:
case PPC::BI__builtin_altivec_vpopcntw:
case PPC::BI__builtin_altivec_vpopcntd: {
  llvm::Type *ResultType = ConvertType(E->getType());
  Value *X = EmitScalarExpr(E->getArg(0));
  llvm::Function *F = CGM.getIntrinsic(Intrinsic::ctpop, ResultType);
  return Builder.CreateCall(F, X);
}
// Copy sign
case PPC::BI__builtin_vsx_xvcpsgnsp:
case PPC::BI__builtin_vsx_xvcpsgndp: {
  llvm::Type *ResultType = ConvertType(E->getType());
  Value *X = EmitScalarExpr(E->getArg(0));
  Value *Y = EmitScalarExpr(E->getArg(1));
  ID = Intrinsic::copysign;
  llvm::Function *F = CGM.getIntrinsic(ID, ResultType);
  return Builder.CreateCall(F, {X, Y});
}
// Rounding/truncation
case PPC::BI__builtin_vsx_xvrspip:
case PPC::BI__builtin_vsx_xvrdpip:
case PPC::BI__builtin_vsx_xvrdpim:
case PPC::BI__builtin_vsx_xvrspim:
case PPC::BI__builtin_vsx_xvrdpi:
case PPC::BI__builtin_vsx_xvrspi:
case PPC::BI__builtin_vsx_xvrdpic:
case PPC::BI__builtin_vsx_xvrspic:
case PPC::BI__builtin_vsx_xvrdpiz:
case PPC::BI__builtin_vsx_xvrspiz: {
  llvm::Type *ResultType = ConvertType(E->getType());
  Value *X = EmitScalarExpr(E->getArg(0));
  if (BuiltinID == PPC::BI__builtin_vsx_xvrdpim ||
      BuiltinID == PPC::BI__builtin_vsx_xvrspim)
    ID = Intrinsic::floor;
  else if (BuiltinID == PPC::BI__builtin_vsx_xvrdpi ||
           BuiltinID == PPC::BI__builtin_vsx_xvrspi)
    ID = Intrinsic::round;
  else if (BuiltinID == PPC::BI__builtin_vsx_xvrdpic ||
           BuiltinID == PPC::BI__builtin_vsx_xvrspic)
    ID = Intrinsic::nearbyint;
  else if (BuiltinID == PPC::BI__builtin_vsx_xvrdpip ||
           BuiltinID == PPC::BI__builtin_vsx_xvrspip)
    ID = Intrinsic::ceil;
  else if (BuiltinID == PPC::BI__builtin_vsx_xvrdpiz ||
           BuiltinID == PPC::BI__builtin_vsx_xvrspiz)
    ID = Intrinsic::trunc;
  llvm::Function *F = CGM.getIntrinsic(ID, ResultType);
  return Builder.CreateCall(F, X);
}

// Absolute value
case PPC::BI__builtin_vsx_xvabsdp:
case PPC::BI__builtin_vsx_xvabssp: {
  llvm::Type *ResultType = ConvertType(E->getType());
  Value *X = EmitScalarExpr(E->getArg(0));
  llvm::Function *F = CGM.getIntrinsic(Intrinsic::fabs, ResultType);
  return Builder.CreateCall(F, X);
}

// FMA variations
case PPC::BI__builtin_vsx_xvmaddadp:
case PPC::BI__builtin_vsx_xvmaddasp:
case PPC::BI__builtin_vsx_xvnmaddadp:
case PPC::BI__builtin_vsx_xvnmaddasp:
case PPC::BI__builtin_vsx_xvmsubadp:
case PPC::BI__builtin_vsx_xvmsubasp:
case PPC::BI__builtin_vsx_xvnmsubadp:
case PPC::BI__builtin_vsx_xvnmsubasp: {
  llvm::Type *ResultType = ConvertType(E->getType());
  Value *X = EmitScalarExpr(E->getArg(0));
  Value *Y = EmitScalarExpr(E->getArg(1));
  Value *Z = EmitScalarExpr(E->getArg(2));
  Value *Zero = llvm::ConstantFP::getZeroValueForNegation(ResultType);
  llvm::Function *F = CGM.getIntrinsic(Intrinsic::fma, ResultType);
  switch (BuiltinID) {
    case PPC::BI__builtin_vsx_xvmaddadp:
    case PPC::BI__builtin_vsx_xvmaddasp:
      return Builder.CreateCall(F, {X, Y, Z});
    case PPC::BI__builtin_vsx_xvnmaddadp:
    case PPC::BI__builtin_vsx_xvnmaddasp:
      return Builder.CreateFSub(Zero,
                                Builder.CreateCall(F, {X, Y, Z}), "sub");
    case PPC::BI__builtin_vsx_xvmsubadp:
    case PPC::BI__builtin_vsx_xvmsubasp:
      return Builder.CreateCall(F,
                                {X, Y, Builder.CreateFSub(Zero, Z, "sub")});
    case PPC::BI__builtin_vsx_xvnmsubadp:
    case PPC::BI__builtin_vsx_xvnmsubasp:
      Value *FsubRes =
        Builder.CreateCall(F, {X, Y, Builder.CreateFSub(Zero, Z, "sub")});
      return Builder.CreateFSub(Zero, FsubRes, "sub");
  }
  llvm_unreachable("Unknown FMA operation")::llvm::llvm_unreachable_internal("Unknown FMA operation", "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 9440);
  return nullptr; // Suppress no-return warning
}

case PPC::BI__builtin_vsx_insertword: {
  llvm::Function *F = CGM.getIntrinsic(Intrinsic::ppc_vsx_xxinsertw);

  // Third argument is a compile time constant int. It must be clamped to
  // to the range [0, 12].
  ConstantInt *ArgCI = dyn_cast<ConstantInt>(Ops[2]);
  assert(ArgCI &&(static_cast <bool> (ArgCI && "Third arg to xxinsertw intrinsic must be constant integer"
) ? void (0) : __assert_fail ("ArgCI && \"Third arg to xxinsertw intrinsic must be constant integer\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 9451, __extension__ __PRETTY_FUNCTION__))
         "Third arg to xxinsertw intrinsic must be constant integer")(static_cast <bool> (ArgCI && "Third arg to xxinsertw intrinsic must be constant integer"
) ? void (0) : __assert_fail ("ArgCI && \"Third arg to xxinsertw intrinsic must be constant integer\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 9451, __extension__ __PRETTY_FUNCTION__));
  const int64_t MaxIndex = 12;
  int64_t Index = clamp(ArgCI->getSExtValue(), 0, MaxIndex);

  // The builtin semantics don't exactly match the xxinsertw instructions
  // semantics (which ppc_vsx_xxinsertw follows). The builtin extracts the
  // word from the first argument, and inserts it in the second argument. The
  // instruction extracts the word from its second input register and inserts
  // it into its first input register, so swap the first and second arguments.
  std::swap(Ops[0], Ops[1]);

  // Need to cast the second argument from a vector of unsigned int to a
  // vector of long long.
  Ops[1] = Builder.CreateBitCast(Ops[1], llvm::VectorType::get(Int64Ty, 2));

  if (getTarget().isLittleEndian()) {
    // Create a shuffle mask of (1, 0)
    Constant *ShuffleElts[2] = { ConstantInt::get(Int32Ty, 1),
                                 ConstantInt::get(Int32Ty, 0)
                               };
    Constant *ShuffleMask = llvm::ConstantVector::get(ShuffleElts);

    // Reverse the double words in the vector we will extract from.
    Ops[0] = Builder.CreateBitCast(Ops[0], llvm::VectorType::get(Int64Ty, 2));
    Ops[0] = Builder.CreateShuffleVector(Ops[0], Ops[0], ShuffleMask);

    // Reverse the index.
    Index = MaxIndex - Index;
  }

  // Intrinsic expects the first arg to be a vector of int.
  Ops[0] = Builder.CreateBitCast(Ops[0], llvm::VectorType::get(Int32Ty, 4));
  Ops[2] = ConstantInt::getSigned(Int32Ty, Index);
  return Builder.CreateCall(F, Ops);
}

case PPC::BI__builtin_vsx_extractuword: {
  llvm::Function *F = CGM.getIntrinsic(Intrinsic::ppc_vsx_xxextractuw);

  // Intrinsic expects the first argument to be a vector of doublewords.
  Ops[0] = Builder.CreateBitCast(Ops[0], llvm::VectorType::get(Int64Ty, 2));

  // The second argument is a compile time constant int that needs to
  // be clamped to the range [0, 12].
  ConstantInt *ArgCI = dyn_cast<ConstantInt>(Ops[1]);
  assert(ArgCI &&(static_cast <bool> (ArgCI && "Second Arg to xxextractuw intrinsic must be a constant integer!"
) ? void (0) : __assert_fail ("ArgCI && \"Second Arg to xxextractuw intrinsic must be a constant integer!\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 9497, __extension__ __PRETTY_FUNCTION__))
         "Second Arg to xxextractuw intrinsic must be a constant integer!")(static_cast <bool> (ArgCI && "Second Arg to xxextractuw intrinsic must be a constant integer!"
) ? void (0) : __assert_fail ("ArgCI && \"Second Arg to xxextractuw intrinsic must be a constant integer!\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 9497, __extension__ __PRETTY_FUNCTION__));
  const int64_t MaxIndex = 12;
  int64_t Index = clamp(ArgCI->getSExtValue(), 0, MaxIndex);

  if (getTarget().isLittleEndian()) {
    // Reverse the index.
    Index = MaxIndex - Index;
    Ops[1] = ConstantInt::getSigned(Int32Ty, Index);

    // Emit the call, then reverse the double words of the results vector.
    Value *Call = Builder.CreateCall(F, Ops);

    // Create a shuffle mask of (1, 0)
    Constant *ShuffleElts[2] = { ConstantInt::get(Int32Ty, 1),
                                 ConstantInt::get(Int32Ty, 0)
                               };
    Constant *ShuffleMask = llvm::ConstantVector::get(ShuffleElts);

    Value *ShuffleCall = Builder.CreateShuffleVector(Call, Call, ShuffleMask);
    return ShuffleCall;
  } else {
    Ops[1] = ConstantInt::getSigned(Int32Ty, Index);
    return Builder.CreateCall(F, Ops);
  }
}

case PPC::BI__builtin_vsx_xxpermdi: {
  ConstantInt *ArgCI = dyn_cast<ConstantInt>(Ops[2]);
  assert(ArgCI && "Third arg must be constant integer!")(static_cast <bool> (ArgCI && "Third arg must be constant integer!"
) ? void (0) : __assert_fail ("ArgCI && \"Third arg must be constant integer!\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 9525, __extension__ __PRETTY_FUNCTION__));

  unsigned Index = ArgCI->getZExtValue();
  Ops[0] = Builder.CreateBitCast(Ops[0], llvm::VectorType::get(Int64Ty, 2));
  Ops[1] = Builder.CreateBitCast(Ops[1], llvm::VectorType::get(Int64Ty, 2));

  // Element zero comes from the first input vector and element one comes from
  // the second. The element indices within each vector are numbered in big
  // endian order so the shuffle mask must be adjusted for this on little
  // endian platforms (i.e. index is complemented and source vector reversed).
  unsigned ElemIdx0;
  unsigned ElemIdx1;
  if (getTarget().isLittleEndian()) {
    ElemIdx0 = (~Index & 1) + 2;
    ElemIdx1 = (~Index & 2) >> 1;
  } else { // BigEndian
    ElemIdx0 = (Index & 2) >> 1;
    ElemIdx1 = 2 + (Index & 1);
  }

  Constant *ShuffleElts[2] = {ConstantInt::get(Int32Ty, ElemIdx0),
                              ConstantInt::get(Int32Ty, ElemIdx1)};
  Constant *ShuffleMask = llvm::ConstantVector::get(ShuffleElts);

  Value *ShuffleCall =
      Builder.CreateShuffleVector(Ops[0], Ops[1], ShuffleMask);
  QualType BIRetType = E->getType();
  auto RetTy = ConvertType(BIRetType);
  return Builder.CreateBitCast(ShuffleCall, RetTy);
}

case PPC::BI__builtin_vsx_xxsldwi: {
  ConstantInt *ArgCI = dyn_cast<ConstantInt>(Ops[2]);
  assert(ArgCI && "Third argument must be a compile time constant")(static_cast <bool> (ArgCI && "Third argument must be a compile time constant"
) ? void (0) : __assert_fail ("ArgCI && \"Third argument must be a compile time constant\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 9558, __extension__ __PRETTY_FUNCTION__));
  unsigned Index = ArgCI->getZExtValue() & 0x3;
  Ops[0] = Builder.CreateBitCast(Ops[0], llvm::VectorType::get(Int32Ty, 4));
  Ops[1] = Builder.CreateBitCast(Ops[1], llvm::VectorType::get(Int32Ty, 4));

  // Create a shuffle mask
  unsigned ElemIdx0;
  unsigned ElemIdx1;
  unsigned ElemIdx2;
  unsigned ElemIdx3;
  if (getTarget().isLittleEndian()) {
    // Little endian element N comes from element 8+N-Index of the
    // concatenated wide vector (of course, using modulo arithmetic on
    // the total number of elements).
    ElemIdx0 = (8 - Index) % 8;
    ElemIdx1 = (9 - Index) % 8;
    ElemIdx2 = (10 - Index) % 8;
    ElemIdx3 = (11 - Index) % 8;
  } else {
    // Big endian ElemIdx<N> = Index + N
    ElemIdx0 = Index;
    ElemIdx1 = Index + 1;
    ElemIdx2 = Index + 2;
    ElemIdx3 = Index + 3;
  }

  Constant *ShuffleElts[4] = {ConstantInt::get(Int32Ty, ElemIdx0),
                              ConstantInt::get(Int32Ty, ElemIdx1),
                              ConstantInt::get(Int32Ty, ElemIdx2),
                              ConstantInt::get(Int32Ty, ElemIdx3)};

  Constant *ShuffleMask = llvm::ConstantVector::get(ShuffleElts);
  Value *ShuffleCall =
      Builder.CreateShuffleVector(Ops[0], Ops[1], ShuffleMask);
  QualType BIRetType = E->getType();
  auto RetTy = ConvertType(BIRetType);
  return Builder.CreateBitCast(ShuffleCall, RetTy);
}
}
9597}

9599Value *CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned BuiltinID,
                                            const CallExpr *E) {
switch (BuiltinID) {
case AMDGPU::BI__builtin_amdgcn_div_scale:
case AMDGPU::BI__builtin_amdgcn_div_scalef: {
  // Translate from the intrinsics's struct return to the builtin's out
  // argument.

  Address FlagOutPtr = EmitPointerWithAlignment(E->getArg(3));

  llvm::Value *X = EmitScalarExpr(E->getArg(0));
  llvm::Value *Y = EmitScalarExpr(E->getArg(1));
  llvm::Value *Z = EmitScalarExpr(E->getArg(2));

  llvm::Value *Callee = CGM.getIntrinsic(Intrinsic::amdgcn_div_scale,
                                         X->getType());

  llvm::Value *Tmp = Builder.CreateCall(Callee, {X, Y, Z});

  llvm::Value *Result = Builder.CreateExtractValue(Tmp, 0);
  llvm::Value *Flag = Builder.CreateExtractValue(Tmp, 1);

  llvm::Type *RealFlagType
    = FlagOutPtr.getPointer()->getType()->getPointerElementType();

  llvm::Value *FlagExt = Builder.CreateZExt(Flag, RealFlagType);
  Builder.CreateStore(FlagExt, FlagOutPtr);
  return Result;
}
case AMDGPU::BI__builtin_amdgcn_div_fmas:
case AMDGPU::BI__builtin_amdgcn_div_fmasf: {
  llvm::Value *Src0 = EmitScalarExpr(E->getArg(0));
  llvm::Value *Src1 = EmitScalarExpr(E->getArg(1));
  llvm::Value *Src2 = EmitScalarExpr(E->getArg(2));
  llvm::Value *Src3 = EmitScalarExpr(E->getArg(3));

  llvm::Value *F = CGM.getIntrinsic(Intrinsic::amdgcn_div_fmas,
                                    Src0->getType());
  llvm::Value *Src3ToBool = Builder.CreateIsNotNull(Src3);
  return Builder.CreateCall(F, {Src0, Src1, Src2, Src3ToBool});
}

case AMDGPU::BI__builtin_amdgcn_ds_swizzle:
  return emitBinaryBuiltin(*this, E, Intrinsic::amdgcn_ds_swizzle);
case AMDGPU::BI__builtin_amdgcn_mov_dpp: {
  llvm::SmallVector<llvm::Value *, 5> Args;
  for (unsigned I = 0; I != 5; ++I)
    Args.push_back(EmitScalarExpr(E->getArg(I)));
  Value *F = CGM.getIntrinsic(Intrinsic::amdgcn_mov_dpp,
                                  Args[0]->getType());
  return Builder.CreateCall(F, Args);
}
case AMDGPU::BI__builtin_amdgcn_div_fixup:
case AMDGPU::BI__builtin_amdgcn_div_fixupf:
case AMDGPU::BI__builtin_amdgcn_div_fixuph:
  return emitTernaryBuiltin(*this, E, Intrinsic::amdgcn_div_fixup);
case AMDGPU::BI__builtin_amdgcn_trig_preop:
case AMDGPU::BI__builtin_amdgcn_trig_preopf:
  return emitFPIntBuiltin(*this, E, Intrinsic::amdgcn_trig_preop);
case AMDGPU::BI__builtin_amdgcn_rcp:
case AMDGPU::BI__builtin_amdgcn_rcpf:
case AMDGPU::BI__builtin_amdgcn_rcph:
  return emitUnaryBuiltin(*this, E, Intrinsic::amdgcn_rcp);
case AMDGPU::BI__builtin_amdgcn_rsq:
case AMDGPU::BI__builtin_amdgcn_rsqf:
case AMDGPU::BI__builtin_amdgcn_rsqh:
  return emitUnaryBuiltin(*this, E, Intrinsic::amdgcn_rsq);
case AMDGPU::BI__builtin_amdgcn_rsq_clamp:
case AMDGPU::BI__builtin_amdgcn_rsq_clampf:
  return emitUnaryBuiltin(*this, E, Intrinsic::amdgcn_rsq_clamp);
case AMDGPU::BI__builtin_amdgcn_sinf:
case AMDGPU::BI__builtin_amdgcn_sinh:
  return emitUnaryBuiltin(*this, E, Intrinsic::amdgcn_sin);
case AMDGPU::BI__builtin_amdgcn_cosf:
case AMDGPU::BI__builtin_amdgcn_cosh:
  return emitUnaryBuiltin(*this, E, Intrinsic::amdgcn_cos);
case AMDGPU::BI__builtin_amdgcn_log_clampf:
  return emitUnaryBuiltin(*this, E, Intrinsic::amdgcn_log_clamp);
case AMDGPU::BI__builtin_amdgcn_ldexp:
case AMDGPU::BI__builtin_amdgcn_ldexpf:
case AMDGPU::BI__builtin_amdgcn_ldexph:
  return emitFPIntBuiltin(*this, E, Intrinsic::amdgcn_ldexp);
case AMDGPU::BI__builtin_amdgcn_frexp_mant:
case AMDGPU::BI__builtin_amdgcn_frexp_mantf:
case AMDGPU::BI__builtin_amdgcn_frexp_manth:
  return emitUnaryBuiltin(*this, E, Intrinsic::amdgcn_frexp_mant);
case AMDGPU::BI__builtin_amdgcn_frexp_exp:
case AMDGPU::BI__builtin_amdgcn_frexp_expf: {
  Value *Src0 = EmitScalarExpr(E->getArg(0));
  Value *F = CGM.getIntrinsic(Intrinsic::amdgcn_frexp_exp,
                              { Builder.getInt32Ty(), Src0->getType() });
  return Builder.CreateCall(F, Src0);
}
case AMDGPU::BI__builtin_amdgcn_frexp_exph: {
  Value *Src0 = EmitScalarExpr(E->getArg(0));
  Value *F = CGM.getIntrinsic(Intrinsic::amdgcn_frexp_exp,
                              { Builder.getInt16Ty(), Src0->getType() });
  return Builder.CreateCall(F, Src0);
}
case AMDGPU::BI__builtin_amdgcn_fract:
case AMDGPU::BI__builtin_amdgcn_fractf:
case AMDGPU::BI__builtin_amdgcn_fracth:
  return emitUnaryBuiltin(*this, E, Intrinsic::amdgcn_fract);
case AMDGPU::BI__builtin_amdgcn_lerp:
  return emitTernaryBuiltin(*this, E, Intrinsic::amdgcn_lerp);
case AMDGPU::BI__builtin_amdgcn_uicmp:
case AMDGPU::BI__builtin_amdgcn_uicmpl:
case AMDGPU::BI__builtin_amdgcn_sicmp:
case AMDGPU::BI__builtin_amdgcn_sicmpl:
  return emitTernaryBuiltin(*this, E, Intrinsic::amdgcn_icmp);
case AMDGPU::BI__builtin_amdgcn_fcmp:
case AMDGPU::BI__builtin_amdgcn_fcmpf:
  return emitTernaryBuiltin(*this, E, Intrinsic::amdgcn_fcmp);
case AMDGPU::BI__builtin_amdgcn_class:
case AMDGPU::BI__builtin_amdgcn_classf:
case AMDGPU::BI__builtin_amdgcn_classh:
  return emitFPIntBuiltin(*this, E, Intrinsic::amdgcn_class);
case AMDGPU::BI__builtin_amdgcn_fmed3f:
case AMDGPU::BI__builtin_amdgcn_fmed3h:
  return emitTernaryBuiltin(*this, E, Intrinsic::amdgcn_fmed3);
case AMDGPU::BI__builtin_amdgcn_read_exec: {
  CallInst *CI = cast<CallInst>(
    EmitSpecialRegisterBuiltin(*this, E, Int64Ty, Int64Ty, true, "exec"));
  CI->setConvergent();
  return CI;
}
case AMDGPU::BI__builtin_amdgcn_read_exec_lo:
case AMDGPU::BI__builtin_amdgcn_read_exec_hi: {
  StringRef RegName = BuiltinID == AMDGPU::BI__builtin_amdgcn_read_exec_lo ?
    "exec_lo" : "exec_hi";
  CallInst *CI = cast<CallInst>(
    EmitSpecialRegisterBuiltin(*this, E, Int32Ty, Int32Ty, true, RegName));
  CI->setConvergent();
  return CI;
}

// amdgcn workitem
case AMDGPU::BI__builtin_amdgcn_workitem_id_x:
  return emitRangedBuiltin(*this, Intrinsic::amdgcn_workitem_id_x, 0, 1024);
case AMDGPU::BI__builtin_amdgcn_workitem_id_y:
  return emitRangedBuiltin(*this, Intrinsic::amdgcn_workitem_id_y, 0, 1024);
case AMDGPU::BI__builtin_amdgcn_workitem_id_z:
  return emitRangedBuiltin(*this, Intrinsic::amdgcn_workitem_id_z, 0, 1024);

// r600 intrinsics
case AMDGPU::BI__builtin_r600_recipsqrt_ieee:
case AMDGPU::BI__builtin_r600_recipsqrt_ieeef:
  return emitUnaryBuiltin(*this, E, Intrinsic::r600_recipsqrt_ieee);
case AMDGPU::BI__builtin_r600_read_tidig_x:
  return emitRangedBuiltin(*this, Intrinsic::r600_read_tidig_x, 0, 1024);
case AMDGPU::BI__builtin_r600_read_tidig_y:
  return emitRangedBuiltin(*this, Intrinsic::r600_read_tidig_y, 0, 1024);
case AMDGPU::BI__builtin_r600_read_tidig_z:
  return emitRangedBuiltin(*this, Intrinsic::r600_read_tidig_z, 0, 1024);
default:
  return nullptr;
}
9756}

9758/// Handle a SystemZ function in which the final argument is a pointer
9759/// to an int that receives the post-instruction CC value.  At the LLVM level
9760/// this is represented as a function that returns a {result, cc} pair.
9761static Value *EmitSystemZIntrinsicWithCC(CodeGenFunction &CGF,
                                       unsigned IntrinsicID,
                                       const CallExpr *E) {
unsigned NumArgs = E->getNumArgs() - 1;
SmallVector<Value *, 8> Args(NumArgs);
for (unsigned I = 0; I < NumArgs; ++I)
  Args[I] = CGF.EmitScalarExpr(E->getArg(I));
Address CCPtr = CGF.EmitPointerWithAlignment(E->getArg(NumArgs));
Value *F = CGF.CGM.getIntrinsic(IntrinsicID);
Value *Call = CGF.Builder.CreateCall(F, Args);
Value *CC = CGF.Builder.CreateExtractValue(Call, 1);
CGF.Builder.CreateStore(CC, CCPtr);
return CGF.Builder.CreateExtractValue(Call, 0);
9774}

9776Value *CodeGenFunction::EmitSystemZBuiltinExpr(unsigned BuiltinID,
                                             const CallExpr *E) {
switch (BuiltinID) {
case SystemZ::BI__builtin_tbegin: {
  Value *TDB = EmitScalarExpr(E->getArg(0));
  Value *Control = llvm::ConstantInt::get(Int32Ty, 0xff0c);
  Value *F = CGM.getIntrinsic(Intrinsic::s390_tbegin);
  return Builder.CreateCall(F, {TDB, Control});
}
case SystemZ::BI__builtin_tbegin_nofloat: {
  Value *TDB = EmitScalarExpr(E->getArg(0));
  Value *Control = llvm::ConstantInt::get(Int32Ty, 0xff0c);
  Value *F = CGM.getIntrinsic(Intrinsic::s390_tbegin_nofloat);
  return Builder.CreateCall(F, {TDB, Control});
}
case SystemZ::BI__builtin_tbeginc: {
  Value *TDB = llvm::ConstantPointerNull::get(Int8PtrTy);
  Value *Control = llvm::ConstantInt::get(Int32Ty, 0xff08);
  Value *F = CGM.getIntrinsic(Intrinsic::s390_tbeginc);
  return Builder.CreateCall(F, {TDB, Control});
}
case SystemZ::BI__builtin_tabort: {
  Value *Data = EmitScalarExpr(E->getArg(0));
  Value *F = CGM.getIntrinsic(Intrinsic::s390_tabort);
  return Builder.CreateCall(F, Builder.CreateSExt(Data, Int64Ty, "tabort"));
}
case SystemZ::BI__builtin_non_tx_store: {
  Value *Address = EmitScalarExpr(E->getArg(0));
  Value *Data = EmitScalarExpr(E->getArg(1));
  Value *F = CGM.getIntrinsic(Intrinsic::s390_ntstg);
  return Builder.CreateCall(F, {Data, Address});
}

// Vector builtins.  Note that most vector builtins are mapped automatically
// to target-specific LLVM intrinsics.  The ones handled specially here can
// be represented via standard LLVM IR, which is preferable to enable common
// LLVM optimizations.

case SystemZ::BI__builtin_s390_vpopctb:
case SystemZ::BI__builtin_s390_vpopcth:
case SystemZ::BI__builtin_s390_vpopctf:
case SystemZ::BI__builtin_s390_vpopctg: {
  llvm::Type *ResultType = ConvertType(E->getType());
  Value *X = EmitScalarExpr(E->getArg(0));
  Function *F = CGM.getIntrinsic(Intrinsic::ctpop, ResultType);
  return Builder.CreateCall(F, X);
}

case SystemZ::BI__builtin_s390_vclzb:
case SystemZ::BI__builtin_s390_vclzh:
case SystemZ::BI__builtin_s390_vclzf:
case SystemZ::BI__builtin_s390_vclzg: {
  llvm::Type *ResultType = ConvertType(E->getType());
  Value *X = EmitScalarExpr(E->getArg(0));
  Value *Undef = ConstantInt::get(Builder.getInt1Ty(), false);
  Function *F = CGM.getIntrinsic(Intrinsic::ctlz, ResultType);
  return Builder.CreateCall(F, {X, Undef});
}

case SystemZ::BI__builtin_s390_vctzb:
case SystemZ::BI__builtin_s390_vctzh:
case SystemZ::BI__builtin_s390_vctzf:
case SystemZ::BI__builtin_s390_vctzg: {
  llvm::Type *ResultType = ConvertType(E->getType());
  Value *X = EmitScalarExpr(E->getArg(0));
  Value *Undef = ConstantInt::get(Builder.getInt1Ty(), false);
  Function *F = CGM.getIntrinsic(Intrinsic::cttz, ResultType);
  return Builder.CreateCall(F, {X, Undef});
}

case SystemZ::BI__builtin_s390_vfsqsb:
case SystemZ::BI__builtin_s390_vfsqdb: {
  llvm::Type *ResultType = ConvertType(E->getType());
  Value *X = EmitScalarExpr(E->getArg(0));
  Function *F = CGM.getIntrinsic(Intrinsic::sqrt, ResultType);
  return Builder.CreateCall(F, X);
}
case SystemZ::BI__builtin_s390_vfmasb:
case SystemZ::BI__builtin_s390_vfmadb: {
  llvm::Type *ResultType = ConvertType(E->getType());
  Value *X = EmitScalarExpr(E->getArg(0));
  Value *Y = EmitScalarExpr(E->getArg(1));
  Value *Z = EmitScalarExpr(E->getArg(2));
  Function *F = CGM.getIntrinsic(Intrinsic::fma, ResultType);
  return Builder.CreateCall(F, {X, Y, Z});
}
case SystemZ::BI__builtin_s390_vfmssb:
case SystemZ::BI__builtin_s390_vfmsdb: {
  llvm::Type *ResultType = ConvertType(E->getType());
  Value *X = EmitScalarExpr(E->getArg(0));
  Value *Y = EmitScalarExpr(E->getArg(1));
  Value *Z = EmitScalarExpr(E->getArg(2));
  Value *Zero = llvm::ConstantFP::getZeroValueForNegation(ResultType);
  Function *F = CGM.getIntrinsic(Intrinsic::fma, ResultType);
  return Builder.CreateCall(F, {X, Y, Builder.CreateFSub(Zero, Z, "sub")});
}
case SystemZ::BI__builtin_s390_vfnmasb:
case SystemZ::BI__builtin_s390_vfnmadb: {
  llvm::Type *ResultType = ConvertType(E->getType());
  Value *X = EmitScalarExpr(E->getArg(0));
  Value *Y = EmitScalarExpr(E->getArg(1));
  Value *Z = EmitScalarExpr(E->getArg(2));
  Value *Zero = llvm::ConstantFP::getZeroValueForNegation(ResultType);
  Function *F = CGM.getIntrinsic(Intrinsic::fma, ResultType);
  return Builder.CreateFSub(Zero, Builder.CreateCall(F, {X, Y, Z}), "sub");
}
case SystemZ::BI__builtin_s390_vfnmssb:
case SystemZ::BI__builtin_s390_vfnmsdb: {
  llvm::Type *ResultType = ConvertType(E->getType());
  Value *X = EmitScalarExpr(E->getArg(0));
  Value *Y = EmitScalarExpr(E->getArg(1));
  Value *Z = EmitScalarExpr(E->getArg(2));
  Value *Zero = llvm::ConstantFP::getZeroValueForNegation(ResultType);
  Function *F = CGM.getIntrinsic(Intrinsic::fma, ResultType);
  Value *NegZ = Builder.CreateFSub(Zero, Z, "sub");
  return Builder.CreateFSub(Zero, Builder.CreateCall(F, {X, Y, NegZ}));
}
case SystemZ::BI__builtin_s390_vflpsb:
case SystemZ::BI__builtin_s390_vflpdb: {
  llvm::Type *ResultType = ConvertType(E->getType());
  Value *X = EmitScalarExpr(E->getArg(0));
  Function *F = CGM.getIntrinsic(Intrinsic::fabs, ResultType);
  return Builder.CreateCall(F, X);
}
case SystemZ::BI__builtin_s390_vflnsb:
case SystemZ::BI__builtin_s390_vflndb: {
  llvm::Type *ResultType = ConvertType(E->getType());
  Value *X = EmitScalarExpr(E->getArg(0));
  Value *Zero = llvm::ConstantFP::getZeroValueForNegation(ResultType);
  Function *F = CGM.getIntrinsic(Intrinsic::fabs, ResultType);
  return Builder.CreateFSub(Zero, Builder.CreateCall(F, X), "sub");
}
case SystemZ::BI__builtin_s390_vfisb:
case SystemZ::BI__builtin_s390_vfidb: {
  llvm::Type *ResultType = ConvertType(E->getType());
  Value *X = EmitScalarExpr(E->getArg(0));
  // Constant-fold the M4 and M5 mask arguments.
  llvm::APSInt M4, M5;
  bool IsConstM4 = E->getArg(1)->isIntegerConstantExpr(M4, getContext());
  bool IsConstM5 = E->getArg(2)->isIntegerConstantExpr(M5, getContext());
  assert(IsConstM4 && IsConstM5 && "Constant arg isn't actually constant?")(static_cast <bool> (IsConstM4 && IsConstM5 &&
 "Constant arg isn't actually constant?") ? void (0) : __assert_fail
 ("IsConstM4 && IsConstM5 && \"Constant arg isn't actually constant?\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 9916, __extension__ __PRETTY_FUNCTION__));
  (void)IsConstM4; (void)IsConstM5;
  // Check whether this instance can be represented via a LLVM standard
  // intrinsic.  We only support some combinations of M4 and M5.
  Intrinsic::ID ID = Intrinsic::not_intrinsic;
  switch (M4.getZExtValue()) {
  default: break;
  case 0:  // IEEE-inexact exception allowed
    switch (M5.getZExtValue()) {
    default: break;
    case 0: ID = Intrinsic::rint; break;
    }
    break;
  case 4:  // IEEE-inexact exception suppressed
    switch (M5.getZExtValue()) {
    default: break;
    case 0: ID = Intrinsic::nearbyint; break;
    case 1: ID = Intrinsic::round; break;
    case 5: ID = Intrinsic::trunc; break;
    case 6: ID = Intrinsic::ceil; break;
    case 7: ID = Intrinsic::floor; break;
    }
    break;
  }
  if (ID != Intrinsic::not_intrinsic) {
    Function *F = CGM.getIntrinsic(ID, ResultType);
    return Builder.CreateCall(F, X);
  }
  switch (BuiltinID) {
    case SystemZ::BI__builtin_s390_vfisb: ID = Intrinsic::s390_vfisb; break;
    case SystemZ::BI__builtin_s390_vfidb: ID = Intrinsic::s390_vfidb; break;
    default: llvm_unreachable("Unknown BuiltinID")::llvm::llvm_unreachable_internal("Unknown BuiltinID", "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 9947);
  }
  Function *F = CGM.getIntrinsic(ID);
  Value *M4Value = llvm::ConstantInt::get(getLLVMContext(), M4);
  Value *M5Value = llvm::ConstantInt::get(getLLVMContext(), M5);
  return Builder.CreateCall(F, {X, M4Value, M5Value});
}
case SystemZ::BI__builtin_s390_vfmaxsb:
case SystemZ::BI__builtin_s390_vfmaxdb: {
  llvm::Type *ResultType = ConvertType(E->getType());
  Value *X = EmitScalarExpr(E->getArg(0));
  Value *Y = EmitScalarExpr(E->getArg(1));
  // Constant-fold the M4 mask argument.
  llvm::APSInt M4;
  bool IsConstM4 = E->getArg(2)->isIntegerConstantExpr(M4, getContext());
  assert(IsConstM4 && "Constant arg isn't actually constant?")(static_cast <bool> (IsConstM4 && "Constant arg isn't actually constant?"
) ? void (0) : __assert_fail ("IsConstM4 && \"Constant arg isn't actually constant?\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 9962, __extension__ __PRETTY_FUNCTION__));
  (void)IsConstM4;
  // Check whether this instance can be represented via a LLVM standard
  // intrinsic.  We only support some values of M4.
  Intrinsic::ID ID = Intrinsic::not_intrinsic;
  switch (M4.getZExtValue()) {
  default: break;
  case 4: ID = Intrinsic::maxnum; break;
  }
  if (ID != Intrinsic::not_intrinsic) {
    Function *F = CGM.getIntrinsic(ID, ResultType);
    return Builder.CreateCall(F, {X, Y});
  }
  switch (BuiltinID) {
    case SystemZ::BI__builtin_s390_vfmaxsb: ID = Intrinsic::s390_vfmaxsb; break;
    case SystemZ::BI__builtin_s390_vfmaxdb: ID = Intrinsic::s390_vfmaxdb; break;
    default: llvm_unreachable("Unknown BuiltinID")::llvm::llvm_unreachable_internal("Unknown BuiltinID", "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 9978);
  }
  Function *F = CGM.getIntrinsic(ID);
  Value *M4Value = llvm::ConstantInt::get(getLLVMContext(), M4);
  return Builder.CreateCall(F, {X, Y, M4Value});
}
case SystemZ::BI__builtin_s390_vfminsb:
case SystemZ::BI__builtin_s390_vfmindb: {
  llvm::Type *ResultType = ConvertType(E->getType());
  Value *X = EmitScalarExpr(E->getArg(0));
  Value *Y = EmitScalarExpr(E->getArg(1));
  // Constant-fold the M4 mask argument.
  llvm::APSInt M4;
  bool IsConstM4 = E->getArg(2)->isIntegerConstantExpr(M4, getContext());
  assert(IsConstM4 && "Constant arg isn't actually constant?")(static_cast <bool> (IsConstM4 && "Constant arg isn't actually constant?"
) ? void (0) : __assert_fail ("IsConstM4 && \"Constant arg isn't actually constant?\""
, "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 9992, __extension__ __PRETTY_FUNCTION__));
  (void)IsConstM4;
  // Check whether this instance can be represented via a LLVM standard
  // intrinsic.  We only support some values of M4.
  Intrinsic::ID ID = Intrinsic::not_intrinsic;
  switch (M4.getZExtValue()) {
  default: break;
  case 4: ID = Intrinsic::minnum; break;
  }
  if (ID != Intrinsic::not_intrinsic) {
    Function *F = CGM.getIntrinsic(ID, ResultType);
    return Builder.CreateCall(F, {X, Y});
  }
  switch (BuiltinID) {
    case SystemZ::BI__builtin_s390_vfminsb: ID = Intrinsic::s390_vfminsb; break;
    case SystemZ::BI__builtin_s390_vfmindb: ID = Intrinsic::s390_vfmindb; break;
    default: llvm_unreachable("Unknown BuiltinID")::llvm::llvm_unreachable_internal("Unknown BuiltinID", "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 10008);
  }
  Function *F = CGM.getIntrinsic(ID);
  Value *M4Value = llvm::ConstantInt::get(getLLVMContext(), M4);
  return Builder.CreateCall(F, {X, Y, M4Value});
}

// Vector intrisincs that output the post-instruction CC value.

10017#define INTRINSIC_WITH_CC(NAME) \
  case SystemZ::BI__builtin_##NAME: \
    return EmitSystemZIntrinsicWithCC(*this, Intrinsic::NAME, E)

INTRINSIC_WITH_CC(s390_vpkshs);
INTRINSIC_WITH_CC(s390_vpksfs);
INTRINSIC_WITH_CC(s390_vpksgs);

INTRINSIC_WITH_CC(s390_vpklshs);
INTRINSIC_WITH_CC(s390_vpklsfs);
INTRINSIC_WITH_CC(s390_vpklsgs);

INTRINSIC_WITH_CC(s390_vceqbs);
INTRINSIC_WITH_CC(s390_vceqhs);
INTRINSIC_WITH_CC(s390_vceqfs);
INTRINSIC_WITH_CC(s390_vceqgs);

INTRINSIC_WITH_CC(s390_vchbs);
INTRINSIC_WITH_CC(s390_vchhs);
INTRINSIC_WITH_CC(s390_vchfs);
INTRINSIC_WITH_CC(s390_vchgs);

INTRINSIC_WITH_CC(s390_vchlbs);
INTRINSIC_WITH_CC(s390_vchlhs);
INTRINSIC_WITH_CC(s390_vchlfs);
INTRINSIC_WITH_CC(s390_vchlgs);

INTRINSIC_WITH_CC(s390_vfaebs);
INTRINSIC_WITH_CC(s390_vfaehs);
INTRINSIC_WITH_CC(s390_vfaefs);

INTRINSIC_WITH_CC(s390_vfaezbs);
INTRINSIC_WITH_CC(s390_vfaezhs);
INTRINSIC_WITH_CC(s390_vfaezfs);

INTRINSIC_WITH_CC(s390_vfeebs);
INTRINSIC_WITH_CC(s390_vfeehs);
INTRINSIC_WITH_CC(s390_vfeefs);

INTRINSIC_WITH_CC(s390_vfeezbs);
INTRINSIC_WITH_CC(s390_vfeezhs);
INTRINSIC_WITH_CC(s390_vfeezfs);

INTRINSIC_WITH_CC(s390_vfenebs);
INTRINSIC_WITH_CC(s390_vfenehs);
INTRINSIC_WITH_CC(s390_vfenefs);

INTRINSIC_WITH_CC(s390_vfenezbs);
INTRINSIC_WITH_CC(s390_vfenezhs);
INTRINSIC_WITH_CC(s390_vfenezfs);

INTRINSIC_WITH_CC(s390_vistrbs);
INTRINSIC_WITH_CC(s390_vistrhs);
INTRINSIC_WITH_CC(s390_vistrfs);

INTRINSIC_WITH_CC(s390_vstrcbs);
INTRINSIC_WITH_CC(s390_vstrchs);
INTRINSIC_WITH_CC(s390_vstrcfs);

INTRINSIC_WITH_CC(s390_vstrczbs);
INTRINSIC_WITH_CC(s390_vstrczhs);
INTRINSIC_WITH_CC(s390_vstrczfs);

INTRINSIC_WITH_CC(s390_vfcesbs);
INTRINSIC_WITH_CC(s390_vfcedbs);
INTRINSIC_WITH_CC(s390_vfchsbs);
INTRINSIC_WITH_CC(s390_vfchdbs);
INTRINSIC_WITH_CC(s390_vfchesbs);
INTRINSIC_WITH_CC(s390_vfchedbs);

INTRINSIC_WITH_CC(s390_vftcisb);
INTRINSIC_WITH_CC(s390_vftcidb);

10090#undef INTRINSIC_WITH_CC

default:
  return nullptr;
}
10095}

10097Value *CodeGenFunction::EmitNVPTXBuiltinExpr(unsigned BuiltinID,
                                           const CallExpr *E) {
auto MakeLdg = [&](unsigned IntrinsicID) {
  Value *Ptr = EmitScalarExpr(E->getArg(0));
  clang::CharUnits Align =
      getNaturalPointeeTypeAlignment(E->getArg(0)->getType());
  return Builder.CreateCall(
      CGM.getIntrinsic(IntrinsicID, {Ptr->getType()->getPointerElementType(),
                                     Ptr->getType()}),
      {Ptr, ConstantInt::get(Builder.getInt32Ty(), Align.getQuantity())});
};
auto MakeScopedAtomic = [&](unsigned IntrinsicID) {
  Value *Ptr = EmitScalarExpr(E->getArg(0));
  return Builder.CreateCall(
      CGM.getIntrinsic(IntrinsicID, {Ptr->getType()->getPointerElementType(),
                                     Ptr->getType()}),
      {Ptr, EmitScalarExpr(E->getArg(1))});
};
switch (BuiltinID) {
case NVPTX::BI__nvvm_atom_add_gen_i:
case NVPTX::BI__nvvm_atom_add_gen_l:
case NVPTX::BI__nvvm_atom_add_gen_ll:
  return MakeBinaryAtomicValue(*this, llvm::AtomicRMWInst::Add, E);

case NVPTX::BI__nvvm_atom_sub_gen_i:
case NVPTX::BI__nvvm_atom_sub_gen_l:
case NVPTX::BI__nvvm_atom_sub_gen_ll:
  return MakeBinaryAtomicValue(*this, llvm::AtomicRMWInst::Sub, E);

case NVPTX::BI__nvvm_atom_and_gen_i:
case NVPTX::BI__nvvm_atom_and_gen_l:
case NVPTX::BI__nvvm_atom_and_gen_ll:
  return MakeBinaryAtomicValue(*this, llvm::AtomicRMWInst::And, E);

case NVPTX::BI__nvvm_atom_or_gen_i:
case NVPTX::BI__nvvm_atom_or_gen_l:
case NVPTX::BI__nvvm_atom_or_gen_ll:
  return MakeBinaryAtomicValue(*this, llvm::AtomicRMWInst::Or, E);

case NVPTX::BI__nvvm_atom_xor_gen_i:
case NVPTX::BI__nvvm_atom_xor_gen_l:
case NVPTX::BI__nvvm_atom_xor_gen_ll:
  return MakeBinaryAtomicValue(*this, llvm::AtomicRMWInst::Xor, E);

case NVPTX::BI__nvvm_atom_xchg_gen_i:
case NVPTX::BI__nvvm_atom_xchg_gen_l:
case NVPTX::BI__nvvm_atom_xchg_gen_ll:
  return MakeBinaryAtomicValue(*this, llvm::AtomicRMWInst::Xchg, E);

case NVPTX::BI__nvvm_atom_max_gen_i:
case NVPTX::BI__nvvm_atom_max_gen_l:
case NVPTX::BI__nvvm_atom_max_gen_ll:
  return MakeBinaryAtomicValue(*this, llvm::AtomicRMWInst::Max, E);

case NVPTX::BI__nvvm_atom_max_gen_ui:
case NVPTX::BI__nvvm_atom_max_gen_ul:
case NVPTX::BI__nvvm_atom_max_gen_ull:
  return MakeBinaryAtomicValue(*this, llvm::AtomicRMWInst::UMax, E);

case NVPTX::BI__nvvm_atom_min_gen_i:
case NVPTX::BI__nvvm_atom_min_gen_l:
case NVPTX::BI__nvvm_atom_min_gen_ll:
  return MakeBinaryAtomicValue(*this, llvm::AtomicRMWInst::Min, E);

case NVPTX::BI__nvvm_atom_min_gen_ui:
case NVPTX::BI__nvvm_atom_min_gen_ul:
case NVPTX::BI__nvvm_atom_min_gen_ull:
  return MakeBinaryAtomicValue(*this, llvm::AtomicRMWInst::UMin, E);

case NVPTX::BI__nvvm_atom_cas_gen_i:
case NVPTX::BI__nvvm_atom_cas_gen_l:
case NVPTX::BI__nvvm_atom_cas_gen_ll:
  // __nvvm_atom_cas_gen_* should return the old value rather than the
  // success flag.
  return MakeAtomicCmpXchgValue(*this, E, /*ReturnBool=*/false);

case NVPTX::BI__nvvm_atom_add_gen_f: {
  Value *Ptr = EmitScalarExpr(E->getArg(0));
  Value *Val = EmitScalarExpr(E->getArg(1));
  // atomicrmw only deals with integer arguments so we need to use
  // LLVM's nvvm_atomic_load_add_f32 intrinsic for that.
  Value *FnALAF32 =
      CGM.getIntrinsic(Intrinsic::nvvm_atomic_load_add_f32, Ptr->getType());
  return Builder.CreateCall(FnALAF32, {Ptr, Val});
}

case NVPTX::BI__nvvm_atom_add_gen_d: {
  Value *Ptr = EmitScalarExpr(E->getArg(0));
  Value *Val = EmitScalarExpr(E->getArg(1));
  // atomicrmw only deals with integer arguments, so we need to use
  // LLVM's nvvm_atomic_load_add_f64 intrinsic.
  Value *FnALAF64 =
      CGM.getIntrinsic(Intrinsic::nvvm_atomic_load_add_f64, Ptr->getType());
  return Builder.CreateCall(FnALAF64, {Ptr, Val});
}

case NVPTX::BI__nvvm_atom_inc_gen_ui: {
  Value *Ptr = EmitScalarExpr(E->getArg(0));
  Value *Val = EmitScalarExpr(E->getArg(1));
  Value *FnALI32 =
      CGM.getIntrinsic(Intrinsic::nvvm_atomic_load_inc_32, Ptr->getType());
  return Builder.CreateCall(FnALI32, {Ptr, Val});
}

case NVPTX::BI__nvvm_atom_dec_gen_ui: {
  Value *Ptr = EmitScalarExpr(E->getArg(0));
  Value *Val = EmitScalarExpr(E->getArg(1));
  Value *FnALD32 =
      CGM.getIntrinsic(Intrinsic::nvvm_atomic_load_dec_32, Ptr->getType());
  return Builder.CreateCall(FnALD32, {Ptr, Val});
}

case NVPTX::BI__nvvm_ldg_c:
case NVPTX::BI__nvvm_ldg_c2:
case NVPTX::BI__nvvm_ldg_c4:
case NVPTX::BI__nvvm_ldg_s:
case NVPTX::BI__nvvm_ldg_s2:
case NVPTX::BI__nvvm_ldg_s4:
case NVPTX::BI__nvvm_ldg_i:
case NVPTX::BI__nvvm_ldg_i2:
case NVPTX::BI__nvvm_ldg_i4:
case NVPTX::BI__nvvm_ldg_l:
case NVPTX::BI__nvvm_ldg_ll:
case NVPTX::BI__nvvm_ldg_ll2:
case NVPTX::BI__nvvm_ldg_uc:
case NVPTX::BI__nvvm_ldg_uc2:
case NVPTX::BI__nvvm_ldg_uc4:
case NVPTX::BI__nvvm_ldg_us:
case NVPTX::BI__nvvm_ldg_us2:
case NVPTX::BI__nvvm_ldg_us4:
case NVPTX::BI__nvvm_ldg_ui:
case NVPTX::BI__nvvm_ldg_ui2:
case NVPTX::BI__nvvm_ldg_ui4:
case NVPTX::BI__nvvm_ldg_ul:
case NVPTX::BI__nvvm_ldg_ull:
case NVPTX::BI__nvvm_ldg_ull2:
  // PTX Interoperability section 2.2: "For a vector with an even number of
  // elements, its alignment is set to number of elements times the alignment
  // of its member: n*alignof(t)."
  return MakeLdg(Intrinsic::nvvm_ldg_global_i);
case NVPTX::BI__nvvm_ldg_f:
case NVPTX::BI__nvvm_ldg_f2:
case NVPTX::BI__nvvm_ldg_f4:
case NVPTX::BI__nvvm_ldg_d:
case NVPTX::BI__nvvm_ldg_d2:
  return MakeLdg(Intrinsic::nvvm_ldg_global_f);

case NVPTX::BI__nvvm_atom_cta_add_gen_i:
case NVPTX::BI__nvvm_atom_cta_add_gen_l:
case NVPTX::BI__nvvm_atom_cta_add_gen_ll:
  return MakeScopedAtomic(Intrinsic::nvvm_atomic_add_gen_i_cta);
case NVPTX::BI__nvvm_atom_sys_add_gen_i:
case NVPTX::BI__nvvm_atom_sys_add_gen_l:
case NVPTX::BI__nvvm_atom_sys_add_gen_ll:
  return MakeScopedAtomic(Intrinsic::nvvm_atomic_add_gen_i_sys);
case NVPTX::BI__nvvm_atom_cta_add_gen_f:
case NVPTX::BI__nvvm_atom_cta_add_gen_d:
  return MakeScopedAtomic(Intrinsic::nvvm_atomic_add_gen_f_cta);
case NVPTX::BI__nvvm_atom_sys_add_gen_f:
case NVPTX::BI__nvvm_atom_sys_add_gen_d:
  return MakeScopedAtomic(Intrinsic::nvvm_atomic_add_gen_f_sys);
case NVPTX::BI__nvvm_atom_cta_xchg_gen_i:
case NVPTX::BI__nvvm_atom_cta_xchg_gen_l:
case NVPTX::BI__nvvm_atom_cta_xchg_gen_ll:
  return MakeScopedAtomic(Intrinsic::nvvm_atomic_exch_gen_i_cta);
case NVPTX::BI__nvvm_atom_sys_xchg_gen_i:
case NVPTX::BI__nvvm_atom_sys_xchg_gen_l:
case NVPTX::BI__nvvm_atom_sys_xchg_gen_ll:
  return MakeScopedAtomic(Intrinsic::nvvm_atomic_exch_gen_i_sys);
case NVPTX::BI__nvvm_atom_cta_max_gen_i:
case NVPTX::BI__nvvm_atom_cta_max_gen_ui:
case NVPTX::BI__nvvm_atom_cta_max_gen_l:
case NVPTX::BI__nvvm_atom_cta_max_gen_ul:
case NVPTX::BI__nvvm_atom_cta_max_gen_ll:
case NVPTX::BI__nvvm_atom_cta_max_gen_ull:
  return MakeScopedAtomic(Intrinsic::nvvm_atomic_max_gen_i_cta);
case NVPTX::BI__nvvm_atom_sys_max_gen_i:
case NVPTX::BI__nvvm_atom_sys_max_gen_ui:
case NVPTX::BI__nvvm_atom_sys_max_gen_l:
case NVPTX::BI__nvvm_atom_sys_max_gen_ul:
case NVPTX::BI__nvvm_atom_sys_max_gen_ll:
case NVPTX::BI__nvvm_atom_sys_max_gen_ull:
  return MakeScopedAtomic(Intrinsic::nvvm_atomic_max_gen_i_sys);
case NVPTX::BI__nvvm_atom_cta_min_gen_i:
case NVPTX::BI__nvvm_atom_cta_min_gen_ui:
case NVPTX::BI__nvvm_atom_cta_min_gen_l:
case NVPTX::BI__nvvm_atom_cta_min_gen_ul:
case NVPTX::BI__nvvm_atom_cta_min_gen_ll:
case NVPTX::BI__nvvm_atom_cta_min_gen_ull:
  return MakeScopedAtomic(Intrinsic::nvvm_atomic_min_gen_i_cta);
case NVPTX::BI__nvvm_atom_sys_min_gen_i:
case NVPTX::BI__nvvm_atom_sys_min_gen_ui:
case NVPTX::BI__nvvm_atom_sys_min_gen_l:
case NVPTX::BI__nvvm_atom_sys_min_gen_ul:
case NVPTX::BI__nvvm_atom_sys_min_gen_ll:
case NVPTX::BI__nvvm_atom_sys_min_gen_ull:
  return MakeScopedAtomic(Intrinsic::nvvm_atomic_min_gen_i_sys);
case NVPTX::BI__nvvm_atom_cta_inc_gen_ui:
  return MakeScopedAtomic(Intrinsic::nvvm_atomic_inc_gen_i_cta);
case NVPTX::BI__nvvm_atom_cta_dec_gen_ui:
  return MakeScopedAtomic(Intrinsic::nvvm_atomic_dec_gen_i_cta);
case NVPTX::BI__nvvm_atom_sys_inc_gen_ui:
  return MakeScopedAtomic(Intrinsic::nvvm_atomic_inc_gen_i_sys);
case NVPTX::BI__nvvm_atom_sys_dec_gen_ui:
  return MakeScopedAtomic(Intrinsic::nvvm_atomic_dec_gen_i_sys);
case NVPTX::BI__nvvm_atom_cta_and_gen_i:
case NVPTX::BI__nvvm_atom_cta_and_gen_l:
case NVPTX::BI__nvvm_atom_cta_and_gen_ll:
  return MakeScopedAtomic(Intrinsic::nvvm_atomic_and_gen_i_cta);
case NVPTX::BI__nvvm_atom_sys_and_gen_i:
case NVPTX::BI__nvvm_atom_sys_and_gen_l:
case NVPTX::BI__nvvm_atom_sys_and_gen_ll:
  return MakeScopedAtomic(Intrinsic::nvvm_atomic_and_gen_i_sys);
case NVPTX::BI__nvvm_atom_cta_or_gen_i:
case NVPTX::BI__nvvm_atom_cta_or_gen_l:
case NVPTX::BI__nvvm_atom_cta_or_gen_ll:
  return MakeScopedAtomic(Intrinsic::nvvm_atomic_or_gen_i_cta);
case NVPTX::BI__nvvm_atom_sys_or_gen_i:
case NVPTX::BI__nvvm_atom_sys_or_gen_l:
case NVPTX::BI__nvvm_atom_sys_or_gen_ll:
  return MakeScopedAtomic(Intrinsic::nvvm_atomic_or_gen_i_sys);
case NVPTX::BI__nvvm_atom_cta_xor_gen_i:
case NVPTX::BI__nvvm_atom_cta_xor_gen_l:
case NVPTX::BI__nvvm_atom_cta_xor_gen_ll:
  return MakeScopedAtomic(Intrinsic::nvvm_atomic_xor_gen_i_cta);
case NVPTX::BI__nvvm_atom_sys_xor_gen_i:
case NVPTX::BI__nvvm_atom_sys_xor_gen_l:
case NVPTX::BI__nvvm_atom_sys_xor_gen_ll:
  return MakeScopedAtomic(Intrinsic::nvvm_atomic_xor_gen_i_sys);
case NVPTX::BI__nvvm_atom_cta_cas_gen_i:
case NVPTX::BI__nvvm_atom_cta_cas_gen_l:
case NVPTX::BI__nvvm_atom_cta_cas_gen_ll: {
  Value *Ptr = EmitScalarExpr(E->getArg(0));
  return Builder.CreateCall(
      CGM.getIntrinsic(
          Intrinsic::nvvm_atomic_cas_gen_i_cta,
          {Ptr->getType()->getPointerElementType(), Ptr->getType()}),
      {Ptr, EmitScalarExpr(E->getArg(1)), EmitScalarExpr(E->getArg(2))});
}
case NVPTX::BI__nvvm_atom_sys_cas_gen_i:
case NVPTX::BI__nvvm_atom_sys_cas_gen_l:
case NVPTX::BI__nvvm_atom_sys_cas_gen_ll: {
  Value *Ptr = EmitScalarExpr(E->getArg(0));
  return Builder.CreateCall(
      CGM.getIntrinsic(
          Intrinsic::nvvm_atomic_cas_gen_i_sys,
          {Ptr->getType()->getPointerElementType(), Ptr->getType()}),
      {Ptr, EmitScalarExpr(E->getArg(1)), EmitScalarExpr(E->getArg(2))});
}
case NVPTX::BI__nvvm_match_all_sync_i32p:
case NVPTX::BI__nvvm_match_all_sync_i64p: {
  Value *Mask = EmitScalarExpr(E->getArg(0));
  Value *Val = EmitScalarExpr(E->getArg(1));
  Address PredOutPtr = EmitPointerWithAlignment(E->getArg(2));
  Value *ResultPair = Builder.CreateCall(
      CGM.getIntrinsic(BuiltinID == NVPTX::BI__nvvm_match_all_sync_i32p
                           ? Intrinsic::nvvm_match_all_sync_i32p
                           : Intrinsic::nvvm_match_all_sync_i64p),
      {Mask, Val});
  Value *Pred = Builder.CreateZExt(Builder.CreateExtractValue(ResultPair, 1),
                                   PredOutPtr.getElementType());
  Builder.CreateStore(Pred, PredOutPtr);
  return Builder.CreateExtractValue(ResultPair, 0);
}
case NVPTX::BI__hmma_m16n16k16_ld_a:
case NVPTX::BI__hmma_m16n16k16_ld_b:
case NVPTX::BI__hmma_m16n16k16_ld_c_f16:
case NVPTX::BI__hmma_m16n16k16_ld_c_f32: {
  Address Dst = EmitPointerWithAlignment(E->getArg(0));
  Value *Src = EmitScalarExpr(E->getArg(1));
  Value *Ldm = EmitScalarExpr(E->getArg(2));
  llvm::APSInt isColMajorArg;
  if (!E->getArg(3)->isIntegerConstantExpr(isColMajorArg, getContext()))
    return nullptr;
  bool isColMajor = isColMajorArg.getSExtValue();
  unsigned IID;
  unsigned NumResults;
  switch (BuiltinID) {
  case NVPTX::BI__hmma_m16n16k16_ld_a:
    IID = isColMajor ? Intrinsic::nvvm_wmma_load_a_f16_col_stride
                     : Intrinsic::nvvm_wmma_load_a_f16_row_stride;
    NumResults = 8;
    break;
  case NVPTX::BI__hmma_m16n16k16_ld_b:
    IID = isColMajor ? Intrinsic::nvvm_wmma_load_b_f16_col_stride
                     : Intrinsic::nvvm_wmma_load_b_f16_row_stride;
    NumResults = 8;
    break;
  case NVPTX::BI__hmma_m16n16k16_ld_c_f16:
    IID = isColMajor ? Intrinsic::nvvm_wmma_load_c_f16_col_stride
                     : Intrinsic::nvvm_wmma_load_c_f16_row_stride;
    NumResults = 4;
    break;
  case NVPTX::BI__hmma_m16n16k16_ld_c_f32:
    IID = isColMajor ? Intrinsic::nvvm_wmma_load_c_f32_col_stride
                     : Intrinsic::nvvm_wmma_load_c_f32_row_stride;
    NumResults = 8;
    break;
  default:
    llvm_unreachable("Unexpected builtin ID.")::llvm::llvm_unreachable_internal("Unexpected builtin ID.", "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 10396);
  }
  Value *Result =
      Builder.CreateCall(CGM.getIntrinsic(IID),
                         {Builder.CreatePointerCast(Src, VoidPtrTy), Ldm});

  // Save returned values.
  for (unsigned i = 0; i < NumResults; ++i) {
    Builder.CreateAlignedStore(
        Builder.CreateBitCast(Builder.CreateExtractValue(Result, i),
                              Dst.getElementType()),
        Builder.CreateGEP(Dst.getPointer(), llvm::ConstantInt::get(IntTy, i)),
        CharUnits::fromQuantity(4));
  }
  return Result;
}

case NVPTX::BI__hmma_m16n16k16_st_c_f16:
case NVPTX::BI__hmma_m16n16k16_st_c_f32: {
  Value *Dst = EmitScalarExpr(E->getArg(0));
  Address Src = EmitPointerWithAlignment(E->getArg(1));
  Value *Ldm = EmitScalarExpr(E->getArg(2));
  llvm::APSInt isColMajorArg;
  if (!E->getArg(3)->isIntegerConstantExpr(isColMajorArg, getContext()))
    return nullptr;
  bool isColMajor = isColMajorArg.getSExtValue();
  unsigned IID;
  unsigned NumResults = 8;
  // PTX Instructions (and LLVM instrinsics) are defined for slice _d_, yet
  // for some reason nvcc builtins use _c_.
  switch (BuiltinID) {
  case NVPTX::BI__hmma_m16n16k16_st_c_f16:
    IID = isColMajor ? Intrinsic::nvvm_wmma_store_d_f16_col_stride
                     : Intrinsic::nvvm_wmma_store_d_f16_row_stride;
    NumResults = 4;
    break;
  case NVPTX::BI__hmma_m16n16k16_st_c_f32:
    IID = isColMajor ? Intrinsic::nvvm_wmma_store_d_f32_col_stride
                     : Intrinsic::nvvm_wmma_store_d_f32_row_stride;
    break;
  default:
    llvm_unreachable("Unexpected builtin ID.")::llvm::llvm_unreachable_internal("Unexpected builtin ID.", "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 10437);
  }
  Function *Intrinsic = CGM.getIntrinsic(IID);
  llvm::Type *ParamType = Intrinsic->getFunctionType()->getParamType(1);
  SmallVector<Value *, 10> Values;
  Values.push_back(Builder.CreatePointerCast(Dst, VoidPtrTy));
  for (unsigned i = 0; i < NumResults; ++i) {
    Value *V = Builder.CreateAlignedLoad(
        Builder.CreateGEP(Src.getPointer(), llvm::ConstantInt::get(IntTy, i)),
        CharUnits::fromQuantity(4));
    Values.push_back(Builder.CreateBitCast(V, ParamType));
  }
  Values.push_back(Ldm);
  Value *Result = Builder.CreateCall(Intrinsic, Values);
  return Result;
}

// BI__hmma_m16n16k16_mma_<Dtype><CType>(d, a, b, c, layout, satf)
//  --> Intrinsic::nvvm_wmma_mma_sync<layout A,B><DType><CType><Satf>
case NVPTX::BI__hmma_m16n16k16_mma_f16f16:
case NVPTX::BI__hmma_m16n16k16_mma_f32f16:
case NVPTX::BI__hmma_m16n16k16_mma_f32f32:
case NVPTX::BI__hmma_m16n16k16_mma_f16f32: {
  Address Dst = EmitPointerWithAlignment(E->getArg(0));
  Address SrcA = EmitPointerWithAlignment(E->getArg(1));
  Address SrcB = EmitPointerWithAlignment(E->getArg(2));
  Address SrcC = EmitPointerWithAlignment(E->getArg(3));
  llvm::APSInt LayoutArg;
  if (!E->getArg(4)->isIntegerConstantExpr(LayoutArg, getContext()))
    return nullptr;
  int Layout = LayoutArg.getSExtValue();
  if (Layout < 0 || Layout > 3)
    return nullptr;
  llvm::APSInt SatfArg;
  if (!E->getArg(5)->isIntegerConstantExpr(SatfArg, getContext()))
    return nullptr;
  bool Satf = SatfArg.getSExtValue();

  // clang-format off
10476#define MMA_VARIANTS(type) {{                                   \
    Intrinsic::nvvm_wmma_mma_sync_row_row_##type,             \
    Intrinsic::nvvm_wmma_mma_sync_row_row_##type##_satfinite, \
    Intrinsic::nvvm_wmma_mma_sync_row_col_##type,             \
    Intrinsic::nvvm_wmma_mma_sync_row_col_##type##_satfinite, \
    Intrinsic::nvvm_wmma_mma_sync_col_row_##type,             \
    Intrinsic::nvvm_wmma_mma_sync_col_row_##type##_satfinite, \
    Intrinsic::nvvm_wmma_mma_sync_col_col_##type,             \
    Intrinsic::nvvm_wmma_mma_sync_col_col_##type##_satfinite  \
  }}
  // clang-format on

  auto getMMAIntrinsic = [Layout, Satf](std::array<unsigned, 8> Variants) {
    unsigned Index = Layout * 2 + Satf;
    assert(Index < 8)(static_cast <bool> (Index < 8) ? void (0) : __assert_fail
 ("Index < 8", "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 10490, __extension__ __PRETTY_FUNCTION__));
    return Variants[Index];
  };
  unsigned IID;
  unsigned NumEltsC;
  unsigned NumEltsD;
  switch (BuiltinID) {
  case NVPTX::BI__hmma_m16n16k16_mma_f16f16:
    IID = getMMAIntrinsic(MMA_VARIANTS(f16_f16));
    NumEltsC = 4;
    NumEltsD = 4;
    break;
  case NVPTX::BI__hmma_m16n16k16_mma_f32f16:
    IID = getMMAIntrinsic(MMA_VARIANTS(f32_f16));
    NumEltsC = 4;
    NumEltsD = 8;
    break;
  case NVPTX::BI__hmma_m16n16k16_mma_f16f32:
    IID = getMMAIntrinsic(MMA_VARIANTS(f16_f32));
    NumEltsC = 8;
    NumEltsD = 4;
    break;
  case NVPTX::BI__hmma_m16n16k16_mma_f32f32:
    IID = getMMAIntrinsic(MMA_VARIANTS(f32_f32));
    NumEltsC = 8;
    NumEltsD = 8;
    break;
  default:
    llvm_unreachable("Unexpected builtin ID.")::llvm::llvm_unreachable_internal("Unexpected builtin ID.", "/build/llvm-toolchain-snapshot-7~svn324650/tools/clang/lib/CodeGen/CGBuiltin.cpp"
, 10518);
  }
10520#undef MMA_VARIANTS

  SmallVector<Value *, 24> Values;
  Function *Intrinsic = CGM.getIntrinsic(IID);
  llvm::Type *ABType = Intrinsic->getFunctionType()->getParamType(0);
  // Load A
  for (unsigned i = 0; i < 8; ++i) {
    Value *V = Builder.CreateAlignedLoad(
        Builder.CreateGEP(SrcA.getPointer(),
                          llvm::ConstantInt::get(IntTy, i)),
        CharUnits::fromQuantity(4));
    Values.push_back(Builder.CreateBitCast(V, ABType));
  }
  // Load B
  for (unsigned i = 0; i < 8; ++i) {
    Value *V = Builder.CreateAlignedLoad(
        Builder.CreateGEP(SrcB.getPointer(),
                          llvm::ConstantInt::get(IntTy, i)),
        CharUnits::fromQuantity(4));
    Values.push_back(Builder.CreateBitCast(V, ABType));
  }
  // Load C
  llvm::Type *CType = Intrinsic->getFunctionType()->getParamType(16);
  for (unsigned i = 0; i < NumEltsC; ++i) {
    Value *V = Builder.CreateAlignedLoad(
        Builder.CreateGEP(SrcC.getPointer(),
                          llvm::ConstantInt::get(IntTy, i)),
        CharUnits::fromQuantity(4));
    Values.push_back(Builder.CreateBitCast(V, CType));
  }
  Value *Result = Builder.CreateCall(Intrinsic, Values);
  llvm::Type *DType = Dst.getElementType();
  for (unsigned i = 0; i < NumEltsD; ++i)
    Builder.CreateAlignedStore(
        Builder.CreateBitCast(Builder.CreateExtractValue(Result, i), DType),
        Builder.CreateGEP(Dst.getPointer(), llvm::ConstantInt::get(IntTy, i)),
        CharUnits::fromQuantity(4));
  return Result;
}
default:
  return nullptr;
}
10562}

10564Value *CodeGenFunction::EmitWebAssemblyBuiltinExpr(unsigned BuiltinID,
                                                 const CallExpr *E) {
switch (BuiltinID) {
case WebAssembly::BI__builtin_wasm_mem_size: {
  llvm::Type *ResultType = ConvertType(E->getType());
  Value *I = EmitScalarExpr(E->getArg(0));
  Value *Callee = CGM.getIntrinsic(Intrinsic::wasm_mem_size, ResultType);
  return Builder.CreateCall(Callee, I);
}
case WebAssembly::BI__builtin_wasm_mem_grow: {
  llvm::Type *ResultType = ConvertType(E->getType());
  Value *Args[] = {
    EmitScalarExpr(E->getArg(0)),
    EmitScalarExpr(E->getArg(1))
  };
  Value *Callee = CGM.getIntrinsic(Intrinsic::wasm_mem_grow, ResultType);
  return Builder.CreateCall(Callee, Args);
}
case WebAssembly::BI__builtin_wasm_current_memory: {
  llvm::Type *ResultType = ConvertType(E->getType());
  Value *Callee = CGM.getIntrinsic(Intrinsic::wasm_current_memory, ResultType);
  return Builder.CreateCall(Callee);
}
case WebAssembly::BI__builtin_wasm_grow_memory: {
  Value *X = EmitScalarExpr(E->getArg(0));
  Value *Callee = CGM.getIntrinsic(Intrinsic::wasm_grow_memory, X->getType());
  return Builder.CreateCall(Callee, X);
}
case WebAssembly::BI__builtin_wasm_throw: {
  Value *Tag = EmitScalarExpr(E->getArg(0));
  Value *Obj = EmitScalarExpr(E->getArg(1));
  Value *Callee = CGM.getIntrinsic(Intrinsic::wasm_throw);
  return Builder.CreateCall(Callee, {Tag, Obj});
}
case WebAssembly::BI__builtin_wasm_rethrow: {
  Value *Callee = CGM.getIntrinsic(Intrinsic::wasm_rethrow);
  return Builder.CreateCall(Callee);
}

default:
  return nullptr;
}
10606}

10608Value *CodeGenFunction::EmitHexagonBuiltinExpr(unsigned BuiltinID,
                                             const CallExpr *E) {
SmallVector<llvm::Value *, 4> Ops;
Intrinsic::ID ID = Intrinsic::not_intrinsic;

switch (BuiltinID) {
case Hexagon::BI__builtin_HEXAGON_V6_vaddcarry:
case Hexagon::BI__builtin_HEXAGON_V6_vaddcarry_128B: {
  Address Dest = EmitPointerWithAlignment(E->getArg(2));
  unsigned Size;
  if (BuiltinID == Hexagon::BI__builtin_HEXAGON_V6_vaddcarry) {
    Size = 512;
    ID = Intrinsic::hexagon_V6_vaddcarry;
  } else {
    Size = 1024;
    ID = Intrinsic::hexagon_V6_vaddcarry_128B;
  }
  Dest = Builder.CreateBitCast(Dest,
      llvm::VectorType::get(Builder.getInt1Ty(), Size)->getPointerTo(0));
  LoadInst *QLd = Builder.CreateLoad(Dest);
  Ops = { EmitScalarExpr(E->getArg(0)), EmitScalarExpr(E->getArg(1)), QLd };
  llvm::Value *Result = Builder.CreateCall(CGM.getIntrinsic(ID), Ops);
  llvm::Value *Vprd = Builder.CreateExtractValue(Result, 1);
  llvm::Value *Base = Builder.CreateBitCast(EmitScalarExpr(E->getArg(2)),
                                            Vprd->getType()->getPointerTo(0));
  Builder.CreateAlignedStore(Vprd, Base, Dest.getAlignment());
  return Builder.CreateExtractValue(Result, 0);
}
case Hexagon::BI__builtin_HEXAGON_V6_vsubcarry:
case Hexagon::BI__builtin_HEXAGON_V6_vsubcarry_128B: {
  Address Dest = EmitPointerWithAlignment(E->getArg(2));
  unsigned Size;
  if (BuiltinID == Hexagon::BI__builtin_HEXAGON_V6_vsubcarry) {
    Size = 512;
    ID = Intrinsic::hexagon_V6_vsubcarry;
  } else {
    Size = 1024;
    ID = Intrinsic::hexagon_V6_vsubcarry_128B;
  }
  Dest = Builder.CreateBitCast(Dest,
      llvm::VectorType::get(Builder.getInt1Ty(), Size)->getPointerTo(0));
  LoadInst *QLd = Builder.CreateLoad(Dest);
  Ops = { EmitScalarExpr(E->getArg(0)), EmitScalarExpr(E->getArg(1)), QLd };
  llvm::Value *Result = Builder.CreateCall(CGM.getIntrinsic(ID), Ops);
  llvm::Value *Vprd = Builder.CreateExtractValue(Result, 1);
  llvm::Value *Base = Builder.CreateBitCast(EmitScalarExpr(E->getArg(2)),
                                            Vprd->getType()->getPointerTo(0));
  Builder.CreateAlignedStore(Vprd, Base, Dest.getAlignment());
  return Builder.CreateExtractValue(Result, 0);
}
} // switch

return nullptr;
10661}

←

/build/llvm-toolchain-snapshot-7~svn324650/include/llvm/IR/DerivedTypes.h

→

1//===- llvm/DerivedTypes.h - Classes for handling data types ----*- C++ -*-===//
2//
3//                     The LLVM Compiler Infrastructure
4//
5// This file is distributed under the University of Illinois Open Source
6// License. See LICENSE.TXT for details.
7//
8//===----------------------------------------------------------------------===//
9//
10// This file contains the declarations of classes that represent "derived
11// types".  These are things like "arrays of x" or "structure of x, y, z" or
12// "function returning x taking (y,z) as parameters", etc...
13//
14// The implementations of these classes live in the Type.cpp file.
15//
16//===----------------------------------------------------------------------===//

18#ifndef LLVM_IR_DERIVEDTYPES_H
19#define LLVM_IR_DERIVEDTYPES_H

21#include "llvm/ADT/ArrayRef.h"
22#include "llvm/ADT/STLExtras.h"
23#include "llvm/ADT/StringRef.h"
24#include "llvm/IR/Type.h"
25#include "llvm/Support/Casting.h"
26#include "llvm/Support/Compiler.h"
27#include <cassert>
28#include <cstdint>

30namespace llvm {

32class Value;
33class APInt;
34class LLVMContext;

36/// Class to represent integer types. Note that this class is also used to
37/// represent the built-in integer types: Int1Ty, Int8Ty, Int16Ty, Int32Ty and
38/// Int64Ty.
39/// @brief Integer representation type
40class IntegerType : public Type {
friend class LLVMContextImpl;

43protected:
explicit IntegerType(LLVMContext &C, unsigned NumBits) : Type(C, IntegerTyID){
  setSubclassData(NumBits);
}

48public:
/// This enum is just used to hold constants we need for IntegerType.
enum {
  MIN_INT_BITS = 1,        ///< Minimum number of bits that can be specified
  MAX_INT_BITS = (1<<24)-1 ///< Maximum number of bits that can be specified
    ///< Note that bit width is stored in the Type classes SubclassData field
    ///< which has 24 bits. This yields a maximum bit width of 16,777,215
    ///< bits.
};

/// This static method is the primary way of constructing an IntegerType.
/// If an IntegerType with the same NumBits value was previously instantiated,
/// that instance will be returned. Otherwise a new one will be created. Only
/// one instance with a given NumBits value is ever created.
/// @brief Get or create an IntegerType instance.
static IntegerType *get(LLVMContext &C, unsigned NumBits);

/// @brief Get the number of bits in this IntegerType
unsigned getBitWidth() const { return getSubclassData(); }

/// Return a bitmask with ones set for all of the bits that can be set by an
/// unsigned version of this type. This is 0xFF for i8, 0xFFFF for i16, etc.
uint64_t getBitMask() const {
  return ~uint64_t(0UL) >> (64-getBitWidth());
}

/// Return a uint64_t with just the most significant bit set (the sign bit, if
/// the value is treated as a signed number).
uint64_t getSignBit() const {
  return 1ULL << (getBitWidth()-1);
}

/// For example, this is 0xFF for an 8 bit integer, 0xFFFF for i16, etc.
/// @returns a bit mask with ones set for all the bits of this type.
/// @brief Get a bit mask for this type.
APInt getMask() const;

/// This method determines if the width of this IntegerType is a power-of-2
/// in terms of 8 bit bytes.
/// @returns true if this is a power-of-2 byte width.
/// @brief Is this a power-of-2 byte-width IntegerType ?
bool isPowerOf2ByteWidth() const;

/// Methods for support type inquiry through isa, cast, and dyn_cast.
static bool classof(const Type *T) {
  return T->getTypeID() == IntegerTyID;
}
95};

97unsigned Type::getIntegerBitWidth() const {
return cast<IntegerType>(this)->getBitWidth();
99}

101/// Class to represent function types
102///
103class FunctionType : public Type {
FunctionType(Type *Result, ArrayRef<Type*> Params, bool IsVarArgs);

106public:
FunctionType(const FunctionType &) = delete;
FunctionType &operator=(const FunctionType &) = delete;

/// This static method is the primary way of constructing a FunctionType.
static FunctionType *get(Type *Result,
                         ArrayRef<Type*> Params, bool isVarArg);

/// Create a FunctionType taking no parameters.
static FunctionType *get(Type *Result, bool isVarArg);

/// Return true if the specified type is valid as a return type.
static bool isValidReturnType(Type *RetTy);

/// Return true if the specified type is valid as an argument type.
static bool isValidArgumentType(Type *ArgTy);

bool isVarArg() const { return getSubclassData()!=0; }
Type *getReturnType() const { return ContainedTys[0]; }

using param_iterator = Type::subtype_iterator;

param_iterator param_begin() const { return ContainedTys + 1; }
param_iterator param_end() const { return &ContainedTys[NumContainedTys]; }
ArrayRef<Type *> params() const {
  return makeArrayRef(param_begin(), param_end());
}

/// Parameter type accessors.
Type *getParamType(unsigned i) const { return ContainedTys[i+1]; }

/// Return the number of fixed parameters this function type requires.
/// This does not consider varargs.
unsigned getNumParams() const { return NumContainedTys - 1; }

/// Methods for support type inquiry through isa, cast, and dyn_cast.
static bool classof(const Type *T) {
  return T->getTypeID() == FunctionTyID;
}
145};
146static_assert(alignof(FunctionType) >= alignof(Type *),
            "Alignment sufficient for objects appended to FunctionType");

149bool Type::isFunctionVarArg() const {
return cast<FunctionType>(this)->isVarArg();
151}

153Type *Type::getFunctionParamType(unsigned i) const {
return cast<FunctionType>(this)->getParamType(i);
155}

157unsigned Type::getFunctionNumParams() const {
return cast<FunctionType>(this)->getNumParams();
159}

161/// Common super class of ArrayType, StructType and VectorType.
162class CompositeType : public Type {
163protected:
explicit CompositeType(LLVMContext &C, TypeID tid) : Type(C, tid) {}

166public:
/// Given an index value into the type, return the type of the element.
Type *getTypeAtIndex(const Value *V) const;
Type *getTypeAtIndex(unsigned Idx) const;
bool indexValid(const Value *V) const;
bool indexValid(unsigned Idx) const;

/// Methods for support type inquiry through isa, cast, and dyn_cast.
static bool classof(const Type *T) {
  return T->getTypeID() == ArrayTyID ||
         T->getTypeID() == StructTyID ||
         T->getTypeID() == VectorTyID;
}
179};

181/// Class to represent struct types. There are two different kinds of struct
182/// types: Literal structs and Identified structs.
183///
184/// Literal struct types (e.g. { i32, i32 }) are uniqued structurally, and must
185/// always have a body when created.  You can get one of these by using one of
186/// the StructType::get() forms.
187///
188/// Identified structs (e.g. %foo or %42) may optionally have a name and are not
189/// uniqued.  The names for identified structs are managed at the LLVMContext
190/// level, so there can only be a single identified struct with a given name in
191/// a particular LLVMContext.  Identified structs may also optionally be opaque
192/// (have no body specified).  You get one of these by using one of the
193/// StructType::create() forms.
194///
195/// Independent of what kind of struct you have, the body of a struct type are
196/// laid out in memory consequtively with the elements directly one after the
197/// other (if the struct is packed) or (if not packed) with padding between the
198/// elements as defined by DataLayout (which is required to match what the code
199/// generator for a target expects).
200///
201class StructType : public CompositeType {
StructType(LLVMContext &C) : CompositeType(C, StructTyID) {}

enum {
  /// This is the contents of the SubClassData field.
  SCDB_HasBody = 1,
  SCDB_Packed = 2,
  SCDB_IsLiteral = 4,
  SCDB_IsSized = 8
};

/// For a named struct that actually has a name, this is a pointer to the
/// symbol table entry (maintained by LLVMContext) for the struct.
/// This is null if the type is an literal struct or if it is a identified
/// type that has an empty name.
void *SymbolTableEntry = nullptr;

218public:
StructType(const StructType &) = delete;
StructType &operator=(const StructType &) = delete;

/// This creates an identified struct.
static StructType *create(LLVMContext &Context, StringRef Name);
static StructType *create(LLVMContext &Context);

static StructType *create(ArrayRef<Type *> Elements, StringRef Name,
                          bool isPacked = false);
static StructType *create(ArrayRef<Type *> Elements);
static StructType *create(LLVMContext &Context, ArrayRef<Type *> Elements,
                          StringRef Name, bool isPacked = false);
static StructType *create(LLVMContext &Context, ArrayRef<Type *> Elements);
template <class... Tys>
static typename std::enable_if<are_base_of<Type, Tys...>::value,
                               StructType *>::type
create(StringRef Name, Type *elt1, Tys *... elts) {
  assert(elt1 && "Cannot create a struct type with no elements with this")(static_cast <bool> (elt1 && "Cannot create a struct type with no elements with this"
) ? void (0) : __assert_fail ("elt1 && \"Cannot create a struct type with no elements with this\""
, "/build/llvm-toolchain-snapshot-7~svn324650/include/llvm/IR/DerivedTypes.h"
, 236, __extension__ __PRETTY_FUNCTION__));
  SmallVector<llvm::Type *, 8> StructFields({elt1, elts...});
  return create(StructFields, Name);
}

/// This static method is the primary way to create a literal StructType.
static StructType *get(LLVMContext &Context, ArrayRef<Type*> Elements,
                       bool isPacked = false);

/// Create an empty structure type.
static StructType *get(LLVMContext &Context, bool isPacked = false);

/// This static method is a convenience method for creating structure types by
/// specifying the elements as arguments. Note that this method always returns
/// a non-packed struct, and requires at least one element type.
template <class... Tys>
static typename std::enable_if<are_base_of<Type, Tys...>::value,
                               StructType *>::type
get(Type *elt1, Tys *... elts) {
  assert(elt1 && "Cannot create a struct type with no elements with this")(static_cast <bool> (elt1 && "Cannot create a struct type with no elements with this"
) ? void (0) : __assert_fail ("elt1 && \"Cannot create a struct type with no elements with this\""
, "/build/llvm-toolchain-snapshot-7~svn324650/include/llvm/IR/DerivedTypes.h"
, 255, __extension__ __PRETTY_FUNCTION__));
  LLVMContext &Ctx = elt1->getContext();
  SmallVector<llvm::Type *, 8> StructFields({elt1, elts...});
  return llvm::StructType::get(Ctx, StructFields);
}

bool isPacked() const { return (getSubclassData() & SCDB_Packed) != 0; }

/// Return true if this type is uniqued by structural equivalence, false if it
/// is a struct definition.
bool isLiteral() const { return (getSubclassData() & SCDB_IsLiteral) != 0; }

/// Return true if this is a type with an identity that has no body specified
/// yet. These prints as 'opaque' in .ll files.
bool isOpaque() const { return (getSubclassData() & SCDB_HasBody) == 0; }

/// isSized - Return true if this is a sized type.
bool isSized(SmallPtrSetImpl<Type *> *Visited = nullptr) const;

/// Return true if this is a named struct that has a non-empty name.
bool hasName() const { return SymbolTableEntry != nullptr; }

/// Return the name for this struct type if it has an identity.
/// This may return an empty string for an unnamed struct type.  Do not call
/// this on an literal type.
StringRef getName() const;

/// Change the name of this type to the specified name, or to a name with a
/// suffix if there is a collision. Do not call this on an literal type.
void setName(StringRef Name);

/// Specify a body for an opaque identified type.
void setBody(ArrayRef<Type*> Elements, bool isPacked = false);

template <typename... Tys>
typename std::enable_if<are_base_of<Type, Tys...>::value, void>::type
setBody(Type *elt1, Tys *... elts) {
  assert(elt1 && "Cannot create a struct type with no elements with this")(static_cast <bool> (elt1 && "Cannot create a struct type with no elements with this"
) ? void (0) : __assert_fail ("elt1 && \"Cannot create a struct type with no elements with this\""
, "/build/llvm-toolchain-snapshot-7~svn324650/include/llvm/IR/DerivedTypes.h"
, 292, __extension__ __PRETTY_FUNCTION__));
  SmallVector<llvm::Type *, 8> StructFields({elt1, elts...});
  setBody(StructFields);
}

/// Return true if the specified type is valid as a element type.
static bool isValidElementType(Type *ElemTy);

// Iterator access to the elements.
using element_iterator = Type::subtype_iterator;

element_iterator element_begin() const { return ContainedTys; }
element_iterator element_end() const { return &ContainedTys[NumContainedTys];}
ArrayRef<Type *> const elements() const {
  return makeArrayRef(element_begin(), element_end());
}

/// Return true if this is layout identical to the specified struct.
bool isLayoutIdentical(StructType *Other) const;

/// Random access to the elements
unsigned getNumElements() const { return NumContainedTys; }
Type *getElementType(unsigned N) const {
  assert(N < NumContainedTys && "Element number out of range!")(static_cast <bool> (N < NumContainedTys && "Element number out of range!"
) ? void (0) : __assert_fail ("N < NumContainedTys && \"Element number out of range!\""
, "/build/llvm-toolchain-snapshot-7~svn324650/include/llvm/IR/DerivedTypes.h"
, 315, __extension__ __PRETTY_FUNCTION__));
  return ContainedTys[N];
}

/// Methods for support type inquiry through isa, cast, and dyn_cast.
static bool classof(const Type *T) {
  return T->getTypeID() == StructTyID;
}
323};

325StringRef Type::getStructName() const {
return cast<StructType>(this)->getName();
327}

329unsigned Type::getStructNumElements() const {
return cast<StructType>(this)->getNumElements();
331}

333Type *Type::getStructElementType(unsigned N) const {
return cast<StructType>(this)->getElementType(N);
335}

337/// This is the superclass of the array and vector type classes. Both of these
338/// represent "arrays" in memory. The array type represents a specifically sized
339/// array, and the vector type represents a specifically sized array that allows
340/// for use of SIMD instructions. SequentialType holds the common features of
341/// both, which stem from the fact that both lay their components out in memory
342/// identically.
343class SequentialType : public CompositeType {
Type *ContainedType;               ///< Storage for the single contained type.
uint64_t NumElements;

347protected:
SequentialType(TypeID TID, Type *ElType, uint64_t NumElements)
  : CompositeType(ElType->getContext(), TID), ContainedType(ElType),
    NumElements(NumElements) {
  ContainedTys = &ContainedType;
  NumContainedTys = 1;
}

355public:
SequentialType(const SequentialType &) = delete;
SequentialType &operator=(const SequentialType &) = delete;

uint64_t getNumElements() const { return NumElements; }
Type *getElementType() const { return ContainedType; }

/// Methods for support type inquiry through isa, cast, and dyn_cast.
static bool classof(const Type *T) {
  return T->getTypeID() == ArrayTyID || T->getTypeID() == VectorTyID;
}
366};

368/// Class to represent array types.
369class ArrayType : public SequentialType {
ArrayType(Type *ElType, uint64_t NumEl);

372public:
ArrayType(const ArrayType &) = delete;
ArrayType &operator=(const ArrayType &) = delete;

/// This static method is the primary way to construct an ArrayType
static ArrayType *get(Type *ElementType, uint64_t NumElements);

/// Return true if the specified type is valid as a element type.
static bool isValidElementType(Type *ElemTy);

/// Methods for support type inquiry through isa, cast, and dyn_cast.
static bool classof(const Type *T) {
  return T->getTypeID() == ArrayTyID;
}
386};

388uint64_t Type::getArrayNumElements() const {
return cast<ArrayType>(this)->getNumElements();
390}

392/// Class to represent vector types.
393class VectorType : public SequentialType {
VectorType(Type *ElType, unsigned NumEl);

396public:
VectorType(const VectorType &) = delete;
VectorType &operator=(const VectorType &) = delete;

/// This static method is the primary way to construct an VectorType.
static VectorType *get(Type *ElementType, unsigned NumElements);

/// This static method gets a VectorType with the same number of elements as
/// the input type, and the element type is an integer type of the same width
/// as the input element type.
static VectorType *getInteger(VectorType *VTy) {
  unsigned EltBits = VTy->getElementType()->getPrimitiveSizeInBits();
  assert(EltBits && "Element size must be of a non-zero size")(static_cast <bool> (EltBits && "Element size must be of a non-zero size"
) ? void (0) : __assert_fail ("EltBits && \"Element size must be of a non-zero size\""
, "/build/llvm-toolchain-snapshot-7~svn324650/include/llvm/IR/DerivedTypes.h"
, 408, __extension__ __PRETTY_FUNCTION__));
  Type *EltTy = IntegerType::get(VTy->getContext(), EltBits);
  return VectorType::get(EltTy, VTy->getNumElements());
}

/// This static method is like getInteger except that the element types are
/// twice as wide as the elements in the input type.
static VectorType *getExtendedElementVectorType(VectorType *VTy) {
  unsigned EltBits = VTy->getElementType()->getPrimitiveSizeInBits();
  Type *EltTy = IntegerType::get(VTy->getContext(), EltBits * 2);
  return VectorType::get(EltTy, VTy->getNumElements());
}

/// This static method is like getInteger except that the element types are
/// half as wide as the elements in the input type.
static VectorType *getTruncatedElementVectorType(VectorType *VTy) {
  unsigned EltBits = VTy->getElementType()->getPrimitiveSizeInBits();
  assert((EltBits & 1) == 0 &&(static_cast <bool> ((EltBits & 1) == 0 && "Cannot truncate vector element with odd bit-width"
) ? void (0) : __assert_fail ("(EltBits & 1) == 0 && \"Cannot truncate vector element with odd bit-width\""
, "/build/llvm-toolchain-snapshot-7~svn324650/include/llvm/IR/DerivedTypes.h"
, 426, __extension__ __PRETTY_FUNCTION__))
         "Cannot truncate vector element with odd bit-width")(static_cast <bool> ((EltBits & 1) == 0 && "Cannot truncate vector element with odd bit-width"
) ? void (0) : __assert_fail ("(EltBits & 1) == 0 && \"Cannot truncate vector element with odd bit-width\""
, "/build/llvm-toolchain-snapshot-7~svn324650/include/llvm/IR/DerivedTypes.h"
, 426, __extension__ __PRETTY_FUNCTION__));
  Type *EltTy = IntegerType::get(VTy->getContext(), EltBits / 2);
  return VectorType::get(EltTy, VTy->getNumElements());
}

/// This static method returns a VectorType with half as many elements as the
/// input type and the same element type.
static VectorType *getHalfElementsVectorType(VectorType *VTy) {
  unsigned NumElts = VTy->getNumElements();
  assert ((NumElts & 1) == 0 &&(static_cast <bool> ((NumElts & 1) == 0 && "Cannot halve vector with odd number of elements."
) ? void (0) : __assert_fail ("(NumElts & 1) == 0 && \"Cannot halve vector with odd number of elements.\""
, "/build/llvm-toolchain-snapshot-7~svn324650/include/llvm/IR/DerivedTypes.h"
, 436, __extension__ __PRETTY_FUNCTION__))
          "Cannot halve vector with odd number of elements.")(static_cast <bool> ((NumElts & 1) == 0 && "Cannot halve vector with odd number of elements."
) ? void (0) : __assert_fail ("(NumElts & 1) == 0 && \"Cannot halve vector with odd number of elements.\""
, "/build/llvm-toolchain-snapshot-7~svn324650/include/llvm/IR/DerivedTypes.h"
, 436, __extension__ __PRETTY_FUNCTION__));
  return VectorType::get(VTy->getElementType(), NumElts/2);
}

/// This static method returns a VectorType with twice as many elements as the
/// input type and the same element type.
static VectorType *getDoubleElementsVectorType(VectorType *VTy) {
  unsigned NumElts = VTy->getNumElements();
  return VectorType::get(VTy->getElementType(), NumElts*2);
}

/// Return true if the specified type is valid as a element type.
static bool isValidElementType(Type *ElemTy);

/// Return the number of bits in the Vector type.
/// Returns zero when the vector is a vector of pointers.
unsigned getBitWidth() const {
  return getNumElements() * getElementType()->getPrimitiveSizeInBits();
}

/// Methods for support type inquiry through isa, cast, and dyn_cast.
static bool classof(const Type *T) {
  return T->getTypeID() == VectorTyID;
15
←
Calling 'Type::getTypeID'→
16
←
Returning from 'Type::getTypeID'→
17
←
Assuming the condition is true→
}
460};

462unsigned Type::getVectorNumElements() const {
return cast<VectorType>(this)->getNumElements();
3
←
Calling 'cast'→
25
←
Returning from 'cast'→
26
←
Calling 'SequentialType::getNumElements'→
27
←
Returning from 'SequentialType::getNumElements'→
464}

466/// Class to represent pointers.
467class PointerType : public Type {
explicit PointerType(Type *ElType, unsigned AddrSpace);

Type *PointeeTy;

472public:
PointerType(const PointerType &) = delete;
PointerType &operator=(const PointerType &) = delete;

/// This constructs a pointer to an object of the specified type in a numbered
/// address space.
static PointerType *get(Type *ElementType, unsigned AddressSpace);

/// This constructs a pointer to an object of the specified type in the
/// generic address space (address space zero).
static PointerType *getUnqual(Type *ElementType) {
  return PointerType::get(ElementType, 0);
}

Type *getElementType() const { return PointeeTy; }

/// Return true if the specified type is valid as a element type.
static bool isValidElementType(Type *ElemTy);

/// Return true if we can load or store from a pointer to this type.
static bool isLoadableOrStorableType(Type *ElemTy);

/// Return the address space of the Pointer type.
inline unsigned getAddressSpace() const { return getSubclassData(); }

/// Implement support type inquiry through isa, cast, and dyn_cast.
static bool classof(const Type *T) {
  return T->getTypeID() == PointerTyID;
}
501};

503unsigned Type::getPointerAddressSpace() const {
return cast<PointerType>(getScalarType())->getAddressSpace();
505}

507} // end namespace llvm

509#endif // LLVM_IR_DERIVEDTYPES_H

←

/build/llvm-toolchain-snapshot-7~svn324650/include/llvm/Support/Casting.h

1//===- llvm/Support/Casting.h - Allow flexible, checked, casts --*- C++ -*-===//
2//
3//                     The LLVM Compiler Infrastructure
4//
5// This file is distributed under the University of Illinois Open Source
6// License. See LICENSE.TXT for details.
7//
8//===----------------------------------------------------------------------===//
9//
10// This file defines the isa<X>(), cast<X>(), dyn_cast<X>(), cast_or_null<X>(),
11// and dyn_cast_or_null<X>() templates.
12//
13//===----------------------------------------------------------------------===//
14 
15#ifndef LLVM_SUPPORT_CASTING_H
16#define LLVM_SUPPORT_CASTING_H
17 
18#include "llvm/Support/Compiler.h"
19#include "llvm/Support/type_traits.h"
20#include <cassert>
21#include <memory>
22#include <type_traits>
23 
24namespace llvm {
25 
26//===----------------------------------------------------------------------===//
27//                          isa<x> Support Templates
28//===----------------------------------------------------------------------===//
29 
30// Define a template that can be specialized by smart pointers to reflect the
31// fact that they are automatically dereferenced, and are not involved with the
32// template selection process...  the default implementation is a noop.
33//
34template<typename From> struct simplify_type {
35  using SimpleType = From; // The real type this represents...
36 
37  // An accessor to get the real value...
38  static SimpleType &getSimplifiedValue(From &Val) { return Val; }
39};
40 
41template<typename From> struct simplify_type<const From> {
42  using NonConstSimpleType = typename simplify_type<From>::SimpleType;
43  using SimpleType =
44      typename add_const_past_pointer<NonConstSimpleType>::type;
45  using RetType =
46      typename add_lvalue_reference_if_not_pointer<SimpleType>::type;
47 
48  static RetType getSimplifiedValue(const From& Val) {
49    return simplify_type<From>::getSimplifiedValue(const_cast<From&>(Val));
7
←
Calling 'simplify_type::getSimplifiedValue'→
8
←
Returning from 'simplify_type::getSimplifiedValue'→
50  }
51};
52 
53// The core of the implementation of isa<X> is here; To and From should be
54// the names of classes.  This template can be specialized to customize the
55// implementation of isa<> without rewriting it from scratch.
56template <typename To, typename From, typename Enabler = void>
57struct isa_impl {
58  static inline bool doit(const From &Val) {
59    return To::classof(&Val);
14
←
Calling 'VectorType::classof'→
18
←
Returning from 'VectorType::classof'→
60  }
61};
62 
63/// \brief Always allow upcasts, and perform no dynamic check for them.
64template <typename To, typename From>
65struct isa_impl<
66    To, From, typename std::enable_if<std::is_base_of<To, From>::value>::type> {
67  static inline bool doit(const From &) { return true; }
68};
69 
70template <typename To, typename From> struct isa_impl_cl {
71  static inline bool doit(const From &Val) {
72    return isa_impl<To, From>::doit(Val);
73  }
74};
75 
76template <typename To, typename From> struct isa_impl_cl<To, const From> {
77  static inline bool doit(const From &Val) {
78    return isa_impl<To, From>::doit(Val);
79  }
80};
81 
82template <typename To, typename From>
83struct isa_impl_cl<To, const std::unique_ptr<From>> {
84  static inline bool doit(const std::unique_ptr<From> &Val) {
85    assert(Val && "isa<> used on a null pointer")(static_cast <bool> (Val && "isa<> used on a null pointer"
) ? void (0) : __assert_fail ("Val && \"isa<> used on a null pointer\""
, "/build/llvm-toolchain-snapshot-7~svn324650/include/llvm/Support/Casting.h"
, 85, __extension__ __PRETTY_FUNCTION__));
86    return isa_impl_cl<To, From>::doit(*Val);
87  }
88};
89 
90template <typename To, typename From> struct isa_impl_cl<To, From*> {
91  static inline bool doit(const From *Val) {
92    assert(Val && "isa<> used on a null pointer")(static_cast <bool> (Val && "isa<> used on a null pointer"
) ? void (0) : __assert_fail ("Val && \"isa<> used on a null pointer\""
, "/build/llvm-toolchain-snapshot-7~svn324650/include/llvm/Support/Casting.h"
, 92, __extension__ __PRETTY_FUNCTION__));
93    return isa_impl<To, From>::doit(*Val);
94  }
95};
96 
97template <typename To, typename From> struct isa_impl_cl<To, From*const> {
98  static inline bool doit(const From *Val) {
99    assert(Val && "isa<> used on a null pointer")(static_cast <bool> (Val && "isa<> used on a null pointer"
) ? void (0) : __assert_fail ("Val && \"isa<> used on a null pointer\""
, "/build/llvm-toolchain-snapshot-7~svn324650/include/llvm/Support/Casting.h"
, 99, __extension__ __PRETTY_FUNCTION__));
100    return isa_impl<To, From>::doit(*Val);
101  }
102};
103 
104template <typename To, typename From> struct isa_impl_cl<To, const From*> {
105  static inline bool doit(const From *Val) {
106    assert(Val && "isa<> used on a null pointer")(static_cast <bool> (Val && "isa<> used on a null pointer"
) ? void (0) : __assert_fail ("Val && \"isa<> used on a null pointer\""
, "/build/llvm-toolchain-snapshot-7~svn324650/include/llvm/Support/Casting.h"
, 106, __extension__ __PRETTY_FUNCTION__));
12
←
Within the expansion of the macro 'assert':
→
107    return isa_impl<To, From>::doit(*Val);
13
←
Calling 'isa_impl::doit'→
19
←
Returning from 'isa_impl::doit'→
108  }
109};
110 
111template <typename To, typename From> struct isa_impl_cl<To, const From*const> {
112  static inline bool doit(const From *Val) {
113    assert(Val && "isa<> used on a null pointer")(static_cast <bool> (Val && "isa<> used on a null pointer"
) ? void (0) : __assert_fail ("Val && \"isa<> used on a null pointer\""
, "/build/llvm-toolchain-snapshot-7~svn324650/include/llvm/Support/Casting.h"
, 113, __extension__ __PRETTY_FUNCTION__));
114    return isa_impl<To, From>::doit(*Val);
115  }
116};
117 
118template<typename To, typename From, typename SimpleFrom>
119struct isa_impl_wrap {
120  // When From != SimplifiedType, we can simplify the type some more by using
121  // the simplify_type template.
122  static bool doit(const From &Val) {
123    return isa_impl_wrap<To, SimpleFrom,
10
←
Calling 'isa_impl_wrap::doit'→
21
←
Returning from 'isa_impl_wrap::doit'→
124      typename simplify_type<SimpleFrom>::SimpleType>::doit(
125                          simplify_type<const From>::getSimplifiedValue(Val));
6
←
Calling 'simplify_type::getSimplifiedValue'→
9
←
Returning from 'simplify_type::getSimplifiedValue'→
126  }
127};
128 
129template<typename To, typename FromTy>
130struct isa_impl_wrap<To, FromTy, FromTy> {
131  // When From == SimpleType, we are as simple as we are going to get.
132  static bool doit(const FromTy &Val) {
133    return isa_impl_cl<To,FromTy>::doit(Val);
11
←
Calling 'isa_impl_cl::doit'→
20
←
Returning from 'isa_impl_cl::doit'→
134  }
135};
136 
137// isa<X> - Return true if the parameter to the template is an instance of the
138// template type argument.  Used like this:
139//
140//  if (isa<Type>(myVal)) { ... }
141//
142template <class X, class Y> LLVM_NODISCARD[[clang::warn_unused_result]] inline bool isa(const Y &Val) {
143  return isa_impl_wrap<X, const Y,
5
←
Calling 'isa_impl_wrap::doit'→
22
←
Returning from 'isa_impl_wrap::doit'→
144                       typename simplify_type<const Y>::SimpleType>::doit(Val);
145}
146 
147//===----------------------------------------------------------------------===//
148//                          cast<x> Support Templates
149//===----------------------------------------------------------------------===//
150 
151template<class To, class From> struct cast_retty;
152 
153// Calculate what type the 'cast' function should return, based on a requested
154// type of To and a source type of From.
155template<class To, class From> struct cast_retty_impl {
156  using ret_type = To &;       // Normal case, return Ty&
157};
158template<class To, class From> struct cast_retty_impl<To, const From> {
159  using ret_type = const To &; // Normal case, return Ty&
160};
161 
162template<class To, class From> struct cast_retty_impl<To, From*> {
163  using ret_type = To *;       // Pointer arg case, return Ty*
164};
165 
166template<class To, class From> struct cast_retty_impl<To, const From*> {
167  using ret_type = const To *; // Constant pointer arg case, return const Ty*
168};
169 
170template<class To, class From> struct cast_retty_impl<To, const From*const> {
171  using ret_type = const To *; // Constant pointer arg case, return const Ty*
172};
173 
174template <class To, class From>
175struct cast_retty_impl<To, std::unique_ptr<From>> {
176private:
177  using PointerType = typename cast_retty_impl<To, From *>::ret_type;
178  using ResultType = typename std::remove_pointer<PointerType>::type;
179 
180public:
181  using ret_type = std::unique_ptr<ResultType>;
182};
183 
184template<class To, class From, class SimpleFrom>
185struct cast_retty_wrap {
186  // When the simplified type and the from type are not the same, use the type
187  // simplifier to reduce the type, then reuse cast_retty_impl to get the
188  // resultant type.
189  using ret_type = typename cast_retty<To, SimpleFrom>::ret_type;
190};
191 
192template<class To, class FromTy>
193struct cast_retty_wrap<To, FromTy, FromTy> {
194  // When the simplified type is equal to the from type, use it directly.
195  using ret_type = typename cast_retty_impl<To,FromTy>::ret_type;
196};
197 
198template<class To, class From>
199struct cast_retty {
200  using ret_type = typename cast_retty_wrap<
201      To, From, typename simplify_type<From>::SimpleType>::ret_type;
202};
203 
204// Ensure the non-simple values are converted using the simplify_type template
205// that may be specialized by smart pointers...
206//
207template<class To, class From, class SimpleFrom> struct cast_convert_val {
208  // This is not a simple type, use the template to simplify it...
209  static typename cast_retty<To, From>::ret_type doit(From &Val) {
210    return cast_convert_val<To, SimpleFrom,
211      typename simplify_type<SimpleFrom>::SimpleType>::doit(
212                          simplify_type<From>::getSimplifiedValue(Val));
213  }
214};
215 
216template<class To, class FromTy> struct cast_convert_val<To,FromTy,FromTy> {
217  // This _is_ a simple type, just cast it.
218  static typename cast_retty<To, FromTy>::ret_type doit(const FromTy &Val) {
219    typename cast_retty<To, FromTy>::ret_type Res2
220     = (typename cast_retty<To, FromTy>::ret_type)const_cast<FromTy&>(Val);
221    return Res2;
222  }
223};
224 
225template <class X> struct is_simple_type {
226  static const bool value =
227      std::is_same<X, typename simplify_type<X>::SimpleType>::value;
228};
229 
230// cast<X> - Return the argument parameter cast to the specified type.  This
231// casting operator asserts that the type is correct, so it does not return null
232// on failure.  It does not allow a null argument (use cast_or_null for that).
233// It is typically used like this:
234//
235//  cast<Instruction>(myVal)->getParent()
236//
237template <class X, class Y>
238inline typename std::enable_if<!is_simple_type<Y>::value,
239                               typename cast_retty<X, const Y>::ret_type>::type
240cast(const Y &Val) {
241  assert(isa<X>(Val) && "cast<Ty>() argument of incompatible type!")(static_cast <bool> (isa<X>(Val) && "cast<Ty>() argument of incompatible type!"
) ? void (0) : __assert_fail ("isa<X>(Val) && \"cast<Ty>() argument of incompatible type!\""
, "/build/llvm-toolchain-snapshot-7~svn324650/include/llvm/Support/Casting.h"
, 241, __extension__ __PRETTY_FUNCTION__));
242  return cast_convert_val<
243      X, const Y, typename simplify_type<const Y>::SimpleType>::doit(Val);
244}
245 
246template <class X, class Y>
247inline typename cast_retty<X, Y>::ret_type cast(Y &Val) {
248  assert(isa<X>(Val) && "cast<Ty>() argument of incompatible type!")(static_cast <bool> (isa<X>(Val) && "cast<Ty>() argument of incompatible type!"
) ? void (0) : __assert_fail ("isa<X>(Val) && \"cast<Ty>() argument of incompatible type!\""
, "/build/llvm-toolchain-snapshot-7~svn324650/include/llvm/Support/Casting.h"
, 248, __extension__ __PRETTY_FUNCTION__));
249  return cast_convert_val<X, Y,
250                          typename simplify_type<Y>::SimpleType>::doit(Val);
251}
252 
253template <class X, class Y>
254inline typename cast_retty<X, Y *>::ret_type cast(Y *Val) {
255  assert(isa<X>(Val) && "cast<Ty>() argument of incompatible type!")(static_cast <bool> (isa<X>(Val) && "cast<Ty>() argument of incompatible type!"
) ? void (0) : __assert_fail ("isa<X>(Val) && \"cast<Ty>() argument of incompatible type!\""
, "/build/llvm-toolchain-snapshot-7~svn324650/include/llvm/Support/Casting.h"
, 255, __extension__ __PRETTY_FUNCTION__));
4
←
Within the expansion of the macro 'assert':
→
a
Calling 'isa'
b
Returning from 'isa'
256  return cast_convert_val<X, Y*,
23
←
Calling 'cast_convert_val::doit'→
24
←
Returning from 'cast_convert_val::doit'→
257                          typename simplify_type<Y*>::SimpleType>::doit(Val);
258}
259 
260template <class X, class Y>
261inline typename cast_retty<X, std::unique_ptr<Y>>::ret_type
262cast(std::unique_ptr<Y> &&Val) {
263  assert(isa<X>(Val.get()) && "cast<Ty>() argument of incompatible type!")(static_cast <bool> (isa<X>(Val.get()) &&
 "cast<Ty>() argument of incompatible type!") ? void (0
) : __assert_fail ("isa<X>(Val.get()) && \"cast<Ty>() argument of incompatible type!\""
, "/build/llvm-toolchain-snapshot-7~svn324650/include/llvm/Support/Casting.h"
, 263, __extension__ __PRETTY_FUNCTION__));
264  using ret_type = typename cast_retty<X, std::unique_ptr<Y>>::ret_type;
265  return ret_type(
266      cast_convert_val<X, Y *, typename simplify_type<Y *>::SimpleType>::doit(
267          Val.release()));
268}
269 
270// cast_or_null<X> - Functionally identical to cast, except that a null value is
271// accepted.
272//
273template <class X, class Y>
274LLVM_NODISCARD[[clang::warn_unused_result]] inline
275    typename std::enable_if<!is_simple_type<Y>::value,
276                            typename cast_retty<X, const Y>::ret_type>::type
277    cast_or_null(const Y &Val) {
278  if (!Val)
279    return nullptr;
280  assert(isa<X>(Val) && "cast_or_null<Ty>() argument of incompatible type!")(static_cast <bool> (isa<X>(Val) && "cast_or_null<Ty>() argument of incompatible type!"
) ? void (0) : __assert_fail ("isa<X>(Val) && \"cast_or_null<Ty>() argument of incompatible type!\""
, "/build/llvm-toolchain-snapshot-7~svn324650/include/llvm/Support/Casting.h"
, 280, __extension__ __PRETTY_FUNCTION__));
281  return cast<X>(Val);
282}
283 
284template <class X, class Y>
285LLVM_NODISCARD[[clang::warn_unused_result]] inline
286    typename std::enable_if<!is_simple_type<Y>::value,
287                            typename cast_retty<X, Y>::ret_type>::type
288    cast_or_null(Y &Val) {
289  if (!Val)
290    return nullptr;
291  assert(isa<X>(Val) && "cast_or_null<Ty>() argument of incompatible type!")(static_cast <bool> (isa<X>(Val) && "cast_or_null<Ty>() argument of incompatible type!"
) ? void (0) : __assert_fail ("isa<X>(Val) && \"cast_or_null<Ty>() argument of incompatible type!\""
, "/build/llvm-toolchain-snapshot-7~svn324650/include/llvm/Support/Casting.h"
, 291, __extension__ __PRETTY_FUNCTION__));
292  return cast<X>(Val);
293}
294 
295template <class X, class Y>
296LLVM_NODISCARD[[clang::warn_unused_result]] inline typename cast_retty<X, Y *>::ret_type
297cast_or_null(Y *Val) {
298  if (!Val) return nullptr;
299  assert(isa<X>(Val) && "cast_or_null<Ty>() argument of incompatible type!")(static_cast <bool> (isa<X>(Val) && "cast_or_null<Ty>() argument of incompatible type!"
) ? void (0) : __assert_fail ("isa<X>(Val) && \"cast_or_null<Ty>() argument of incompatible type!\""
, "/build/llvm-toolchain-snapshot-7~svn324650/include/llvm/Support/Casting.h"
, 299, __extension__ __PRETTY_FUNCTION__));
300  return cast<X>(Val);
301}
302 
303template <class X, class Y>
304inline typename cast_retty<X, std::unique_ptr<Y>>::ret_type
305cast_or_null(std::unique_ptr<Y> &&Val) {
306  if (!Val)
307    return nullptr;
308  return cast<X>(std::move(Val));
309}
310 
311// dyn_cast<X> - Return the argument parameter cast to the specified type.  This
312// casting operator returns null if the argument is of the wrong type, so it can
313// be used to test for a type as well as cast if successful.  This should be
314// used in the context of an if statement like this:
315//
316//  if (const Instruction *I = dyn_cast<Instruction>(myVal)) { ... }
317//
318 
319template <class X, class Y>
320LLVM_NODISCARD[[clang::warn_unused_result]] inline
321    typename std::enable_if<!is_simple_type<Y>::value,
322                            typename cast_retty<X, const Y>::ret_type>::type
323    dyn_cast(const Y &Val) {
324  return isa<X>(Val) ? cast<X>(Val) : nullptr;
325}
326 
327template <class X, class Y>
328LLVM_NODISCARD[[clang::warn_unused_result]] inline typename cast_retty<X, Y>::ret_type dyn_cast(Y &Val) {
329  return isa<X>(Val) ? cast<X>(Val) : nullptr;
330}
331 
332template <class X, class Y>
333LLVM_NODISCARD[[clang::warn_unused_result]] inline typename cast_retty<X, Y *>::ret_type dyn_cast(Y *Val) {
334  return isa<X>(Val) ? cast<X>(Val) : nullptr;
335}
336 
337// dyn_cast_or_null<X> - Functionally identical to dyn_cast, except that a null
338// value is accepted.
339//
340template <class X, class Y>
341LLVM_NODISCARD[[clang::warn_unused_result]] inline
342    typename std::enable_if<!is_simple_type<Y>::value,
343                            typename cast_retty<X, const Y>::ret_type>::type
344    dyn_cast_or_null(const Y &Val) {
345  return (Val && isa<X>(Val)) ? cast<X>(Val) : nullptr;
346}
347 
348template <class X, class Y>
349LLVM_NODISCARD[[clang::warn_unused_result]] inline
350    typename std::enable_if<!is_simple_type<Y>::value,
351                            typename cast_retty<X, Y>::ret_type>::type
352    dyn_cast_or_null(Y &Val) {
353  return (Val && isa<X>(Val)) ? cast<X>(Val) : nullptr;
354}
355 
356template <class X, class Y>
357LLVM_NODISCARD[[clang::warn_unused_result]] inline typename cast_retty<X, Y *>::ret_type
358dyn_cast_or_null(Y *Val) {
359  return (Val && isa<X>(Val)) ? cast<X>(Val) : nullptr;
360}
361 
362// unique_dyn_cast<X> - Given a unique_ptr<Y>, try to return a unique_ptr<X>,
363// taking ownership of the input pointer iff isa<X>(Val) is true.  If the
364// cast is successful, From refers to nullptr on exit and the casted value
365// is returned.  If the cast is unsuccessful, the function returns nullptr
366// and From is unchanged.
367template <class X, class Y>
368LLVM_NODISCARD[[clang::warn_unused_result]] inline auto unique_dyn_cast(std::unique_ptr<Y> &Val)
369    -> decltype(cast<X>(Val)) {
370  if (!isa<X>(Val))
371    return nullptr;
372  return cast<X>(std::move(Val));
373}
374 
375template <class X, class Y>
376LLVM_NODISCARD[[clang::warn_unused_result]] inline auto unique_dyn_cast(std::unique_ptr<Y> &&Val)
377    -> decltype(cast<X>(Val)) {
378  return unique_dyn_cast<X, Y>(Val);
379}
380 
381// dyn_cast_or_null<X> - Functionally identical to unique_dyn_cast, except that
382// a null value is accepted.
383template <class X, class Y>
384LLVM_NODISCARD[[clang::warn_unused_result]] inline auto unique_dyn_cast_or_null(std::unique_ptr<Y> &Val)
385    -> decltype(cast<X>(Val)) {
386  if (!Val)
387    return nullptr;
388  return unique_dyn_cast<X, Y>(Val);
389}
390 
391template <class X, class Y>
392LLVM_NODISCARD[[clang::warn_unused_result]] inline auto unique_dyn_cast_or_null(std::unique_ptr<Y> &&Val)
393    -> decltype(cast<X>(Val)) {
394  return unique_dyn_cast_or_null<X, Y>(Val);
395}
396 
397} // end namespace llvm
398 
399#endif // LLVM_SUPPORT_CASTING_H