/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp

Bug Summary

File:	llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
Warning:	line 6707, column 49 Called C++ object pointer is null

Annotated Source Code

Press '?' to see keyboard shortcuts

Show analyzer invocation

clang -cc1 -cc1 -triple x86_64-pc-linux-gnu -analyze -disable-free -disable-llvm-verifier -discard-value-names -main-file-name SLPVectorizer.cpp -analyzer-store=region -analyzer-opt-analyze-nested-blocks -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 -setup-static-analyzer -analyzer-config-compatibility-mode=true -mrelocation-model pic -pic-level 2 -fhalf-no-semantic-interposition -mframe-pointer=none -fmath-errno -fno-rounding-math -mconstructor-aliases -munwind-tables -target-cpu x86-64 -tune-cpu generic -debugger-tuning=gdb -ffunction-sections -fdata-sections -fcoverage-compilation-dir=/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/build-llvm/lib/Transforms/Vectorize -resource-dir /usr/lib/llvm-13/lib/clang/13.0.0 -D _DEBUG -D _GNU_SOURCE -D __STDC_CONSTANT_MACROS -D __STDC_FORMAT_MACROS -D __STDC_LIMIT_MACROS -I /build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/build-llvm/lib/Transforms/Vectorize -I /build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize -I /build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/build-llvm/include -I /build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/include -U NDEBUG -internal-isystem /usr/lib/gcc/x86_64-linux-gnu/6.3.0/../../../../include/c++/6.3.0 -internal-isystem /usr/lib/gcc/x86_64-linux-gnu/6.3.0/../../../../include/x86_64-linux-gnu/c++/6.3.0 -internal-isystem /usr/lib/gcc/x86_64-linux-gnu/6.3.0/../../../../include/c++/6.3.0/backward -internal-isystem /usr/lib/llvm-13/lib/clang/13.0.0/include -internal-isystem /usr/local/include -internal-isystem /usr/lib/gcc/x86_64-linux-gnu/6.3.0/../../../../x86_64-linux-gnu/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++14 -fdeprecated-macro -fdebug-compilation-dir=/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/build-llvm/lib/Transforms/Vectorize -fdebug-prefix-map=/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f=. -ferror-limit 19 -fvisibility-inlines-hidden -stack-protector 2 -fgnuc-version=4.2.1 -vectorize-loops -vectorize-slp -analyzer-output=html -analyzer-config stable-report-filename=true -faddrsig -D__GCC_HAVE_DWARF2_CFI_ASM=1 -o /tmp/scan-build-2021-04-14-063029-18377-1 -x c++ /build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp

/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp

→

1//===- SLPVectorizer.cpp - A bottom up SLP Vectorizer ---------------------===//
2//
3// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
4// See https://llvm.org/LICENSE.txt for license information.
5// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
6//
7//===----------------------------------------------------------------------===//
8//
9// This pass implements the Bottom Up SLP vectorizer. It detects consecutive
10// stores that can be put together into vector-stores. Next, it attempts to
11// construct vectorizable tree using the use-def chains. If a profitable tree
12// was found, the SLP vectorizer performs vectorization on the tree.
13//
14// The pass is inspired by the work described in the paper:
15//  "Loop-Aware SLP in GCC" by Ira Rosen, Dorit Nuzman, Ayal Zaks.
16//
17//===----------------------------------------------------------------------===//

19#include "llvm/Transforms/Vectorize/SLPVectorizer.h"
20#include "llvm/ADT/DenseMap.h"
21#include "llvm/ADT/DenseSet.h"
22#include "llvm/ADT/Optional.h"
23#include "llvm/ADT/PostOrderIterator.h"
24#include "llvm/ADT/STLExtras.h"
25#include "llvm/ADT/SetVector.h"
26#include "llvm/ADT/SmallBitVector.h"
27#include "llvm/ADT/SmallPtrSet.h"
28#include "llvm/ADT/SmallSet.h"
29#include "llvm/ADT/SmallString.h"
30#include "llvm/ADT/Statistic.h"
31#include "llvm/ADT/iterator.h"
32#include "llvm/ADT/iterator_range.h"
33#include "llvm/Analysis/AliasAnalysis.h"
34#include "llvm/Analysis/AssumptionCache.h"
35#include "llvm/Analysis/CodeMetrics.h"
36#include "llvm/Analysis/DemandedBits.h"
37#include "llvm/Analysis/GlobalsModRef.h"
38#include "llvm/Analysis/IVDescriptors.h"
39#include "llvm/Analysis/LoopAccessAnalysis.h"
40#include "llvm/Analysis/LoopInfo.h"
41#include "llvm/Analysis/MemoryLocation.h"
42#include "llvm/Analysis/OptimizationRemarkEmitter.h"
43#include "llvm/Analysis/ScalarEvolution.h"
44#include "llvm/Analysis/ScalarEvolutionExpressions.h"
45#include "llvm/Analysis/TargetLibraryInfo.h"
46#include "llvm/Analysis/TargetTransformInfo.h"
47#include "llvm/Analysis/ValueTracking.h"
48#include "llvm/Analysis/VectorUtils.h"
49#include "llvm/IR/Attributes.h"
50#include "llvm/IR/BasicBlock.h"
51#include "llvm/IR/Constant.h"
52#include "llvm/IR/Constants.h"
53#include "llvm/IR/DataLayout.h"
54#include "llvm/IR/DebugLoc.h"
55#include "llvm/IR/DerivedTypes.h"
56#include "llvm/IR/Dominators.h"
57#include "llvm/IR/Function.h"
58#include "llvm/IR/IRBuilder.h"
59#include "llvm/IR/InstrTypes.h"
60#include "llvm/IR/Instruction.h"
61#include "llvm/IR/Instructions.h"
62#include "llvm/IR/IntrinsicInst.h"
63#include "llvm/IR/Intrinsics.h"
64#include "llvm/IR/Module.h"
65#include "llvm/IR/NoFolder.h"
66#include "llvm/IR/Operator.h"
67#include "llvm/IR/PatternMatch.h"
68#include "llvm/IR/Type.h"
69#include "llvm/IR/Use.h"
70#include "llvm/IR/User.h"
71#include "llvm/IR/Value.h"
72#include "llvm/IR/ValueHandle.h"
73#include "llvm/IR/Verifier.h"
74#include "llvm/InitializePasses.h"
75#include "llvm/Pass.h"
76#include "llvm/Support/Casting.h"
77#include "llvm/Support/CommandLine.h"
78#include "llvm/Support/Compiler.h"
79#include "llvm/Support/DOTGraphTraits.h"
80#include "llvm/Support/Debug.h"
81#include "llvm/Support/ErrorHandling.h"
82#include "llvm/Support/GraphWriter.h"
83#include "llvm/Support/InstructionCost.h"
84#include "llvm/Support/KnownBits.h"
85#include "llvm/Support/MathExtras.h"
86#include "llvm/Support/raw_ostream.h"
87#include "llvm/Transforms/Utils/InjectTLIMappings.h"
88#include "llvm/Transforms/Utils/LoopUtils.h"
89#include "llvm/Transforms/Vectorize.h"
90#include <algorithm>
91#include <cassert>
92#include <cstdint>
93#include <iterator>
94#include <memory>
95#include <set>
96#include <string>
97#include <tuple>
98#include <utility>
99#include <vector>

101using namespace llvm;
102using namespace llvm::PatternMatch;
103using namespace slpvectorizer;

105#define SV_NAME"slp-vectorizer" "slp-vectorizer"
106#define DEBUG_TYPE"SLP" "SLP"

108STATISTIC(NumVectorInstructions, "Number of vector instructions generated")static llvm::Statistic NumVectorInstructions = {"SLP", "NumVectorInstructions"
, "Number of vector instructions generated"};

110cl::opt<bool> RunSLPVectorization("vectorize-slp", cl::init(true), cl::Hidden,
                                cl::desc("Run the SLP vectorization passes"));

113static cl::opt<int>
  SLPCostThreshold("slp-threshold", cl::init(0), cl::Hidden,
                   cl::desc("Only vectorize if you gain more than this "
                            "number "));

118static cl::opt<bool>
119ShouldVectorizeHor("slp-vectorize-hor", cl::init(true), cl::Hidden,
                 cl::desc("Attempt to vectorize horizontal reductions"));

122static cl::opt<bool> ShouldStartVectorizeHorAtStore(
  "slp-vectorize-hor-store", cl::init(false), cl::Hidden,
  cl::desc(
      "Attempt to vectorize horizontal reductions feeding into a store"));

127static cl::opt<int>
128MaxVectorRegSizeOption("slp-max-reg-size", cl::init(128), cl::Hidden,
  cl::desc("Attempt to vectorize for this register size in bits"));

131static cl::opt<unsigned>
132MaxVFOption("slp-max-vf", cl::init(0), cl::Hidden,
  cl::desc("Maximum SLP vectorization factor (0=unlimited)"));

135static cl::opt<int>
136MaxStoreLookup("slp-max-store-lookup", cl::init(32), cl::Hidden,
  cl::desc("Maximum depth of the lookup for consecutive stores."));

139/// Limits the size of scheduling regions in a block.
140/// It avoid long compile times for _very_ large blocks where vector
141/// instructions are spread over a wide range.
142/// This limit is way higher than needed by real-world functions.
143static cl::opt<int>
144ScheduleRegionSizeBudget("slp-schedule-budget", cl::init(100000), cl::Hidden,
  cl::desc("Limit the size of the SLP scheduling region per block"));

147static cl::opt<int> MinVectorRegSizeOption(
  "slp-min-reg-size", cl::init(128), cl::Hidden,
  cl::desc("Attempt to vectorize for this register size in bits"));

151static cl::opt<unsigned> RecursionMaxDepth(
  "slp-recursion-max-depth", cl::init(12), cl::Hidden,
  cl::desc("Limit the recursion depth when building a vectorizable tree"));

155static cl::opt<unsigned> MinTreeSize(
  "slp-min-tree-size", cl::init(3), cl::Hidden,
  cl::desc("Only vectorize small trees if they are fully vectorizable"));

159// The maximum depth that the look-ahead score heuristic will explore.
160// The higher this value, the higher the compilation time overhead.
161static cl::opt<int> LookAheadMaxDepth(
  "slp-max-look-ahead-depth", cl::init(2), cl::Hidden,
  cl::desc("The maximum look-ahead depth for operand reordering scores"));

165// The Look-ahead heuristic goes through the users of the bundle to calculate
166// the users cost in getExternalUsesCost(). To avoid compilation time increase
167// we limit the number of users visited to this value.
168static cl::opt<unsigned> LookAheadUsersBudget(
  "slp-look-ahead-users-budget", cl::init(2), cl::Hidden,
  cl::desc("The maximum number of users to visit while visiting the "
           "predecessors. This prevents compilation time increase."));

173static cl::opt<bool>
  ViewSLPTree("view-slp-tree", cl::Hidden,
              cl::desc("Display the SLP trees with Graphviz"));

177// Limit the number of alias checks. The limit is chosen so that
178// it has no negative effect on the llvm benchmarks.
179static const unsigned AliasedCheckLimit = 10;

181// Another limit for the alias checks: The maximum distance between load/store
182// instructions where alias checks are done.
183// This limit is useful for very large basic blocks.
184static const unsigned MaxMemDepDistance = 160;

186/// If the ScheduleRegionSizeBudget is exhausted, we allow small scheduling
187/// regions to be handled.
188static const int MinScheduleRegionSize = 16;

190/// Predicate for the element types that the SLP vectorizer supports.
191///
192/// The most important thing to filter here are types which are invalid in LLVM
193/// vectors. We also filter target specific types which have absolutely no
194/// meaningful vectorization path such as x86_fp80 and ppc_f128. This just
195/// avoids spending time checking the cost model and realizing that they will
196/// be inevitably scalarized.
197static bool isValidElementType(Type *Ty) {
return VectorType::isValidElementType(Ty) && !Ty->isX86_FP80Ty() &&
       !Ty->isPPC_FP128Ty();
200}

202/// \returns true if all of the instructions in \p VL are in the same block or
203/// false otherwise.
204static bool allSameBlock(ArrayRef<Value *> VL) {
Instruction *I0 = dyn_cast<Instruction>(VL[0]);
if (!I0)
  return false;
BasicBlock *BB = I0->getParent();
for (int I = 1, E = VL.size(); I < E; I++) {
  auto *II = dyn_cast<Instruction>(VL[I]);
  if (!II)
    return false;

  if (BB != II->getParent())
    return false;
}
return true;
218}

220/// \returns True if all of the values in \p VL are constants (but not
221/// globals/constant expressions).
222static bool allConstant(ArrayRef<Value *> VL) {
// Constant expressions and globals can't be vectorized like normal integer/FP
// constants.
for (Value *i : VL)
  if (!isa<Constant>(i) || isa<ConstantExpr>(i) || isa<GlobalValue>(i))
    return false;
return true;
229}

231/// \returns True if all of the values in \p VL are identical.
232static bool isSplat(ArrayRef<Value *> VL) {
for (unsigned i = 1, e = VL.size(); i < e; ++i)
  if (VL[i] != VL[0])
    return false;
return true;
237}

239/// \returns True if \p I is commutative, handles CmpInst and BinaryOperator.
240static bool isCommutative(Instruction *I) {
if (auto *Cmp = dyn_cast<CmpInst>(I))
  return Cmp->isCommutative();
if (auto *BO = dyn_cast<BinaryOperator>(I))
  return BO->isCommutative();
// TODO: This should check for generic Instruction::isCommutative(), but
//       we need to confirm that the caller code correctly handles Intrinsics
//       for example (does not have 2 operands).
return false;
249}

251/// Checks if the vector of instructions can be represented as a shuffle, like:
252/// %x0 = extractelement <4 x i8> %x, i32 0
253/// %x3 = extractelement <4 x i8> %x, i32 3
254/// %y1 = extractelement <4 x i8> %y, i32 1
255/// %y2 = extractelement <4 x i8> %y, i32 2
256/// %x0x0 = mul i8 %x0, %x0
257/// %x3x3 = mul i8 %x3, %x3
258/// %y1y1 = mul i8 %y1, %y1
259/// %y2y2 = mul i8 %y2, %y2
260/// %ins1 = insertelement <4 x i8> poison, i8 %x0x0, i32 0
261/// %ins2 = insertelement <4 x i8> %ins1, i8 %x3x3, i32 1
262/// %ins3 = insertelement <4 x i8> %ins2, i8 %y1y1, i32 2
263/// %ins4 = insertelement <4 x i8> %ins3, i8 %y2y2, i32 3
264/// ret <4 x i8> %ins4
265/// can be transformed into:
266/// %1 = shufflevector <4 x i8> %x, <4 x i8> %y, <4 x i32> <i32 0, i32 3, i32 5,
267///                                                         i32 6>
268/// %2 = mul <4 x i8> %1, %1
269/// ret <4 x i8> %2
270/// We convert this initially to something like:
271/// %x0 = extractelement <4 x i8> %x, i32 0
272/// %x3 = extractelement <4 x i8> %x, i32 3
273/// %y1 = extractelement <4 x i8> %y, i32 1
274/// %y2 = extractelement <4 x i8> %y, i32 2
275/// %1 = insertelement <4 x i8> poison, i8 %x0, i32 0
276/// %2 = insertelement <4 x i8> %1, i8 %x3, i32 1
277/// %3 = insertelement <4 x i8> %2, i8 %y1, i32 2
278/// %4 = insertelement <4 x i8> %3, i8 %y2, i32 3
279/// %5 = mul <4 x i8> %4, %4
280/// %6 = extractelement <4 x i8> %5, i32 0
281/// %ins1 = insertelement <4 x i8> poison, i8 %6, i32 0
282/// %7 = extractelement <4 x i8> %5, i32 1
283/// %ins2 = insertelement <4 x i8> %ins1, i8 %7, i32 1
284/// %8 = extractelement <4 x i8> %5, i32 2
285/// %ins3 = insertelement <4 x i8> %ins2, i8 %8, i32 2
286/// %9 = extractelement <4 x i8> %5, i32 3
287/// %ins4 = insertelement <4 x i8> %ins3, i8 %9, i32 3
288/// ret <4 x i8> %ins4
289/// InstCombiner transforms this into a shuffle and vector mul
290/// Mask will return the Shuffle Mask equivalent to the extracted elements.
291/// TODO: Can we split off and reuse the shuffle mask detection from
292/// TargetTransformInfo::getInstructionThroughput?
293static Optional<TargetTransformInfo::ShuffleKind>
294isShuffle(ArrayRef<Value *> VL, SmallVectorImpl<int> &Mask) {
auto *EI0 = cast<ExtractElementInst>(VL[0]);
unsigned Size =
    cast<FixedVectorType>(EI0->getVectorOperandType())->getNumElements();
Value *Vec1 = nullptr;
Value *Vec2 = nullptr;
enum ShuffleMode { Unknown, Select, Permute };
ShuffleMode CommonShuffleMode = Unknown;
for (unsigned I = 0, E = VL.size(); I < E; ++I) {
  auto *EI = cast<ExtractElementInst>(VL[I]);
  auto *Vec = EI->getVectorOperand();
  // All vector operands must have the same number of vector elements.
  if (cast<FixedVectorType>(Vec->getType())->getNumElements() != Size)
    return None;
  auto *Idx = dyn_cast<ConstantInt>(EI->getIndexOperand());
  if (!Idx)
    return None;
  // Undefined behavior if Idx is negative or >= Size.
  if (Idx->getValue().uge(Size)) {
    Mask.push_back(UndefMaskElem);
    continue;
  }
  unsigned IntIdx = Idx->getValue().getZExtValue();
  Mask.push_back(IntIdx);
  // We can extractelement from undef or poison vector.
  if (isa<UndefValue>(Vec))
    continue;
  // For correct shuffling we have to have at most 2 different vector operands
  // in all extractelement instructions.
  if (!Vec1 || Vec1 == Vec)
    Vec1 = Vec;
  else if (!Vec2 || Vec2 == Vec)
    Vec2 = Vec;
  else
    return None;
  if (CommonShuffleMode == Permute)
    continue;
  // If the extract index is not the same as the operation number, it is a
  // permutation.
  if (IntIdx != I) {
    CommonShuffleMode = Permute;
    continue;
  }
  CommonShuffleMode = Select;
}
// If we're not crossing lanes in different vectors, consider it as blending.
if (CommonShuffleMode == Select && Vec2)
  return TargetTransformInfo::SK_Select;
// If Vec2 was never used, we have a permutation of a single vector, otherwise
// we have permutation of 2 vectors.
return Vec2 ? TargetTransformInfo::SK_PermuteTwoSrc
            : TargetTransformInfo::SK_PermuteSingleSrc;
346}

348namespace {

350/// Main data required for vectorization of instructions.
351struct InstructionsState {
/// The very first instruction in the list with the main opcode.
Value *OpValue = nullptr;

/// The main/alternate instruction.
Instruction *MainOp = nullptr;
Instruction *AltOp = nullptr;

/// The main/alternate opcodes for the list of instructions.
unsigned getOpcode() const {
  return MainOp ? MainOp->getOpcode() : 0;
}

unsigned getAltOpcode() const {
  return AltOp ? AltOp->getOpcode() : 0;
}

/// Some of the instructions in the list have alternate opcodes.
bool isAltShuffle() const { return getOpcode() != getAltOpcode(); }

bool isOpcodeOrAlt(Instruction *I) const {
  unsigned CheckedOpcode = I->getOpcode();
  return getOpcode() == CheckedOpcode || getAltOpcode() == CheckedOpcode;
}

InstructionsState() = delete;
InstructionsState(Value *OpValue, Instruction *MainOp, Instruction *AltOp)
    : OpValue(OpValue), MainOp(MainOp), AltOp(AltOp) {}
379};

381} // end anonymous namespace

383/// Chooses the correct key for scheduling data. If \p Op has the same (or
384/// alternate) opcode as \p OpValue, the key is \p Op. Otherwise the key is \p
385/// OpValue.
386static Value *isOneOf(const InstructionsState &S, Value *Op) {
auto *I = dyn_cast<Instruction>(Op);
if (I && S.isOpcodeOrAlt(I))
  return Op;
return S.OpValue;
391}

393/// \returns true if \p Opcode is allowed as part of of the main/alternate
394/// instruction for SLP vectorization.
395///
396/// Example of unsupported opcode is SDIV that can potentially cause UB if the
397/// "shuffled out" lane would result in division by zero.
398static bool isValidForAlternation(unsigned Opcode) {
if (Instruction::isIntDivRem(Opcode))
  return false;

return true;
403}

405/// \returns analysis of the Instructions in \p VL described in
406/// InstructionsState, the Opcode that we suppose the whole list
407/// could be vectorized even if its structure is diverse.
408static InstructionsState getSameOpcode(ArrayRef<Value *> VL,
                                     unsigned BaseIndex = 0) {
// Make sure these are all Instructions.
if (llvm::any_of(VL, [](Value *V) { return !isa<Instruction>(V); }))
  return InstructionsState(VL[BaseIndex], nullptr, nullptr);

bool IsCastOp = isa<CastInst>(VL[BaseIndex]);
bool IsBinOp = isa<BinaryOperator>(VL[BaseIndex]);
unsigned Opcode = cast<Instruction>(VL[BaseIndex])->getOpcode();
unsigned AltOpcode = Opcode;
unsigned AltIndex = BaseIndex;

// Check for one alternate opcode from another BinaryOperator.
// TODO - generalize to support all operators (types, calls etc.).
for (int Cnt = 0, E = VL.size(); Cnt < E; Cnt++) {
  unsigned InstOpcode = cast<Instruction>(VL[Cnt])->getOpcode();
  if (IsBinOp && isa<BinaryOperator>(VL[Cnt])) {
    if (InstOpcode == Opcode || InstOpcode == AltOpcode)
      continue;
    if (Opcode == AltOpcode && isValidForAlternation(InstOpcode) &&
        isValidForAlternation(Opcode)) {
      AltOpcode = InstOpcode;
      AltIndex = Cnt;
      continue;
    }
  } else if (IsCastOp && isa<CastInst>(VL[Cnt])) {
    Type *Ty0 = cast<Instruction>(VL[BaseIndex])->getOperand(0)->getType();
    Type *Ty1 = cast<Instruction>(VL[Cnt])->getOperand(0)->getType();
    if (Ty0 == Ty1) {
      if (InstOpcode == Opcode || InstOpcode == AltOpcode)
        continue;
      if (Opcode == AltOpcode) {
        assert(isValidForAlternation(Opcode) &&((isValidForAlternation(Opcode) && isValidForAlternation
(InstOpcode) && "Cast isn't safe for alternation, logic needs to be updated!"
) ? static_cast<void> (0) : __assert_fail ("isValidForAlternation(Opcode) && isValidForAlternation(InstOpcode) && \"Cast isn't safe for alternation, logic needs to be updated!\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 442, __PRETTY_FUNCTION__))
               isValidForAlternation(InstOpcode) &&((isValidForAlternation(Opcode) && isValidForAlternation
(InstOpcode) && "Cast isn't safe for alternation, logic needs to be updated!"
) ? static_cast<void> (0) : __assert_fail ("isValidForAlternation(Opcode) && isValidForAlternation(InstOpcode) && \"Cast isn't safe for alternation, logic needs to be updated!\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 442, __PRETTY_FUNCTION__))
               "Cast isn't safe for alternation, logic needs to be updated!")((isValidForAlternation(Opcode) && isValidForAlternation
(InstOpcode) && "Cast isn't safe for alternation, logic needs to be updated!"
) ? static_cast<void> (0) : __assert_fail ("isValidForAlternation(Opcode) && isValidForAlternation(InstOpcode) && \"Cast isn't safe for alternation, logic needs to be updated!\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 442, __PRETTY_FUNCTION__));
        AltOpcode = InstOpcode;
        AltIndex = Cnt;
        continue;
      }
    }
  } else if (InstOpcode == Opcode || InstOpcode == AltOpcode)
    continue;
  return InstructionsState(VL[BaseIndex], nullptr, nullptr);
}

return InstructionsState(VL[BaseIndex], cast<Instruction>(VL[BaseIndex]),
                         cast<Instruction>(VL[AltIndex]));
455}

457/// \returns true if all of the values in \p VL have the same type or false
458/// otherwise.
459static bool allSameType(ArrayRef<Value *> VL) {
Type *Ty = VL[0]->getType();
for (int i = 1, e = VL.size(); i < e; i++)
  if (VL[i]->getType() != Ty)
    return false;

return true;
466}

468/// \returns True if Extract{Value,Element} instruction extracts element Idx.
469static Optional<unsigned> getExtractIndex(Instruction *E) {
unsigned Opcode = E->getOpcode();
assert((Opcode == Instruction::ExtractElement ||(((Opcode == Instruction::ExtractElement || Opcode == Instruction
::ExtractValue) && "Expected extractelement or extractvalue instruction."
) ? static_cast<void> (0) : __assert_fail ("(Opcode == Instruction::ExtractElement || Opcode == Instruction::ExtractValue) && \"Expected extractelement or extractvalue instruction.\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 473, __PRETTY_FUNCTION__))
        Opcode == Instruction::ExtractValue) &&(((Opcode == Instruction::ExtractElement || Opcode == Instruction
::ExtractValue) && "Expected extractelement or extractvalue instruction."
) ? static_cast<void> (0) : __assert_fail ("(Opcode == Instruction::ExtractElement || Opcode == Instruction::ExtractValue) && \"Expected extractelement or extractvalue instruction.\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 473, __PRETTY_FUNCTION__))
       "Expected extractelement or extractvalue instruction.")(((Opcode == Instruction::ExtractElement || Opcode == Instruction
::ExtractValue) && "Expected extractelement or extractvalue instruction."
) ? static_cast<void> (0) : __assert_fail ("(Opcode == Instruction::ExtractElement || Opcode == Instruction::ExtractValue) && \"Expected extractelement or extractvalue instruction.\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 473, __PRETTY_FUNCTION__));
if (Opcode == Instruction::ExtractElement) {
  auto *CI = dyn_cast<ConstantInt>(E->getOperand(1));
  if (!CI)
    return None;
  return CI->getZExtValue();
}
ExtractValueInst *EI = cast<ExtractValueInst>(E);
if (EI->getNumIndices() != 1)
  return None;
return *EI->idx_begin();
484}

486/// \returns True if in-tree use also needs extract. This refers to
487/// possible scalar operand in vectorized instruction.
488static bool InTreeUserNeedToExtract(Value *Scalar, Instruction *UserInst,
                                  TargetLibraryInfo *TLI) {
unsigned Opcode = UserInst->getOpcode();
switch (Opcode) {
case Instruction::Load: {
  LoadInst *LI = cast<LoadInst>(UserInst);
  return (LI->getPointerOperand() == Scalar);
}
case Instruction::Store: {
  StoreInst *SI = cast<StoreInst>(UserInst);
  return (SI->getPointerOperand() == Scalar);
}
case Instruction::Call: {
  CallInst *CI = cast<CallInst>(UserInst);
  Intrinsic::ID ID = getVectorIntrinsicIDForCall(CI, TLI);
  for (unsigned i = 0, e = CI->getNumArgOperands(); i != e; ++i) {
    if (hasVectorInstrinsicScalarOpd(ID, i))
      return (CI->getArgOperand(i) == Scalar);
  }
  LLVM_FALLTHROUGH[[gnu::fallthrough]];
}
default:
  return false;
}
512}

514/// \returns the AA location that is being access by the instruction.
515static MemoryLocation getLocation(Instruction *I, AAResults *AA) {
if (StoreInst *SI = dyn_cast<StoreInst>(I))
  return MemoryLocation::get(SI);
if (LoadInst *LI = dyn_cast<LoadInst>(I))
  return MemoryLocation::get(LI);
return MemoryLocation();
521}

523/// \returns True if the instruction is not a volatile or atomic load/store.
524static bool isSimple(Instruction *I) {
if (LoadInst *LI = dyn_cast<LoadInst>(I))
  return LI->isSimple();
if (StoreInst *SI = dyn_cast<StoreInst>(I))
  return SI->isSimple();
if (MemIntrinsic *MI = dyn_cast<MemIntrinsic>(I))
  return !MI->isVolatile();
return true;
532}

534namespace llvm {

536static void inversePermutation(ArrayRef<unsigned> Indices,
                             SmallVectorImpl<int> &Mask) {
Mask.clear();
const unsigned E = Indices.size();
Mask.resize(E, E + 1);
for (unsigned I = 0; I < E; ++I)
  Mask[Indices[I]] = I;
543}

545namespace slpvectorizer {

547/// Bottom Up SLP Vectorizer.
548class BoUpSLP {
struct TreeEntry;
struct ScheduleData;

552public:
using ValueList = SmallVector<Value *, 8>;
using InstrList = SmallVector<Instruction *, 16>;
using ValueSet = SmallPtrSet<Value *, 16>;
using StoreList = SmallVector<StoreInst *, 8>;
using ExtraValueToDebugLocsMap =
    MapVector<Value *, SmallVector<Instruction *, 2>>;
using OrdersType = SmallVector<unsigned, 4>;

BoUpSLP(Function *Func, ScalarEvolution *Se, TargetTransformInfo *Tti,
        TargetLibraryInfo *TLi, AAResults *Aa, LoopInfo *Li,
        DominatorTree *Dt, AssumptionCache *AC, DemandedBits *DB,
        const DataLayout *DL, OptimizationRemarkEmitter *ORE)
    : F(Func), SE(Se), TTI(Tti), TLI(TLi), AA(Aa), LI(Li), DT(Dt), AC(AC),
      DB(DB), DL(DL), ORE(ORE), Builder(Se->getContext()) {
  CodeMetrics::collectEphemeralValues(F, AC, EphValues);
  // Use the vector register size specified by the target unless overridden
  // by a command-line option.
  // TODO: It would be better to limit the vectorization factor based on
  //       data type rather than just register size. For example, x86 AVX has
  //       256-bit registers, but it does not support integer operations
  //       at that width (that requires AVX2).
  if (MaxVectorRegSizeOption.getNumOccurrences())
    MaxVecRegSize = MaxVectorRegSizeOption;
  else
    MaxVecRegSize =
        TTI->getRegisterBitWidth(TargetTransformInfo::RGK_FixedWidthVector)
            .getFixedSize();

  if (MinVectorRegSizeOption.getNumOccurrences())
    MinVecRegSize = MinVectorRegSizeOption;
  else
    MinVecRegSize = TTI->getMinVectorRegisterBitWidth();
}

/// Vectorize the tree that starts with the elements in \p VL.
/// Returns the vectorized root.
Value *vectorizeTree();

/// Vectorize the tree but with the list of externally used values \p
/// ExternallyUsedValues. Values in this MapVector can be replaced but the
/// generated extractvalue instructions.
Value *vectorizeTree(ExtraValueToDebugLocsMap &ExternallyUsedValues);

/// \returns the cost incurred by unwanted spills and fills, caused by
/// holding live values over call sites.
InstructionCost getSpillCost() const;

/// \returns the vectorization cost of the subtree that starts at \p VL.
/// A negative number means that this is profitable.
InstructionCost getTreeCost();

/// Construct a vectorizable tree that starts at \p Roots, ignoring users for
/// the purpose of scheduling and extraction in the \p UserIgnoreLst.
void buildTree(ArrayRef<Value *> Roots,
               ArrayRef<Value *> UserIgnoreLst = None);

/// Construct a vectorizable tree that starts at \p Roots, ignoring users for
/// the purpose of scheduling and extraction in the \p UserIgnoreLst taking
/// into account (and updating it, if required) list of externally used
/// values stored in \p ExternallyUsedValues.
void buildTree(ArrayRef<Value *> Roots,
               ExtraValueToDebugLocsMap &ExternallyUsedValues,
               ArrayRef<Value *> UserIgnoreLst = None);

/// Clear the internal data structures that are created by 'buildTree'.
void deleteTree() {
  VectorizableTree.clear();
  ScalarToTreeEntry.clear();
  MustGather.clear();
  ExternalUses.clear();
  NumOpsWantToKeepOrder.clear();
  NumOpsWantToKeepOriginalOrder = 0;
  for (auto &Iter : BlocksSchedules) {
    BlockScheduling *BS = Iter.second.get();
    BS->clear();
  }
  MinBWs.clear();
  InstrElementSize.clear();
}

unsigned getTreeSize() const { return VectorizableTree.size(); }

/// Perform LICM and CSE on the newly generated gather sequences.
void optimizeGatherSequence();

/// \returns The best order of instructions for vectorization.
Optional<ArrayRef<unsigned>> bestOrder() const {
  assert(llvm::all_of(((llvm::all_of( NumOpsWantToKeepOrder, [this](const decltype(
NumOpsWantToKeepOrder)::value_type &D) { return D.getFirst
().size() == VectorizableTree[0]->Scalars.size(); }) &&
 "All orders must have the same size as number of instructions in "
 "tree node.") ? static_cast<void> (0) : __assert_fail (
"llvm::all_of( NumOpsWantToKeepOrder, [this](const decltype(NumOpsWantToKeepOrder)::value_type &D) { return D.getFirst().size() == VectorizableTree[0]->Scalars.size(); }) && \"All orders must have the same size as number of instructions in \" \"tree node.\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 647, __PRETTY_FUNCTION__))
             NumOpsWantToKeepOrder,((llvm::all_of( NumOpsWantToKeepOrder, [this](const decltype(
NumOpsWantToKeepOrder)::value_type &D) { return D.getFirst
().size() == VectorizableTree[0]->Scalars.size(); }) &&
 "All orders must have the same size as number of instructions in "
 "tree node.") ? static_cast<void> (0) : __assert_fail (
"llvm::all_of( NumOpsWantToKeepOrder, [this](const decltype(NumOpsWantToKeepOrder)::value_type &D) { return D.getFirst().size() == VectorizableTree[0]->Scalars.size(); }) && \"All orders must have the same size as number of instructions in \" \"tree node.\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 647, __PRETTY_FUNCTION__))
             [this](const decltype(NumOpsWantToKeepOrder)::value_type &D) {((llvm::all_of( NumOpsWantToKeepOrder, [this](const decltype(
NumOpsWantToKeepOrder)::value_type &D) { return D.getFirst
().size() == VectorizableTree[0]->Scalars.size(); }) &&
 "All orders must have the same size as number of instructions in "
 "tree node.") ? static_cast<void> (0) : __assert_fail (
"llvm::all_of( NumOpsWantToKeepOrder, [this](const decltype(NumOpsWantToKeepOrder)::value_type &D) { return D.getFirst().size() == VectorizableTree[0]->Scalars.size(); }) && \"All orders must have the same size as number of instructions in \" \"tree node.\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 647, __PRETTY_FUNCTION__))
               return D.getFirst().size() ==((llvm::all_of( NumOpsWantToKeepOrder, [this](const decltype(
NumOpsWantToKeepOrder)::value_type &D) { return D.getFirst
().size() == VectorizableTree[0]->Scalars.size(); }) &&
 "All orders must have the same size as number of instructions in "
 "tree node.") ? static_cast<void> (0) : __assert_fail (
"llvm::all_of( NumOpsWantToKeepOrder, [this](const decltype(NumOpsWantToKeepOrder)::value_type &D) { return D.getFirst().size() == VectorizableTree[0]->Scalars.size(); }) && \"All orders must have the same size as number of instructions in \" \"tree node.\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 647, __PRETTY_FUNCTION__))
                      VectorizableTree[0]->Scalars.size();((llvm::all_of( NumOpsWantToKeepOrder, [this](const decltype(
NumOpsWantToKeepOrder)::value_type &D) { return D.getFirst
().size() == VectorizableTree[0]->Scalars.size(); }) &&
 "All orders must have the same size as number of instructions in "
 "tree node.") ? static_cast<void> (0) : __assert_fail (
"llvm::all_of( NumOpsWantToKeepOrder, [this](const decltype(NumOpsWantToKeepOrder)::value_type &D) { return D.getFirst().size() == VectorizableTree[0]->Scalars.size(); }) && \"All orders must have the same size as number of instructions in \" \"tree node.\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 647, __PRETTY_FUNCTION__))
             }) &&((llvm::all_of( NumOpsWantToKeepOrder, [this](const decltype(
NumOpsWantToKeepOrder)::value_type &D) { return D.getFirst
().size() == VectorizableTree[0]->Scalars.size(); }) &&
 "All orders must have the same size as number of instructions in "
 "tree node.") ? static_cast<void> (0) : __assert_fail (
"llvm::all_of( NumOpsWantToKeepOrder, [this](const decltype(NumOpsWantToKeepOrder)::value_type &D) { return D.getFirst().size() == VectorizableTree[0]->Scalars.size(); }) && \"All orders must have the same size as number of instructions in \" \"tree node.\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 647, __PRETTY_FUNCTION__))
         "All orders must have the same size as number of instructions in "((llvm::all_of( NumOpsWantToKeepOrder, [this](const decltype(
NumOpsWantToKeepOrder)::value_type &D) { return D.getFirst
().size() == VectorizableTree[0]->Scalars.size(); }) &&
 "All orders must have the same size as number of instructions in "
 "tree node.") ? static_cast<void> (0) : __assert_fail (
"llvm::all_of( NumOpsWantToKeepOrder, [this](const decltype(NumOpsWantToKeepOrder)::value_type &D) { return D.getFirst().size() == VectorizableTree[0]->Scalars.size(); }) && \"All orders must have the same size as number of instructions in \" \"tree node.\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 647, __PRETTY_FUNCTION__))
         "tree node.")((llvm::all_of( NumOpsWantToKeepOrder, [this](const decltype(
NumOpsWantToKeepOrder)::value_type &D) { return D.getFirst
().size() == VectorizableTree[0]->Scalars.size(); }) &&
 "All orders must have the same size as number of instructions in "
 "tree node.") ? static_cast<void> (0) : __assert_fail (
"llvm::all_of( NumOpsWantToKeepOrder, [this](const decltype(NumOpsWantToKeepOrder)::value_type &D) { return D.getFirst().size() == VectorizableTree[0]->Scalars.size(); }) && \"All orders must have the same size as number of instructions in \" \"tree node.\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 647, __PRETTY_FUNCTION__));
  auto I = std::max_element(
      NumOpsWantToKeepOrder.begin(), NumOpsWantToKeepOrder.end(),
      [](const decltype(NumOpsWantToKeepOrder)::value_type &D1,
         const decltype(NumOpsWantToKeepOrder)::value_type &D2) {
        return D1.second < D2.second;
      });
  if (I == NumOpsWantToKeepOrder.end() ||
      I->getSecond() <= NumOpsWantToKeepOriginalOrder)
    return None;

  return makeArrayRef(I->getFirst());
}

/// Builds the correct order for root instructions.
/// If some leaves have the same instructions to be vectorized, we may
/// incorrectly evaluate the best order for the root node (it is built for the
/// vector of instructions without repeated instructions and, thus, has less
/// elements than the root node). This function builds the correct order for
/// the root node.
/// For example, if the root node is \<a+b, a+c, a+d, f+e\>, then the leaves
/// are \<a, a, a, f\> and \<b, c, d, e\>. When we try to vectorize the first
/// leaf, it will be shrink to \<a, b\>. If instructions in this leaf should
/// be reordered, the best order will be \<1, 0\>. We need to extend this
/// order for the root node. For the root node this order should look like
/// \<3, 0, 1, 2\>. This function extends the order for the reused
/// instructions.
void findRootOrder(OrdersType &Order) {
  // If the leaf has the same number of instructions to vectorize as the root
  // - order must be set already.
  unsigned RootSize = VectorizableTree[0]->Scalars.size();
  if (Order.size() == RootSize)
    return;
  SmallVector<unsigned, 4> RealOrder(Order.size());
  std::swap(Order, RealOrder);
  SmallVector<int, 4> Mask;
  inversePermutation(RealOrder, Mask);
  Order.assign(Mask.begin(), Mask.end());
  // The leaf has less number of instructions - need to find the true order of
  // the root.
  // Scan the nodes starting from the leaf back to the root.
  const TreeEntry *PNode = VectorizableTree.back().get();
  SmallVector<const TreeEntry *, 4> Nodes(1, PNode);
  SmallPtrSet<const TreeEntry *, 4> Visited;
  while (!Nodes.empty() && Order.size() != RootSize) {
    const TreeEntry *PNode = Nodes.pop_back_val();
    if (!Visited.insert(PNode).second)
      continue;
    const TreeEntry &Node = *PNode;
    for (const EdgeInfo &EI : Node.UserTreeIndices)
      if (EI.UserTE)
        Nodes.push_back(EI.UserTE);
    if (Node.ReuseShuffleIndices.empty())
      continue;
    // Build the order for the parent node.
    OrdersType NewOrder(Node.ReuseShuffleIndices.size(), RootSize);
    SmallVector<unsigned, 4> OrderCounter(Order.size(), 0);
    // The algorithm of the order extension is:
    // 1. Calculate the number of the same instructions for the order.
    // 2. Calculate the index of the new order: total number of instructions
    // with order less than the order of the current instruction + reuse
    // number of the current instruction.
    // 3. The new order is just the index of the instruction in the original
    // vector of the instructions.
    for (unsigned I : Node.ReuseShuffleIndices)
      ++OrderCounter[Order[I]];
    SmallVector<unsigned, 4> CurrentCounter(Order.size(), 0);
    for (unsigned I = 0, E = Node.ReuseShuffleIndices.size(); I < E; ++I) {
      unsigned ReusedIdx = Node.ReuseShuffleIndices[I];
      unsigned OrderIdx = Order[ReusedIdx];
      unsigned NewIdx = 0;
      for (unsigned J = 0; J < OrderIdx; ++J)
        NewIdx += OrderCounter[J];
      NewIdx += CurrentCounter[OrderIdx];
      ++CurrentCounter[OrderIdx];
      assert(NewOrder[NewIdx] == RootSize &&((NewOrder[NewIdx] == RootSize && "The order index should not be written already."
) ? static_cast<void> (0) : __assert_fail ("NewOrder[NewIdx] == RootSize && \"The order index should not be written already.\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 723, __PRETTY_FUNCTION__))
             "The order index should not be written already.")((NewOrder[NewIdx] == RootSize && "The order index should not be written already."
) ? static_cast<void> (0) : __assert_fail ("NewOrder[NewIdx] == RootSize && \"The order index should not be written already.\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 723, __PRETTY_FUNCTION__));
      NewOrder[NewIdx] = I;
    }
    std::swap(Order, NewOrder);
  }
  assert(Order.size() == RootSize &&((Order.size() == RootSize && "Root node is expected or the size of the order must be the same as "
 "the number of elements in the root node.") ? static_cast<
void> (0) : __assert_fail ("Order.size() == RootSize && \"Root node is expected or the size of the order must be the same as \" \"the number of elements in the root node.\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 730, __PRETTY_FUNCTION__))
         "Root node is expected or the size of the order must be the same as "((Order.size() == RootSize && "Root node is expected or the size of the order must be the same as "
 "the number of elements in the root node.") ? static_cast<
void> (0) : __assert_fail ("Order.size() == RootSize && \"Root node is expected or the size of the order must be the same as \" \"the number of elements in the root node.\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 730, __PRETTY_FUNCTION__))
         "the number of elements in the root node.")((Order.size() == RootSize && "Root node is expected or the size of the order must be the same as "
 "the number of elements in the root node.") ? static_cast<
void> (0) : __assert_fail ("Order.size() == RootSize && \"Root node is expected or the size of the order must be the same as \" \"the number of elements in the root node.\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 730, __PRETTY_FUNCTION__));
  assert(llvm::all_of(Order,((llvm::all_of(Order, [RootSize](unsigned Val) { return Val !=
 RootSize; }) && "All indices must be initialized") ?
 static_cast<void> (0) : __assert_fail ("llvm::all_of(Order, [RootSize](unsigned Val) { return Val != RootSize; }) && \"All indices must be initialized\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 733, __PRETTY_FUNCTION__))
                      [RootSize](unsigned Val) { return Val != RootSize; }) &&((llvm::all_of(Order, [RootSize](unsigned Val) { return Val !=
 RootSize; }) && "All indices must be initialized") ?
 static_cast<void> (0) : __assert_fail ("llvm::all_of(Order, [RootSize](unsigned Val) { return Val != RootSize; }) && \"All indices must be initialized\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 733, __PRETTY_FUNCTION__))
         "All indices must be initialized")((llvm::all_of(Order, [RootSize](unsigned Val) { return Val !=
 RootSize; }) && "All indices must be initialized") ?
 static_cast<void> (0) : __assert_fail ("llvm::all_of(Order, [RootSize](unsigned Val) { return Val != RootSize; }) && \"All indices must be initialized\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 733, __PRETTY_FUNCTION__));
}

/// \return The vector element size in bits to use when vectorizing the
/// expression tree ending at \p V. If V is a store, the size is the width of
/// the stored value. Otherwise, the size is the width of the largest loaded
/// value reaching V. This method is used by the vectorizer to calculate
/// vectorization factors.
unsigned getVectorElementSize(Value *V);

/// Compute the minimum type sizes required to represent the entries in a
/// vectorizable tree.
void computeMinimumValueSizes();

// \returns maximum vector register size as set by TTI or overridden by cl::opt.
unsigned getMaxVecRegSize() const {
  return MaxVecRegSize;
}

// \returns minimum vector register size as set by cl::opt.
unsigned getMinVecRegSize() const {
  return MinVecRegSize;
}

unsigned getMaximumVF(unsigned ElemWidth, unsigned Opcode) const {
  unsigned MaxVF = MaxVFOption.getNumOccurrences() ?
    MaxVFOption : TTI->getMaximumVF(ElemWidth, Opcode);
  return MaxVF ? MaxVF : UINT_MAX(2147483647 *2U +1U);
}

/// Check if homogeneous aggregate is isomorphic to some VectorType.
/// Accepts homogeneous multidimensional aggregate of scalars/vectors like
/// {[4 x i16], [4 x i16]}, { <2 x float>, <2 x float> },
/// {{{i16, i16}, {i16, i16}}, {{i16, i16}, {i16, i16}}} and so on.
///
/// \returns number of elements in vector if isomorphism exists, 0 otherwise.
unsigned canMapToVector(Type *T, const DataLayout &DL) const;

/// \returns True if the VectorizableTree is both tiny and not fully
/// vectorizable. We do not vectorize such trees.
bool isTreeTinyAndNotFullyVectorizable() const;

/// Assume that a legal-sized 'or'-reduction of shifted/zexted loaded values
/// can be load combined in the backend. Load combining may not be allowed in
/// the IR optimizer, so we do not want to alter the pattern. For example,
/// partially transforming a scalar bswap() pattern into vector code is
/// effectively impossible for the backend to undo.
/// TODO: If load combining is allowed in the IR optimizer, this analysis
///       may not be necessary.
bool isLoadCombineReductionCandidate(RecurKind RdxKind) const;

/// Assume that a vector of stores of bitwise-or/shifted/zexted loaded values
/// can be load combined in the backend. Load combining may not be allowed in
/// the IR optimizer, so we do not want to alter the pattern. For example,
/// partially transforming a scalar bswap() pattern into vector code is
/// effectively impossible for the backend to undo.
/// TODO: If load combining is allowed in the IR optimizer, this analysis
///       may not be necessary.
bool isLoadCombineCandidate() const;

OptimizationRemarkEmitter *getORE() { return ORE; }

/// This structure holds any data we need about the edges being traversed
/// during buildTree_rec(). We keep track of:
/// (i) the user TreeEntry index, and
/// (ii) the index of the edge.
struct EdgeInfo {
  EdgeInfo() = default;
  EdgeInfo(TreeEntry *UserTE, unsigned EdgeIdx)
      : UserTE(UserTE), EdgeIdx(EdgeIdx) {}
  /// The user TreeEntry.
  TreeEntry *UserTE = nullptr;
  /// The operand index of the use.
  unsigned EdgeIdx = UINT_MAX(2147483647 *2U +1U);
807#ifndef NDEBUG
  friend inline raw_ostream &operator<<(raw_ostream &OS,
                                        const BoUpSLP::EdgeInfo &EI) {
    EI.dump(OS);
    return OS;
  }
  /// Debug print.
  void dump(raw_ostream &OS) const {
    OS << "{User:" << (UserTE ? std::to_string(UserTE->Idx) : "null")
       << " EdgeIdx:" << EdgeIdx << "}";
  }
  LLVM_DUMP_METHOD__attribute__((noinline)) __attribute__((__used__)) void dump() const { dump(dbgs()); }
819#endif
};

/// A helper data structure to hold the operands of a vector of instructions.
/// This supports a fixed vector length for all operand vectors.
class VLOperands {
  /// For each operand we need (i) the value, and (ii) the opcode that it
  /// would be attached to if the expression was in a left-linearized form.
  /// This is required to avoid illegal operand reordering.
  /// For example:
  /// \verbatim
  ///                         0 Op1
  ///                         |/
  /// Op1 Op2   Linearized    + Op2
  ///   \ /     ---------->   |/
  ///    -                    -
  ///
  /// Op1 - Op2            (0 + Op1) - Op2
  /// \endverbatim
  ///
  /// Value Op1 is attached to a '+' operation, and Op2 to a '-'.
  ///
  /// Another way to think of this is to track all the operations across the
  /// path from the operand all the way to the root of the tree and to
  /// calculate the operation that corresponds to this path. For example, the
  /// path from Op2 to the root crosses the RHS of the '-', therefore the
  /// corresponding operation is a '-' (which matches the one in the
  /// linearized tree, as shown above).
  ///
  /// For lack of a better term, we refer to this operation as Accumulated
  /// Path Operation (APO).
  struct OperandData {
    OperandData() = default;
    OperandData(Value *V, bool APO, bool IsUsed)
        : V(V), APO(APO), IsUsed(IsUsed) {}
    /// The operand value.
    Value *V = nullptr;
    /// TreeEntries only allow a single opcode, or an alternate sequence of
    /// them (e.g, +, -). Therefore, we can safely use a boolean value for the
    /// APO. It is set to 'true' if 'V' is attached to an inverse operation
    /// in the left-linearized form (e.g., Sub/Div), and 'false' otherwise
    /// (e.g., Add/Mul)
    bool APO = false;
    /// Helper data for the reordering function.
    bool IsUsed = false;
  };

  /// During operand reordering, we are trying to select the operand at lane
  /// that matches best with the operand at the neighboring lane. Our
  /// selection is based on the type of value we are looking for. For example,
  /// if the neighboring lane has a load, we need to look for a load that is
  /// accessing a consecutive address. These strategies are summarized in the
  /// 'ReorderingMode' enumerator.
  enum class ReorderingMode {
    Load,     ///< Matching loads to consecutive memory addresses
    Opcode,   ///< Matching instructions based on opcode (same or alternate)
    Constant, ///< Matching constants
    Splat,    ///< Matching the same instruction multiple times (broadcast)
    Failed,   ///< We failed to create a vectorizable group
  };

  using OperandDataVec = SmallVector<OperandData, 2>;

  /// A vector of operand vectors.
  SmallVector<OperandDataVec, 4> OpsVec;

  const DataLayout &DL;
  ScalarEvolution &SE;
  const BoUpSLP &R;

  /// \returns the operand data at \p OpIdx and \p Lane.
  OperandData &getData(unsigned OpIdx, unsigned Lane) {
    return OpsVec[OpIdx][Lane];
  }

  /// \returns the operand data at \p OpIdx and \p Lane. Const version.
  const OperandData &getData(unsigned OpIdx, unsigned Lane) const {
    return OpsVec[OpIdx][Lane];
  }

  /// Clears the used flag for all entries.
  void clearUsed() {
    for (unsigned OpIdx = 0, NumOperands = getNumOperands();
         OpIdx != NumOperands; ++OpIdx)
      for (unsigned Lane = 0, NumLanes = getNumLanes(); Lane != NumLanes;
           ++Lane)
        OpsVec[OpIdx][Lane].IsUsed = false;
  }

  /// Swap the operand at \p OpIdx1 with that one at \p OpIdx2.
  void swap(unsigned OpIdx1, unsigned OpIdx2, unsigned Lane) {
    std::swap(OpsVec[OpIdx1][Lane], OpsVec[OpIdx2][Lane]);
  }

  // The hard-coded scores listed here are not very important. When computing
  // the scores of matching one sub-tree with another, we are basically
  // counting the number of values that are matching. So even if all scores
  // are set to 1, we would still get a decent matching result.
  // However, sometimes we have to break ties. For example we may have to
  // choose between matching loads vs matching opcodes. This is what these
  // scores are helping us with: they provide the order of preference.

  /// Loads from consecutive memory addresses, e.g. load(A[i]), load(A[i+1]).
  static const int ScoreConsecutiveLoads = 3;
  /// ExtractElementInst from same vector and consecutive indexes.
  static const int ScoreConsecutiveExtracts = 3;
  /// Constants.
  static const int ScoreConstants = 2;
  /// Instructions with the same opcode.
  static const int ScoreSameOpcode = 2;
  /// Instructions with alt opcodes (e.g, add + sub).
  static const int ScoreAltOpcodes = 1;
  /// Identical instructions (a.k.a. splat or broadcast).
  static const int ScoreSplat = 1;
  /// Matching with an undef is preferable to failing.
  static const int ScoreUndef = 1;
  /// Score for failing to find a decent match.
  static const int ScoreFail = 0;
  /// User exteranl to the vectorized code.
  static const int ExternalUseCost = 1;
  /// The user is internal but in a different lane.
  static const int UserInDiffLaneCost = ExternalUseCost;

  /// \returns the score of placing \p V1 and \p V2 in consecutive lanes.
  static int getShallowScore(Value *V1, Value *V2, const DataLayout &DL,
                             ScalarEvolution &SE) {
    auto *LI1 = dyn_cast<LoadInst>(V1);
    auto *LI2 = dyn_cast<LoadInst>(V2);
    if (LI1 && LI2) {
      if (LI1->getParent() != LI2->getParent())
        return VLOperands::ScoreFail;

      Optional<int> Dist =
          getPointersDiff(LI1->getPointerOperand(), LI2->getPointerOperand(),
                          DL, SE, /*StrictCheck=*/true);
      return (Dist && *Dist == 1) ? VLOperands::ScoreConsecutiveLoads
                                  : VLOperands::ScoreFail;
    }

    auto *C1 = dyn_cast<Constant>(V1);
    auto *C2 = dyn_cast<Constant>(V2);
    if (C1 && C2)
      return VLOperands::ScoreConstants;

    // Extracts from consecutive indexes of the same vector better score as
    // the extracts could be optimized away.
    Value *EV;
    ConstantInt *Ex1Idx, *Ex2Idx;
    if (match(V1, m_ExtractElt(m_Value(EV), m_ConstantInt(Ex1Idx))) &&
        match(V2, m_ExtractElt(m_Deferred(EV), m_ConstantInt(Ex2Idx))) &&
        Ex1Idx->getZExtValue() + 1 == Ex2Idx->getZExtValue())
      return VLOperands::ScoreConsecutiveExtracts;

    auto *I1 = dyn_cast<Instruction>(V1);
    auto *I2 = dyn_cast<Instruction>(V2);
    if (I1 && I2) {
      if (I1 == I2)
        return VLOperands::ScoreSplat;
      InstructionsState S = getSameOpcode({I1, I2});
      // Note: Only consider instructions with <= 2 operands to avoid
      // complexity explosion.
      if (S.getOpcode() && S.MainOp->getNumOperands() <= 2)
        return S.isAltShuffle() ? VLOperands::ScoreAltOpcodes
                                : VLOperands::ScoreSameOpcode;
    }

    if (isa<UndefValue>(V2))
      return VLOperands::ScoreUndef;

    return VLOperands::ScoreFail;
  }

  /// Holds the values and their lane that are taking part in the look-ahead
  /// score calculation. This is used in the external uses cost calculation.
  SmallDenseMap<Value *, int> InLookAheadValues;

  /// \Returns the additinal cost due to uses of \p LHS and \p RHS that are
  /// either external to the vectorized code, or require shuffling.
  int getExternalUsesCost(const std::pair<Value *, int> &LHS,
                          const std::pair<Value *, int> &RHS) {
    int Cost = 0;
    std::array<std::pair<Value *, int>, 2> Values = {{LHS, RHS}};
    for (int Idx = 0, IdxE = Values.size(); Idx != IdxE; ++Idx) {
      Value *V = Values[Idx].first;
      if (isa<Constant>(V)) {
        // Since this is a function pass, it doesn't make semantic sense to
        // walk the users of a subclass of Constant. The users could be in
        // another function, or even another module that happens to be in
        // the same LLVMContext.
        continue;
      }

      // Calculate the absolute lane, using the minimum relative lane of LHS
      // and RHS as base and Idx as the offset.
      int Ln = std::min(LHS.second, RHS.second) + Idx;
      assert(Ln >= 0 && "Bad lane calculation")((Ln >= 0 && "Bad lane calculation") ? static_cast
<void> (0) : __assert_fail ("Ln >= 0 && \"Bad lane calculation\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 1014, __PRETTY_FUNCTION__));
      unsigned UsersBudget = LookAheadUsersBudget;
      for (User *U : V->users()) {
        if (const TreeEntry *UserTE = R.getTreeEntry(U)) {
          // The user is in the VectorizableTree. Check if we need to insert.
          auto It = llvm::find(UserTE->Scalars, U);
          assert(It != UserTE->Scalars.end() && "U is in UserTE")((It != UserTE->Scalars.end() && "U is in UserTE")
 ? static_cast<void> (0) : __assert_fail ("It != UserTE->Scalars.end() && \"U is in UserTE\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 1020, __PRETTY_FUNCTION__));
          int UserLn = std::distance(UserTE->Scalars.begin(), It);
          assert(UserLn >= 0 && "Bad lane")((UserLn >= 0 && "Bad lane") ? static_cast<void
> (0) : __assert_fail ("UserLn >= 0 && \"Bad lane\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 1022, __PRETTY_FUNCTION__));
          if (UserLn != Ln)
            Cost += UserInDiffLaneCost;
        } else {
          // Check if the user is in the look-ahead code.
          auto It2 = InLookAheadValues.find(U);
          if (It2 != InLookAheadValues.end()) {
            // The user is in the look-ahead code. Check the lane.
            if (It2->second != Ln)
              Cost += UserInDiffLaneCost;
          } else {
            // The user is neither in SLP tree nor in the look-ahead code.
            Cost += ExternalUseCost;
          }
        }
        // Limit the number of visited uses to cap compilation time.
        if (--UsersBudget == 0)
          break;
      }
    }
    return Cost;
  }

  /// Go through the operands of \p LHS and \p RHS recursively until \p
  /// MaxLevel, and return the cummulative score. For example:
  /// \verbatim
  ///  A[0]  B[0]  A[1]  B[1]  C[0] D[0]  B[1] A[1]
  ///     \ /         \ /         \ /        \ /
  ///      +           +           +          +
  ///     G1          G2          G3         G4
  /// \endverbatim
  /// The getScoreAtLevelRec(G1, G2) function will try to match the nodes at
  /// each level recursively, accumulating the score. It starts from matching
  /// the additions at level 0, then moves on to the loads (level 1). The
  /// score of G1 and G2 is higher than G1 and G3, because {A[0],A[1]} and
  /// {B[0],B[1]} match with VLOperands::ScoreConsecutiveLoads, while
  /// {A[0],C[0]} has a score of VLOperands::ScoreFail.
  /// Please note that the order of the operands does not matter, as we
  /// evaluate the score of all profitable combinations of operands. In
  /// other words the score of G1 and G4 is the same as G1 and G2. This
  /// heuristic is based on ideas described in:
  ///   Look-ahead SLP: Auto-vectorization in the presence of commutative
  ///   operations, CGO 2018 by Vasileios Porpodas, Rodrigo C. O. Rocha,
  ///   Luís F. W. Góes
  int getScoreAtLevelRec(const std::pair<Value *, int> &LHS,
                         const std::pair<Value *, int> &RHS, int CurrLevel,
                         int MaxLevel) {

    Value *V1 = LHS.first;
    Value *V2 = RHS.first;
    // Get the shallow score of V1 and V2.
    int ShallowScoreAtThisLevel =
        std::max((int)ScoreFail, getShallowScore(V1, V2, DL, SE) -
                                     getExternalUsesCost(LHS, RHS));
    int Lane1 = LHS.second;
    int Lane2 = RHS.second;

    // If reached MaxLevel,
    //  or if V1 and V2 are not instructions,
    //  or if they are SPLAT,
    //  or if they are not consecutive, early return the current cost.
    auto *I1 = dyn_cast<Instruction>(V1);
    auto *I2 = dyn_cast<Instruction>(V2);
    if (CurrLevel == MaxLevel || !(I1 && I2) || I1 == I2 ||
        ShallowScoreAtThisLevel == VLOperands::ScoreFail ||
        (isa<LoadInst>(I1) && isa<LoadInst>(I2) && ShallowScoreAtThisLevel))
      return ShallowScoreAtThisLevel;
    assert(I1 && I2 && "Should have early exited.")((I1 && I2 && "Should have early exited.") ? static_cast
<void> (0) : __assert_fail ("I1 && I2 && \"Should have early exited.\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 1089, __PRETTY_FUNCTION__));

    // Keep track of in-tree values for determining the external-use cost.
    InLookAheadValues[V1] = Lane1;
    InLookAheadValues[V2] = Lane2;

    // Contains the I2 operand indexes that got matched with I1 operands.
    SmallSet<unsigned, 4> Op2Used;

    // Recursion towards the operands of I1 and I2. We are trying all possbile
    // operand pairs, and keeping track of the best score.
    for (unsigned OpIdx1 = 0, NumOperands1 = I1->getNumOperands();
         OpIdx1 != NumOperands1; ++OpIdx1) {
      // Try to pair op1I with the best operand of I2.
      int MaxTmpScore = 0;
      unsigned MaxOpIdx2 = 0;
      bool FoundBest = false;
      // If I2 is commutative try all combinations.
      unsigned FromIdx = isCommutative(I2) ? 0 : OpIdx1;
      unsigned ToIdx = isCommutative(I2)
                           ? I2->getNumOperands()
                           : std::min(I2->getNumOperands(), OpIdx1 + 1);
      assert(FromIdx <= ToIdx && "Bad index")((FromIdx <= ToIdx && "Bad index") ? static_cast<
void> (0) : __assert_fail ("FromIdx <= ToIdx && \"Bad index\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 1111, __PRETTY_FUNCTION__));
      for (unsigned OpIdx2 = FromIdx; OpIdx2 != ToIdx; ++OpIdx2) {
        // Skip operands already paired with OpIdx1.
        if (Op2Used.count(OpIdx2))
          continue;
        // Recursively calculate the cost at each level
        int TmpScore = getScoreAtLevelRec({I1->getOperand(OpIdx1), Lane1},
                                          {I2->getOperand(OpIdx2), Lane2},
                                          CurrLevel + 1, MaxLevel);
        // Look for the best score.
        if (TmpScore > VLOperands::ScoreFail && TmpScore > MaxTmpScore) {
          MaxTmpScore = TmpScore;
          MaxOpIdx2 = OpIdx2;
          FoundBest = true;
        }
      }
      if (FoundBest) {
        // Pair {OpIdx1, MaxOpIdx2} was found to be best. Never revisit it.
        Op2Used.insert(MaxOpIdx2);
        ShallowScoreAtThisLevel += MaxTmpScore;
      }
    }
    return ShallowScoreAtThisLevel;
  }

  /// \Returns the look-ahead score, which tells us how much the sub-trees
  /// rooted at \p LHS and \p RHS match, the more they match the higher the
  /// score. This helps break ties in an informed way when we cannot decide on
  /// the order of the operands by just considering the immediate
  /// predecessors.
  int getLookAheadScore(const std::pair<Value *, int> &LHS,
                        const std::pair<Value *, int> &RHS) {
    InLookAheadValues.clear();
    return getScoreAtLevelRec(LHS, RHS, 1, LookAheadMaxDepth);
  }

  // Search all operands in Ops[*][Lane] for the one that matches best
  // Ops[OpIdx][LastLane] and return its opreand index.
  // If no good match can be found, return None.
  Optional<unsigned>
  getBestOperand(unsigned OpIdx, int Lane, int LastLane,
                 ArrayRef<ReorderingMode> ReorderingModes) {
    unsigned NumOperands = getNumOperands();

    // The operand of the previous lane at OpIdx.
    Value *OpLastLane = getData(OpIdx, LastLane).V;

    // Our strategy mode for OpIdx.
    ReorderingMode RMode = ReorderingModes[OpIdx];

    // The linearized opcode of the operand at OpIdx, Lane.
    bool OpIdxAPO = getData(OpIdx, Lane).APO;

    // The best operand index and its score.
    // Sometimes we have more than one option (e.g., Opcode and Undefs), so we
    // are using the score to differentiate between the two.
    struct BestOpData {
      Optional<unsigned> Idx = None;
      unsigned Score = 0;
    } BestOp;

    // Iterate through all unused operands and look for the best.
    for (unsigned Idx = 0; Idx != NumOperands; ++Idx) {
      // Get the operand at Idx and Lane.
      OperandData &OpData = getData(Idx, Lane);
      Value *Op = OpData.V;
      bool OpAPO = OpData.APO;

      // Skip already selected operands.
      if (OpData.IsUsed)
        continue;

      // Skip if we are trying to move the operand to a position with a
      // different opcode in the linearized tree form. This would break the
      // semantics.
      if (OpAPO != OpIdxAPO)
        continue;

      // Look for an operand that matches the current mode.
      switch (RMode) {
      case ReorderingMode::Load:
      case ReorderingMode::Constant:
      case ReorderingMode::Opcode: {
        bool LeftToRight = Lane > LastLane;
        Value *OpLeft = (LeftToRight) ? OpLastLane : Op;
        Value *OpRight = (LeftToRight) ? Op : OpLastLane;
        unsigned Score =
            getLookAheadScore({OpLeft, LastLane}, {OpRight, Lane});
        if (Score > BestOp.Score) {
          BestOp.Idx = Idx;
          BestOp.Score = Score;
        }
        break;
      }
      case ReorderingMode::Splat:
        if (Op == OpLastLane)
          BestOp.Idx = Idx;
        break;
      case ReorderingMode::Failed:
        return None;
      }
    }

    if (BestOp.Idx) {
      getData(BestOp.Idx.getValue(), Lane).IsUsed = true;
      return BestOp.Idx;
    }
    // If we could not find a good match return None.
    return None;
  }

  /// Helper for reorderOperandVecs. \Returns the lane that we should start
  /// reordering from. This is the one which has the least number of operands
  /// that can freely move about.
  unsigned getBestLaneToStartReordering() const {
    unsigned BestLane = 0;
    unsigned Min = UINT_MAX(2147483647 *2U +1U);
    for (unsigned Lane = 0, NumLanes = getNumLanes(); Lane != NumLanes;
         ++Lane) {
      unsigned NumFreeOps = getMaxNumOperandsThatCanBeReordered(Lane);
      if (NumFreeOps < Min) {
        Min = NumFreeOps;
        BestLane = Lane;
      }
    }
    return BestLane;
  }

  /// \Returns the maximum number of operands that are allowed to be reordered
  /// for \p Lane. This is used as a heuristic for selecting the first lane to
  /// start operand reordering.
  unsigned getMaxNumOperandsThatCanBeReordered(unsigned Lane) const {
    unsigned CntTrue = 0;
    unsigned NumOperands = getNumOperands();
    // Operands with the same APO can be reordered. We therefore need to count
    // how many of them we have for each APO, like this: Cnt[APO] = x.
    // Since we only have two APOs, namely true and false, we can avoid using
    // a map. Instead we can simply count the number of operands that
    // correspond to one of them (in this case the 'true' APO), and calculate
    // the other by subtracting it from the total number of operands.
    for (unsigned OpIdx = 0; OpIdx != NumOperands; ++OpIdx)
      if (getData(OpIdx, Lane).APO)
        ++CntTrue;
    unsigned CntFalse = NumOperands - CntTrue;
    return std::max(CntTrue, CntFalse);
  }

  /// Go through the instructions in VL and append their operands.
  void appendOperandsOfVL(ArrayRef<Value *> VL) {
    assert(!VL.empty() && "Bad VL")((!VL.empty() && "Bad VL") ? static_cast<void> (
0) : __assert_fail ("!VL.empty() && \"Bad VL\"", "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 1260, __PRETTY_FUNCTION__));
    assert((empty() || VL.size() == getNumLanes()) &&(((empty() || VL.size() == getNumLanes()) && "Expected same number of lanes"
) ? static_cast<void> (0) : __assert_fail ("(empty() || VL.size() == getNumLanes()) && \"Expected same number of lanes\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 1262, __PRETTY_FUNCTION__))
           "Expected same number of lanes")(((empty() || VL.size() == getNumLanes()) && "Expected same number of lanes"
) ? static_cast<void> (0) : __assert_fail ("(empty() || VL.size() == getNumLanes()) && \"Expected same number of lanes\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 1262, __PRETTY_FUNCTION__));
    assert(isa<Instruction>(VL[0]) && "Expected instruction")((isa<Instruction>(VL[0]) && "Expected instruction"
) ? static_cast<void> (0) : __assert_fail ("isa<Instruction>(VL[0]) && \"Expected instruction\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 1263, __PRETTY_FUNCTION__));
    unsigned NumOperands = cast<Instruction>(VL[0])->getNumOperands();
    OpsVec.resize(NumOperands);
    unsigned NumLanes = VL.size();
    for (unsigned OpIdx = 0; OpIdx != NumOperands; ++OpIdx) {
      OpsVec[OpIdx].resize(NumLanes);
      for (unsigned Lane = 0; Lane != NumLanes; ++Lane) {
        assert(isa<Instruction>(VL[Lane]) && "Expected instruction")((isa<Instruction>(VL[Lane]) && "Expected instruction"
) ? static_cast<void> (0) : __assert_fail ("isa<Instruction>(VL[Lane]) && \"Expected instruction\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 1270, __PRETTY_FUNCTION__));
        // Our tree has just 3 nodes: the root and two operands.
        // It is therefore trivial to get the APO. We only need to check the
        // opcode of VL[Lane] and whether the operand at OpIdx is the LHS or
        // RHS operand. The LHS operand of both add and sub is never attached
        // to an inversese operation in the linearized form, therefore its APO
        // is false. The RHS is true only if VL[Lane] is an inverse operation.

        // Since operand reordering is performed on groups of commutative
        // operations or alternating sequences (e.g., +, -), we can safely
        // tell the inverse operations by checking commutativity.
        bool IsInverseOperation = !isCommutative(cast<Instruction>(VL[Lane]));
        bool APO = (OpIdx == 0) ? false : IsInverseOperation;
        OpsVec[OpIdx][Lane] = {cast<Instruction>(VL[Lane])->getOperand(OpIdx),
                               APO, false};
      }
    }
  }

  /// \returns the number of operands.
  unsigned getNumOperands() const { return OpsVec.size(); }

  /// \returns the number of lanes.
  unsigned getNumLanes() const { return OpsVec[0].size(); }

  /// \returns the operand value at \p OpIdx and \p Lane.
  Value *getValue(unsigned OpIdx, unsigned Lane) const {
    return getData(OpIdx, Lane).V;
  }

  /// \returns true if the data structure is empty.
  bool empty() const { return OpsVec.empty(); }

  /// Clears the data.
  void clear() { OpsVec.clear(); }

  /// \Returns true if there are enough operands identical to \p Op to fill
  /// the whole vector.
  /// Note: This modifies the 'IsUsed' flag, so a cleanUsed() must follow.
  bool shouldBroadcast(Value *Op, unsigned OpIdx, unsigned Lane) {
    bool OpAPO = getData(OpIdx, Lane).APO;
    for (unsigned Ln = 0, Lns = getNumLanes(); Ln != Lns; ++Ln) {
      if (Ln == Lane)
        continue;
      // This is set to true if we found a candidate for broadcast at Lane.
      bool FoundCandidate = false;
      for (unsigned OpI = 0, OpE = getNumOperands(); OpI != OpE; ++OpI) {
        OperandData &Data = getData(OpI, Ln);
        if (Data.APO != OpAPO || Data.IsUsed)
          continue;
        if (Data.V == Op) {
          FoundCandidate = true;
          Data.IsUsed = true;
          break;
        }
      }
      if (!FoundCandidate)
        return false;
    }
    return true;
  }

public:
  /// Initialize with all the operands of the instruction vector \p RootVL.
  VLOperands(ArrayRef<Value *> RootVL, const DataLayout &DL,
             ScalarEvolution &SE, const BoUpSLP &R)
      : DL(DL), SE(SE), R(R) {
    // Append all the operands of RootVL.
    appendOperandsOfVL(RootVL);
  }

  /// \Returns a value vector with the operands across all lanes for the
  /// opearnd at \p OpIdx.
  ValueList getVL(unsigned OpIdx) const {
    ValueList OpVL(OpsVec[OpIdx].size());
    assert(OpsVec[OpIdx].size() == getNumLanes() &&((OpsVec[OpIdx].size() == getNumLanes() && "Expected same num of lanes across all operands"
) ? static_cast<void> (0) : __assert_fail ("OpsVec[OpIdx].size() == getNumLanes() && \"Expected same num of lanes across all operands\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 1346, __PRETTY_FUNCTION__))
           "Expected same num of lanes across all operands")((OpsVec[OpIdx].size() == getNumLanes() && "Expected same num of lanes across all operands"
) ? static_cast<void> (0) : __assert_fail ("OpsVec[OpIdx].size() == getNumLanes() && \"Expected same num of lanes across all operands\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 1346, __PRETTY_FUNCTION__));
    for (unsigned Lane = 0, Lanes = getNumLanes(); Lane != Lanes; ++Lane)
      OpVL[Lane] = OpsVec[OpIdx][Lane].V;
    return OpVL;
  }

  // Performs operand reordering for 2 or more operands.
  // The original operands are in OrigOps[OpIdx][Lane].
  // The reordered operands are returned in 'SortedOps[OpIdx][Lane]'.
  void reorder() {
    unsigned NumOperands = getNumOperands();
    unsigned NumLanes = getNumLanes();
    // Each operand has its own mode. We are using this mode to help us select
    // the instructions for each lane, so that they match best with the ones
    // we have selected so far.
    SmallVector<ReorderingMode, 2> ReorderingModes(NumOperands);

    // This is a greedy single-pass algorithm. We are going over each lane
    // once and deciding on the best order right away with no back-tracking.
    // However, in order to increase its effectiveness, we start with the lane
    // that has operands that can move the least. For example, given the
    // following lanes:
    //  Lane 0 : A[0] = B[0] + C[0]   // Visited 3rd
    //  Lane 1 : A[1] = C[1] - B[1]   // Visited 1st
    //  Lane 2 : A[2] = B[2] + C[2]   // Visited 2nd
    //  Lane 3 : A[3] = C[3] - B[3]   // Visited 4th
    // we will start at Lane 1, since the operands of the subtraction cannot
    // be reordered. Then we will visit the rest of the lanes in a circular
    // fashion. That is, Lanes 2, then Lane 0, and finally Lane 3.

    // Find the first lane that we will start our search from.
    unsigned FirstLane = getBestLaneToStartReordering();

    // Initialize the modes.
    for (unsigned OpIdx = 0; OpIdx != NumOperands; ++OpIdx) {
      Value *OpLane0 = getValue(OpIdx, FirstLane);
      // Keep track if we have instructions with all the same opcode on one
      // side.
      if (isa<LoadInst>(OpLane0))
        ReorderingModes[OpIdx] = ReorderingMode::Load;
      else if (isa<Instruction>(OpLane0)) {
        // Check if OpLane0 should be broadcast.
        if (shouldBroadcast(OpLane0, OpIdx, FirstLane))
          ReorderingModes[OpIdx] = ReorderingMode::Splat;
        else
          ReorderingModes[OpIdx] = ReorderingMode::Opcode;
      }
      else if (isa<Constant>(OpLane0))
        ReorderingModes[OpIdx] = ReorderingMode::Constant;
      else if (isa<Argument>(OpLane0))
        // Our best hope is a Splat. It may save some cost in some cases.
        ReorderingModes[OpIdx] = ReorderingMode::Splat;
      else
        // NOTE: This should be unreachable.
        ReorderingModes[OpIdx] = ReorderingMode::Failed;
    }

    // If the initial strategy fails for any of the operand indexes, then we
    // perform reordering again in a second pass. This helps avoid assigning
    // high priority to the failed strategy, and should improve reordering for
    // the non-failed operand indexes.
    for (int Pass = 0; Pass != 2; ++Pass) {
      // Skip the second pass if the first pass did not fail.
      bool StrategyFailed = false;
      // Mark all operand data as free to use.
      clearUsed();
      // We keep the original operand order for the FirstLane, so reorder the
      // rest of the lanes. We are visiting the nodes in a circular fashion,
      // using FirstLane as the center point and increasing the radius
      // distance.
      for (unsigned Distance = 1; Distance != NumLanes; ++Distance) {
        // Visit the lane on the right and then the lane on the left.
        for (int Direction : {+1, -1}) {
          int Lane = FirstLane + Direction * Distance;
          if (Lane < 0 || Lane >= (int)NumLanes)
            continue;
          int LastLane = Lane - Direction;
          assert(LastLane >= 0 && LastLane < (int)NumLanes &&((LastLane >= 0 && LastLane < (int)NumLanes &&
 "Out of bounds") ? static_cast<void> (0) : __assert_fail
 ("LastLane >= 0 && LastLane < (int)NumLanes && \"Out of bounds\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 1424, __PRETTY_FUNCTION__))
                 "Out of bounds")((LastLane >= 0 && LastLane < (int)NumLanes &&
 "Out of bounds") ? static_cast<void> (0) : __assert_fail
 ("LastLane >= 0 && LastLane < (int)NumLanes && \"Out of bounds\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 1424, __PRETTY_FUNCTION__));
          // Look for a good match for each operand.
          for (unsigned OpIdx = 0; OpIdx != NumOperands; ++OpIdx) {
            // Search for the operand that matches SortedOps[OpIdx][Lane-1].
            Optional<unsigned> BestIdx =
                getBestOperand(OpIdx, Lane, LastLane, ReorderingModes);
            // By not selecting a value, we allow the operands that follow to
            // select a better matching value. We will get a non-null value in
            // the next run of getBestOperand().
            if (BestIdx) {
              // Swap the current operand with the one returned by
              // getBestOperand().
              swap(OpIdx, BestIdx.getValue(), Lane);
            } else {
              // We failed to find a best operand, set mode to 'Failed'.
              ReorderingModes[OpIdx] = ReorderingMode::Failed;
              // Enable the second pass.
              StrategyFailed = true;
            }
          }
        }
      }
      // Skip second pass if the strategy did not fail.
      if (!StrategyFailed)
        break;
    }
  }

1452#if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
  LLVM_DUMP_METHOD__attribute__((noinline)) __attribute__((__used__)) static StringRef getModeStr(ReorderingMode RMode) {
    switch (RMode) {
    case ReorderingMode::Load:
      return "Load";
    case ReorderingMode::Opcode:
      return "Opcode";
    case ReorderingMode::Constant:
      return "Constant";
    case ReorderingMode::Splat:
      return "Splat";
    case ReorderingMode::Failed:
      return "Failed";
    }
    llvm_unreachable("Unimplemented Reordering Type")::llvm::llvm_unreachable_internal("Unimplemented Reordering Type"
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 1466);
  }

  LLVM_DUMP_METHOD__attribute__((noinline)) __attribute__((__used__)) static raw_ostream &printMode(ReorderingMode RMode,
                                                 raw_ostream &OS) {
    return OS << getModeStr(RMode);
  }

  /// Debug print.
  LLVM_DUMP_METHOD__attribute__((noinline)) __attribute__((__used__)) static void dumpMode(ReorderingMode RMode) {
    printMode(RMode, dbgs());
  }

  friend raw_ostream &operator<<(raw_ostream &OS, ReorderingMode RMode) {
    return printMode(RMode, OS);
  }

  LLVM_DUMP_METHOD__attribute__((noinline)) __attribute__((__used__)) raw_ostream &print(raw_ostream &OS) const {
    const unsigned Indent = 2;
    unsigned Cnt = 0;
    for (const OperandDataVec &OpDataVec : OpsVec) {
      OS << "Operand " << Cnt++ << "\n";
      for (const OperandData &OpData : OpDataVec) {
        OS.indent(Indent) << "{";
        if (Value *V = OpData.V)
          OS << *V;
        else
          OS << "null";
        OS << ", APO:" << OpData.APO << "}\n";
      }
      OS << "\n";
    }
    return OS;
  }

  /// Debug print.
  LLVM_DUMP_METHOD__attribute__((noinline)) __attribute__((__used__)) void dump() const { print(dbgs()); }
1503#endif
};

/// Checks if the instruction is marked for deletion.
bool isDeleted(Instruction *I) const { return DeletedInstructions.count(I); }

/// Marks values operands for later deletion by replacing them with Undefs.
void eraseInstructions(ArrayRef<Value *> AV);

~BoUpSLP();

1514private:
/// Checks if all users of \p I are the part of the vectorization tree.
bool areAllUsersVectorized(Instruction *I) const;

/// \returns the cost of the vectorizable entry.
InstructionCost getEntryCost(TreeEntry *E);

/// This is the recursive part of buildTree.
void buildTree_rec(ArrayRef<Value *> Roots, unsigned Depth,
                   const EdgeInfo &EI);

/// \returns true if the ExtractElement/ExtractValue instructions in \p VL can
/// be vectorized to use the original vector (or aggregate "bitcast" to a
/// vector) and sets \p CurrentOrder to the identity permutation; otherwise
/// returns false, setting \p CurrentOrder to either an empty vector or a
/// non-identity permutation that allows to reuse extract instructions.
bool canReuseExtract(ArrayRef<Value *> VL, Value *OpValue,
                     SmallVectorImpl<unsigned> &CurrentOrder) const;

/// Vectorize a single entry in the tree.
Value *vectorizeTree(TreeEntry *E);

/// Vectorize a single entry in the tree, starting in \p VL.
Value *vectorizeTree(ArrayRef<Value *> VL);

/// \returns the scalarization cost for this type. Scalarization in this
/// context means the creation of vectors from a group of scalars.
InstructionCost
getGatherCost(FixedVectorType *Ty,
              const DenseSet<unsigned> &ShuffledIndices) const;

/// \returns the scalarization cost for this list of values. Assuming that
/// this subtree gets vectorized, we may need to extract the values from the
/// roots. This method calculates the cost of extracting the values.
InstructionCost getGatherCost(ArrayRef<Value *> VL) const;

/// Set the Builder insert point to one after the last instruction in
/// the bundle
void setInsertPointAfterBundle(TreeEntry *E);

/// \returns a vector from a collection of scalars in \p VL.
Value *gather(ArrayRef<Value *> VL);

/// \returns whether the VectorizableTree is fully vectorizable and will
/// be beneficial even the tree height is tiny.
bool isFullyVectorizableTinyTree() const;

/// Reorder commutative or alt operands to get better probability of
/// generating vectorized code.
static void reorderInputsAccordingToOpcode(ArrayRef<Value *> VL,
                                           SmallVectorImpl<Value *> &Left,
                                           SmallVectorImpl<Value *> &Right,
                                           const DataLayout &DL,
                                           ScalarEvolution &SE,
                                           const BoUpSLP &R);
struct TreeEntry {
  using VecTreeTy = SmallVector<std::unique_ptr<TreeEntry>, 8>;
  TreeEntry(VecTreeTy &Container) : Container(Container) {}

  /// \returns true if the scalars in VL are equal to this entry.
  bool isSame(ArrayRef<Value *> VL) const {
    if (VL.size() == Scalars.size())
      return std::equal(VL.begin(), VL.end(), Scalars.begin());
    return VL.size() == ReuseShuffleIndices.size() &&
           std::equal(
               VL.begin(), VL.end(), ReuseShuffleIndices.begin(),
               [this](Value *V, int Idx) { return V == Scalars[Idx]; });
  }

  /// A vector of scalars.
  ValueList Scalars;

  /// The Scalars are vectorized into this value. It is initialized to Null.
  Value *VectorizedValue = nullptr;

  /// Do we need to gather this sequence or vectorize it
  /// (either with vector instruction or with scatter/gather
  /// intrinsics for store/load)?
  enum EntryState { Vectorize, ScatterVectorize, NeedToGather };
  EntryState State;

  /// Does this sequence require some shuffling?
  SmallVector<int, 4> ReuseShuffleIndices;

  /// Does this entry require reordering?
  SmallVector<unsigned, 4> ReorderIndices;

  /// Points back to the VectorizableTree.
  ///
  /// Only used for Graphviz right now.  Unfortunately GraphTrait::NodeRef has
  /// to be a pointer and needs to be able to initialize the child iterator.
  /// Thus we need a reference back to the container to translate the indices
  /// to entries.
  VecTreeTy &Container;

  /// The TreeEntry index containing the user of this entry.  We can actually
  /// have multiple users so the data structure is not truly a tree.
  SmallVector<EdgeInfo, 1> UserTreeIndices;

  /// The index of this treeEntry in VectorizableTree.
  int Idx = -1;

private:
  /// The operands of each instruction in each lane Operands[op_index][lane].
  /// Note: This helps avoid the replication of the code that performs the
  /// reordering of operands during buildTree_rec() and vectorizeTree().
  SmallVector<ValueList, 2> Operands;

  /// The main/alternate instruction.
  Instruction *MainOp = nullptr;
  Instruction *AltOp = nullptr;

public:
  /// Set this bundle's \p OpIdx'th operand to \p OpVL.
  void setOperand(unsigned OpIdx, ArrayRef<Value *> OpVL) {
    if (Operands.size() < OpIdx + 1)
      Operands.resize(OpIdx + 1);
    assert(Operands[OpIdx].size() == 0 && "Already resized?")((Operands[OpIdx].size() == 0 && "Already resized?") ?
 static_cast<void> (0) : __assert_fail ("Operands[OpIdx].size() == 0 && \"Already resized?\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 1631, __PRETTY_FUNCTION__));
    Operands[OpIdx].resize(Scalars.size());
    for (unsigned Lane = 0, E = Scalars.size(); Lane != E; ++Lane)
      Operands[OpIdx][Lane] = OpVL[Lane];
  }

  /// Set the operands of this bundle in their original order.
  void setOperandsInOrder() {
    assert(Operands.empty() && "Already initialized?")((Operands.empty() && "Already initialized?") ? static_cast
<void> (0) : __assert_fail ("Operands.empty() && \"Already initialized?\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 1639, __PRETTY_FUNCTION__));
    auto *I0 = cast<Instruction>(Scalars[0]);
    Operands.resize(I0->getNumOperands());
    unsigned NumLanes = Scalars.size();
    for (unsigned OpIdx = 0, NumOperands = I0->getNumOperands();
         OpIdx != NumOperands; ++OpIdx) {
      Operands[OpIdx].resize(NumLanes);
      for (unsigned Lane = 0; Lane != NumLanes; ++Lane) {
        auto *I = cast<Instruction>(Scalars[Lane]);
        assert(I->getNumOperands() == NumOperands &&((I->getNumOperands() == NumOperands && "Expected same number of operands"
) ? static_cast<void> (0) : __assert_fail ("I->getNumOperands() == NumOperands && \"Expected same number of operands\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 1649, __PRETTY_FUNCTION__))
               "Expected same number of operands")((I->getNumOperands() == NumOperands && "Expected same number of operands"
) ? static_cast<void> (0) : __assert_fail ("I->getNumOperands() == NumOperands && \"Expected same number of operands\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 1649, __PRETTY_FUNCTION__));
        Operands[OpIdx][Lane] = I->getOperand(OpIdx);
      }
    }
  }

  /// \returns the \p OpIdx operand of this TreeEntry.
  ValueList &getOperand(unsigned OpIdx) {
    assert(OpIdx < Operands.size() && "Off bounds")((OpIdx < Operands.size() && "Off bounds") ? static_cast
<void> (0) : __assert_fail ("OpIdx < Operands.size() && \"Off bounds\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 1657, __PRETTY_FUNCTION__));
    return Operands[OpIdx];
  }

  /// \returns the number of operands.
  unsigned getNumOperands() const { return Operands.size(); }

  /// \return the single \p OpIdx operand.
  Value *getSingleOperand(unsigned OpIdx) const {
    assert(OpIdx < Operands.size() && "Off bounds")((OpIdx < Operands.size() && "Off bounds") ? static_cast
<void> (0) : __assert_fail ("OpIdx < Operands.size() && \"Off bounds\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 1666, __PRETTY_FUNCTION__));
    assert(!Operands[OpIdx].empty() && "No operand available")((!Operands[OpIdx].empty() && "No operand available")
 ? static_cast<void> (0) : __assert_fail ("!Operands[OpIdx].empty() && \"No operand available\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 1667, __PRETTY_FUNCTION__));
    return Operands[OpIdx][0];
  }

  /// Some of the instructions in the list have alternate opcodes.
  bool isAltShuffle() const {
    return getOpcode() != getAltOpcode();
  }

  bool isOpcodeOrAlt(Instruction *I) const {
    unsigned CheckedOpcode = I->getOpcode();
    return (getOpcode() == CheckedOpcode ||
            getAltOpcode() == CheckedOpcode);
  }

  /// Chooses the correct key for scheduling data. If \p Op has the same (or
  /// alternate) opcode as \p OpValue, the key is \p Op. Otherwise the key is
  /// \p OpValue.
  Value *isOneOf(Value *Op) const {
    auto *I = dyn_cast<Instruction>(Op);
    if (I && isOpcodeOrAlt(I))
      return Op;
    return MainOp;
  }

  void setOperations(const InstructionsState &S) {
    MainOp = S.MainOp;
    AltOp = S.AltOp;
  }

  Instruction *getMainOp() const {
    return MainOp;
  }

  Instruction *getAltOp() const {
    return AltOp;
  }

  /// The main/alternate opcodes for the list of instructions.
  unsigned getOpcode() const {
    return MainOp ? MainOp->getOpcode() : 0;
  }

  unsigned getAltOpcode() const {
    return AltOp ? AltOp->getOpcode() : 0;
  }

  /// Update operations state of this entry if reorder occurred.
  bool updateStateIfReorder() {
    if (ReorderIndices.empty())
      return false;
    InstructionsState S = getSameOpcode(Scalars, ReorderIndices.front());
    setOperations(S);
    return true;
  }

1723#ifndef NDEBUG
  /// Debug printer.
  LLVM_DUMP_METHOD__attribute__((noinline)) __attribute__((__used__)) void dump() const {
    dbgs() << Idx << ".\n";
    for (unsigned OpI = 0, OpE = Operands.size(); OpI != OpE; ++OpI) {
      dbgs() << "Operand " << OpI << ":\n";
      for (const Value *V : Operands[OpI])
        dbgs().indent(2) << *V << "\n";
    }
    dbgs() << "Scalars: \n";
    for (Value *V : Scalars)
      dbgs().indent(2) << *V << "\n";
    dbgs() << "State: ";
    switch (State) {
    case Vectorize:
      dbgs() << "Vectorize\n";
      break;
    case ScatterVectorize:
      dbgs() << "ScatterVectorize\n";
      break;
    case NeedToGather:
      dbgs() << "NeedToGather\n";
      break;
    }
    dbgs() << "MainOp: ";
    if (MainOp)
      dbgs() << *MainOp << "\n";
    else
      dbgs() << "NULL\n";
    dbgs() << "AltOp: ";
    if (AltOp)
      dbgs() << *AltOp << "\n";
    else
      dbgs() << "NULL\n";
    dbgs() << "VectorizedValue: ";
    if (VectorizedValue)
      dbgs() << *VectorizedValue << "\n";
    else
      dbgs() << "NULL\n";
    dbgs() << "ReuseShuffleIndices: ";
    if (ReuseShuffleIndices.empty())
      dbgs() << "Empty";
    else
      for (unsigned ReuseIdx : ReuseShuffleIndices)
        dbgs() << ReuseIdx << ", ";
    dbgs() << "\n";
    dbgs() << "ReorderIndices: ";
    for (unsigned ReorderIdx : ReorderIndices)
      dbgs() << ReorderIdx << ", ";
    dbgs() << "\n";
    dbgs() << "UserTreeIndices: ";
    for (const auto &EInfo : UserTreeIndices)
      dbgs() << EInfo << ", ";
    dbgs() << "\n";
  }
1778#endif
};

1781#ifndef NDEBUG
void dumpTreeCosts(TreeEntry *E, InstructionCost ReuseShuffleCost,
                   InstructionCost VecCost,
                   InstructionCost ScalarCost) const {
  dbgs() << "SLP: Calculated costs for Tree:\n"; E->dump();
  dbgs() << "SLP: Costs:\n";
  dbgs() << "SLP:     ReuseShuffleCost = " << ReuseShuffleCost << "\n";
  dbgs() << "SLP:     VectorCost = " << VecCost << "\n";
  dbgs() << "SLP:     ScalarCost = " << ScalarCost << "\n";
  dbgs() << "SLP:     ReuseShuffleCost + VecCost - ScalarCost = " <<
             ReuseShuffleCost + VecCost - ScalarCost << "\n";
}
1793#endif

/// Create a new VectorizableTree entry.
TreeEntry *newTreeEntry(ArrayRef<Value *> VL, Optional<ScheduleData *> Bundle,
                        const InstructionsState &S,
                        const EdgeInfo &UserTreeIdx,
                        ArrayRef<unsigned> ReuseShuffleIndices = None,
                        ArrayRef<unsigned> ReorderIndices = None) {
  TreeEntry::EntryState EntryState =
      Bundle ? TreeEntry::Vectorize : TreeEntry::NeedToGather;
  return newTreeEntry(VL, EntryState, Bundle, S, UserTreeIdx,
                      ReuseShuffleIndices, ReorderIndices);
}

TreeEntry *newTreeEntry(ArrayRef<Value *> VL,
                        TreeEntry::EntryState EntryState,
                        Optional<ScheduleData *> Bundle,
                        const InstructionsState &S,
                        const EdgeInfo &UserTreeIdx,
                        ArrayRef<unsigned> ReuseShuffleIndices = None,
                        ArrayRef<unsigned> ReorderIndices = None) {
  assert(((!Bundle && EntryState == TreeEntry::NeedToGather) ||((((!Bundle && EntryState == TreeEntry::NeedToGather)
 || (Bundle && EntryState != TreeEntry::NeedToGather)
) && "Need to vectorize gather entry?") ? static_cast
<void> (0) : __assert_fail ("((!Bundle && EntryState == TreeEntry::NeedToGather) || (Bundle && EntryState != TreeEntry::NeedToGather)) && \"Need to vectorize gather entry?\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 1816, __PRETTY_FUNCTION__))
          (Bundle && EntryState != TreeEntry::NeedToGather)) &&((((!Bundle && EntryState == TreeEntry::NeedToGather)
 || (Bundle && EntryState != TreeEntry::NeedToGather)
) && "Need to vectorize gather entry?") ? static_cast
<void> (0) : __assert_fail ("((!Bundle && EntryState == TreeEntry::NeedToGather) || (Bundle && EntryState != TreeEntry::NeedToGather)) && \"Need to vectorize gather entry?\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 1816, __PRETTY_FUNCTION__))
         "Need to vectorize gather entry?")((((!Bundle && EntryState == TreeEntry::NeedToGather)
 || (Bundle && EntryState != TreeEntry::NeedToGather)
) && "Need to vectorize gather entry?") ? static_cast
<void> (0) : __assert_fail ("((!Bundle && EntryState == TreeEntry::NeedToGather) || (Bundle && EntryState != TreeEntry::NeedToGather)) && \"Need to vectorize gather entry?\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 1816, __PRETTY_FUNCTION__));
  VectorizableTree.push_back(std::make_unique<TreeEntry>(VectorizableTree));
  TreeEntry *Last = VectorizableTree.back().get();
  Last->Idx = VectorizableTree.size() - 1;
  Last->Scalars.insert(Last->Scalars.begin(), VL.begin(), VL.end());
  Last->State = EntryState;
  Last->ReuseShuffleIndices.append(ReuseShuffleIndices.begin(),
                                   ReuseShuffleIndices.end());
  Last->ReorderIndices.append(ReorderIndices.begin(), ReorderIndices.end());
  Last->setOperations(S);
  if (Last->State != TreeEntry::NeedToGather) {
    for (Value *V : VL) {
      assert(!getTreeEntry(V) && "Scalar already in tree!")((!getTreeEntry(V) && "Scalar already in tree!") ? static_cast
<void> (0) : __assert_fail ("!getTreeEntry(V) && \"Scalar already in tree!\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 1828, __PRETTY_FUNCTION__));
      ScalarToTreeEntry[V] = Last;
    }
    // Update the scheduler bundle to point to this TreeEntry.
    unsigned Lane = 0;
    for (ScheduleData *BundleMember = Bundle.getValue(); BundleMember;
         BundleMember = BundleMember->NextInBundle) {
      BundleMember->TE = Last;
      BundleMember->Lane = Lane;
      ++Lane;
    }
    assert((!Bundle.getValue() || Lane == VL.size()) &&(((!Bundle.getValue() || Lane == VL.size()) && "Bundle and VL out of sync"
) ? static_cast<void> (0) : __assert_fail ("(!Bundle.getValue() || Lane == VL.size()) && \"Bundle and VL out of sync\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 1840, __PRETTY_FUNCTION__))
           "Bundle and VL out of sync")(((!Bundle.getValue() || Lane == VL.size()) && "Bundle and VL out of sync"
) ? static_cast<void> (0) : __assert_fail ("(!Bundle.getValue() || Lane == VL.size()) && \"Bundle and VL out of sync\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 1840, __PRETTY_FUNCTION__));
  } else {
    MustGather.insert(VL.begin(), VL.end());
  }

  if (UserTreeIdx.UserTE)
    Last->UserTreeIndices.push_back(UserTreeIdx);

  return Last;
}

/// -- Vectorization State --
/// Holds all of the tree entries.
TreeEntry::VecTreeTy VectorizableTree;

1855#ifndef NDEBUG
/// Debug printer.
LLVM_DUMP_METHOD__attribute__((noinline)) __attribute__((__used__)) void dumpVectorizableTree() const {
  for (unsigned Id = 0, IdE = VectorizableTree.size(); Id != IdE; ++Id) {
    VectorizableTree[Id]->dump();
    dbgs() << "\n";
  }
}
1863#endif

TreeEntry *getTreeEntry(Value *V) { return ScalarToTreeEntry.lookup(V); }

const TreeEntry *getTreeEntry(Value *V) const {
  return ScalarToTreeEntry.lookup(V);
}

/// Maps a specific scalar to its tree entry.
SmallDenseMap<Value*, TreeEntry *> ScalarToTreeEntry;

/// Maps a value to the proposed vectorizable size.
SmallDenseMap<Value *, unsigned> InstrElementSize;

/// A list of scalars that we found that we need to keep as scalars.
ValueSet MustGather;

/// This POD struct describes one external user in the vectorized tree.
struct ExternalUser {
  ExternalUser(Value *S, llvm::User *U, int L)
      : Scalar(S), User(U), Lane(L) {}

  // Which scalar in our function.
  Value *Scalar;

  // Which user that uses the scalar.
  llvm::User *User;

  // Which lane does the scalar belong to.
  int Lane;
};
using UserList = SmallVector<ExternalUser, 16>;

/// Checks if two instructions may access the same memory.
///
/// \p Loc1 is the location of \p Inst1. It is passed explicitly because it
/// is invariant in the calling loop.
bool isAliased(const MemoryLocation &Loc1, Instruction *Inst1,
               Instruction *Inst2) {
  // First check if the result is already in the cache.
  AliasCacheKey key = std::make_pair(Inst1, Inst2);
  Optional<bool> &result = AliasCache[key];
  if (result.hasValue()) {
    return result.getValue();
  }
  MemoryLocation Loc2 = getLocation(Inst2, AA);
  bool aliased = true;
  if (Loc1.Ptr && Loc2.Ptr && isSimple(Inst1) && isSimple(Inst2)) {
    // Do the alias check.
    aliased = !AA->isNoAlias(Loc1, Loc2);
  }
  // Store the result in the cache.
  result = aliased;
  return aliased;
}

using AliasCacheKey = std::pair<Instruction *, Instruction *>;

/// Cache for alias results.
/// TODO: consider moving this to the AliasAnalysis itself.
DenseMap<AliasCacheKey, Optional<bool>> AliasCache;

/// Removes an instruction from its block and eventually deletes it.
/// It's like Instruction::eraseFromParent() except that the actual deletion
/// is delayed until BoUpSLP is destructed.
/// This is required to ensure that there are no incorrect collisions in the
/// AliasCache, which can happen if a new instruction is allocated at the
/// same address as a previously deleted instruction.
void eraseInstruction(Instruction *I, bool ReplaceOpsWithUndef = false) {
  auto It = DeletedInstructions.try_emplace(I, ReplaceOpsWithUndef).first;
  It->getSecond() = It->getSecond() && ReplaceOpsWithUndef;
}

/// Temporary store for deleted instructions. Instructions will be deleted
/// eventually when the BoUpSLP is destructed.
DenseMap<Instruction *, bool> DeletedInstructions;

/// A list of values that need to extracted out of the tree.
/// This list holds pairs of (Internal Scalar : External User). External User
/// can be nullptr, it means that this Internal Scalar will be used later,
/// after vectorization.
UserList ExternalUses;

/// Values used only by @llvm.assume calls.
SmallPtrSet<const Value *, 32> EphValues;

/// Holds all of the instructions that we gathered.
SetVector<Instruction *> GatherSeq;

/// A list of blocks that we are going to CSE.
SetVector<BasicBlock *> CSEBlocks;

/// Contains all scheduling relevant data for an instruction.
/// A ScheduleData either represents a single instruction or a member of an
/// instruction bundle (= a group of instructions which is combined into a
/// vector instruction).
struct ScheduleData {
  // The initial value for the dependency counters. It means that the
  // dependencies are not calculated yet.
  enum { InvalidDeps = -1 };

  ScheduleData() = default;

  void init(int BlockSchedulingRegionID, Value *OpVal) {
    FirstInBundle = this;
    NextInBundle = nullptr;
    NextLoadStore = nullptr;
    IsScheduled = false;
    SchedulingRegionID = BlockSchedulingRegionID;
    UnscheduledDepsInBundle = UnscheduledDeps;
    clearDependencies();
    OpValue = OpVal;
    TE = nullptr;
    Lane = -1;
  }

  /// Returns true if the dependency information has been calculated.
  bool hasValidDependencies() const { return Dependencies != InvalidDeps; }

  /// Returns true for single instructions and for bundle representatives
  /// (= the head of a bundle).
  bool isSchedulingEntity() const { return FirstInBundle == this; }

  /// Returns true if it represents an instruction bundle and not only a
  /// single instruction.
  bool isPartOfBundle() const {
    return NextInBundle != nullptr || FirstInBundle != this;
  }

  /// Returns true if it is ready for scheduling, i.e. it has no more
  /// unscheduled depending instructions/bundles.
  bool isReady() const {
    assert(isSchedulingEntity() &&((isSchedulingEntity() && "can't consider non-scheduling entity for ready list"
) ? static_cast<void> (0) : __assert_fail ("isSchedulingEntity() && \"can't consider non-scheduling entity for ready list\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 1996, __PRETTY_FUNCTION__))
           "can't consider non-scheduling entity for ready list")((isSchedulingEntity() && "can't consider non-scheduling entity for ready list"
) ? static_cast<void> (0) : __assert_fail ("isSchedulingEntity() && \"can't consider non-scheduling entity for ready list\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 1996, __PRETTY_FUNCTION__));
    return UnscheduledDepsInBundle == 0 && !IsScheduled;
  }

  /// Modifies the number of unscheduled dependencies, also updating it for
  /// the whole bundle.
  int incrementUnscheduledDeps(int Incr) {
    UnscheduledDeps += Incr;
    return FirstInBundle->UnscheduledDepsInBundle += Incr;
  }

  /// Sets the number of unscheduled dependencies to the number of
  /// dependencies.
  void resetUnscheduledDeps() {
    incrementUnscheduledDeps(Dependencies - UnscheduledDeps);
  }

  /// Clears all dependency information.
  void clearDependencies() {
    Dependencies = InvalidDeps;
    resetUnscheduledDeps();
    MemoryDependencies.clear();
  }

  void dump(raw_ostream &os) const {
    if (!isSchedulingEntity()) {
      os << "/ " << *Inst;
    } else if (NextInBundle) {
      os << '[' << *Inst;
      ScheduleData *SD = NextInBundle;
      while (SD) {
        os << ';' << *SD->Inst;
        SD = SD->NextInBundle;
      }
      os << ']';
    } else {
      os << *Inst;
    }
  }

  Instruction *Inst = nullptr;

  /// Points to the head in an instruction bundle (and always to this for
  /// single instructions).
  ScheduleData *FirstInBundle = nullptr;

  /// Single linked list of all instructions in a bundle. Null if it is a
  /// single instruction.
  ScheduleData *NextInBundle = nullptr;

  /// Single linked list of all memory instructions (e.g. load, store, call)
  /// in the block - until the end of the scheduling region.
  ScheduleData *NextLoadStore = nullptr;

  /// The dependent memory instructions.
  /// This list is derived on demand in calculateDependencies().
  SmallVector<ScheduleData *, 4> MemoryDependencies;

  /// This ScheduleData is in the current scheduling region if this matches
  /// the current SchedulingRegionID of BlockScheduling.
  int SchedulingRegionID = 0;

  /// Used for getting a "good" final ordering of instructions.
  int SchedulingPriority = 0;

  /// The number of dependencies. Constitutes of the number of users of the
  /// instruction plus the number of dependent memory instructions (if any).
  /// This value is calculated on demand.
  /// If InvalidDeps, the number of dependencies is not calculated yet.
  int Dependencies = InvalidDeps;

  /// The number of dependencies minus the number of dependencies of scheduled
  /// instructions. As soon as this is zero, the instruction/bundle gets ready
  /// for scheduling.
  /// Note that this is negative as long as Dependencies is not calculated.
  int UnscheduledDeps = InvalidDeps;

  /// The sum of UnscheduledDeps in a bundle. Equals to UnscheduledDeps for
  /// single instructions.
  int UnscheduledDepsInBundle = InvalidDeps;

  /// True if this instruction is scheduled (or considered as scheduled in the
  /// dry-run).
  bool IsScheduled = false;

  /// Opcode of the current instruction in the schedule data.
  Value *OpValue = nullptr;

  /// The TreeEntry that this instruction corresponds to.
  TreeEntry *TE = nullptr;

  /// The lane of this node in the TreeEntry.
  int Lane = -1;
};

2091#ifndef NDEBUG
friend inline raw_ostream &operator<<(raw_ostream &os,
                                      const BoUpSLP::ScheduleData &SD) {
  SD.dump(os);
  return os;
}
2097#endif

friend struct GraphTraits<BoUpSLP *>;
friend struct DOTGraphTraits<BoUpSLP *>;

/// Contains all scheduling data for a basic block.
struct BlockScheduling {
  BlockScheduling(BasicBlock *BB)
      : BB(BB), ChunkSize(BB->size()), ChunkPos(ChunkSize) {}

  void clear() {
    ReadyInsts.clear();
    ScheduleStart = nullptr;
    ScheduleEnd = nullptr;
    FirstLoadStoreInRegion = nullptr;
    LastLoadStoreInRegion = nullptr;

    // Reduce the maximum schedule region size by the size of the
    // previous scheduling run.
    ScheduleRegionSizeLimit -= ScheduleRegionSize;
    if (ScheduleRegionSizeLimit < MinScheduleRegionSize)
      ScheduleRegionSizeLimit = MinScheduleRegionSize;
    ScheduleRegionSize = 0;

    // Make a new scheduling region, i.e. all existing ScheduleData is not
    // in the new region yet.
    ++SchedulingRegionID;
  }

  ScheduleData *getScheduleData(Value *V) {
    ScheduleData *SD = ScheduleDataMap[V];
    if (SD && SD->SchedulingRegionID == SchedulingRegionID)
      return SD;
    return nullptr;
  }

  ScheduleData *getScheduleData(Value *V, Value *Key) {
    if (V == Key)
      return getScheduleData(V);
    auto I = ExtraScheduleDataMap.find(V);
    if (I != ExtraScheduleDataMap.end()) {
      ScheduleData *SD = I->second[Key];
      if (SD && SD->SchedulingRegionID == SchedulingRegionID)
        return SD;
    }
    return nullptr;
  }

  bool isInSchedulingRegion(ScheduleData *SD) const {
    return SD->SchedulingRegionID == SchedulingRegionID;
  }

  /// Marks an instruction as scheduled and puts all dependent ready
  /// instructions into the ready-list.
  template <typename ReadyListType>
  void schedule(ScheduleData *SD, ReadyListType &ReadyList) {
    SD->IsScheduled = true;
    LLVM_DEBUG(dbgs() << "SLP:   schedule " << *SD << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP:   schedule " << *SD <<
 "\n"; } } while (false);

    ScheduleData *BundleMember = SD;
    while (BundleMember) {
      if (BundleMember->Inst != BundleMember->OpValue) {
        BundleMember = BundleMember->NextInBundle;
        continue;
      }
      // Handle the def-use chain dependencies.

      // Decrement the unscheduled counter and insert to ready list if ready.
      auto &&DecrUnsched = [this, &ReadyList](Instruction *I) {
        doForAllOpcodes(I, [&ReadyList](ScheduleData *OpDef) {
          if (OpDef && OpDef->hasValidDependencies() &&
              OpDef->incrementUnscheduledDeps(-1) == 0) {
            // There are no more unscheduled dependencies after
            // decrementing, so we can put the dependent instruction
            // into the ready list.
            ScheduleData *DepBundle = OpDef->FirstInBundle;
            assert(!DepBundle->IsScheduled &&((!DepBundle->IsScheduled && "already scheduled bundle gets ready"
) ? static_cast<void> (0) : __assert_fail ("!DepBundle->IsScheduled && \"already scheduled bundle gets ready\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 2174, __PRETTY_FUNCTION__))
                   "already scheduled bundle gets ready")((!DepBundle->IsScheduled && "already scheduled bundle gets ready"
) ? static_cast<void> (0) : __assert_fail ("!DepBundle->IsScheduled && \"already scheduled bundle gets ready\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 2174, __PRETTY_FUNCTION__));
            ReadyList.insert(DepBundle);
            LLVM_DEBUG(dbgs()do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP:    gets ready (def): " <<
 *DepBundle << "\n"; } } while (false)
                       << "SLP:    gets ready (def): " << *DepBundle << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP:    gets ready (def): " <<
 *DepBundle << "\n"; } } while (false);
          }
        });
      };

      // If BundleMember is a vector bundle, its operands may have been
      // reordered duiring buildTree(). We therefore need to get its operands
      // through the TreeEntry.
      if (TreeEntry *TE = BundleMember->TE) {
        int Lane = BundleMember->Lane;
        assert(Lane >= 0 && "Lane not set")((Lane >= 0 && "Lane not set") ? static_cast<void
> (0) : __assert_fail ("Lane >= 0 && \"Lane not set\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 2187, __PRETTY_FUNCTION__));

        // Since vectorization tree is being built recursively this assertion
        // ensures that the tree entry has all operands set before reaching
        // this code. Couple of exceptions known at the moment are extracts
        // where their second (immediate) operand is not added. Since
        // immediates do not affect scheduler behavior this is considered
        // okay.
        auto *In = TE->getMainOp();
        assert(In &&((In && (isa<ExtractValueInst>(In) || isa<ExtractElementInst
>(In) || In->getNumOperands() == TE->getNumOperands(
)) && "Missed TreeEntry operands?") ? static_cast<
void> (0) : __assert_fail ("In && (isa<ExtractValueInst>(In) || isa<ExtractElementInst>(In) || In->getNumOperands() == TE->getNumOperands()) && \"Missed TreeEntry operands?\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 2199, __PRETTY_FUNCTION__))
               (isa<ExtractValueInst>(In) || isa<ExtractElementInst>(In) ||((In && (isa<ExtractValueInst>(In) || isa<ExtractElementInst
>(In) || In->getNumOperands() == TE->getNumOperands(
)) && "Missed TreeEntry operands?") ? static_cast<
void> (0) : __assert_fail ("In && (isa<ExtractValueInst>(In) || isa<ExtractElementInst>(In) || In->getNumOperands() == TE->getNumOperands()) && \"Missed TreeEntry operands?\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 2199, __PRETTY_FUNCTION__))
                In->getNumOperands() == TE->getNumOperands()) &&((In && (isa<ExtractValueInst>(In) || isa<ExtractElementInst
>(In) || In->getNumOperands() == TE->getNumOperands(
)) && "Missed TreeEntry operands?") ? static_cast<
void> (0) : __assert_fail ("In && (isa<ExtractValueInst>(In) || isa<ExtractElementInst>(In) || In->getNumOperands() == TE->getNumOperands()) && \"Missed TreeEntry operands?\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 2199, __PRETTY_FUNCTION__))
               "Missed TreeEntry operands?")((In && (isa<ExtractValueInst>(In) || isa<ExtractElementInst
>(In) || In->getNumOperands() == TE->getNumOperands(
)) && "Missed TreeEntry operands?") ? static_cast<
void> (0) : __assert_fail ("In && (isa<ExtractValueInst>(In) || isa<ExtractElementInst>(In) || In->getNumOperands() == TE->getNumOperands()) && \"Missed TreeEntry operands?\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 2199, __PRETTY_FUNCTION__));
        (void)In; // fake use to avoid build failure when assertions disabled

        for (unsigned OpIdx = 0, NumOperands = TE->getNumOperands();
             OpIdx != NumOperands; ++OpIdx)
          if (auto *I = dyn_cast<Instruction>(TE->getOperand(OpIdx)[Lane]))
            DecrUnsched(I);
      } else {
        // If BundleMember is a stand-alone instruction, no operand reordering
        // has taken place, so we directly access its operands.
        for (Use &U : BundleMember->Inst->operands())
          if (auto *I = dyn_cast<Instruction>(U.get()))
            DecrUnsched(I);
      }
      // Handle the memory dependencies.
      for (ScheduleData *MemoryDepSD : BundleMember->MemoryDependencies) {
        if (MemoryDepSD->incrementUnscheduledDeps(-1) == 0) {
          // There are no more unscheduled dependencies after decrementing,
          // so we can put the dependent instruction into the ready list.
          ScheduleData *DepBundle = MemoryDepSD->FirstInBundle;
          assert(!DepBundle->IsScheduled &&((!DepBundle->IsScheduled && "already scheduled bundle gets ready"
) ? static_cast<void> (0) : __assert_fail ("!DepBundle->IsScheduled && \"already scheduled bundle gets ready\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 2220, __PRETTY_FUNCTION__))
                 "already scheduled bundle gets ready")((!DepBundle->IsScheduled && "already scheduled bundle gets ready"
) ? static_cast<void> (0) : __assert_fail ("!DepBundle->IsScheduled && \"already scheduled bundle gets ready\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 2220, __PRETTY_FUNCTION__));
          ReadyList.insert(DepBundle);
          LLVM_DEBUG(dbgs()do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP:    gets ready (mem): " <<
 *DepBundle << "\n"; } } while (false)
                     << "SLP:    gets ready (mem): " << *DepBundle << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP:    gets ready (mem): " <<
 *DepBundle << "\n"; } } while (false);
        }
      }
      BundleMember = BundleMember->NextInBundle;
    }
  }

  void doForAllOpcodes(Value *V,
                       function_ref<void(ScheduleData *SD)> Action) {
    if (ScheduleData *SD = getScheduleData(V))
      Action(SD);
    auto I = ExtraScheduleDataMap.find(V);
    if (I != ExtraScheduleDataMap.end())
      for (auto &P : I->second)
        if (P.second->SchedulingRegionID == SchedulingRegionID)
          Action(P.second);
  }

  /// Put all instructions into the ReadyList which are ready for scheduling.
  template <typename ReadyListType>
  void initialFillReadyList(ReadyListType &ReadyList) {
    for (auto *I = ScheduleStart; I != ScheduleEnd; I = I->getNextNode()) {
      doForAllOpcodes(I, [&](ScheduleData *SD) {
        if (SD->isSchedulingEntity() && SD->isReady()) {
          ReadyList.insert(SD);
          LLVM_DEBUG(dbgs()do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP:    initially in ready list: "
 << *I << "\n"; } } while (false)
                     << "SLP:    initially in ready list: " << *I << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP:    initially in ready list: "
 << *I << "\n"; } } while (false);
        }
      });
    }
  }

  /// Checks if a bundle of instructions can be scheduled, i.e. has no
  /// cyclic dependencies. This is only a dry-run, no instructions are
  /// actually moved at this stage.
  /// \returns the scheduling bundle. The returned Optional value is non-None
  /// if \p VL is allowed to be scheduled.
  Optional<ScheduleData *>
  tryScheduleBundle(ArrayRef<Value *> VL, BoUpSLP *SLP,
                    const InstructionsState &S);

  /// Un-bundles a group of instructions.
  void cancelScheduling(ArrayRef<Value *> VL, Value *OpValue);

  /// Allocates schedule data chunk.
  ScheduleData *allocateScheduleDataChunks();

  /// Extends the scheduling region so that V is inside the region.
  /// \returns true if the region size is within the limit.
  bool extendSchedulingRegion(Value *V, const InstructionsState &S);

  /// Initialize the ScheduleData structures for new instructions in the
  /// scheduling region.
  void initScheduleData(Instruction *FromI, Instruction *ToI,
                        ScheduleData *PrevLoadStore,
                        ScheduleData *NextLoadStore);

  /// Updates the dependency information of a bundle and of all instructions/
  /// bundles which depend on the original bundle.
  void calculateDependencies(ScheduleData *SD, bool InsertInReadyList,
                             BoUpSLP *SLP);

  /// Sets all instruction in the scheduling region to un-scheduled.
  void resetSchedule();

  BasicBlock *BB;

  /// Simple memory allocation for ScheduleData.
  std::vector<std::unique_ptr<ScheduleData[]>> ScheduleDataChunks;

  /// The size of a ScheduleData array in ScheduleDataChunks.
  int ChunkSize;

  /// The allocator position in the current chunk, which is the last entry
  /// of ScheduleDataChunks.
  int ChunkPos;

  /// Attaches ScheduleData to Instruction.
  /// Note that the mapping survives during all vectorization iterations, i.e.
  /// ScheduleData structures are recycled.
  DenseMap<Value *, ScheduleData *> ScheduleDataMap;

  /// Attaches ScheduleData to Instruction with the leading key.
  DenseMap<Value *, SmallDenseMap<Value *, ScheduleData *>>
      ExtraScheduleDataMap;

  struct ReadyList : SmallVector<ScheduleData *, 8> {
    void insert(ScheduleData *SD) { push_back(SD); }
  };

  /// The ready-list for scheduling (only used for the dry-run).
  ReadyList ReadyInsts;

  /// The first instruction of the scheduling region.
  Instruction *ScheduleStart = nullptr;

  /// The first instruction _after_ the scheduling region.
  Instruction *ScheduleEnd = nullptr;

  /// The first memory accessing instruction in the scheduling region
  /// (can be null).
  ScheduleData *FirstLoadStoreInRegion = nullptr;

  /// The last memory accessing instruction in the scheduling region
  /// (can be null).
  ScheduleData *LastLoadStoreInRegion = nullptr;

  /// The current size of the scheduling region.
  int ScheduleRegionSize = 0;

  /// The maximum size allowed for the scheduling region.
  int ScheduleRegionSizeLimit = ScheduleRegionSizeBudget;

  /// The ID of the scheduling region. For a new vectorization iteration this
  /// is incremented which "removes" all ScheduleData from the region.
  // Make sure that the initial SchedulingRegionID is greater than the
  // initial SchedulingRegionID in ScheduleData (which is 0).
  int SchedulingRegionID = 1;
};

/// Attaches the BlockScheduling structures to basic blocks.
MapVector<BasicBlock *, std::unique_ptr<BlockScheduling>> BlocksSchedules;

/// Performs the "real" scheduling. Done before vectorization is actually
/// performed in a basic block.
void scheduleBlock(BlockScheduling *BS);

/// List of users to ignore during scheduling and that don't need extracting.
ArrayRef<Value *> UserIgnoreList;

/// A DenseMapInfo implementation for holding DenseMaps and DenseSets of
/// sorted SmallVectors of unsigned.
struct OrdersTypeDenseMapInfo {
  static OrdersType getEmptyKey() {
    OrdersType V;
    V.push_back(~1U);
    return V;
  }

  static OrdersType getTombstoneKey() {
    OrdersType V;
    V.push_back(~2U);
    return V;
  }

  static unsigned getHashValue(const OrdersType &V) {
    return static_cast<unsigned>(hash_combine_range(V.begin(), V.end()));
  }

  static bool isEqual(const OrdersType &LHS, const OrdersType &RHS) {
    return LHS == RHS;
  }
};

/// Contains orders of operations along with the number of bundles that have
/// operations in this order. It stores only those orders that require
/// reordering, if reordering is not required it is counted using \a
/// NumOpsWantToKeepOriginalOrder.
DenseMap<OrdersType, unsigned, OrdersTypeDenseMapInfo> NumOpsWantToKeepOrder;
/// Number of bundles that do not require reordering.
unsigned NumOpsWantToKeepOriginalOrder = 0;

// Analysis and block reference.
Function *F;
ScalarEvolution *SE;
TargetTransformInfo *TTI;
TargetLibraryInfo *TLI;
AAResults *AA;
LoopInfo *LI;
DominatorTree *DT;
AssumptionCache *AC;
DemandedBits *DB;
const DataLayout *DL;
OptimizationRemarkEmitter *ORE;

unsigned MaxVecRegSize; // This is set by TTI or overridden by cl::opt.
unsigned MinVecRegSize; // Set by cl::opt (default: 128).

/// Instruction builder to construct the vectorized tree.
IRBuilder<> Builder;

/// A map of scalar integer values to the smallest bit width with which they
/// can legally be represented. The values map to (width, signed) pairs,
/// where "width" indicates the minimum bit width and "signed" is True if the
/// value must be signed-extended, rather than zero-extended, back to its
/// original width.
MapVector<Value *, std::pair<uint64_t, bool>> MinBWs;
2410};

2412} // end namespace slpvectorizer

2414template <> struct GraphTraits<BoUpSLP *> {
using TreeEntry = BoUpSLP::TreeEntry;

/// NodeRef has to be a pointer per the GraphWriter.
using NodeRef = TreeEntry *;

using ContainerTy = BoUpSLP::TreeEntry::VecTreeTy;

/// Add the VectorizableTree to the index iterator to be able to return
/// TreeEntry pointers.
struct ChildIteratorType
    : public iterator_adaptor_base<
          ChildIteratorType, SmallVector<BoUpSLP::EdgeInfo, 1>::iterator> {
  ContainerTy &VectorizableTree;

  ChildIteratorType(SmallVector<BoUpSLP::EdgeInfo, 1>::iterator W,
                    ContainerTy &VT)
      : ChildIteratorType::iterator_adaptor_base(W), VectorizableTree(VT) {}

  NodeRef operator*() { return I->UserTE; }
};

static NodeRef getEntryNode(BoUpSLP &R) {
  return R.VectorizableTree[0].get();
}

static ChildIteratorType child_begin(NodeRef N) {
  return {N->UserTreeIndices.begin(), N->Container};
}

static ChildIteratorType child_end(NodeRef N) {
  return {N->UserTreeIndices.end(), N->Container};
}

/// For the node iterator we just need to turn the TreeEntry iterator into a
/// TreeEntry* iterator so that it dereferences to NodeRef.
class nodes_iterator {
  using ItTy = ContainerTy::iterator;
  ItTy It;

public:
  nodes_iterator(const ItTy &It2) : It(It2) {}
  NodeRef operator*() { return It->get(); }
  nodes_iterator operator++() {
    ++It;
    return *this;
  }
  bool operator!=(const nodes_iterator &N2) const { return N2.It != It; }
};

static nodes_iterator nodes_begin(BoUpSLP *R) {
  return nodes_iterator(R->VectorizableTree.begin());
}

static nodes_iterator nodes_end(BoUpSLP *R) {
  return nodes_iterator(R->VectorizableTree.end());
}

static unsigned size(BoUpSLP *R) { return R->VectorizableTree.size(); }
2473};

2475template <> struct DOTGraphTraits<BoUpSLP *> : public DefaultDOTGraphTraits {
using TreeEntry = BoUpSLP::TreeEntry;

DOTGraphTraits(bool isSimple = false) : DefaultDOTGraphTraits(isSimple) {}

std::string getNodeLabel(const TreeEntry *Entry, const BoUpSLP *R) {
  std::string Str;
  raw_string_ostream OS(Str);
  if (isSplat(Entry->Scalars)) {
    OS << "<splat> " << *Entry->Scalars[0];
    return Str;
  }
  for (auto V : Entry->Scalars) {
    OS << *V;
    if (llvm::any_of(R->ExternalUses, [&](const BoUpSLP::ExternalUser &EU) {
          return EU.Scalar == V;
        }))
      OS << " <extract>";
    OS << "\n";
  }
  return Str;
}

static std::string getNodeAttributes(const TreeEntry *Entry,
                                     const BoUpSLP *) {
  if (Entry->State == TreeEntry::NeedToGather)
    return "color=red";
  return "";
}
2504};

2506} // end namespace llvm

2508BoUpSLP::~BoUpSLP() {
for (const auto &Pair : DeletedInstructions) {
  // Replace operands of ignored instructions with Undefs in case if they were
  // marked for deletion.
  if (Pair.getSecond()) {
    Value *Undef = UndefValue::get(Pair.getFirst()->getType());
    Pair.getFirst()->replaceAllUsesWith(Undef);
  }
  Pair.getFirst()->dropAllReferences();
}
for (const auto &Pair : DeletedInstructions) {
  assert(Pair.getFirst()->use_empty() &&((Pair.getFirst()->use_empty() && "trying to erase instruction with users."
) ? static_cast<void> (0) : __assert_fail ("Pair.getFirst()->use_empty() && \"trying to erase instruction with users.\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 2520, __PRETTY_FUNCTION__))
         "trying to erase instruction with users.")((Pair.getFirst()->use_empty() && "trying to erase instruction with users."
) ? static_cast<void> (0) : __assert_fail ("Pair.getFirst()->use_empty() && \"trying to erase instruction with users.\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 2520, __PRETTY_FUNCTION__));
  Pair.getFirst()->eraseFromParent();
}
2523#ifdef EXPENSIVE_CHECKS
// If we could guarantee that this call is not extremely slow, we could
// remove the ifdef limitation (see PR47712).
assert(!verifyFunction(*F, &dbgs()))((!verifyFunction(*F, &dbgs())) ? static_cast<void>
 (0) : __assert_fail ("!verifyFunction(*F, &dbgs())", "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 2526, __PRETTY_FUNCTION__));
2527#endif
2528}

2530void BoUpSLP::eraseInstructions(ArrayRef<Value *> AV) {
for (auto *V : AV) {
  if (auto *I = dyn_cast<Instruction>(V))
    eraseInstruction(I, /*ReplaceOpsWithUndef=*/true);
};
2535}

2537void BoUpSLP::buildTree(ArrayRef<Value *> Roots,
                      ArrayRef<Value *> UserIgnoreLst) {
ExtraValueToDebugLocsMap ExternallyUsedValues;
buildTree(Roots, ExternallyUsedValues, UserIgnoreLst);
2541}

2543void BoUpSLP::buildTree(ArrayRef<Value *> Roots,
                      ExtraValueToDebugLocsMap &ExternallyUsedValues,
                      ArrayRef<Value *> UserIgnoreLst) {
deleteTree();
UserIgnoreList = UserIgnoreLst;
if (!allSameType(Roots))
  return;
buildTree_rec(Roots, 0, EdgeInfo());

// Collect the values that we need to extract from the tree.
for (auto &TEPtr : VectorizableTree) {
  TreeEntry *Entry = TEPtr.get();

  // No need to handle users of gathered values.
  if (Entry->State == TreeEntry::NeedToGather)
    continue;

  // For each lane:
  for (int Lane = 0, LE = Entry->Scalars.size(); Lane != LE; ++Lane) {
    Value *Scalar = Entry->Scalars[Lane];
    int FoundLane = Lane;
    if (!Entry->ReuseShuffleIndices.empty()) {
      FoundLane =
          std::distance(Entry->ReuseShuffleIndices.begin(),
                        llvm::find(Entry->ReuseShuffleIndices, FoundLane));
    }

    // Check if the scalar is externally used as an extra arg.
    auto ExtI = ExternallyUsedValues.find(Scalar);
    if (ExtI != ExternallyUsedValues.end()) {
      LLVM_DEBUG(dbgs() << "SLP: Need to extract: Extra arg from lane "do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Need to extract: Extra arg from lane "
 << Lane << " from " << *Scalar << ".\n"
; } } while (false)
                        << Lane << " from " << *Scalar << ".\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Need to extract: Extra arg from lane "
 << Lane << " from " << *Scalar << ".\n"
; } } while (false);
      ExternalUses.emplace_back(Scalar, nullptr, FoundLane);
    }
    for (User *U : Scalar->users()) {
      LLVM_DEBUG(dbgs() << "SLP: Checking user:" << *U << ".\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Checking user:" << *U <<
 ".\n"; } } while (false);

      Instruction *UserInst = dyn_cast<Instruction>(U);
      if (!UserInst)
        continue;

      // Skip in-tree scalars that become vectors
      if (TreeEntry *UseEntry = getTreeEntry(U)) {
        Value *UseScalar = UseEntry->Scalars[0];
        // Some in-tree scalars will remain as scalar in vectorized
        // instructions. If that is the case, the one in Lane 0 will
        // be used.
        if (UseScalar != U ||
            UseEntry->State == TreeEntry::ScatterVectorize ||
            !InTreeUserNeedToExtract(Scalar, UserInst, TLI)) {
          LLVM_DEBUG(dbgs() << "SLP: \tInternal user will be removed:" << *Udo { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: \tInternal user will be removed:"
 << *U << ".\n"; } } while (false)
                            << ".\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: \tInternal user will be removed:"
 << *U << ".\n"; } } while (false);
          assert(UseEntry->State != TreeEntry::NeedToGather && "Bad state")((UseEntry->State != TreeEntry::NeedToGather && "Bad state"
) ? static_cast<void> (0) : __assert_fail ("UseEntry->State != TreeEntry::NeedToGather && \"Bad state\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 2595, __PRETTY_FUNCTION__));
          continue;
        }
      }

      // Ignore users in the user ignore list.
      if (is_contained(UserIgnoreList, UserInst))
        continue;

      LLVM_DEBUG(dbgs() << "SLP: Need to extract:" << *U << " from lane "do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Need to extract:" << *
U << " from lane " << Lane << " from " <<
 *Scalar << ".\n"; } } while (false)
                        << Lane << " from " << *Scalar << ".\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Need to extract:" << *
U << " from lane " << Lane << " from " <<
 *Scalar << ".\n"; } } while (false);
      ExternalUses.push_back(ExternalUser(Scalar, U, FoundLane));
    }
  }
}
2610}

2612void BoUpSLP::buildTree_rec(ArrayRef<Value *> VL, unsigned Depth,
                          const EdgeInfo &UserTreeIdx) {
assert((allConstant(VL) || allSameType(VL)) && "Invalid types!")(((allConstant(VL) || allSameType(VL)) && "Invalid types!"
) ? static_cast<void> (0) : __assert_fail ("(allConstant(VL) || allSameType(VL)) && \"Invalid types!\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 2614, __PRETTY_FUNCTION__));

InstructionsState S = getSameOpcode(VL);
if (Depth == RecursionMaxDepth) {
  LLVM_DEBUG(dbgs() << "SLP: Gathering due to max recursion depth.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Gathering due to max recursion depth.\n"
; } } while (false);
  newTreeEntry(VL, None /*not vectorized*/, S, UserTreeIdx);
  return;
}

// Don't handle vectors.
if (S.OpValue->getType()->isVectorTy()) {
  LLVM_DEBUG(dbgs() << "SLP: Gathering due to vector type.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Gathering due to vector type.\n"
; } } while (false);
  newTreeEntry(VL, None /*not vectorized*/, S, UserTreeIdx);
  return;
}

if (StoreInst *SI = dyn_cast<StoreInst>(S.OpValue))
  if (SI->getValueOperand()->getType()->isVectorTy()) {
    LLVM_DEBUG(dbgs() << "SLP: Gathering due to store vector type.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Gathering due to store vector type.\n"
; } } while (false);
    newTreeEntry(VL, None /*not vectorized*/, S, UserTreeIdx);
    return;
  }

// If all of the operands are identical or constant we have a simple solution.
if (allConstant(VL) || isSplat(VL) || !allSameBlock(VL) || !S.getOpcode()) {
  LLVM_DEBUG(dbgs() << "SLP: Gathering due to C,S,B,O. \n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Gathering due to C,S,B,O. \n"
; } } while (false);
  newTreeEntry(VL, None /*not vectorized*/, S, UserTreeIdx);
  return;
}

// We now know that this is a vector of instructions of the same type from
// the same block.

// Don't vectorize ephemeral values.
for (Value *V : VL) {
  if (EphValues.count(V)) {
    LLVM_DEBUG(dbgs() << "SLP: The instruction (" << *Vdo { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: The instruction (" << *
V << ") is ephemeral.\n"; } } while (false)
                      << ") is ephemeral.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: The instruction (" << *
V << ") is ephemeral.\n"; } } while (false);
    newTreeEntry(VL, None /*not vectorized*/, S, UserTreeIdx);
    return;
  }
}

// Check if this is a duplicate of another entry.
if (TreeEntry *E = getTreeEntry(S.OpValue)) {
  LLVM_DEBUG(dbgs() << "SLP: \tChecking bundle: " << *S.OpValue << ".\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: \tChecking bundle: " <<
 *S.OpValue << ".\n"; } } while (false);
  if (!E->isSame(VL)) {
    LLVM_DEBUG(dbgs() << "SLP: Gathering due to partial overlap.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Gathering due to partial overlap.\n"
; } } while (false);
    newTreeEntry(VL, None /*not vectorized*/, S, UserTreeIdx);
    return;
  }
  // Record the reuse of the tree node.  FIXME, currently this is only used to
  // properly draw the graph rather than for the actual vectorization.
  E->UserTreeIndices.push_back(UserTreeIdx);
  LLVM_DEBUG(dbgs() << "SLP: Perfect diamond merge at " << *S.OpValuedo { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Perfect diamond merge at " <<
 *S.OpValue << ".\n"; } } while (false)
                    << ".\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Perfect diamond merge at " <<
 *S.OpValue << ".\n"; } } while (false);
  return;
}

// Check that none of the instructions in the bundle are already in the tree.
for (Value *V : VL) {
  auto *I = dyn_cast<Instruction>(V);
  if (!I)
    continue;
  if (getTreeEntry(I)) {
    LLVM_DEBUG(dbgs() << "SLP: The instruction (" << *Vdo { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: The instruction (" << *
V << ") is already in tree.\n"; } } while (false)
                      << ") is already in tree.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: The instruction (" << *
V << ") is already in tree.\n"; } } while (false);
    newTreeEntry(VL, None /*not vectorized*/, S, UserTreeIdx);
    return;
  }
}

// If any of the scalars is marked as a value that needs to stay scalar, then
// we need to gather the scalars.
// The reduction nodes (stored in UserIgnoreList) also should stay scalar.
for (Value *V : VL) {
  if (MustGather.count(V) || is_contained(UserIgnoreList, V)) {
    LLVM_DEBUG(dbgs() << "SLP: Gathering due to gathered scalar.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Gathering due to gathered scalar.\n"
; } } while (false);
    newTreeEntry(VL, None /*not vectorized*/, S, UserTreeIdx);
    return;
  }
}

// Check that all of the users of the scalars that we want to vectorize are
// schedulable.
auto *VL0 = cast<Instruction>(S.OpValue);
BasicBlock *BB = VL0->getParent();

if (!DT->isReachableFromEntry(BB)) {
  // Don't go into unreachable blocks. They may contain instructions with
  // dependency cycles which confuse the final scheduling.
  LLVM_DEBUG(dbgs() << "SLP: bundle in unreachable block.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: bundle in unreachable block.\n"
; } } while (false);
  newTreeEntry(VL, None /*not vectorized*/, S, UserTreeIdx);
  return;
}

// Check that every instruction appears once in this bundle.
SmallVector<unsigned, 4> ReuseShuffleIndicies;
SmallVector<Value *, 4> UniqueValues;
DenseMap<Value *, unsigned> UniquePositions;
for (Value *V : VL) {
  auto Res = UniquePositions.try_emplace(V, UniqueValues.size());
  ReuseShuffleIndicies.emplace_back(Res.first->second);
  if (Res.second)
    UniqueValues.emplace_back(V);
}
size_t NumUniqueScalarValues = UniqueValues.size();
if (NumUniqueScalarValues == VL.size()) {
  ReuseShuffleIndicies.clear();
} else {
  LLVM_DEBUG(dbgs() << "SLP: Shuffle for reused scalars.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Shuffle for reused scalars.\n"
; } } while (false);
  if (NumUniqueScalarValues <= 1 ||
      !llvm::isPowerOf2_32(NumUniqueScalarValues)) {
    LLVM_DEBUG(dbgs() << "SLP: Scalar used twice in bundle.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Scalar used twice in bundle.\n"
; } } while (false);
    newTreeEntry(VL, None /*not vectorized*/, S, UserTreeIdx);
    return;
  }
  VL = UniqueValues;
}

auto &BSRef = BlocksSchedules[BB];
if (!BSRef)
  BSRef = std::make_unique<BlockScheduling>(BB);

BlockScheduling &BS = *BSRef.get();

Optional<ScheduleData *> Bundle = BS.tryScheduleBundle(VL, this, S);
if (!Bundle) {
  LLVM_DEBUG(dbgs() << "SLP: We are not able to schedule this bundle!\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: We are not able to schedule this bundle!\n"
; } } while (false);
  assert((!BS.getScheduleData(VL0) ||(((!BS.getScheduleData(VL0) || !BS.getScheduleData(VL0)->isPartOfBundle
()) && "tryScheduleBundle should cancelScheduling on failure"
) ? static_cast<void> (0) : __assert_fail ("(!BS.getScheduleData(VL0) || !BS.getScheduleData(VL0)->isPartOfBundle()) && \"tryScheduleBundle should cancelScheduling on failure\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 2745, __PRETTY_FUNCTION__))
          !BS.getScheduleData(VL0)->isPartOfBundle()) &&(((!BS.getScheduleData(VL0) || !BS.getScheduleData(VL0)->isPartOfBundle
()) && "tryScheduleBundle should cancelScheduling on failure"
) ? static_cast<void> (0) : __assert_fail ("(!BS.getScheduleData(VL0) || !BS.getScheduleData(VL0)->isPartOfBundle()) && \"tryScheduleBundle should cancelScheduling on failure\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 2745, __PRETTY_FUNCTION__))
         "tryScheduleBundle should cancelScheduling on failure")(((!BS.getScheduleData(VL0) || !BS.getScheduleData(VL0)->isPartOfBundle
()) && "tryScheduleBundle should cancelScheduling on failure"
) ? static_cast<void> (0) : __assert_fail ("(!BS.getScheduleData(VL0) || !BS.getScheduleData(VL0)->isPartOfBundle()) && \"tryScheduleBundle should cancelScheduling on failure\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 2745, __PRETTY_FUNCTION__));
  newTreeEntry(VL, None /*not vectorized*/, S, UserTreeIdx,
               ReuseShuffleIndicies);
  return;
}
LLVM_DEBUG(dbgs() << "SLP: We are able to schedule this bundle.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: We are able to schedule this bundle.\n"
; } } while (false);

unsigned ShuffleOrOp = S.isAltShuffle() ?
              (unsigned) Instruction::ShuffleVector : S.getOpcode();
switch (ShuffleOrOp) {
  case Instruction::PHI: {
    auto *PH = cast<PHINode>(VL0);

    // Check for terminator values (e.g. invoke).
    for (Value *V : VL)
      for (unsigned I = 0, E = PH->getNumIncomingValues(); I < E; ++I) {
        Instruction *Term = dyn_cast<Instruction>(
            cast<PHINode>(V)->getIncomingValueForBlock(
                PH->getIncomingBlock(I)));
        if (Term && Term->isTerminator()) {
          LLVM_DEBUG(dbgs()do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Need to swizzle PHINodes (terminator use).\n"
; } } while (false)
                     << "SLP: Need to swizzle PHINodes (terminator use).\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Need to swizzle PHINodes (terminator use).\n"
; } } while (false);
          BS.cancelScheduling(VL, VL0);
          newTreeEntry(VL, None /*not vectorized*/, S, UserTreeIdx,
                       ReuseShuffleIndicies);
          return;
        }
      }

    TreeEntry *TE =
        newTreeEntry(VL, Bundle, S, UserTreeIdx, ReuseShuffleIndicies);
    LLVM_DEBUG(dbgs() << "SLP: added a vector of PHINodes.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: added a vector of PHINodes.\n"
; } } while (false);

    // Keeps the reordered operands to avoid code duplication.
    SmallVector<ValueList, 2> OperandsVec;
    for (unsigned I = 0, E = PH->getNumIncomingValues(); I < E; ++I) {
      ValueList Operands;
      // Prepare the operand vector.
      for (Value *V : VL)
        Operands.push_back(cast<PHINode>(V)->getIncomingValueForBlock(
            PH->getIncomingBlock(I)));
      TE->setOperand(I, Operands);
      OperandsVec.push_back(Operands);
    }
    for (unsigned OpIdx = 0, OpE = OperandsVec.size(); OpIdx != OpE; ++OpIdx)
      buildTree_rec(OperandsVec[OpIdx], Depth + 1, {TE, OpIdx});
    return;
  }
  case Instruction::ExtractValue:
  case Instruction::ExtractElement: {
    OrdersType CurrentOrder;
    bool Reuse = canReuseExtract(VL, VL0, CurrentOrder);
    if (Reuse) {
      LLVM_DEBUG(dbgs() << "SLP: Reusing or shuffling extract sequence.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Reusing or shuffling extract sequence.\n"
; } } while (false);
      ++NumOpsWantToKeepOriginalOrder;
      newTreeEntry(VL, Bundle /*vectorized*/, S, UserTreeIdx,
                   ReuseShuffleIndicies);
      // This is a special case, as it does not gather, but at the same time
      // we are not extending buildTree_rec() towards the operands.
      ValueList Op0;
      Op0.assign(VL.size(), VL0->getOperand(0));
      VectorizableTree.back()->setOperand(0, Op0);
      return;
    }
    if (!CurrentOrder.empty()) {
      LLVM_DEBUG({do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { { dbgs() << "SLP: Reusing or shuffling of reordered extract sequence "
 "with order"; for (unsigned Idx : CurrentOrder) dbgs() <<
 " " << Idx; dbgs() << "\n"; }; } } while (false)
        dbgs() << "SLP: Reusing or shuffling of reordered extract sequence "do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { { dbgs() << "SLP: Reusing or shuffling of reordered extract sequence "
 "with order"; for (unsigned Idx : CurrentOrder) dbgs() <<
 " " << Idx; dbgs() << "\n"; }; } } while (false)
                  "with order";do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { { dbgs() << "SLP: Reusing or shuffling of reordered extract sequence "
 "with order"; for (unsigned Idx : CurrentOrder) dbgs() <<
 " " << Idx; dbgs() << "\n"; }; } } while (false)
        for (unsigned Idx : CurrentOrder)do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { { dbgs() << "SLP: Reusing or shuffling of reordered extract sequence "
 "with order"; for (unsigned Idx : CurrentOrder) dbgs() <<
 " " << Idx; dbgs() << "\n"; }; } } while (false)
          dbgs() << " " << Idx;do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { { dbgs() << "SLP: Reusing or shuffling of reordered extract sequence "
 "with order"; for (unsigned Idx : CurrentOrder) dbgs() <<
 " " << Idx; dbgs() << "\n"; }; } } while (false)
        dbgs() << "\n";do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { { dbgs() << "SLP: Reusing or shuffling of reordered extract sequence "
 "with order"; for (unsigned Idx : CurrentOrder) dbgs() <<
 " " << Idx; dbgs() << "\n"; }; } } while (false)
      })do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { { dbgs() << "SLP: Reusing or shuffling of reordered extract sequence "
 "with order"; for (unsigned Idx : CurrentOrder) dbgs() <<
 " " << Idx; dbgs() << "\n"; }; } } while (false);
      // Insert new order with initial value 0, if it does not exist,
      // otherwise return the iterator to the existing one.
      newTreeEntry(VL, Bundle /*vectorized*/, S, UserTreeIdx,
                   ReuseShuffleIndicies, CurrentOrder);
      findRootOrder(CurrentOrder);
      ++NumOpsWantToKeepOrder[CurrentOrder];
      // This is a special case, as it does not gather, but at the same time
      // we are not extending buildTree_rec() towards the operands.
      ValueList Op0;
      Op0.assign(VL.size(), VL0->getOperand(0));
      VectorizableTree.back()->setOperand(0, Op0);
      return;
    }
    LLVM_DEBUG(dbgs() << "SLP: Gather extract sequence.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Gather extract sequence.\n";
 } } while (false);
    newTreeEntry(VL, None /*not vectorized*/, S, UserTreeIdx,
                 ReuseShuffleIndicies);
    BS.cancelScheduling(VL, VL0);
    return;
  }
  case Instruction::Load: {
    // Check that a vectorized load would load the same memory as a scalar
    // load. For example, we don't want to vectorize loads that are smaller
    // than 8-bit. Even though we have a packed struct {<i2, i2, i2, i2>} LLVM
    // treats loading/storing it as an i8 struct. If we vectorize loads/stores
    // from such a struct, we read/write packed bits disagreeing with the
    // unvectorized version.
    Type *ScalarTy = VL0->getType();

    if (DL->getTypeSizeInBits(ScalarTy) !=
        DL->getTypeAllocSizeInBits(ScalarTy)) {
      BS.cancelScheduling(VL, VL0);
      newTreeEntry(VL, None /*not vectorized*/, S, UserTreeIdx,
                   ReuseShuffleIndicies);
      LLVM_DEBUG(dbgs() << "SLP: Gathering loads of non-packed type.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Gathering loads of non-packed type.\n"
; } } while (false);
      return;
    }

    // Make sure all loads in the bundle are simple - we can't vectorize
    // atomic or volatile loads.
    SmallVector<Value *, 4> PointerOps(VL.size());
    auto POIter = PointerOps.begin();
    for (Value *V : VL) {
      auto *L = cast<LoadInst>(V);
      if (!L->isSimple()) {
        BS.cancelScheduling(VL, VL0);
        newTreeEntry(VL, None /*not vectorized*/, S, UserTreeIdx,
                     ReuseShuffleIndicies);
        LLVM_DEBUG(dbgs() << "SLP: Gathering non-simple loads.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Gathering non-simple loads.\n"
; } } while (false);
        return;
      }
      *POIter = L->getPointerOperand();
      ++POIter;
    }

    OrdersType CurrentOrder;
    // Check the order of pointer operands.
    if (llvm::sortPtrAccesses(PointerOps, *DL, *SE, CurrentOrder)) {
      Value *Ptr0;
      Value *PtrN;
      if (CurrentOrder.empty()) {
        Ptr0 = PointerOps.front();
        PtrN = PointerOps.back();
      } else {
        Ptr0 = PointerOps[CurrentOrder.front()];
        PtrN = PointerOps[CurrentOrder.back()];
      }
      Optional<int> Diff = getPointersDiff(Ptr0, PtrN, *DL, *SE);
      // Check that the sorted loads are consecutive.
      if (static_cast<unsigned>(*Diff) == VL.size() - 1) {
        if (CurrentOrder.empty()) {
          // Original loads are consecutive and does not require reordering.
          ++NumOpsWantToKeepOriginalOrder;
          TreeEntry *TE = newTreeEntry(VL, Bundle /*vectorized*/, S,
                                       UserTreeIdx, ReuseShuffleIndicies);
          TE->setOperandsInOrder();
          LLVM_DEBUG(dbgs() << "SLP: added a vector of loads.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: added a vector of loads.\n";
 } } while (false);
        } else {
          // Need to reorder.
          TreeEntry *TE =
              newTreeEntry(VL, Bundle /*vectorized*/, S, UserTreeIdx,
                           ReuseShuffleIndicies, CurrentOrder);
          TE->setOperandsInOrder();
          LLVM_DEBUG(dbgs() << "SLP: added a vector of jumbled loads.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: added a vector of jumbled loads.\n"
; } } while (false);
          findRootOrder(CurrentOrder);
          ++NumOpsWantToKeepOrder[CurrentOrder];
        }
        return;
      }
      // Vectorizing non-consecutive loads with `llvm.masked.gather`.
      TreeEntry *TE = newTreeEntry(VL, TreeEntry::ScatterVectorize, Bundle, S,
                                   UserTreeIdx, ReuseShuffleIndicies);
      TE->setOperandsInOrder();
      buildTree_rec(PointerOps, Depth + 1, {TE, 0});
      LLVM_DEBUG(dbgs() << "SLP: added a vector of non-consecutive loads.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: added a vector of non-consecutive loads.\n"
; } } while (false);
      return;
    }

    LLVM_DEBUG(dbgs() << "SLP: Gathering non-consecutive loads.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Gathering non-consecutive loads.\n"
; } } while (false);
    BS.cancelScheduling(VL, VL0);
    newTreeEntry(VL, None /*not vectorized*/, S, UserTreeIdx,
                 ReuseShuffleIndicies);
    return;
  }
  case Instruction::ZExt:
  case Instruction::SExt:
  case Instruction::FPToUI:
  case Instruction::FPToSI:
  case Instruction::FPExt:
  case Instruction::PtrToInt:
  case Instruction::IntToPtr:
  case Instruction::SIToFP:
  case Instruction::UIToFP:
  case Instruction::Trunc:
  case Instruction::FPTrunc:
  case Instruction::BitCast: {
    Type *SrcTy = VL0->getOperand(0)->getType();
    for (Value *V : VL) {
      Type *Ty = cast<Instruction>(V)->getOperand(0)->getType();
      if (Ty != SrcTy || !isValidElementType(Ty)) {
        BS.cancelScheduling(VL, VL0);
        newTreeEntry(VL, None /*not vectorized*/, S, UserTreeIdx,
                     ReuseShuffleIndicies);
        LLVM_DEBUG(dbgs()do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Gathering casts with different src types.\n"
; } } while (false)
                   << "SLP: Gathering casts with different src types.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Gathering casts with different src types.\n"
; } } while (false);
        return;
      }
    }
    TreeEntry *TE = newTreeEntry(VL, Bundle /*vectorized*/, S, UserTreeIdx,
                                 ReuseShuffleIndicies);
    LLVM_DEBUG(dbgs() << "SLP: added a vector of casts.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: added a vector of casts.\n";
 } } while (false);

    TE->setOperandsInOrder();
    for (unsigned i = 0, e = VL0->getNumOperands(); i < e; ++i) {
      ValueList Operands;
      // Prepare the operand vector.
      for (Value *V : VL)
        Operands.push_back(cast<Instruction>(V)->getOperand(i));

      buildTree_rec(Operands, Depth + 1, {TE, i});
    }
    return;
  }
  case Instruction::ICmp:
  case Instruction::FCmp: {
    // Check that all of the compares have the same predicate.
    CmpInst::Predicate P0 = cast<CmpInst>(VL0)->getPredicate();
    CmpInst::Predicate SwapP0 = CmpInst::getSwappedPredicate(P0);
    Type *ComparedTy = VL0->getOperand(0)->getType();
    for (Value *V : VL) {
      CmpInst *Cmp = cast<CmpInst>(V);
      if ((Cmp->getPredicate() != P0 && Cmp->getPredicate() != SwapP0) ||
          Cmp->getOperand(0)->getType() != ComparedTy) {
        BS.cancelScheduling(VL, VL0);
        newTreeEntry(VL, None /*not vectorized*/, S, UserTreeIdx,
                     ReuseShuffleIndicies);
        LLVM_DEBUG(dbgs()do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Gathering cmp with different predicate.\n"
; } } while (false)
                   << "SLP: Gathering cmp with different predicate.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Gathering cmp with different predicate.\n"
; } } while (false);
        return;
      }
    }

    TreeEntry *TE = newTreeEntry(VL, Bundle /*vectorized*/, S, UserTreeIdx,
                                 ReuseShuffleIndicies);
    LLVM_DEBUG(dbgs() << "SLP: added a vector of compares.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: added a vector of compares.\n"
; } } while (false);

    ValueList Left, Right;
    if (cast<CmpInst>(VL0)->isCommutative()) {
      // Commutative predicate - collect + sort operands of the instructions
      // so that each side is more likely to have the same opcode.
      assert(P0 == SwapP0 && "Commutative Predicate mismatch")((P0 == SwapP0 && "Commutative Predicate mismatch") ?
 static_cast<void> (0) : __assert_fail ("P0 == SwapP0 && \"Commutative Predicate mismatch\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 2986, __PRETTY_FUNCTION__));
      reorderInputsAccordingToOpcode(VL, Left, Right, *DL, *SE, *this);
    } else {
      // Collect operands - commute if it uses the swapped predicate.
      for (Value *V : VL) {
        auto *Cmp = cast<CmpInst>(V);
        Value *LHS = Cmp->getOperand(0);
        Value *RHS = Cmp->getOperand(1);
        if (Cmp->getPredicate() != P0)
          std::swap(LHS, RHS);
        Left.push_back(LHS);
        Right.push_back(RHS);
      }
    }
    TE->setOperand(0, Left);
    TE->setOperand(1, Right);
    buildTree_rec(Left, Depth + 1, {TE, 0});
    buildTree_rec(Right, Depth + 1, {TE, 1});
    return;
  }
  case Instruction::Select:
  case Instruction::FNeg:
  case Instruction::Add:
  case Instruction::FAdd:
  case Instruction::Sub:
  case Instruction::FSub:
  case Instruction::Mul:
  case Instruction::FMul:
  case Instruction::UDiv:
  case Instruction::SDiv:
  case Instruction::FDiv:
  case Instruction::URem:
  case Instruction::SRem:
  case Instruction::FRem:
  case Instruction::Shl:
  case Instruction::LShr:
  case Instruction::AShr:
  case Instruction::And:
  case Instruction::Or:
  case Instruction::Xor: {
    TreeEntry *TE = newTreeEntry(VL, Bundle /*vectorized*/, S, UserTreeIdx,
                                 ReuseShuffleIndicies);
    LLVM_DEBUG(dbgs() << "SLP: added a vector of un/bin op.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: added a vector of un/bin op.\n"
; } } while (false);

    // Sort operands of the instructions so that each side is more likely to
    // have the same opcode.
    if (isa<BinaryOperator>(VL0) && VL0->isCommutative()) {
      ValueList Left, Right;
      reorderInputsAccordingToOpcode(VL, Left, Right, *DL, *SE, *this);
      TE->setOperand(0, Left);
      TE->setOperand(1, Right);
      buildTree_rec(Left, Depth + 1, {TE, 0});
      buildTree_rec(Right, Depth + 1, {TE, 1});
      return;
    }

    TE->setOperandsInOrder();
    for (unsigned i = 0, e = VL0->getNumOperands(); i < e; ++i) {
      ValueList Operands;
      // Prepare the operand vector.
      for (Value *V : VL)
        Operands.push_back(cast<Instruction>(V)->getOperand(i));

      buildTree_rec(Operands, Depth + 1, {TE, i});
    }
    return;
  }
  case Instruction::GetElementPtr: {
    // We don't combine GEPs with complicated (nested) indexing.
    for (Value *V : VL) {
      if (cast<Instruction>(V)->getNumOperands() != 2) {
        LLVM_DEBUG(dbgs() << "SLP: not-vectorizable GEP (nested indexes).\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: not-vectorizable GEP (nested indexes).\n"
; } } while (false);
        BS.cancelScheduling(VL, VL0);
        newTreeEntry(VL, None /*not vectorized*/, S, UserTreeIdx,
                     ReuseShuffleIndicies);
        return;
      }
    }

    // We can't combine several GEPs into one vector if they operate on
    // different types.
    Type *Ty0 = VL0->getOperand(0)->getType();
    for (Value *V : VL) {
      Type *CurTy = cast<Instruction>(V)->getOperand(0)->getType();
      if (Ty0 != CurTy) {
        LLVM_DEBUG(dbgs()do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: not-vectorizable GEP (different types).\n"
; } } while (false)
                   << "SLP: not-vectorizable GEP (different types).\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: not-vectorizable GEP (different types).\n"
; } } while (false);
        BS.cancelScheduling(VL, VL0);
        newTreeEntry(VL, None /*not vectorized*/, S, UserTreeIdx,
                     ReuseShuffleIndicies);
        return;
      }
    }

    // We don't combine GEPs with non-constant indexes.
    Type *Ty1 = VL0->getOperand(1)->getType();
    for (Value *V : VL) {
      auto Op = cast<Instruction>(V)->getOperand(1);
      if (!isa<ConstantInt>(Op) ||
          (Op->getType() != Ty1 &&
           Op->getType()->getScalarSizeInBits() >
               DL->getIndexSizeInBits(
                   V->getType()->getPointerAddressSpace()))) {
        LLVM_DEBUG(dbgs()do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: not-vectorizable GEP (non-constant indexes).\n"
; } } while (false)
                   << "SLP: not-vectorizable GEP (non-constant indexes).\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: not-vectorizable GEP (non-constant indexes).\n"
; } } while (false);
        BS.cancelScheduling(VL, VL0);
        newTreeEntry(VL, None /*not vectorized*/, S, UserTreeIdx,
                     ReuseShuffleIndicies);
        return;
      }
    }

    TreeEntry *TE = newTreeEntry(VL, Bundle /*vectorized*/, S, UserTreeIdx,
                                 ReuseShuffleIndicies);
    LLVM_DEBUG(dbgs() << "SLP: added a vector of GEPs.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: added a vector of GEPs.\n"; }
 } while (false);
    TE->setOperandsInOrder();
    for (unsigned i = 0, e = 2; i < e; ++i) {
      ValueList Operands;
      // Prepare the operand vector.
      for (Value *V : VL)
        Operands.push_back(cast<Instruction>(V)->getOperand(i));

      buildTree_rec(Operands, Depth + 1, {TE, i});
    }
    return;
  }
  case Instruction::Store: {
    // Check if the stores are consecutive or if we need to swizzle them.
    llvm::Type *ScalarTy = cast<StoreInst>(VL0)->getValueOperand()->getType();
    // Avoid types that are padded when being allocated as scalars, while
    // being packed together in a vector (such as i1).
    if (DL->getTypeSizeInBits(ScalarTy) !=
        DL->getTypeAllocSizeInBits(ScalarTy)) {
      BS.cancelScheduling(VL, VL0);
      newTreeEntry(VL, None /*not vectorized*/, S, UserTreeIdx,
                   ReuseShuffleIndicies);
      LLVM_DEBUG(dbgs() << "SLP: Gathering stores of non-packed type.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Gathering stores of non-packed type.\n"
; } } while (false);
      return;
    }
    // Make sure all stores in the bundle are simple - we can't vectorize
    // atomic or volatile stores.
    SmallVector<Value *, 4> PointerOps(VL.size());
    ValueList Operands(VL.size());
    auto POIter = PointerOps.begin();
    auto OIter = Operands.begin();
    for (Value *V : VL) {
      auto *SI = cast<StoreInst>(V);
      if (!SI->isSimple()) {
        BS.cancelScheduling(VL, VL0);
        newTreeEntry(VL, None /*not vectorized*/, S, UserTreeIdx,
                     ReuseShuffleIndicies);
        LLVM_DEBUG(dbgs() << "SLP: Gathering non-simple stores.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Gathering non-simple stores.\n"
; } } while (false);
        return;
      }
      *POIter = SI->getPointerOperand();
      *OIter = SI->getValueOperand();
      ++POIter;
      ++OIter;
    }

    OrdersType CurrentOrder;
    // Check the order of pointer operands.
    if (llvm::sortPtrAccesses(PointerOps, *DL, *SE, CurrentOrder)) {
      Value *Ptr0;
      Value *PtrN;
      if (CurrentOrder.empty()) {
        Ptr0 = PointerOps.front();
        PtrN = PointerOps.back();
      } else {
        Ptr0 = PointerOps[CurrentOrder.front()];
        PtrN = PointerOps[CurrentOrder.back()];
      }
      Optional<int> Dist = getPointersDiff(Ptr0, PtrN, *DL, *SE);
      // Check that the sorted pointer operands are consecutive.
      if (static_cast<unsigned>(*Dist) == VL.size() - 1) {
        if (CurrentOrder.empty()) {
          // Original stores are consecutive and does not require reordering.
          ++NumOpsWantToKeepOriginalOrder;
          TreeEntry *TE = newTreeEntry(VL, Bundle /*vectorized*/, S,
                                       UserTreeIdx, ReuseShuffleIndicies);
          TE->setOperandsInOrder();
          buildTree_rec(Operands, Depth + 1, {TE, 0});
          LLVM_DEBUG(dbgs() << "SLP: added a vector of stores.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: added a vector of stores.\n"
; } } while (false);
        } else {
          TreeEntry *TE =
              newTreeEntry(VL, Bundle /*vectorized*/, S, UserTreeIdx,
                           ReuseShuffleIndicies, CurrentOrder);
          TE->setOperandsInOrder();
          buildTree_rec(Operands, Depth + 1, {TE, 0});
          LLVM_DEBUG(dbgs() << "SLP: added a vector of jumbled stores.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: added a vector of jumbled stores.\n"
; } } while (false);
          findRootOrder(CurrentOrder);
          ++NumOpsWantToKeepOrder[CurrentOrder];
        }
        return;
      }
    }

    BS.cancelScheduling(VL, VL0);
    newTreeEntry(VL, None /*not vectorized*/, S, UserTreeIdx,
                 ReuseShuffleIndicies);
    LLVM_DEBUG(dbgs() << "SLP: Non-consecutive store.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Non-consecutive store.\n"; }
 } while (false);
    return;
  }
  case Instruction::Call: {
    // Check if the calls are all to the same vectorizable intrinsic or
    // library function.
    CallInst *CI = cast<CallInst>(VL0);
    Intrinsic::ID ID = getVectorIntrinsicIDForCall(CI, TLI);

    VFShape Shape = VFShape::get(
        *CI, ElementCount::getFixed(static_cast<unsigned int>(VL.size())),
        false /*HasGlobalPred*/);
    Function *VecFunc = VFDatabase(*CI).getVectorizedFunction(Shape);

    if (!VecFunc && !isTriviallyVectorizable(ID)) {
      BS.cancelScheduling(VL, VL0);
      newTreeEntry(VL, None /*not vectorized*/, S, UserTreeIdx,
                   ReuseShuffleIndicies);
      LLVM_DEBUG(dbgs() << "SLP: Non-vectorizable call.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Non-vectorizable call.\n"; }
 } while (false);
      return;
    }
    Function *F = CI->getCalledFunction();
    unsigned NumArgs = CI->getNumArgOperands();
    SmallVector<Value*, 4> ScalarArgs(NumArgs, nullptr);
    for (unsigned j = 0; j != NumArgs; ++j)
      if (hasVectorInstrinsicScalarOpd(ID, j))
        ScalarArgs[j] = CI->getArgOperand(j);
    for (Value *V : VL) {
      CallInst *CI2 = dyn_cast<CallInst>(V);
      if (!CI2 || CI2->getCalledFunction() != F ||
          getVectorIntrinsicIDForCall(CI2, TLI) != ID ||
          (VecFunc &&
           VecFunc != VFDatabase(*CI2).getVectorizedFunction(Shape)) ||
          !CI->hasIdenticalOperandBundleSchema(*CI2)) {
        BS.cancelScheduling(VL, VL0);
        newTreeEntry(VL, None /*not vectorized*/, S, UserTreeIdx,
                     ReuseShuffleIndicies);
        LLVM_DEBUG(dbgs() << "SLP: mismatched calls:" << *CI << "!=" << *Vdo { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: mismatched calls:" << *
CI << "!=" << *V << "\n"; } } while (false)
                          << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: mismatched calls:" << *
CI << "!=" << *V << "\n"; } } while (false);
        return;
      }
      // Some intrinsics have scalar arguments and should be same in order for
      // them to be vectorized.
      for (unsigned j = 0; j != NumArgs; ++j) {
        if (hasVectorInstrinsicScalarOpd(ID, j)) {
          Value *A1J = CI2->getArgOperand(j);
          if (ScalarArgs[j] != A1J) {
            BS.cancelScheduling(VL, VL0);
            newTreeEntry(VL, None /*not vectorized*/, S, UserTreeIdx,
                         ReuseShuffleIndicies);
            LLVM_DEBUG(dbgs() << "SLP: mismatched arguments in call:" << *CIdo { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: mismatched arguments in call:"
 << *CI << " argument " << ScalarArgs[j] <<
 "!=" << A1J << "\n"; } } while (false)
                              << " argument " << ScalarArgs[j] << "!=" << A1Jdo { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: mismatched arguments in call:"
 << *CI << " argument " << ScalarArgs[j] <<
 "!=" << A1J << "\n"; } } while (false)
                              << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: mismatched arguments in call:"
 << *CI << " argument " << ScalarArgs[j] <<
 "!=" << A1J << "\n"; } } while (false);
            return;
          }
        }
      }
      // Verify that the bundle operands are identical between the two calls.
      if (CI->hasOperandBundles() &&
          !std::equal(CI->op_begin() + CI->getBundleOperandsStartIndex(),
                      CI->op_begin() + CI->getBundleOperandsEndIndex(),
                      CI2->op_begin() + CI2->getBundleOperandsStartIndex())) {
        BS.cancelScheduling(VL, VL0);
        newTreeEntry(VL, None /*not vectorized*/, S, UserTreeIdx,
                     ReuseShuffleIndicies);
        LLVM_DEBUG(dbgs() << "SLP: mismatched bundle operands in calls:"do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: mismatched bundle operands in calls:"
 << *CI << "!=" << *V << '\n'; } } while
 (false)
                          << *CI << "!=" << *V << '\n')do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: mismatched bundle operands in calls:"
 << *CI << "!=" << *V << '\n'; } } while
 (false);
        return;
      }
    }

    TreeEntry *TE = newTreeEntry(VL, Bundle /*vectorized*/, S, UserTreeIdx,
                                 ReuseShuffleIndicies);
    TE->setOperandsInOrder();
    for (unsigned i = 0, e = CI->getNumArgOperands(); i != e; ++i) {
      ValueList Operands;
      // Prepare the operand vector.
      for (Value *V : VL) {
        auto *CI2 = cast<CallInst>(V);
        Operands.push_back(CI2->getArgOperand(i));
      }
      buildTree_rec(Operands, Depth + 1, {TE, i});
    }
    return;
  }
  case Instruction::ShuffleVector: {
    // If this is not an alternate sequence of opcode like add-sub
    // then do not vectorize this instruction.
    if (!S.isAltShuffle()) {
      BS.cancelScheduling(VL, VL0);
      newTreeEntry(VL, None /*not vectorized*/, S, UserTreeIdx,
                   ReuseShuffleIndicies);
      LLVM_DEBUG(dbgs() << "SLP: ShuffleVector are not vectorized.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: ShuffleVector are not vectorized.\n"
; } } while (false);
      return;
    }
    TreeEntry *TE = newTreeEntry(VL, Bundle /*vectorized*/, S, UserTreeIdx,
                                 ReuseShuffleIndicies);
    LLVM_DEBUG(dbgs() << "SLP: added a ShuffleVector op.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: added a ShuffleVector op.\n"
; } } while (false);

    // Reorder operands if reordering would enable vectorization.
    if (isa<BinaryOperator>(VL0)) {
      ValueList Left, Right;
      reorderInputsAccordingToOpcode(VL, Left, Right, *DL, *SE, *this);
      TE->setOperand(0, Left);
      TE->setOperand(1, Right);
      buildTree_rec(Left, Depth + 1, {TE, 0});
      buildTree_rec(Right, Depth + 1, {TE, 1});
      return;
    }

    TE->setOperandsInOrder();
    for (unsigned i = 0, e = VL0->getNumOperands(); i < e; ++i) {
      ValueList Operands;
      // Prepare the operand vector.
      for (Value *V : VL)
        Operands.push_back(cast<Instruction>(V)->getOperand(i));

      buildTree_rec(Operands, Depth + 1, {TE, i});
    }
    return;
  }
  default:
    BS.cancelScheduling(VL, VL0);
    newTreeEntry(VL, None /*not vectorized*/, S, UserTreeIdx,
                 ReuseShuffleIndicies);
    LLVM_DEBUG(dbgs() << "SLP: Gathering unknown instruction.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Gathering unknown instruction.\n"
; } } while (false);
    return;
}
3314}

3316unsigned BoUpSLP::canMapToVector(Type *T, const DataLayout &DL) const {
unsigned N = 1;
Type *EltTy = T;

while (isa<StructType>(EltTy) || isa<ArrayType>(EltTy) ||
       isa<VectorType>(EltTy)) {
  if (auto *ST = dyn_cast<StructType>(EltTy)) {
    // Check that struct is homogeneous.
    for (const auto *Ty : ST->elements())
      if (Ty != *ST->element_begin())
        return 0;
    N *= ST->getNumElements();
    EltTy = *ST->element_begin();
  } else if (auto *AT = dyn_cast<ArrayType>(EltTy)) {
    N *= AT->getNumElements();
    EltTy = AT->getElementType();
  } else {
    auto *VT = cast<FixedVectorType>(EltTy);
    N *= VT->getNumElements();
    EltTy = VT->getElementType();
  }
}

if (!isValidElementType(EltTy))
  return 0;
uint64_t VTSize = DL.getTypeStoreSizeInBits(FixedVectorType::get(EltTy, N));
if (VTSize < MinVecRegSize || VTSize > MaxVecRegSize || VTSize != DL.getTypeStoreSizeInBits(T))
  return 0;
return N;
3345}

3347bool BoUpSLP::canReuseExtract(ArrayRef<Value *> VL, Value *OpValue,
                            SmallVectorImpl<unsigned> &CurrentOrder) const {
Instruction *E0 = cast<Instruction>(OpValue);
assert(E0->getOpcode() == Instruction::ExtractElement ||((E0->getOpcode() == Instruction::ExtractElement || E0->
getOpcode() == Instruction::ExtractValue) ? static_cast<void
> (0) : __assert_fail ("E0->getOpcode() == Instruction::ExtractElement || E0->getOpcode() == Instruction::ExtractValue"
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 3351, __PRETTY_FUNCTION__))
       E0->getOpcode() == Instruction::ExtractValue)((E0->getOpcode() == Instruction::ExtractElement || E0->
getOpcode() == Instruction::ExtractValue) ? static_cast<void
> (0) : __assert_fail ("E0->getOpcode() == Instruction::ExtractElement || E0->getOpcode() == Instruction::ExtractValue"
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 3351, __PRETTY_FUNCTION__));
assert(E0->getOpcode() == getSameOpcode(VL).getOpcode() && "Invalid opcode")((E0->getOpcode() == getSameOpcode(VL).getOpcode() &&
 "Invalid opcode") ? static_cast<void> (0) : __assert_fail
 ("E0->getOpcode() == getSameOpcode(VL).getOpcode() && \"Invalid opcode\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 3352, __PRETTY_FUNCTION__));
// Check if all of the extracts come from the same vector and from the
// correct offset.
Value *Vec = E0->getOperand(0);

CurrentOrder.clear();

// We have to extract from a vector/aggregate with the same number of elements.
unsigned NElts;
if (E0->getOpcode() == Instruction::ExtractValue) {
  const DataLayout &DL = E0->getModule()->getDataLayout();
  NElts = canMapToVector(Vec->getType(), DL);
  if (!NElts)
    return false;
  // Check if load can be rewritten as load of vector.
  LoadInst *LI = dyn_cast<LoadInst>(Vec);
  if (!LI || !LI->isSimple() || !LI->hasNUses(VL.size()))
    return false;
} else {
  NElts = cast<FixedVectorType>(Vec->getType())->getNumElements();
}

if (NElts != VL.size())
  return false;

// Check that all of the indices extract from the correct offset.
bool ShouldKeepOrder = true;
unsigned E = VL.size();
// Assign to all items the initial value E + 1 so we can check if the extract
// instruction index was used already.
// Also, later we can check that all the indices are used and we have a
// consecutive access in the extract instructions, by checking that no
// element of CurrentOrder still has value E + 1.
CurrentOrder.assign(E, E + 1);
unsigned I = 0;
for (; I < E; ++I) {
  auto *Inst = cast<Instruction>(VL[I]);
  if (Inst->getOperand(0) != Vec)
    break;
  Optional<unsigned> Idx = getExtractIndex(Inst);
  if (!Idx)
    break;
  const unsigned ExtIdx = *Idx;
  if (ExtIdx != I) {
    if (ExtIdx >= E || CurrentOrder[ExtIdx] != E + 1)
      break;
    ShouldKeepOrder = false;
    CurrentOrder[ExtIdx] = I;
  } else {
    if (CurrentOrder[I] != E + 1)
      break;
    CurrentOrder[I] = I;
  }
}
if (I < E) {
  CurrentOrder.clear();
  return false;
}

return ShouldKeepOrder;
3412}

3414bool BoUpSLP::areAllUsersVectorized(Instruction *I) const {
return I->hasOneUse() || llvm::all_of(I->users(), [this](User *U) {
         return ScalarToTreeEntry.count(U) > 0;
       });
3418}

3420static std::pair<InstructionCost, InstructionCost>
3421getVectorCallCosts(CallInst *CI, FixedVectorType *VecTy,
                 TargetTransformInfo *TTI, TargetLibraryInfo *TLI) {
Intrinsic::ID ID = getVectorIntrinsicIDForCall(CI, TLI);

// Calculate the cost of the scalar and vector calls.
SmallVector<Type *, 4> VecTys;
for (Use &Arg : CI->args())
  VecTys.push_back(
      FixedVectorType::get(Arg->getType(), VecTy->getNumElements()));
FastMathFlags FMF;
if (auto *FPCI = dyn_cast<FPMathOperator>(CI))
  FMF = FPCI->getFastMathFlags();
SmallVector<const Value *> Arguments(CI->arg_begin(), CI->arg_end());
IntrinsicCostAttributes CostAttrs(ID, VecTy, Arguments, VecTys, FMF,
                                  dyn_cast<IntrinsicInst>(CI));
auto IntrinsicCost =
  TTI->getIntrinsicInstrCost(CostAttrs, TTI::TCK_RecipThroughput);

auto Shape = VFShape::get(*CI, ElementCount::getFixed(static_cast<unsigned>(
                                   VecTy->getNumElements())),
                          false /*HasGlobalPred*/);
Function *VecFunc = VFDatabase(*CI).getVectorizedFunction(Shape);
auto LibCost = IntrinsicCost;
if (!CI->isNoBuiltin() && VecFunc) {
  // Calculate the cost of the vector library call.
  // If the corresponding vector call is cheaper, return its cost.
  LibCost = TTI->getCallInstrCost(nullptr, VecTy, VecTys,
                                  TTI::TCK_RecipThroughput);
}
return {IntrinsicCost, LibCost};
3451}

3453/// Compute the cost of creating a vector of type \p VecTy containing the
3454/// extracted values from \p VL.
3455static InstructionCost
3456computeExtractCost(ArrayRef<Value *> VL, FixedVectorType *VecTy,
                 TargetTransformInfo::ShuffleKind ShuffleKind,
                 ArrayRef<int> Mask, TargetTransformInfo &TTI) {
unsigned NumOfParts = TTI.getNumberOfParts(VecTy);

if (ShuffleKind != TargetTransformInfo::SK_PermuteSingleSrc || !NumOfParts ||
    VecTy->getNumElements() < NumOfParts)
  return TTI.getShuffleCost(ShuffleKind, VecTy, Mask);

bool AllConsecutive = true;
unsigned EltsPerVector = VecTy->getNumElements() / NumOfParts;
unsigned Idx = -1;
InstructionCost Cost = 0;

// Process extracts in blocks of EltsPerVector to check if the source vector
// operand can be re-used directly. If not, add the cost of creating a shuffle
// to extract the values into a vector register.
for (auto *V : VL) {
  ++Idx;

  // Reached the start of a new vector registers.
  if (Idx % EltsPerVector == 0) {
    AllConsecutive = true;
    continue;
  }

  // Check all extracts for a vector register on the target directly
  // extract values in order.
  unsigned CurrentIdx = *getExtractIndex(cast<Instruction>(V));
  unsigned PrevIdx = *getExtractIndex(cast<Instruction>(VL[Idx - 1]));
  AllConsecutive &= PrevIdx + 1 == CurrentIdx &&
                    CurrentIdx % EltsPerVector == Idx % EltsPerVector;

  if (AllConsecutive)
    continue;

  // Skip all indices, except for the last index per vector block.
  if ((Idx + 1) % EltsPerVector != 0 && Idx + 1 != VL.size())
    continue;

  // If we have a series of extracts which are not consecutive and hence
  // cannot re-use the source vector register directly, compute the shuffle
  // cost to extract the a vector with EltsPerVector elements.
  Cost += TTI.getShuffleCost(
      TargetTransformInfo::SK_PermuteSingleSrc,
      FixedVectorType::get(VecTy->getElementType(), EltsPerVector));
}
return Cost;
3504}

3506InstructionCost BoUpSLP::getEntryCost(TreeEntry *E) {
ArrayRef<Value*> VL = E->Scalars;

Type *ScalarTy = VL[0]->getType();
if (StoreInst *SI = dyn_cast<StoreInst>(VL[0]))
  ScalarTy = SI->getValueOperand()->getType();
else if (CmpInst *CI = dyn_cast<CmpInst>(VL[0]))
  ScalarTy = CI->getOperand(0)->getType();
auto *VecTy = FixedVectorType::get(ScalarTy, VL.size());
TTI::TargetCostKind CostKind = TTI::TCK_RecipThroughput;

// If we have computed a smaller type for the expression, update VecTy so
// that the costs will be accurate.
if (MinBWs.count(VL[0]))
  VecTy = FixedVectorType::get(
      IntegerType::get(F->getContext(), MinBWs[VL[0]].first), VL.size());

unsigned ReuseShuffleNumbers = E->ReuseShuffleIndices.size();
bool NeedToShuffleReuses = !E->ReuseShuffleIndices.empty();
InstructionCost ReuseShuffleCost = 0;
if (NeedToShuffleReuses) {
  ReuseShuffleCost =
      TTI->getShuffleCost(TargetTransformInfo::SK_PermuteSingleSrc, VecTy,
                          E->ReuseShuffleIndices);
}
if (E->State == TreeEntry::NeedToGather) {
  if (allConstant(VL))
    return 0;
  if (isSplat(VL)) {
    return ReuseShuffleCost +
           TTI->getShuffleCost(TargetTransformInfo::SK_Broadcast, VecTy, None,
                               0);
  }
  if (E->getOpcode() == Instruction::ExtractElement &&
      allSameType(VL) && allSameBlock(VL)) {
    SmallVector<int> Mask;
    Optional<TargetTransformInfo::ShuffleKind> ShuffleKind =
        isShuffle(VL, Mask);
    if (ShuffleKind.hasValue()) {
      InstructionCost Cost =
          computeExtractCost(VL, VecTy, *ShuffleKind, Mask, *TTI);
      for (auto *V : VL) {
        // If all users of instruction are going to be vectorized and this
        // instruction itself is not going to be vectorized, consider this
        // instruction as dead and remove its cost from the final cost of the
        // vectorized tree.
        if (areAllUsersVectorized(cast<Instruction>(V)) &&
            !ScalarToTreeEntry.count(V)) {
          auto *IO = cast<ConstantInt>(
              cast<ExtractElementInst>(V)->getIndexOperand());
          Cost -= TTI->getVectorInstrCost(Instruction::ExtractElement, VecTy,
                                          IO->getZExtValue());
        }
      }
      return ReuseShuffleCost + Cost;
    }
  }
  return ReuseShuffleCost + getGatherCost(VL);
}
assert((E->State == TreeEntry::Vectorize ||(((E->State == TreeEntry::Vectorize || E->State == TreeEntry
::ScatterVectorize) && "Unhandled state") ? static_cast
<void> (0) : __assert_fail ("(E->State == TreeEntry::Vectorize || E->State == TreeEntry::ScatterVectorize) && \"Unhandled state\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 3567, __PRETTY_FUNCTION__))
        E->State == TreeEntry::ScatterVectorize) &&(((E->State == TreeEntry::Vectorize || E->State == TreeEntry
::ScatterVectorize) && "Unhandled state") ? static_cast
<void> (0) : __assert_fail ("(E->State == TreeEntry::Vectorize || E->State == TreeEntry::ScatterVectorize) && \"Unhandled state\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 3567, __PRETTY_FUNCTION__))
       "Unhandled state")(((E->State == TreeEntry::Vectorize || E->State == TreeEntry
::ScatterVectorize) && "Unhandled state") ? static_cast
<void> (0) : __assert_fail ("(E->State == TreeEntry::Vectorize || E->State == TreeEntry::ScatterVectorize) && \"Unhandled state\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 3567, __PRETTY_FUNCTION__));
assert(E->getOpcode() && allSameType(VL) && allSameBlock(VL) && "Invalid VL")((E->getOpcode() && allSameType(VL) && allSameBlock
(VL) && "Invalid VL") ? static_cast<void> (0) :
 __assert_fail ("E->getOpcode() && allSameType(VL) && allSameBlock(VL) && \"Invalid VL\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 3568, __PRETTY_FUNCTION__));
Instruction *VL0 = E->getMainOp();
unsigned ShuffleOrOp =
    E->isAltShuffle() ? (unsigned)Instruction::ShuffleVector : E->getOpcode();
switch (ShuffleOrOp) {
  case Instruction::PHI:
    return 0;

  case Instruction::ExtractValue:
  case Instruction::ExtractElement: {
    // The common cost of removal ExtractElement/ExtractValue instructions +
    // the cost of shuffles, if required to resuffle the original vector.
    InstructionCost CommonCost = 0;
    if (NeedToShuffleReuses) {
      unsigned Idx = 0;
      for (unsigned I : E->ReuseShuffleIndices) {
        if (ShuffleOrOp == Instruction::ExtractElement) {
          auto *IO = cast<ConstantInt>(
              cast<ExtractElementInst>(VL[I])->getIndexOperand());
          Idx = IO->getZExtValue();
          ReuseShuffleCost -= TTI->getVectorInstrCost(
              Instruction::ExtractElement, VecTy, Idx);
        } else {
          ReuseShuffleCost -= TTI->getVectorInstrCost(
              Instruction::ExtractElement, VecTy, Idx);
          ++Idx;
        }
      }
      Idx = ReuseShuffleNumbers;
      for (Value *V : VL) {
        if (ShuffleOrOp == Instruction::ExtractElement) {
          auto *IO = cast<ConstantInt>(
              cast<ExtractElementInst>(V)->getIndexOperand());
          Idx = IO->getZExtValue();
        } else {
          --Idx;
        }
        ReuseShuffleCost +=
            TTI->getVectorInstrCost(Instruction::ExtractElement, VecTy, Idx);
      }
      CommonCost = ReuseShuffleCost;
    } else if (!E->ReorderIndices.empty()) {
      SmallVector<int> NewMask;
      inversePermutation(E->ReorderIndices, NewMask);
      CommonCost = TTI->getShuffleCost(
          TargetTransformInfo::SK_PermuteSingleSrc, VecTy, NewMask);
    }
    for (unsigned I = 0, E = VL.size(); I < E; ++I) {
      Instruction *EI = cast<Instruction>(VL[I]);
      // If all users are going to be vectorized, instruction can be
      // considered as dead.
      // The same, if have only one user, it will be vectorized for sure.
      if (areAllUsersVectorized(EI)) {
        // Take credit for instruction that will become dead.
        if (EI->hasOneUse()) {
          Instruction *Ext = EI->user_back();
          if ((isa<SExtInst>(Ext) || isa<ZExtInst>(Ext)) &&
              all_of(Ext->users(),
                     [](User *U) { return isa<GetElementPtrInst>(U); })) {
            // Use getExtractWithExtendCost() to calculate the cost of
            // extractelement/ext pair.
            CommonCost -= TTI->getExtractWithExtendCost(
                Ext->getOpcode(), Ext->getType(), VecTy, I);
            // Add back the cost of s|zext which is subtracted separately.
            CommonCost += TTI->getCastInstrCost(
                Ext->getOpcode(), Ext->getType(), EI->getType(),
                TTI::getCastContextHint(Ext), CostKind, Ext);
            continue;
          }
        }
        CommonCost -=
            TTI->getVectorInstrCost(Instruction::ExtractElement, VecTy, I);
      }
    }
    return CommonCost;
  }
  case Instruction::ZExt:
  case Instruction::SExt:
  case Instruction::FPToUI:
  case Instruction::FPToSI:
  case Instruction::FPExt:
  case Instruction::PtrToInt:
  case Instruction::IntToPtr:
  case Instruction::SIToFP:
  case Instruction::UIToFP:
  case Instruction::Trunc:
  case Instruction::FPTrunc:
  case Instruction::BitCast: {
    Type *SrcTy = VL0->getOperand(0)->getType();
    InstructionCost ScalarEltCost =
        TTI->getCastInstrCost(E->getOpcode(), ScalarTy, SrcTy,
                              TTI::getCastContextHint(VL0), CostKind, VL0);
    if (NeedToShuffleReuses) {
      ReuseShuffleCost -= (ReuseShuffleNumbers - VL.size()) * ScalarEltCost;
    }

    // Calculate the cost of this instruction.
    InstructionCost ScalarCost = VL.size() * ScalarEltCost;

    auto *SrcVecTy = FixedVectorType::get(SrcTy, VL.size());
    InstructionCost VecCost = 0;
    // Check if the values are candidates to demote.
    if (!MinBWs.count(VL0) || VecTy != SrcVecTy) {
      VecCost =
          ReuseShuffleCost +
          TTI->getCastInstrCost(E->getOpcode(), VecTy, SrcVecTy,
                                TTI::getCastContextHint(VL0), CostKind, VL0);
    }
    LLVM_DEBUG(dumpTreeCosts(E, ReuseShuffleCost, VecCost, ScalarCost))do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dumpTreeCosts(E, ReuseShuffleCost, VecCost, ScalarCost
); } } while (false);
    return VecCost - ScalarCost;
  }
  case Instruction::FCmp:
  case Instruction::ICmp:
  case Instruction::Select: {
    // Calculate the cost of this instruction.
    InstructionCost ScalarEltCost =
        TTI->getCmpSelInstrCost(E->getOpcode(), ScalarTy, Builder.getInt1Ty(),
                                CmpInst::BAD_ICMP_PREDICATE, CostKind, VL0);
    if (NeedToShuffleReuses) {
      ReuseShuffleCost -= (ReuseShuffleNumbers - VL.size()) * ScalarEltCost;
    }
    auto *MaskTy = FixedVectorType::get(Builder.getInt1Ty(), VL.size());
    InstructionCost ScalarCost = VecTy->getNumElements() * ScalarEltCost;

    // Check if all entries in VL are either compares or selects with compares
    // as condition that have the same predicates.
    CmpInst::Predicate VecPred = CmpInst::BAD_ICMP_PREDICATE;
    bool First = true;
    for (auto *V : VL) {
      CmpInst::Predicate CurrentPred;
      auto MatchCmp = m_Cmp(CurrentPred, m_Value(), m_Value());
      if ((!match(V, m_Select(MatchCmp, m_Value(), m_Value())) &&
           !match(V, MatchCmp)) ||
          (!First && VecPred != CurrentPred)) {
        VecPred = CmpInst::BAD_ICMP_PREDICATE;
        break;
      }
      First = false;
      VecPred = CurrentPred;
    }

    InstructionCost VecCost = TTI->getCmpSelInstrCost(
        E->getOpcode(), VecTy, MaskTy, VecPred, CostKind, VL0);
    // Check if it is possible and profitable to use min/max for selects in
    // VL.
    //
    auto IntrinsicAndUse = canConvertToMinOrMaxIntrinsic(VL);
    if (IntrinsicAndUse.first != Intrinsic::not_intrinsic) {
      IntrinsicCostAttributes CostAttrs(IntrinsicAndUse.first, VecTy,
                                        {VecTy, VecTy});
      InstructionCost IntrinsicCost =
          TTI->getIntrinsicInstrCost(CostAttrs, CostKind);
      // If the selects are the only uses of the compares, they will be dead
      // and we can adjust the cost by removing their cost.
      if (IntrinsicAndUse.second)
        IntrinsicCost -=
            TTI->getCmpSelInstrCost(Instruction::ICmp, VecTy, MaskTy,
                                    CmpInst::BAD_ICMP_PREDICATE, CostKind);
      VecCost = std::min(VecCost, IntrinsicCost);
    }
    LLVM_DEBUG(dumpTreeCosts(E, ReuseShuffleCost, VecCost, ScalarCost))do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dumpTreeCosts(E, ReuseShuffleCost, VecCost, ScalarCost
); } } while (false);
    return ReuseShuffleCost + VecCost - ScalarCost;
  }
  case Instruction::FNeg:
  case Instruction::Add:
  case Instruction::FAdd:
  case Instruction::Sub:
  case Instruction::FSub:
  case Instruction::Mul:
  case Instruction::FMul:
  case Instruction::UDiv:
  case Instruction::SDiv:
  case Instruction::FDiv:
  case Instruction::URem:
  case Instruction::SRem:
  case Instruction::FRem:
  case Instruction::Shl:
  case Instruction::LShr:
  case Instruction::AShr:
  case Instruction::And:
  case Instruction::Or:
  case Instruction::Xor: {
    // Certain instructions can be cheaper to vectorize if they have a
    // constant second vector operand.
    TargetTransformInfo::OperandValueKind Op1VK =
        TargetTransformInfo::OK_AnyValue;
    TargetTransformInfo::OperandValueKind Op2VK =
        TargetTransformInfo::OK_UniformConstantValue;
    TargetTransformInfo::OperandValueProperties Op1VP =
        TargetTransformInfo::OP_None;
    TargetTransformInfo::OperandValueProperties Op2VP =
        TargetTransformInfo::OP_PowerOf2;

    // If all operands are exactly the same ConstantInt then set the
    // operand kind to OK_UniformConstantValue.
    // If instead not all operands are constants, then set the operand kind
    // to OK_AnyValue. If all operands are constants but not the same,
    // then set the operand kind to OK_NonUniformConstantValue.
    ConstantInt *CInt0 = nullptr;
    for (unsigned i = 0, e = VL.size(); i < e; ++i) {
      const Instruction *I = cast<Instruction>(VL[i]);
      unsigned OpIdx = isa<BinaryOperator>(I) ? 1 : 0;
      ConstantInt *CInt = dyn_cast<ConstantInt>(I->getOperand(OpIdx));
      if (!CInt) {
        Op2VK = TargetTransformInfo::OK_AnyValue;
        Op2VP = TargetTransformInfo::OP_None;
        break;
      }
      if (Op2VP == TargetTransformInfo::OP_PowerOf2 &&
          !CInt->getValue().isPowerOf2())
        Op2VP = TargetTransformInfo::OP_None;
      if (i == 0) {
        CInt0 = CInt;
        continue;
      }
      if (CInt0 != CInt)
        Op2VK = TargetTransformInfo::OK_NonUniformConstantValue;
    }

    SmallVector<const Value *, 4> Operands(VL0->operand_values());
    InstructionCost ScalarEltCost =
        TTI->getArithmeticInstrCost(E->getOpcode(), ScalarTy, CostKind, Op1VK,
                                    Op2VK, Op1VP, Op2VP, Operands, VL0);
    if (NeedToShuffleReuses) {
      ReuseShuffleCost -= (ReuseShuffleNumbers - VL.size()) * ScalarEltCost;
    }
    InstructionCost ScalarCost = VecTy->getNumElements() * ScalarEltCost;
    InstructionCost VecCost =
        TTI->getArithmeticInstrCost(E->getOpcode(), VecTy, CostKind, Op1VK,
                                    Op2VK, Op1VP, Op2VP, Operands, VL0);
    LLVM_DEBUG(dumpTreeCosts(E, ReuseShuffleCost, VecCost, ScalarCost))do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dumpTreeCosts(E, ReuseShuffleCost, VecCost, ScalarCost
); } } while (false);
    return ReuseShuffleCost + VecCost - ScalarCost;
  }
  case Instruction::GetElementPtr: {
    TargetTransformInfo::OperandValueKind Op1VK =
        TargetTransformInfo::OK_AnyValue;
    TargetTransformInfo::OperandValueKind Op2VK =
        TargetTransformInfo::OK_UniformConstantValue;

    InstructionCost ScalarEltCost = TTI->getArithmeticInstrCost(
        Instruction::Add, ScalarTy, CostKind, Op1VK, Op2VK);
    if (NeedToShuffleReuses) {
      ReuseShuffleCost -= (ReuseShuffleNumbers - VL.size()) * ScalarEltCost;
    }
    InstructionCost ScalarCost = VecTy->getNumElements() * ScalarEltCost;
    InstructionCost VecCost = TTI->getArithmeticInstrCost(
        Instruction::Add, VecTy, CostKind, Op1VK, Op2VK);
    LLVM_DEBUG(dumpTreeCosts(E, ReuseShuffleCost, VecCost, ScalarCost))do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dumpTreeCosts(E, ReuseShuffleCost, VecCost, ScalarCost
); } } while (false);
    return ReuseShuffleCost + VecCost - ScalarCost;
  }
  case Instruction::Load: {
    // Cost of wide load - cost of scalar loads.
    Align alignment = cast<LoadInst>(VL0)->getAlign();
    InstructionCost ScalarEltCost = TTI->getMemoryOpCost(
        Instruction::Load, ScalarTy, alignment, 0, CostKind, VL0);
    if (NeedToShuffleReuses) {
      ReuseShuffleCost -= (ReuseShuffleNumbers - VL.size()) * ScalarEltCost;
    }
    InstructionCost ScalarLdCost = VecTy->getNumElements() * ScalarEltCost;
    InstructionCost VecLdCost;
    if (E->State == TreeEntry::Vectorize) {
      VecLdCost = TTI->getMemoryOpCost(Instruction::Load, VecTy, alignment, 0,
                                       CostKind, VL0);
    } else {
      assert(E->State == TreeEntry::ScatterVectorize && "Unknown EntryState")((E->State == TreeEntry::ScatterVectorize && "Unknown EntryState"
) ? static_cast<void> (0) : __assert_fail ("E->State == TreeEntry::ScatterVectorize && \"Unknown EntryState\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 3832, __PRETTY_FUNCTION__));
      VecLdCost = TTI->getGatherScatterOpCost(
          Instruction::Load, VecTy, cast<LoadInst>(VL0)->getPointerOperand(),
          /*VariableMask=*/false, alignment, CostKind, VL0);
    }
    if (!NeedToShuffleReuses && !E->ReorderIndices.empty()) {
      SmallVector<int> NewMask;
      inversePermutation(E->ReorderIndices, NewMask);
      VecLdCost += TTI->getShuffleCost(
          TargetTransformInfo::SK_PermuteSingleSrc, VecTy, NewMask);
    }
    LLVM_DEBUG(dumpTreeCosts(E, ReuseShuffleCost, VecLdCost, ScalarLdCost))do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dumpTreeCosts(E, ReuseShuffleCost, VecLdCost, ScalarLdCost
); } } while (false);
    return ReuseShuffleCost + VecLdCost - ScalarLdCost;
  }
  case Instruction::Store: {
    // We know that we can merge the stores. Calculate the cost.
    bool IsReorder = !E->ReorderIndices.empty();
    auto *SI =
        cast<StoreInst>(IsReorder ? VL[E->ReorderIndices.front()] : VL0);
    Align Alignment = SI->getAlign();
    InstructionCost ScalarEltCost = TTI->getMemoryOpCost(
        Instruction::Store, ScalarTy, Alignment, 0, CostKind, VL0);
    InstructionCost ScalarStCost = VecTy->getNumElements() * ScalarEltCost;
    InstructionCost VecStCost = TTI->getMemoryOpCost(
        Instruction::Store, VecTy, Alignment, 0, CostKind, VL0);
    if (IsReorder) {
      SmallVector<int> NewMask;
      inversePermutation(E->ReorderIndices, NewMask);
      VecStCost += TTI->getShuffleCost(
          TargetTransformInfo::SK_PermuteSingleSrc, VecTy, NewMask);
    }
    LLVM_DEBUG(dumpTreeCosts(E, ReuseShuffleCost, VecStCost, ScalarStCost))do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dumpTreeCosts(E, ReuseShuffleCost, VecStCost, ScalarStCost
); } } while (false);
    return VecStCost - ScalarStCost;
  }
  case Instruction::Call: {
    CallInst *CI = cast<CallInst>(VL0);
    Intrinsic::ID ID = getVectorIntrinsicIDForCall(CI, TLI);

    // Calculate the cost of the scalar and vector calls.
    IntrinsicCostAttributes CostAttrs(ID, *CI, 1);
    InstructionCost ScalarEltCost =
        TTI->getIntrinsicInstrCost(CostAttrs, CostKind);
    if (NeedToShuffleReuses) {
      ReuseShuffleCost -= (ReuseShuffleNumbers - VL.size()) * ScalarEltCost;
    }
    InstructionCost ScalarCallCost = VecTy->getNumElements() * ScalarEltCost;

    auto VecCallCosts = getVectorCallCosts(CI, VecTy, TTI, TLI);
    InstructionCost VecCallCost =
        std::min(VecCallCosts.first, VecCallCosts.second);

    LLVM_DEBUG(dbgs() << "SLP: Call cost " << VecCallCost - ScalarCallCostdo { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Call cost " << VecCallCost
 - ScalarCallCost << " (" << VecCallCost <<
 "-" << ScalarCallCost << ")" << " for " <<
 *CI << "\n"; } } while (false)
                      << " (" << VecCallCost << "-" << ScalarCallCost << ")"do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Call cost " << VecCallCost
 - ScalarCallCost << " (" << VecCallCost <<
 "-" << ScalarCallCost << ")" << " for " <<
 *CI << "\n"; } } while (false)
                      << " for " << *CI << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Call cost " << VecCallCost
 - ScalarCallCost << " (" << VecCallCost <<
 "-" << ScalarCallCost << ")" << " for " <<
 *CI << "\n"; } } while (false);

    return ReuseShuffleCost + VecCallCost - ScalarCallCost;
  }
  case Instruction::ShuffleVector: {
    assert(E->isAltShuffle() &&((E->isAltShuffle() && ((Instruction::isBinaryOp(E
->getOpcode()) && Instruction::isBinaryOp(E->getAltOpcode
())) || (Instruction::isCast(E->getOpcode()) && Instruction
::isCast(E->getAltOpcode()))) && "Invalid Shuffle Vector Operand"
) ? static_cast<void> (0) : __assert_fail ("E->isAltShuffle() && ((Instruction::isBinaryOp(E->getOpcode()) && Instruction::isBinaryOp(E->getAltOpcode())) || (Instruction::isCast(E->getOpcode()) && Instruction::isCast(E->getAltOpcode()))) && \"Invalid Shuffle Vector Operand\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 3895, __PRETTY_FUNCTION__))
           ((Instruction::isBinaryOp(E->getOpcode()) &&((E->isAltShuffle() && ((Instruction::isBinaryOp(E
->getOpcode()) && Instruction::isBinaryOp(E->getAltOpcode
())) || (Instruction::isCast(E->getOpcode()) && Instruction
::isCast(E->getAltOpcode()))) && "Invalid Shuffle Vector Operand"
) ? static_cast<void> (0) : __assert_fail ("E->isAltShuffle() && ((Instruction::isBinaryOp(E->getOpcode()) && Instruction::isBinaryOp(E->getAltOpcode())) || (Instruction::isCast(E->getOpcode()) && Instruction::isCast(E->getAltOpcode()))) && \"Invalid Shuffle Vector Operand\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 3895, __PRETTY_FUNCTION__))
             Instruction::isBinaryOp(E->getAltOpcode())) ||((E->isAltShuffle() && ((Instruction::isBinaryOp(E
->getOpcode()) && Instruction::isBinaryOp(E->getAltOpcode
())) || (Instruction::isCast(E->getOpcode()) && Instruction
::isCast(E->getAltOpcode()))) && "Invalid Shuffle Vector Operand"
) ? static_cast<void> (0) : __assert_fail ("E->isAltShuffle() && ((Instruction::isBinaryOp(E->getOpcode()) && Instruction::isBinaryOp(E->getAltOpcode())) || (Instruction::isCast(E->getOpcode()) && Instruction::isCast(E->getAltOpcode()))) && \"Invalid Shuffle Vector Operand\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 3895, __PRETTY_FUNCTION__))
            (Instruction::isCast(E->getOpcode()) &&((E->isAltShuffle() && ((Instruction::isBinaryOp(E
->getOpcode()) && Instruction::isBinaryOp(E->getAltOpcode
())) || (Instruction::isCast(E->getOpcode()) && Instruction
::isCast(E->getAltOpcode()))) && "Invalid Shuffle Vector Operand"
) ? static_cast<void> (0) : __assert_fail ("E->isAltShuffle() && ((Instruction::isBinaryOp(E->getOpcode()) && Instruction::isBinaryOp(E->getAltOpcode())) || (Instruction::isCast(E->getOpcode()) && Instruction::isCast(E->getAltOpcode()))) && \"Invalid Shuffle Vector Operand\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 3895, __PRETTY_FUNCTION__))
             Instruction::isCast(E->getAltOpcode()))) &&((E->isAltShuffle() && ((Instruction::isBinaryOp(E
->getOpcode()) && Instruction::isBinaryOp(E->getAltOpcode
())) || (Instruction::isCast(E->getOpcode()) && Instruction
::isCast(E->getAltOpcode()))) && "Invalid Shuffle Vector Operand"
) ? static_cast<void> (0) : __assert_fail ("E->isAltShuffle() && ((Instruction::isBinaryOp(E->getOpcode()) && Instruction::isBinaryOp(E->getAltOpcode())) || (Instruction::isCast(E->getOpcode()) && Instruction::isCast(E->getAltOpcode()))) && \"Invalid Shuffle Vector Operand\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 3895, __PRETTY_FUNCTION__))
           "Invalid Shuffle Vector Operand")((E->isAltShuffle() && ((Instruction::isBinaryOp(E
->getOpcode()) && Instruction::isBinaryOp(E->getAltOpcode
())) || (Instruction::isCast(E->getOpcode()) && Instruction
::isCast(E->getAltOpcode()))) && "Invalid Shuffle Vector Operand"
) ? static_cast<void> (0) : __assert_fail ("E->isAltShuffle() && ((Instruction::isBinaryOp(E->getOpcode()) && Instruction::isBinaryOp(E->getAltOpcode())) || (Instruction::isCast(E->getOpcode()) && Instruction::isCast(E->getAltOpcode()))) && \"Invalid Shuffle Vector Operand\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 3895, __PRETTY_FUNCTION__));
    InstructionCost ScalarCost = 0;
    if (NeedToShuffleReuses) {
      for (unsigned Idx : E->ReuseShuffleIndices) {
        Instruction *I = cast<Instruction>(VL[Idx]);
        ReuseShuffleCost -= TTI->getInstructionCost(I, CostKind);
      }
      for (Value *V : VL) {
        Instruction *I = cast<Instruction>(V);
        ReuseShuffleCost += TTI->getInstructionCost(I, CostKind);
      }
    }
    for (Value *V : VL) {
      Instruction *I = cast<Instruction>(V);
      assert(E->isOpcodeOrAlt(I) && "Unexpected main/alternate opcode")((E->isOpcodeOrAlt(I) && "Unexpected main/alternate opcode"
) ? static_cast<void> (0) : __assert_fail ("E->isOpcodeOrAlt(I) && \"Unexpected main/alternate opcode\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 3909, __PRETTY_FUNCTION__));
      ScalarCost += TTI->getInstructionCost(I, CostKind);
    }
    // VecCost is equal to sum of the cost of creating 2 vectors
    // and the cost of creating shuffle.
    InstructionCost VecCost = 0;
    if (Instruction::isBinaryOp(E->getOpcode())) {
      VecCost = TTI->getArithmeticInstrCost(E->getOpcode(), VecTy, CostKind);
      VecCost += TTI->getArithmeticInstrCost(E->getAltOpcode(), VecTy,
                                             CostKind);
    } else {
      Type *Src0SclTy = E->getMainOp()->getOperand(0)->getType();
      Type *Src1SclTy = E->getAltOp()->getOperand(0)->getType();
      auto *Src0Ty = FixedVectorType::get(Src0SclTy, VL.size());
      auto *Src1Ty = FixedVectorType::get(Src1SclTy, VL.size());
      VecCost = TTI->getCastInstrCost(E->getOpcode(), VecTy, Src0Ty,
                                      TTI::CastContextHint::None, CostKind);
      VecCost += TTI->getCastInstrCost(E->getAltOpcode(), VecTy, Src1Ty,
                                       TTI::CastContextHint::None, CostKind);
    }

    SmallVector<int> Mask(E->Scalars.size());
    for (unsigned I = 0, End = E->Scalars.size(); I < End; ++I) {
      auto *OpInst = cast<Instruction>(E->Scalars[I]);
      assert(E->isOpcodeOrAlt(OpInst) && "Unexpected main/alternate opcode")((E->isOpcodeOrAlt(OpInst) && "Unexpected main/alternate opcode"
) ? static_cast<void> (0) : __assert_fail ("E->isOpcodeOrAlt(OpInst) && \"Unexpected main/alternate opcode\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 3933, __PRETTY_FUNCTION__));
      Mask[I] = I + (OpInst->getOpcode() == E->getAltOpcode() ? End : 0);
    }
    VecCost +=
        TTI->getShuffleCost(TargetTransformInfo::SK_Select, VecTy, Mask, 0);
    LLVM_DEBUG(dumpTreeCosts(E, ReuseShuffleCost, VecCost, ScalarCost))do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dumpTreeCosts(E, ReuseShuffleCost, VecCost, ScalarCost
); } } while (false);
    return ReuseShuffleCost + VecCost - ScalarCost;
  }
  default:
    llvm_unreachable("Unknown instruction")::llvm::llvm_unreachable_internal("Unknown instruction", "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 3942);
}
3944}

3946bool BoUpSLP::isFullyVectorizableTinyTree() const {
LLVM_DEBUG(dbgs() << "SLP: Check whether the tree with height "do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Check whether the tree with height "
 << VectorizableTree.size() << " is fully vectorizable .\n"
; } } while (false)
                  << VectorizableTree.size() << " is fully vectorizable .\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Check whether the tree with height "
 << VectorizableTree.size() << " is fully vectorizable .\n"
; } } while (false);

// We only handle trees of heights 1 and 2.
if (VectorizableTree.size() == 1 &&
    VectorizableTree[0]->State == TreeEntry::Vectorize)
  return true;

if (VectorizableTree.size() != 2)
  return false;

// Handle splat and all-constants stores.
if (VectorizableTree[0]->State == TreeEntry::Vectorize &&
    (allConstant(VectorizableTree[1]->Scalars) ||
     isSplat(VectorizableTree[1]->Scalars)))
  return true;

// Gathering cost would be too much for tiny trees.
if (VectorizableTree[0]->State == TreeEntry::NeedToGather ||
    VectorizableTree[1]->State == TreeEntry::NeedToGather)
  return false;

return true;
3970}

3972static bool isLoadCombineCandidateImpl(Value *Root, unsigned NumElts,
                                     TargetTransformInfo *TTI) {
// Look past the root to find a source value. Arbitrarily follow the
// path through operand 0 of any 'or'. Also, peek through optional
// shift-left-by-multiple-of-8-bits.
Value *ZextLoad = Root;
const APInt *ShAmtC;
while (!isa<ConstantExpr>(ZextLoad) &&
       (match(ZextLoad, m_Or(m_Value(), m_Value())) ||
        (match(ZextLoad, m_Shl(m_Value(), m_APInt(ShAmtC))) &&
         ShAmtC->urem(8) == 0)))
  ZextLoad = cast<BinaryOperator>(ZextLoad)->getOperand(0);

// Check if the input is an extended load of the required or/shift expression.
Value *LoadPtr;
if (ZextLoad == Root || !match(ZextLoad, m_ZExt(m_Load(m_Value(LoadPtr)))))
  return false;

// Require that the total load bit width is a legal integer type.
// For example, <8 x i8> --> i64 is a legal integer on a 64-bit target.
// But <16 x i8> --> i128 is not, so the backend probably can't reduce it.
Type *SrcTy = LoadPtr->getType()->getPointerElementType();
unsigned LoadBitWidth = SrcTy->getIntegerBitWidth() * NumElts;
if (!TTI->isTypeLegal(IntegerType::get(Root->getContext(), LoadBitWidth)))
  return false;

// Everything matched - assume that we can fold the whole sequence using
// load combining.
LLVM_DEBUG(dbgs() << "SLP: Assume load combining for tree starting at "do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Assume load combining for tree starting at "
 << *(cast<Instruction>(Root)) << "\n"; } }
 while (false)
           << *(cast<Instruction>(Root)) << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Assume load combining for tree starting at "
 << *(cast<Instruction>(Root)) << "\n"; } }
 while (false);

return true;
4004}

4006bool BoUpSLP::isLoadCombineReductionCandidate(RecurKind RdxKind) const {
if (RdxKind != RecurKind::Or)
  return false;

unsigned NumElts = VectorizableTree[0]->Scalars.size();
Value *FirstReduced = VectorizableTree[0]->Scalars[0];
return isLoadCombineCandidateImpl(FirstReduced, NumElts, TTI);
4013}

4015bool BoUpSLP::isLoadCombineCandidate() const {
// Peek through a final sequence of stores and check if all operations are
// likely to be load-combined.
unsigned NumElts = VectorizableTree[0]->Scalars.size();
for (Value *Scalar : VectorizableTree[0]->Scalars) {
  Value *X;
  if (!match(Scalar, m_Store(m_Value(X), m_Value())) ||
      !isLoadCombineCandidateImpl(X, NumElts, TTI))
    return false;
}
return true;
4026}

4028bool BoUpSLP::isTreeTinyAndNotFullyVectorizable() const {
// We can vectorize the tree if its size is greater than or equal to the
// minimum size specified by the MinTreeSize command line option.
if (VectorizableTree.size() >= MinTreeSize)
  return false;

// If we have a tiny tree (a tree whose size is less than MinTreeSize), we
// can vectorize it if we can prove it fully vectorizable.
if (isFullyVectorizableTinyTree())
  return false;

assert(VectorizableTree.empty()((VectorizableTree.empty() ? ExternalUses.empty() : true &&
 "We shouldn't have any external users") ? static_cast<void
> (0) : __assert_fail ("VectorizableTree.empty() ? ExternalUses.empty() : true && \"We shouldn't have any external users\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 4041, __PRETTY_FUNCTION__))
           ? ExternalUses.empty()((VectorizableTree.empty() ? ExternalUses.empty() : true &&
 "We shouldn't have any external users") ? static_cast<void
> (0) : __assert_fail ("VectorizableTree.empty() ? ExternalUses.empty() : true && \"We shouldn't have any external users\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 4041, __PRETTY_FUNCTION__))
           : true && "We shouldn't have any external users")((VectorizableTree.empty() ? ExternalUses.empty() : true &&
 "We shouldn't have any external users") ? static_cast<void
> (0) : __assert_fail ("VectorizableTree.empty() ? ExternalUses.empty() : true && \"We shouldn't have any external users\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 4041, __PRETTY_FUNCTION__));

// Otherwise, we can't vectorize the tree. It is both tiny and not fully
// vectorizable.
return true;
4046}

4048InstructionCost BoUpSLP::getSpillCost() const {
// Walk from the bottom of the tree to the top, tracking which values are
// live. When we see a call instruction that is not part of our tree,
// query TTI to see if there is a cost to keeping values live over it
// (for example, if spills and fills are required).
unsigned BundleWidth = VectorizableTree.front()->Scalars.size();
InstructionCost Cost = 0;

SmallPtrSet<Instruction*, 4> LiveValues;
Instruction *PrevInst = nullptr;

// The entries in VectorizableTree are not necessarily ordered by their
// position in basic blocks. Collect them and order them by dominance so later
// instructions are guaranteed to be visited first. For instructions in
// different basic blocks, we only scan to the beginning of the block, so
// their order does not matter, as long as all instructions in a basic block
// are grouped together. Using dominance ensures a deterministic order.
SmallVector<Instruction *, 16> OrderedScalars;
for (const auto &TEPtr : VectorizableTree) {
  Instruction *Inst = dyn_cast<Instruction>(TEPtr->Scalars[0]);
  if (!Inst)
    continue;
  OrderedScalars.push_back(Inst);
}
llvm::stable_sort(OrderedScalars, [this](Instruction *A, Instruction *B) {
  return DT->dominates(B, A);
});

for (Instruction *Inst : OrderedScalars) {
  if (!PrevInst) {
    PrevInst = Inst;
    continue;
  }

  // Update LiveValues.
  LiveValues.erase(PrevInst);
  for (auto &J : PrevInst->operands()) {
    if (isa<Instruction>(&*J) && getTreeEntry(&*J))
      LiveValues.insert(cast<Instruction>(&*J));
  }

  LLVM_DEBUG({do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { { dbgs() << "SLP: #LV: " << LiveValues
.size(); for (auto *X : LiveValues) dbgs() << " " <<
 X->getName(); dbgs() << ", Looking at "; Inst->dump
(); }; } } while (false)
    dbgs() << "SLP: #LV: " << LiveValues.size();do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { { dbgs() << "SLP: #LV: " << LiveValues
.size(); for (auto *X : LiveValues) dbgs() << " " <<
 X->getName(); dbgs() << ", Looking at "; Inst->dump
(); }; } } while (false)
    for (auto *X : LiveValues)do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { { dbgs() << "SLP: #LV: " << LiveValues
.size(); for (auto *X : LiveValues) dbgs() << " " <<
 X->getName(); dbgs() << ", Looking at "; Inst->dump
(); }; } } while (false)
      dbgs() << " " << X->getName();do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { { dbgs() << "SLP: #LV: " << LiveValues
.size(); for (auto *X : LiveValues) dbgs() << " " <<
 X->getName(); dbgs() << ", Looking at "; Inst->dump
(); }; } } while (false)
    dbgs() << ", Looking at ";do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { { dbgs() << "SLP: #LV: " << LiveValues
.size(); for (auto *X : LiveValues) dbgs() << " " <<
 X->getName(); dbgs() << ", Looking at "; Inst->dump
(); }; } } while (false)
    Inst->dump();do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { { dbgs() << "SLP: #LV: " << LiveValues
.size(); for (auto *X : LiveValues) dbgs() << " " <<
 X->getName(); dbgs() << ", Looking at "; Inst->dump
(); }; } } while (false)
  })do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { { dbgs() << "SLP: #LV: " << LiveValues
.size(); for (auto *X : LiveValues) dbgs() << " " <<
 X->getName(); dbgs() << ", Looking at "; Inst->dump
(); }; } } while (false);

  // Now find the sequence of instructions between PrevInst and Inst.
  unsigned NumCalls = 0;
  BasicBlock::reverse_iterator InstIt = ++Inst->getIterator().getReverse(),
                               PrevInstIt =
                                   PrevInst->getIterator().getReverse();
  while (InstIt != PrevInstIt) {
    if (PrevInstIt == PrevInst->getParent()->rend()) {
      PrevInstIt = Inst->getParent()->rbegin();
      continue;
    }

    // Debug information does not impact spill cost.
    if ((isa<CallInst>(&*PrevInstIt) &&
         !isa<DbgInfoIntrinsic>(&*PrevInstIt)) &&
        &*PrevInstIt != PrevInst)
      NumCalls++;

    ++PrevInstIt;
  }

  if (NumCalls) {
    SmallVector<Type*, 4> V;
    for (auto *II : LiveValues)
      V.push_back(FixedVectorType::get(II->getType(), BundleWidth));
    Cost += NumCalls * TTI->getCostOfKeepingLiveOverCall(V);
  }

  PrevInst = Inst;
}

return Cost;
4128}

4130InstructionCost BoUpSLP::getTreeCost() {
InstructionCost Cost = 0;
LLVM_DEBUG(dbgs() << "SLP: Calculating cost for tree of size "do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Calculating cost for tree of size "
 << VectorizableTree.size() << ".\n"; } } while (
false)
                  << VectorizableTree.size() << ".\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Calculating cost for tree of size "
 << VectorizableTree.size() << ".\n"; } } while (
false);

unsigned BundleWidth = VectorizableTree[0]->Scalars.size();

for (unsigned I = 0, E = VectorizableTree.size(); I < E; ++I) {
  TreeEntry &TE = *VectorizableTree[I].get();

  // We create duplicate tree entries for gather sequences that have multiple
  // uses. However, we should not compute the cost of duplicate sequences.
  // For example, if we have a build vector (i.e., insertelement sequence)
  // that is used by more than one vector instruction, we only need to
  // compute the cost of the insertelement instructions once. The redundant
  // instructions will be eliminated by CSE.
  //
  // We should consider not creating duplicate tree entries for gather
  // sequences, and instead add additional edges to the tree representing
  // their uses. Since such an approach results in fewer total entries,
  // existing heuristics based on tree size may yield different results.
  //
  if (TE.State == TreeEntry::NeedToGather &&
      std::any_of(std::next(VectorizableTree.begin(), I + 1),
                  VectorizableTree.end(),
                  [TE](const std::unique_ptr<TreeEntry> &EntryPtr) {
                    return EntryPtr->State == TreeEntry::NeedToGather &&
                           EntryPtr->isSame(TE.Scalars);
                  }))
    continue;

  InstructionCost C = getEntryCost(&TE);
  Cost += C;
  LLVM_DEBUG(dbgs() << "SLP: Adding cost " << Cdo { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Adding cost " << C <<
 " for bundle that starts with " << *TE.Scalars[0] <<
 ".\n" << "SLP: Current total cost = " << Cost <<
 "\n"; } } while (false)
                    << " for bundle that starts with " << *TE.Scalars[0]do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Adding cost " << C <<
 " for bundle that starts with " << *TE.Scalars[0] <<
 ".\n" << "SLP: Current total cost = " << Cost <<
 "\n"; } } while (false)
                    << ".\n"do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Adding cost " << C <<
 " for bundle that starts with " << *TE.Scalars[0] <<
 ".\n" << "SLP: Current total cost = " << Cost <<
 "\n"; } } while (false)
                    << "SLP: Current total cost = " << Cost << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Adding cost " << C <<
 " for bundle that starts with " << *TE.Scalars[0] <<
 ".\n" << "SLP: Current total cost = " << Cost <<
 "\n"; } } while (false);
}

SmallPtrSet<Value *, 16> ExtractCostCalculated;
InstructionCost ExtractCost = 0;
for (ExternalUser &EU : ExternalUses) {
  // We only add extract cost once for the same scalar.
  if (!ExtractCostCalculated.insert(EU.Scalar).second)
    continue;

  // Uses by ephemeral values are free (because the ephemeral value will be
  // removed prior to code generation, and so the extraction will be
  // removed as well).
  if (EphValues.count(EU.User))
    continue;

  // If we plan to rewrite the tree in a smaller type, we will need to sign
  // extend the extracted value back to the original type. Here, we account
  // for the extract and the added cost of the sign extend if needed.
  auto *VecTy = FixedVectorType::get(EU.Scalar->getType(), BundleWidth);
  auto *ScalarRoot = VectorizableTree[0]->Scalars[0];
  if (MinBWs.count(ScalarRoot)) {
    auto *MinTy = IntegerType::get(F->getContext(), MinBWs[ScalarRoot].first);
    auto Extend =
        MinBWs[ScalarRoot].second ? Instruction::SExt : Instruction::ZExt;
    VecTy = FixedVectorType::get(MinTy, BundleWidth);
    ExtractCost += TTI->getExtractWithExtendCost(Extend, EU.Scalar->getType(),
                                                 VecTy, EU.Lane);
  } else {
    ExtractCost +=
        TTI->getVectorInstrCost(Instruction::ExtractElement, VecTy, EU.Lane);
  }
}

InstructionCost SpillCost = getSpillCost();
Cost += SpillCost + ExtractCost;

4203#ifndef NDEBUG
SmallString<256> Str;
{
  raw_svector_ostream OS(Str);
  OS << "SLP: Spill Cost = " << SpillCost << ".\n"
     << "SLP: Extract Cost = " << ExtractCost << ".\n"
     << "SLP: Total Cost = " << Cost << ".\n";
}
LLVM_DEBUG(dbgs() << Str)do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << Str; } } while (false);
if (ViewSLPTree)
  ViewGraph(this, "SLP" + F->getName(), false, Str);
4214#endif

return Cost;
4217}

4219InstructionCost
4220BoUpSLP::getGatherCost(FixedVectorType *Ty,
                     const DenseSet<unsigned> &ShuffledIndices) const {
unsigned NumElts = Ty->getNumElements();
APInt DemandedElts = APInt::getNullValue(NumElts);
for (unsigned I = 0; I < NumElts; ++I)
  if (!ShuffledIndices.count(I))
    DemandedElts.setBit(I);
InstructionCost Cost =
    TTI->getScalarizationOverhead(Ty, DemandedElts, /*Insert*/ true,
                                  /*Extract*/ false);
if (!ShuffledIndices.empty())
  Cost += TTI->getShuffleCost(TargetTransformInfo::SK_PermuteSingleSrc, Ty);
return Cost;
4233}

4235InstructionCost BoUpSLP::getGatherCost(ArrayRef<Value *> VL) const {
// Find the type of the operands in VL.
Type *ScalarTy = VL[0]->getType();
if (StoreInst *SI = dyn_cast<StoreInst>(VL[0]))
  ScalarTy = SI->getValueOperand()->getType();
auto *VecTy = FixedVectorType::get(ScalarTy, VL.size());
// Find the cost of inserting/extracting values from the vector.
// Check if the same elements are inserted several times and count them as
// shuffle candidates.
DenseSet<unsigned> ShuffledElements;
DenseSet<Value *> UniqueElements;
// Iterate in reverse order to consider insert elements with the high cost.
for (unsigned I = VL.size(); I > 0; --I) {
  unsigned Idx = I - 1;
  if (!UniqueElements.insert(VL[Idx]).second)
    ShuffledElements.insert(Idx);
}
return getGatherCost(VecTy, ShuffledElements);
4253}

4255// Perform operand reordering on the instructions in VL and return the reordered
4256// operands in Left and Right.
4257void BoUpSLP::reorderInputsAccordingToOpcode(ArrayRef<Value *> VL,
                                           SmallVectorImpl<Value *> &Left,
                                           SmallVectorImpl<Value *> &Right,
                                           const DataLayout &DL,
                                           ScalarEvolution &SE,
                                           const BoUpSLP &R) {
if (VL.empty())
  return;
VLOperands Ops(VL, DL, SE, R);
// Reorder the operands in place.
Ops.reorder();
Left = Ops.getVL(0);
Right = Ops.getVL(1);
4270}

4272void BoUpSLP::setInsertPointAfterBundle(TreeEntry *E) {
// Get the basic block this bundle is in. All instructions in the bundle
// should be in this block.
auto *Front = E->getMainOp();
auto *BB = Front->getParent();
assert(llvm::all_of(E->Scalars, [=](Value *V) -> bool {((llvm::all_of(E->Scalars, [=](Value *V) -> bool { auto
 *I = cast<Instruction>(V); return !E->isOpcodeOrAlt
(I) || I->getParent() == BB; })) ? static_cast<void>
 (0) : __assert_fail ("llvm::all_of(E->Scalars, [=](Value *V) -> bool { auto *I = cast<Instruction>(V); return !E->isOpcodeOrAlt(I) || I->getParent() == BB; })"
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 4280, __PRETTY_FUNCTION__))
  auto *I = cast<Instruction>(V);((llvm::all_of(E->Scalars, [=](Value *V) -> bool { auto
 *I = cast<Instruction>(V); return !E->isOpcodeOrAlt
(I) || I->getParent() == BB; })) ? static_cast<void>
 (0) : __assert_fail ("llvm::all_of(E->Scalars, [=](Value *V) -> bool { auto *I = cast<Instruction>(V); return !E->isOpcodeOrAlt(I) || I->getParent() == BB; })"
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 4280, __PRETTY_FUNCTION__))
  return !E->isOpcodeOrAlt(I) || I->getParent() == BB;((llvm::all_of(E->Scalars, [=](Value *V) -> bool { auto
 *I = cast<Instruction>(V); return !E->isOpcodeOrAlt
(I) || I->getParent() == BB; })) ? static_cast<void>
 (0) : __assert_fail ("llvm::all_of(E->Scalars, [=](Value *V) -> bool { auto *I = cast<Instruction>(V); return !E->isOpcodeOrAlt(I) || I->getParent() == BB; })"
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 4280, __PRETTY_FUNCTION__))
}))((llvm::all_of(E->Scalars, [=](Value *V) -> bool { auto
 *I = cast<Instruction>(V); return !E->isOpcodeOrAlt
(I) || I->getParent() == BB; })) ? static_cast<void>
 (0) : __assert_fail ("llvm::all_of(E->Scalars, [=](Value *V) -> bool { auto *I = cast<Instruction>(V); return !E->isOpcodeOrAlt(I) || I->getParent() == BB; })"
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 4280, __PRETTY_FUNCTION__));

// The last instruction in the bundle in program order.
Instruction *LastInst = nullptr;

// Find the last instruction. The common case should be that BB has been
// scheduled, and the last instruction is VL.back(). So we start with
// VL.back() and iterate over schedule data until we reach the end of the
// bundle. The end of the bundle is marked by null ScheduleData.
if (BlocksSchedules.count(BB)) {
  auto *Bundle =
      BlocksSchedules[BB]->getScheduleData(E->isOneOf(E->Scalars.back()));
  if (Bundle && Bundle->isPartOfBundle())
    for (; Bundle; Bundle = Bundle->NextInBundle)
      if (Bundle->OpValue == Bundle->Inst)
        LastInst = Bundle->Inst;
}

// LastInst can still be null at this point if there's either not an entry
// for BB in BlocksSchedules or there's no ScheduleData available for
// VL.back(). This can be the case if buildTree_rec aborts for various
// reasons (e.g., the maximum recursion depth is reached, the maximum region
// size is reached, etc.). ScheduleData is initialized in the scheduling
// "dry-run".
//
// If this happens, we can still find the last instruction by brute force. We
// iterate forwards from Front (inclusive) until we either see all
// instructions in the bundle or reach the end of the block. If Front is the
// last instruction in program order, LastInst will be set to Front, and we
// will visit all the remaining instructions in the block.
//
// One of the reasons we exit early from buildTree_rec is to place an upper
// bound on compile-time. Thus, taking an additional compile-time hit here is
// not ideal. However, this should be exceedingly rare since it requires that
// we both exit early from buildTree_rec and that the bundle be out-of-order
// (causing us to iterate all the way to the end of the block).
if (!LastInst) {
  SmallPtrSet<Value *, 16> Bundle(E->Scalars.begin(), E->Scalars.end());
  for (auto &I : make_range(BasicBlock::iterator(Front), BB->end())) {
    if (Bundle.erase(&I) && E->isOpcodeOrAlt(&I))
      LastInst = &I;
    if (Bundle.empty())
      break;
  }
}
assert(LastInst && "Failed to find last instruction in bundle")((LastInst && "Failed to find last instruction in bundle"
) ? static_cast<void> (0) : __assert_fail ("LastInst && \"Failed to find last instruction in bundle\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 4325, __PRETTY_FUNCTION__));

// Set the insertion point after the last instruction in the bundle. Set the
// debug location to Front.
Builder.SetInsertPoint(BB, ++LastInst->getIterator());
Builder.SetCurrentDebugLocation(Front->getDebugLoc());
4331}

4333Value *BoUpSLP::gather(ArrayRef<Value *> VL) {
Value *Val0 =
    isa<StoreInst>(VL[0]) ? cast<StoreInst>(VL[0])->getValueOperand() : VL[0];
FixedVectorType *VecTy = FixedVectorType::get(Val0->getType(), VL.size());
Value *Vec = PoisonValue::get(VecTy);
unsigned InsIndex = 0;
for (Value *Val : VL) {
  Vec = Builder.CreateInsertElement(Vec, Val, Builder.getInt32(InsIndex++));
  auto *InsElt = dyn_cast<InsertElementInst>(Vec);
  if (!InsElt)
    continue;
  GatherSeq.insert(InsElt);
  CSEBlocks.insert(InsElt->getParent());
  // Add to our 'need-to-extract' list.
  if (TreeEntry *Entry = getTreeEntry(Val)) {
    // Find which lane we need to extract.
    unsigned FoundLane = std::distance(Entry->Scalars.begin(),
                                       find(Entry->Scalars, Val));
    assert(FoundLane < Entry->Scalars.size() && "Couldn't find extract lane")((FoundLane < Entry->Scalars.size() && "Couldn't find extract lane"
) ? static_cast<void> (0) : __assert_fail ("FoundLane < Entry->Scalars.size() && \"Couldn't find extract lane\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 4351, __PRETTY_FUNCTION__));
    if (!Entry->ReuseShuffleIndices.empty()) {
      FoundLane = std::distance(Entry->ReuseShuffleIndices.begin(),
                                find(Entry->ReuseShuffleIndices, FoundLane));
    }
    ExternalUses.push_back(ExternalUser(Val, InsElt, FoundLane));
  }
}

return Vec;
4361}

4363Value *BoUpSLP::vectorizeTree(ArrayRef<Value *> VL) {
InstructionsState S = getSameOpcode(VL);
if (S.getOpcode()) {
  if (TreeEntry *E = getTreeEntry(S.OpValue)) {
    if (E->isSame(VL)) {
      Value *V = vectorizeTree(E);
      if (VL.size() == E->Scalars.size() && !E->ReuseShuffleIndices.empty()) {
        // Reshuffle to get only unique values.
        // If some of the scalars are duplicated in the vectorization tree
        // entry, we do not vectorize them but instead generate a mask for the
        // reuses. But if there are several users of the same entry, they may
        // have different vectorization factors. This is especially important
        // for PHI nodes. In this case, we need to adapt the resulting
        // instruction for the user vectorization factor and have to reshuffle
        // it again to take only unique elements of the vector. Without this
        // code the function incorrectly returns reduced vector instruction
        // with the same elements, not with the unique ones.
        // block:
        // %phi = phi <2 x > { .., %entry} {%shuffle, %block}
        // %2 = shuffle <2 x > %phi, %poison, <4 x > <0, 0, 1, 1>
        // ... (use %2)
        // %shuffle = shuffle <2 x> %2, poison, <2 x> {0, 2}
        // br %block
        SmallVector<int, 4> UniqueIdxs;
        SmallSet<int, 4> UsedIdxs;
        int Pos = 0;
        for (int Idx : E->ReuseShuffleIndices) {
          if (UsedIdxs.insert(Idx).second)
            UniqueIdxs.emplace_back(Pos);
          ++Pos;
        }
        V = Builder.CreateShuffleVector(V, UniqueIdxs, "shrink.shuffle");
      }
      return V;
    }
  }
}

// Check that every instruction appears once in this bundle.
SmallVector<int, 4> ReuseShuffleIndicies;
SmallVector<Value *, 4> UniqueValues;
if (VL.size() > 2) {
  DenseMap<Value *, unsigned> UniquePositions;
  for (Value *V : VL) {
    auto Res = UniquePositions.try_emplace(V, UniqueValues.size());
    ReuseShuffleIndicies.emplace_back(Res.first->second);
    if (Res.second || isa<Constant>(V))
      UniqueValues.emplace_back(V);
  }
  // Do not shuffle single element or if number of unique values is not power
  // of 2.
  if (UniqueValues.size() == VL.size() || UniqueValues.size() <= 1 ||
      !llvm::isPowerOf2_32(UniqueValues.size()))
    ReuseShuffleIndicies.clear();
  else
    VL = UniqueValues;
}

Value *Vec = gather(VL);
if (!ReuseShuffleIndicies.empty()) {
  Vec = Builder.CreateShuffleVector(Vec, ReuseShuffleIndicies, "shuffle");
  if (auto *I = dyn_cast<Instruction>(Vec)) {
    GatherSeq.insert(I);
    CSEBlocks.insert(I->getParent());
  }
}
return Vec;
4430}

4432namespace {
4433/// Merges shuffle masks and emits final shuffle instruction, if required.
4434class ShuffleInstructionBuilder {
IRBuilderBase &Builder;
bool IsFinalized = false;
SmallVector<int, 4> Mask;

4439public:
ShuffleInstructionBuilder(IRBuilderBase &Builder) : Builder(Builder) {}

/// Adds a mask, inverting it before applying.
void addInversedMask(ArrayRef<unsigned> SubMask) {
  if (SubMask.empty())
    return;
  SmallVector<int, 4> NewMask;
  inversePermutation(SubMask, NewMask);
  addMask(NewMask);
}

/// Functions adds masks, merging them into  single one.
void addMask(ArrayRef<unsigned> SubMask) {
  SmallVector<int, 4> NewMask(SubMask.begin(), SubMask.end());
  addMask(NewMask);
}

void addMask(ArrayRef<int> SubMask) {
  if (SubMask.empty())
    return;
  if (Mask.empty()) {
    Mask.append(SubMask.begin(), SubMask.end());
    return;
  }
  SmallVector<int, 4> NewMask(SubMask.size(), SubMask.size());
  int TermValue = std::min(Mask.size(), SubMask.size());
  for (int I = 0, E = SubMask.size(); I < E; ++I) {
    if (SubMask[I] >= TermValue || Mask[SubMask[I]] >= TermValue) {
      NewMask[I] = E;
      continue;
    }
    NewMask[I] = Mask[SubMask[I]];
  }
  Mask.swap(NewMask);
}

Value *finalize(Value *V) {
  IsFinalized = true;
  if (Mask.empty())
    return V;
  return Builder.CreateShuffleVector(V, Mask, "shuffle");
}

~ShuffleInstructionBuilder() {
  assert((IsFinalized || Mask.empty()) &&(((IsFinalized || Mask.empty()) && "Shuffle construction must be finalized."
) ? static_cast<void> (0) : __assert_fail ("(IsFinalized || Mask.empty()) && \"Shuffle construction must be finalized.\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 4485, __PRETTY_FUNCTION__))
         "Shuffle construction must be finalized.")(((IsFinalized || Mask.empty()) && "Shuffle construction must be finalized."
) ? static_cast<void> (0) : __assert_fail ("(IsFinalized || Mask.empty()) && \"Shuffle construction must be finalized.\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 4485, __PRETTY_FUNCTION__));
}
4487};
4488} // namespace

4490Value *BoUpSLP::vectorizeTree(TreeEntry *E) {
IRBuilder<>::InsertPointGuard Guard(Builder);

if (E->VectorizedValue) {
  LLVM_DEBUG(dbgs() << "SLP: Diamond merged for " << *E->Scalars[0] << ".\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Diamond merged for " <<
 *E->Scalars[0] << ".\n"; } } while (false);
  return E->VectorizedValue;
}

ShuffleInstructionBuilder ShuffleBuilder(Builder);
bool NeedToShuffleReuses = !E->ReuseShuffleIndices.empty();
if (E->State == TreeEntry::NeedToGather) {
  setInsertPointAfterBundle(E);
  Value *Vec = gather(E->Scalars);
  if (NeedToShuffleReuses) {
    ShuffleBuilder.addMask(E->ReuseShuffleIndices);
    Vec = ShuffleBuilder.finalize(Vec);
    if (auto *I = dyn_cast<Instruction>(Vec)) {
      GatherSeq.insert(I);
      CSEBlocks.insert(I->getParent());
    }
  }
  E->VectorizedValue = Vec;
  return Vec;
}

assert((E->State == TreeEntry::Vectorize ||(((E->State == TreeEntry::Vectorize || E->State == TreeEntry
::ScatterVectorize) && "Unhandled state") ? static_cast
<void> (0) : __assert_fail ("(E->State == TreeEntry::Vectorize || E->State == TreeEntry::ScatterVectorize) && \"Unhandled state\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 4517, __PRETTY_FUNCTION__))
        E->State == TreeEntry::ScatterVectorize) &&(((E->State == TreeEntry::Vectorize || E->State == TreeEntry
::ScatterVectorize) && "Unhandled state") ? static_cast
<void> (0) : __assert_fail ("(E->State == TreeEntry::Vectorize || E->State == TreeEntry::ScatterVectorize) && \"Unhandled state\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 4517, __PRETTY_FUNCTION__))
       "Unhandled state")(((E->State == TreeEntry::Vectorize || E->State == TreeEntry
::ScatterVectorize) && "Unhandled state") ? static_cast
<void> (0) : __assert_fail ("(E->State == TreeEntry::Vectorize || E->State == TreeEntry::ScatterVectorize) && \"Unhandled state\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 4517, __PRETTY_FUNCTION__));
unsigned ShuffleOrOp =
    E->isAltShuffle() ? (unsigned)Instruction::ShuffleVector : E->getOpcode();
Instruction *VL0 = E->getMainOp();
Type *ScalarTy = VL0->getType();
if (auto *Store = dyn_cast<StoreInst>(VL0))
  ScalarTy = Store->getValueOperand()->getType();
auto *VecTy = FixedVectorType::get(ScalarTy, E->Scalars.size());
switch (ShuffleOrOp) {
  case Instruction::PHI: {
    auto *PH = cast<PHINode>(VL0);
    Builder.SetInsertPoint(PH->getParent()->getFirstNonPHI());
    Builder.SetCurrentDebugLocation(PH->getDebugLoc());
    PHINode *NewPhi = Builder.CreatePHI(VecTy, PH->getNumIncomingValues());
    Value *V = NewPhi;
    if (NeedToShuffleReuses)
      V = Builder.CreateShuffleVector(V, E->ReuseShuffleIndices, "shuffle");

    E->VectorizedValue = V;

    // PHINodes may have multiple entries from the same block. We want to
    // visit every block once.
    SmallPtrSet<BasicBlock*, 4> VisitedBBs;

    for (unsigned i = 0, e = PH->getNumIncomingValues(); i < e; ++i) {
      ValueList Operands;
      BasicBlock *IBB = PH->getIncomingBlock(i);

      if (!VisitedBBs.insert(IBB).second) {
        NewPhi->addIncoming(NewPhi->getIncomingValueForBlock(IBB), IBB);
        continue;
      }

      Builder.SetInsertPoint(IBB->getTerminator());
      Builder.SetCurrentDebugLocation(PH->getDebugLoc());
      Value *Vec = vectorizeTree(E->getOperand(i));
      NewPhi->addIncoming(Vec, IBB);
    }

    assert(NewPhi->getNumIncomingValues() == PH->getNumIncomingValues() &&((NewPhi->getNumIncomingValues() == PH->getNumIncomingValues
() && "Invalid number of incoming values") ? static_cast
<void> (0) : __assert_fail ("NewPhi->getNumIncomingValues() == PH->getNumIncomingValues() && \"Invalid number of incoming values\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 4557, __PRETTY_FUNCTION__))
           "Invalid number of incoming values")((NewPhi->getNumIncomingValues() == PH->getNumIncomingValues
() && "Invalid number of incoming values") ? static_cast
<void> (0) : __assert_fail ("NewPhi->getNumIncomingValues() == PH->getNumIncomingValues() && \"Invalid number of incoming values\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 4557, __PRETTY_FUNCTION__));
    return V;
  }

  case Instruction::ExtractElement: {
    Value *V = E->getSingleOperand(0);
    Builder.SetInsertPoint(VL0);
    ShuffleBuilder.addInversedMask(E->ReorderIndices);
    ShuffleBuilder.addMask(E->ReuseShuffleIndices);
    V = ShuffleBuilder.finalize(V);
    E->VectorizedValue = V;
    return V;
  }
  case Instruction::ExtractValue: {
    auto *LI = cast<LoadInst>(E->getSingleOperand(0));
    Builder.SetInsertPoint(LI);
    auto *PtrTy = PointerType::get(VecTy, LI->getPointerAddressSpace());
    Value *Ptr = Builder.CreateBitCast(LI->getOperand(0), PtrTy);
    LoadInst *V = Builder.CreateAlignedLoad(VecTy, Ptr, LI->getAlign());
    Value *NewV = propagateMetadata(V, E->Scalars);
    ShuffleBuilder.addInversedMask(E->ReorderIndices);
    ShuffleBuilder.addMask(E->ReuseShuffleIndices);
    NewV = ShuffleBuilder.finalize(NewV);
    E->VectorizedValue = NewV;
    return NewV;
  }
  case Instruction::ZExt:
  case Instruction::SExt:
  case Instruction::FPToUI:
  case Instruction::FPToSI:
  case Instruction::FPExt:
  case Instruction::PtrToInt:
  case Instruction::IntToPtr:
  case Instruction::SIToFP:
  case Instruction::UIToFP:
  case Instruction::Trunc:
  case Instruction::FPTrunc:
  case Instruction::BitCast: {
    setInsertPointAfterBundle(E);

    Value *InVec = vectorizeTree(E->getOperand(0));

    if (E->VectorizedValue) {
      LLVM_DEBUG(dbgs() << "SLP: Diamond merged for " << *VL0 << ".\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Diamond merged for " <<
 *VL0 << ".\n"; } } while (false);
      return E->VectorizedValue;
    }

    auto *CI = cast<CastInst>(VL0);
    Value *V = Builder.CreateCast(CI->getOpcode(), InVec, VecTy);
    ShuffleBuilder.addMask(E->ReuseShuffleIndices);
    V = ShuffleBuilder.finalize(V);

    E->VectorizedValue = V;
    ++NumVectorInstructions;
    return V;
  }
  case Instruction::FCmp:
  case Instruction::ICmp: {
    setInsertPointAfterBundle(E);

    Value *L = vectorizeTree(E->getOperand(0));
    Value *R = vectorizeTree(E->getOperand(1));

    if (E->VectorizedValue) {
      LLVM_DEBUG(dbgs() << "SLP: Diamond merged for " << *VL0 << ".\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Diamond merged for " <<
 *VL0 << ".\n"; } } while (false);
      return E->VectorizedValue;
    }

    CmpInst::Predicate P0 = cast<CmpInst>(VL0)->getPredicate();
    Value *V = Builder.CreateCmp(P0, L, R);
    propagateIRFlags(V, E->Scalars, VL0);
    ShuffleBuilder.addMask(E->ReuseShuffleIndices);
    V = ShuffleBuilder.finalize(V);

    E->VectorizedValue = V;
    ++NumVectorInstructions;
    return V;
  }
  case Instruction::Select: {
    setInsertPointAfterBundle(E);

    Value *Cond = vectorizeTree(E->getOperand(0));
    Value *True = vectorizeTree(E->getOperand(1));
    Value *False = vectorizeTree(E->getOperand(2));

    if (E->VectorizedValue) {
      LLVM_DEBUG(dbgs() << "SLP: Diamond merged for " << *VL0 << ".\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Diamond merged for " <<
 *VL0 << ".\n"; } } while (false);
      return E->VectorizedValue;
    }

    Value *V = Builder.CreateSelect(Cond, True, False);
    ShuffleBuilder.addMask(E->ReuseShuffleIndices);
    V = ShuffleBuilder.finalize(V);

    E->VectorizedValue = V;
    ++NumVectorInstructions;
    return V;
  }
  case Instruction::FNeg: {
    setInsertPointAfterBundle(E);

    Value *Op = vectorizeTree(E->getOperand(0));

    if (E->VectorizedValue) {
      LLVM_DEBUG(dbgs() << "SLP: Diamond merged for " << *VL0 << ".\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Diamond merged for " <<
 *VL0 << ".\n"; } } while (false);
      return E->VectorizedValue;
    }

    Value *V = Builder.CreateUnOp(
        static_cast<Instruction::UnaryOps>(E->getOpcode()), Op);
    propagateIRFlags(V, E->Scalars, VL0);
    if (auto *I = dyn_cast<Instruction>(V))
      V = propagateMetadata(I, E->Scalars);

    ShuffleBuilder.addMask(E->ReuseShuffleIndices);
    V = ShuffleBuilder.finalize(V);

    E->VectorizedValue = V;
    ++NumVectorInstructions;

    return V;
  }
  case Instruction::Add:
  case Instruction::FAdd:
  case Instruction::Sub:
  case Instruction::FSub:
  case Instruction::Mul:
  case Instruction::FMul:
  case Instruction::UDiv:
  case Instruction::SDiv:
  case Instruction::FDiv:
  case Instruction::URem:
  case Instruction::SRem:
  case Instruction::FRem:
  case Instruction::Shl:
  case Instruction::LShr:
  case Instruction::AShr:
  case Instruction::And:
  case Instruction::Or:
  case Instruction::Xor: {
    setInsertPointAfterBundle(E);

    Value *LHS = vectorizeTree(E->getOperand(0));
    Value *RHS = vectorizeTree(E->getOperand(1));

    if (E->VectorizedValue) {
      LLVM_DEBUG(dbgs() << "SLP: Diamond merged for " << *VL0 << ".\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Diamond merged for " <<
 *VL0 << ".\n"; } } while (false);
      return E->VectorizedValue;
    }

    Value *V = Builder.CreateBinOp(
        static_cast<Instruction::BinaryOps>(E->getOpcode()), LHS,
        RHS);
    propagateIRFlags(V, E->Scalars, VL0);
    if (auto *I = dyn_cast<Instruction>(V))
      V = propagateMetadata(I, E->Scalars);

    ShuffleBuilder.addMask(E->ReuseShuffleIndices);
    V = ShuffleBuilder.finalize(V);

    E->VectorizedValue = V;
    ++NumVectorInstructions;

    return V;
  }
  case Instruction::Load: {
    // Loads are inserted at the head of the tree because we don't want to
    // sink them all the way down past store instructions.
    bool IsReorder = E->updateStateIfReorder();
    if (IsReorder)
      VL0 = E->getMainOp();
    setInsertPointAfterBundle(E);

    LoadInst *LI = cast<LoadInst>(VL0);
    Instruction *NewLI;
    unsigned AS = LI->getPointerAddressSpace();
    Value *PO = LI->getPointerOperand();
    if (E->State == TreeEntry::Vectorize) {

      Value *VecPtr = Builder.CreateBitCast(PO, VecTy->getPointerTo(AS));

      // The pointer operand uses an in-tree scalar so we add the new BitCast
      // to ExternalUses list to make sure that an extract will be generated
      // in the future.
      if (getTreeEntry(PO))
        ExternalUses.emplace_back(PO, cast<User>(VecPtr), 0);

      NewLI = Builder.CreateAlignedLoad(VecTy, VecPtr, LI->getAlign());
    } else {
      assert(E->State == TreeEntry::ScatterVectorize && "Unhandled state")((E->State == TreeEntry::ScatterVectorize && "Unhandled state"
) ? static_cast<void> (0) : __assert_fail ("E->State == TreeEntry::ScatterVectorize && \"Unhandled state\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 4746, __PRETTY_FUNCTION__));
      Value *VecPtr = vectorizeTree(E->getOperand(0));
      // Use the minimum alignment of the gathered loads.
      Align CommonAlignment = LI->getAlign();
      for (Value *V : E->Scalars)
        CommonAlignment =
            commonAlignment(CommonAlignment, cast<LoadInst>(V)->getAlign());
      NewLI = Builder.CreateMaskedGather(VecPtr, CommonAlignment);
    }
    Value *V = propagateMetadata(NewLI, E->Scalars);

    ShuffleBuilder.addInversedMask(E->ReorderIndices);
    ShuffleBuilder.addMask(E->ReuseShuffleIndices);
    V = ShuffleBuilder.finalize(V);
    E->VectorizedValue = V;
    ++NumVectorInstructions;
    return V;
  }
  case Instruction::Store: {
    bool IsReorder = !E->ReorderIndices.empty();
    auto *SI = cast<StoreInst>(
        IsReorder ? E->Scalars[E->ReorderIndices.front()] : VL0);
    unsigned AS = SI->getPointerAddressSpace();

    setInsertPointAfterBundle(E);

    Value *VecValue = vectorizeTree(E->getOperand(0));
    ShuffleBuilder.addMask(E->ReorderIndices);
    VecValue = ShuffleBuilder.finalize(VecValue);

    Value *ScalarPtr = SI->getPointerOperand();
    Value *VecPtr = Builder.CreateBitCast(
        ScalarPtr, VecValue->getType()->getPointerTo(AS));
    StoreInst *ST = Builder.CreateAlignedStore(VecValue, VecPtr,
                                               SI->getAlign());

    // The pointer operand uses an in-tree scalar, so add the new BitCast to
    // ExternalUses to make sure that an extract will be generated in the
    // future.
    if (getTreeEntry(ScalarPtr))
      ExternalUses.push_back(ExternalUser(ScalarPtr, cast<User>(VecPtr), 0));

    Value *V = propagateMetadata(ST, E->Scalars);

    E->VectorizedValue = V;
    ++NumVectorInstructions;
    return V;
  }
  case Instruction::GetElementPtr: {
    setInsertPointAfterBundle(E);

    Value *Op0 = vectorizeTree(E->getOperand(0));

    std::vector<Value *> OpVecs;
    for (int j = 1, e = cast<GetElementPtrInst>(VL0)->getNumOperands(); j < e;
         ++j) {
      ValueList &VL = E->getOperand(j);
      // Need to cast all elements to the same type before vectorization to
      // avoid crash.
      Type *VL0Ty = VL0->getOperand(j)->getType();
      Type *Ty = llvm::all_of(
                     VL, [VL0Ty](Value *V) { return VL0Ty == V->getType(); })
                     ? VL0Ty
                     : DL->getIndexType(cast<GetElementPtrInst>(VL0)
                                            ->getPointerOperandType()
                                            ->getScalarType());
      for (Value *&V : VL) {
        auto *CI = cast<ConstantInt>(V);
        V = ConstantExpr::getIntegerCast(CI, Ty,
                                         CI->getValue().isSignBitSet());
      }
      Value *OpVec = vectorizeTree(VL);
      OpVecs.push_back(OpVec);
    }

    Value *V = Builder.CreateGEP(
        cast<GetElementPtrInst>(VL0)->getSourceElementType(), Op0, OpVecs);
    if (Instruction *I = dyn_cast<Instruction>(V))
      V = propagateMetadata(I, E->Scalars);

    ShuffleBuilder.addMask(E->ReuseShuffleIndices);
    V = ShuffleBuilder.finalize(V);

    E->VectorizedValue = V;
    ++NumVectorInstructions;

    return V;
  }
  case Instruction::Call: {
    CallInst *CI = cast<CallInst>(VL0);
    setInsertPointAfterBundle(E);

    Intrinsic::ID IID  = Intrinsic::not_intrinsic;
    if (Function *FI = CI->getCalledFunction())
      IID = FI->getIntrinsicID();

    Intrinsic::ID ID = getVectorIntrinsicIDForCall(CI, TLI);

    auto VecCallCosts = getVectorCallCosts(CI, VecTy, TTI, TLI);
    bool UseIntrinsic = ID != Intrinsic::not_intrinsic &&
                        VecCallCosts.first <= VecCallCosts.second;

    Value *ScalarArg = nullptr;
    std::vector<Value *> OpVecs;
    for (int j = 0, e = CI->getNumArgOperands(); j < e; ++j) {
      ValueList OpVL;
      // Some intrinsics have scalar arguments. This argument should not be
      // vectorized.
      if (UseIntrinsic && hasVectorInstrinsicScalarOpd(IID, j)) {
        CallInst *CEI = cast<CallInst>(VL0);
        ScalarArg = CEI->getArgOperand(j);
        OpVecs.push_back(CEI->getArgOperand(j));
        continue;
      }

      Value *OpVec = vectorizeTree(E->getOperand(j));
      LLVM_DEBUG(dbgs() << "SLP: OpVec[" << j << "]: " << *OpVec << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: OpVec[" << j << "]: "
 << *OpVec << "\n"; } } while (false);
      OpVecs.push_back(OpVec);
    }

    Function *CF;
    if (!UseIntrinsic) {
      VFShape Shape =
          VFShape::get(*CI, ElementCount::getFixed(static_cast<unsigned>(
                                VecTy->getNumElements())),
                       false /*HasGlobalPred*/);
      CF = VFDatabase(*CI).getVectorizedFunction(Shape);
    } else {
      Type *Tys[] = {FixedVectorType::get(CI->getType(), E->Scalars.size())};
      CF = Intrinsic::getDeclaration(F->getParent(), ID, Tys);
    }

    SmallVector<OperandBundleDef, 1> OpBundles;
    CI->getOperandBundlesAsDefs(OpBundles);
    Value *V = Builder.CreateCall(CF, OpVecs, OpBundles);

    // The scalar argument uses an in-tree scalar so we add the new vectorized
    // call to ExternalUses list to make sure that an extract will be
    // generated in the future.
    if (ScalarArg && getTreeEntry(ScalarArg))
      ExternalUses.push_back(ExternalUser(ScalarArg, cast<User>(V), 0));

    propagateIRFlags(V, E->Scalars, VL0);
    ShuffleBuilder.addMask(E->ReuseShuffleIndices);
    V = ShuffleBuilder.finalize(V);

    E->VectorizedValue = V;
    ++NumVectorInstructions;
    return V;
  }
  case Instruction::ShuffleVector: {
    assert(E->isAltShuffle() &&((E->isAltShuffle() && ((Instruction::isBinaryOp(E
->getOpcode()) && Instruction::isBinaryOp(E->getAltOpcode
())) || (Instruction::isCast(E->getOpcode()) && Instruction
::isCast(E->getAltOpcode()))) && "Invalid Shuffle Vector Operand"
) ? static_cast<void> (0) : __assert_fail ("E->isAltShuffle() && ((Instruction::isBinaryOp(E->getOpcode()) && Instruction::isBinaryOp(E->getAltOpcode())) || (Instruction::isCast(E->getOpcode()) && Instruction::isCast(E->getAltOpcode()))) && \"Invalid Shuffle Vector Operand\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 4902, __PRETTY_FUNCTION__))
           ((Instruction::isBinaryOp(E->getOpcode()) &&((E->isAltShuffle() && ((Instruction::isBinaryOp(E
->getOpcode()) && Instruction::isBinaryOp(E->getAltOpcode
())) || (Instruction::isCast(E->getOpcode()) && Instruction
::isCast(E->getAltOpcode()))) && "Invalid Shuffle Vector Operand"
) ? static_cast<void> (0) : __assert_fail ("E->isAltShuffle() && ((Instruction::isBinaryOp(E->getOpcode()) && Instruction::isBinaryOp(E->getAltOpcode())) || (Instruction::isCast(E->getOpcode()) && Instruction::isCast(E->getAltOpcode()))) && \"Invalid Shuffle Vector Operand\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 4902, __PRETTY_FUNCTION__))
             Instruction::isBinaryOp(E->getAltOpcode())) ||((E->isAltShuffle() && ((Instruction::isBinaryOp(E
->getOpcode()) && Instruction::isBinaryOp(E->getAltOpcode
())) || (Instruction::isCast(E->getOpcode()) && Instruction
::isCast(E->getAltOpcode()))) && "Invalid Shuffle Vector Operand"
) ? static_cast<void> (0) : __assert_fail ("E->isAltShuffle() && ((Instruction::isBinaryOp(E->getOpcode()) && Instruction::isBinaryOp(E->getAltOpcode())) || (Instruction::isCast(E->getOpcode()) && Instruction::isCast(E->getAltOpcode()))) && \"Invalid Shuffle Vector Operand\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 4902, __PRETTY_FUNCTION__))
            (Instruction::isCast(E->getOpcode()) &&((E->isAltShuffle() && ((Instruction::isBinaryOp(E
->getOpcode()) && Instruction::isBinaryOp(E->getAltOpcode
())) || (Instruction::isCast(E->getOpcode()) && Instruction
::isCast(E->getAltOpcode()))) && "Invalid Shuffle Vector Operand"
) ? static_cast<void> (0) : __assert_fail ("E->isAltShuffle() && ((Instruction::isBinaryOp(E->getOpcode()) && Instruction::isBinaryOp(E->getAltOpcode())) || (Instruction::isCast(E->getOpcode()) && Instruction::isCast(E->getAltOpcode()))) && \"Invalid Shuffle Vector Operand\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 4902, __PRETTY_FUNCTION__))
             Instruction::isCast(E->getAltOpcode()))) &&((E->isAltShuffle() && ((Instruction::isBinaryOp(E
->getOpcode()) && Instruction::isBinaryOp(E->getAltOpcode
())) || (Instruction::isCast(E->getOpcode()) && Instruction
::isCast(E->getAltOpcode()))) && "Invalid Shuffle Vector Operand"
) ? static_cast<void> (0) : __assert_fail ("E->isAltShuffle() && ((Instruction::isBinaryOp(E->getOpcode()) && Instruction::isBinaryOp(E->getAltOpcode())) || (Instruction::isCast(E->getOpcode()) && Instruction::isCast(E->getAltOpcode()))) && \"Invalid Shuffle Vector Operand\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 4902, __PRETTY_FUNCTION__))
           "Invalid Shuffle Vector Operand")((E->isAltShuffle() && ((Instruction::isBinaryOp(E
->getOpcode()) && Instruction::isBinaryOp(E->getAltOpcode
())) || (Instruction::isCast(E->getOpcode()) && Instruction
::isCast(E->getAltOpcode()))) && "Invalid Shuffle Vector Operand"
) ? static_cast<void> (0) : __assert_fail ("E->isAltShuffle() && ((Instruction::isBinaryOp(E->getOpcode()) && Instruction::isBinaryOp(E->getAltOpcode())) || (Instruction::isCast(E->getOpcode()) && Instruction::isCast(E->getAltOpcode()))) && \"Invalid Shuffle Vector Operand\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 4902, __PRETTY_FUNCTION__));

    Value *LHS = nullptr, *RHS = nullptr;
    if (Instruction::isBinaryOp(E->getOpcode())) {
      setInsertPointAfterBundle(E);
      LHS = vectorizeTree(E->getOperand(0));
      RHS = vectorizeTree(E->getOperand(1));
    } else {
      setInsertPointAfterBundle(E);
      LHS = vectorizeTree(E->getOperand(0));
    }

    if (E->VectorizedValue) {
      LLVM_DEBUG(dbgs() << "SLP: Diamond merged for " << *VL0 << ".\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Diamond merged for " <<
 *VL0 << ".\n"; } } while (false);
      return E->VectorizedValue;
    }

    Value *V0, *V1;
    if (Instruction::isBinaryOp(E->getOpcode())) {
      V0 = Builder.CreateBinOp(
          static_cast<Instruction::BinaryOps>(E->getOpcode()), LHS, RHS);
      V1 = Builder.CreateBinOp(
          static_cast<Instruction::BinaryOps>(E->getAltOpcode()), LHS, RHS);
    } else {
      V0 = Builder.CreateCast(
          static_cast<Instruction::CastOps>(E->getOpcode()), LHS, VecTy);
      V1 = Builder.CreateCast(
          static_cast<Instruction::CastOps>(E->getAltOpcode()), LHS, VecTy);
    }

    // Create shuffle to take alternate operations from the vector.
    // Also, gather up main and alt scalar ops to propagate IR flags to
    // each vector operation.
    ValueList OpScalars, AltScalars;
    unsigned e = E->Scalars.size();
    SmallVector<int, 8> Mask(e);
    for (unsigned i = 0; i < e; ++i) {
      auto *OpInst = cast<Instruction>(E->Scalars[i]);
      assert(E->isOpcodeOrAlt(OpInst) && "Unexpected main/alternate opcode")((E->isOpcodeOrAlt(OpInst) && "Unexpected main/alternate opcode"
) ? static_cast<void> (0) : __assert_fail ("E->isOpcodeOrAlt(OpInst) && \"Unexpected main/alternate opcode\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 4940, __PRETTY_FUNCTION__));
      if (OpInst->getOpcode() == E->getAltOpcode()) {
        Mask[i] = e + i;
        AltScalars.push_back(E->Scalars[i]);
      } else {
        Mask[i] = i;
        OpScalars.push_back(E->Scalars[i]);
      }
    }

    propagateIRFlags(V0, OpScalars);
    propagateIRFlags(V1, AltScalars);

    Value *V = Builder.CreateShuffleVector(V0, V1, Mask);
    if (Instruction *I = dyn_cast<Instruction>(V))
      V = propagateMetadata(I, E->Scalars);
    ShuffleBuilder.addMask(E->ReuseShuffleIndices);
    V = ShuffleBuilder.finalize(V);

    E->VectorizedValue = V;
    ++NumVectorInstructions;

    return V;
  }
  default:
  llvm_unreachable("unknown inst")::llvm::llvm_unreachable_internal("unknown inst", "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 4965);
}
return nullptr;
4968}

4970Value *BoUpSLP::vectorizeTree() {
ExtraValueToDebugLocsMap ExternallyUsedValues;
return vectorizeTree(ExternallyUsedValues);
4973}

4975Value *
4976BoUpSLP::vectorizeTree(ExtraValueToDebugLocsMap &ExternallyUsedValues) {
// All blocks must be scheduled before any instructions are inserted.
for (auto &BSIter : BlocksSchedules) {
  scheduleBlock(BSIter.second.get());
}

Builder.SetInsertPoint(&F->getEntryBlock().front());
auto *VectorRoot = vectorizeTree(VectorizableTree[0].get());

// If the vectorized tree can be rewritten in a smaller type, we truncate the
// vectorized root. InstCombine will then rewrite the entire expression. We
// sign extend the extracted values below.
auto *ScalarRoot = VectorizableTree[0]->Scalars[0];
if (MinBWs.count(ScalarRoot)) {
  if (auto *I = dyn_cast<Instruction>(VectorRoot)) {
    // If current instr is a phi and not the last phi, insert it after the
    // last phi node.
    if (isa<PHINode>(I))
      Builder.SetInsertPoint(&*I->getParent()->getFirstInsertionPt());
    else
      Builder.SetInsertPoint(&*++BasicBlock::iterator(I));
  }
  auto BundleWidth = VectorizableTree[0]->Scalars.size();
  auto *MinTy = IntegerType::get(F->getContext(), MinBWs[ScalarRoot].first);
  auto *VecTy = FixedVectorType::get(MinTy, BundleWidth);
  auto *Trunc = Builder.CreateTrunc(VectorRoot, VecTy);
  VectorizableTree[0]->VectorizedValue = Trunc;
}

LLVM_DEBUG(dbgs() << "SLP: Extracting " << ExternalUses.size()do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Extracting " << ExternalUses
.size() << " values .\n"; } } while (false)
                  << " values .\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Extracting " << ExternalUses
.size() << " values .\n"; } } while (false);

// If necessary, sign-extend or zero-extend ScalarRoot to the larger type
// specified by ScalarType.
auto extend = [&](Value *ScalarRoot, Value *Ex, Type *ScalarType) {
  if (!MinBWs.count(ScalarRoot))
    return Ex;
  if (MinBWs[ScalarRoot].second)
    return Builder.CreateSExt(Ex, ScalarType);
  return Builder.CreateZExt(Ex, ScalarType);
};

// Extract all of the elements with the external uses.
for (const auto &ExternalUse : ExternalUses) {
  Value *Scalar = ExternalUse.Scalar;
  llvm::User *User = ExternalUse.User;

  // Skip users that we already RAUW. This happens when one instruction
  // has multiple uses of the same value.
  if (User && !is_contained(Scalar->users(), User))
    continue;
  TreeEntry *E = getTreeEntry(Scalar);
  assert(E && "Invalid scalar")((E && "Invalid scalar") ? static_cast<void> (0
) : __assert_fail ("E && \"Invalid scalar\"", "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5028, __PRETTY_FUNCTION__));
  assert(E->State != TreeEntry::NeedToGather &&((E->State != TreeEntry::NeedToGather && "Extracting from a gather list"
) ? static_cast<void> (0) : __assert_fail ("E->State != TreeEntry::NeedToGather && \"Extracting from a gather list\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5030, __PRETTY_FUNCTION__))
         "Extracting from a gather list")((E->State != TreeEntry::NeedToGather && "Extracting from a gather list"
) ? static_cast<void> (0) : __assert_fail ("E->State != TreeEntry::NeedToGather && \"Extracting from a gather list\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5030, __PRETTY_FUNCTION__));

  Value *Vec = E->VectorizedValue;
  assert(Vec && "Can't find vectorizable value")((Vec && "Can't find vectorizable value") ? static_cast
<void> (0) : __assert_fail ("Vec && \"Can't find vectorizable value\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5033, __PRETTY_FUNCTION__));

  Value *Lane = Builder.getInt32(ExternalUse.Lane);
  // If User == nullptr, the Scalar is used as extra arg. Generate
  // ExtractElement instruction and update the record for this scalar in
  // ExternallyUsedValues.
  if (!User) {
    assert(ExternallyUsedValues.count(Scalar) &&((ExternallyUsedValues.count(Scalar) && "Scalar with nullptr as an external user must be registered in "
 "ExternallyUsedValues map") ? static_cast<void> (0) : __assert_fail
 ("ExternallyUsedValues.count(Scalar) && \"Scalar with nullptr as an external user must be registered in \" \"ExternallyUsedValues map\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5042, __PRETTY_FUNCTION__))
           "Scalar with nullptr as an external user must be registered in "((ExternallyUsedValues.count(Scalar) && "Scalar with nullptr as an external user must be registered in "
 "ExternallyUsedValues map") ? static_cast<void> (0) : __assert_fail
 ("ExternallyUsedValues.count(Scalar) && \"Scalar with nullptr as an external user must be registered in \" \"ExternallyUsedValues map\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5042, __PRETTY_FUNCTION__))
           "ExternallyUsedValues map")((ExternallyUsedValues.count(Scalar) && "Scalar with nullptr as an external user must be registered in "
 "ExternallyUsedValues map") ? static_cast<void> (0) : __assert_fail
 ("ExternallyUsedValues.count(Scalar) && \"Scalar with nullptr as an external user must be registered in \" \"ExternallyUsedValues map\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5042, __PRETTY_FUNCTION__));
    if (auto *VecI = dyn_cast<Instruction>(Vec)) {
      Builder.SetInsertPoint(VecI->getParent(),
                             std::next(VecI->getIterator()));
    } else {
      Builder.SetInsertPoint(&F->getEntryBlock().front());
    }
    Value *Ex = Builder.CreateExtractElement(Vec, Lane);
    Ex = extend(ScalarRoot, Ex, Scalar->getType());
    CSEBlocks.insert(cast<Instruction>(Scalar)->getParent());
    auto &Locs = ExternallyUsedValues[Scalar];
    ExternallyUsedValues.insert({Ex, Locs});
    ExternallyUsedValues.erase(Scalar);
    // Required to update internally referenced instructions.
    Scalar->replaceAllUsesWith(Ex);
    continue;
  }

  // Generate extracts for out-of-tree users.
  // Find the insertion point for the extractelement lane.
  if (auto *VecI = dyn_cast<Instruction>(Vec)) {
    if (PHINode *PH = dyn_cast<PHINode>(User)) {
      for (int i = 0, e = PH->getNumIncomingValues(); i != e; ++i) {
        if (PH->getIncomingValue(i) == Scalar) {
          Instruction *IncomingTerminator =
              PH->getIncomingBlock(i)->getTerminator();
          if (isa<CatchSwitchInst>(IncomingTerminator)) {
            Builder.SetInsertPoint(VecI->getParent(),
                                   std::next(VecI->getIterator()));
          } else {
            Builder.SetInsertPoint(PH->getIncomingBlock(i)->getTerminator());
          }
          Value *Ex = Builder.CreateExtractElement(Vec, Lane);
          Ex = extend(ScalarRoot, Ex, Scalar->getType());
          CSEBlocks.insert(PH->getIncomingBlock(i));
          PH->setOperand(i, Ex);
        }
      }
    } else {
      Builder.SetInsertPoint(cast<Instruction>(User));
      Value *Ex = Builder.CreateExtractElement(Vec, Lane);
      Ex = extend(ScalarRoot, Ex, Scalar->getType());
      CSEBlocks.insert(cast<Instruction>(User)->getParent());
      User->replaceUsesOfWith(Scalar, Ex);
    }
  } else {
    Builder.SetInsertPoint(&F->getEntryBlock().front());
    Value *Ex = Builder.CreateExtractElement(Vec, Lane);
    Ex = extend(ScalarRoot, Ex, Scalar->getType());
    CSEBlocks.insert(&F->getEntryBlock());
    User->replaceUsesOfWith(Scalar, Ex);
  }

  LLVM_DEBUG(dbgs() << "SLP: Replaced:" << *User << ".\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Replaced:" << *User <<
 ".\n"; } } while (false);
}

// For each vectorized value:
for (auto &TEPtr : VectorizableTree) {
  TreeEntry *Entry = TEPtr.get();

  // No need to handle users of gathered values.
  if (Entry->State == TreeEntry::NeedToGather)
    continue;

  assert(Entry->VectorizedValue && "Can't find vectorizable value")((Entry->VectorizedValue && "Can't find vectorizable value"
) ? static_cast<void> (0) : __assert_fail ("Entry->VectorizedValue && \"Can't find vectorizable value\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5106, __PRETTY_FUNCTION__));

  // For each lane:
  for (int Lane = 0, LE = Entry->Scalars.size(); Lane != LE; ++Lane) {
    Value *Scalar = Entry->Scalars[Lane];

5112#ifndef NDEBUG
    Type *Ty = Scalar->getType();
    if (!Ty->isVoidTy()) {
      for (User *U : Scalar->users()) {
        LLVM_DEBUG(dbgs() << "SLP: \tvalidating user:" << *U << ".\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: \tvalidating user:" <<
 *U << ".\n"; } } while (false);

        // It is legal to delete users in the ignorelist.
        assert((getTreeEntry(U) || is_contained(UserIgnoreList, U)) &&(((getTreeEntry(U) || is_contained(UserIgnoreList, U)) &&
 "Deleting out-of-tree value") ? static_cast<void> (0) :
 __assert_fail ("(getTreeEntry(U) || is_contained(UserIgnoreList, U)) && \"Deleting out-of-tree value\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5120, __PRETTY_FUNCTION__))
               "Deleting out-of-tree value")(((getTreeEntry(U) || is_contained(UserIgnoreList, U)) &&
 "Deleting out-of-tree value") ? static_cast<void> (0) :
 __assert_fail ("(getTreeEntry(U) || is_contained(UserIgnoreList, U)) && \"Deleting out-of-tree value\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5120, __PRETTY_FUNCTION__));
      }
    }
5123#endif
    LLVM_DEBUG(dbgs() << "SLP: \tErasing scalar:" << *Scalar << ".\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: \tErasing scalar:" << *
Scalar << ".\n"; } } while (false);
    eraseInstruction(cast<Instruction>(Scalar));
  }
}

Builder.ClearInsertionPoint();
InstrElementSize.clear();

return VectorizableTree[0]->VectorizedValue;
5133}

5135void BoUpSLP::optimizeGatherSequence() {
LLVM_DEBUG(dbgs() << "SLP: Optimizing " << GatherSeq.size()do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Optimizing " << GatherSeq
.size() << " gather sequences instructions.\n"; } } while
 (false)
                  << " gather sequences instructions.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Optimizing " << GatherSeq
.size() << " gather sequences instructions.\n"; } } while
 (false);
// LICM InsertElementInst sequences.
for (Instruction *I : GatherSeq) {
  if (isDeleted(I))
    continue;

  // Check if this block is inside a loop.
  Loop *L = LI->getLoopFor(I->getParent());
  if (!L)
    continue;

  // Check if it has a preheader.
  BasicBlock *PreHeader = L->getLoopPreheader();
  if (!PreHeader)
    continue;

  // If the vector or the element that we insert into it are
  // instructions that are defined in this basic block then we can't
  // hoist this instruction.
  auto *Op0 = dyn_cast<Instruction>(I->getOperand(0));
  auto *Op1 = dyn_cast<Instruction>(I->getOperand(1));
  if (Op0 && L->contains(Op0))
    continue;
  if (Op1 && L->contains(Op1))
    continue;

  // We can hoist this instruction. Move it to the pre-header.
  I->moveBefore(PreHeader->getTerminator());
}

// Make a list of all reachable blocks in our CSE queue.
SmallVector<const DomTreeNode *, 8> CSEWorkList;
CSEWorkList.reserve(CSEBlocks.size());
for (BasicBlock *BB : CSEBlocks)
  if (DomTreeNode *N = DT->getNode(BB)) {
    assert(DT->isReachableFromEntry(N))((DT->isReachableFromEntry(N)) ? static_cast<void> (
0) : __assert_fail ("DT->isReachableFromEntry(N)", "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5172, __PRETTY_FUNCTION__));
    CSEWorkList.push_back(N);
  }

// Sort blocks by domination. This ensures we visit a block after all blocks
// dominating it are visited.
llvm::stable_sort(CSEWorkList,
                  [this](const DomTreeNode *A, const DomTreeNode *B) {
                    return DT->properlyDominates(A, B);
                  });

// Perform O(N^2) search over the gather sequences and merge identical
// instructions. TODO: We can further optimize this scan if we split the
// instructions into different buckets based on the insert lane.
SmallVector<Instruction *, 16> Visited;
for (auto I = CSEWorkList.begin(), E = CSEWorkList.end(); I != E; ++I) {
  assert(*I &&((*I && (I == CSEWorkList.begin() || !DT->dominates
(*I, *std::prev(I))) && "Worklist not sorted properly!"
) ? static_cast<void> (0) : __assert_fail ("*I && (I == CSEWorkList.begin() || !DT->dominates(*I, *std::prev(I))) && \"Worklist not sorted properly!\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5190, __PRETTY_FUNCTION__))
         (I == CSEWorkList.begin() || !DT->dominates(*I, *std::prev(I))) &&((*I && (I == CSEWorkList.begin() || !DT->dominates
(*I, *std::prev(I))) && "Worklist not sorted properly!"
) ? static_cast<void> (0) : __assert_fail ("*I && (I == CSEWorkList.begin() || !DT->dominates(*I, *std::prev(I))) && \"Worklist not sorted properly!\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5190, __PRETTY_FUNCTION__))
         "Worklist not sorted properly!")((*I && (I == CSEWorkList.begin() || !DT->dominates
(*I, *std::prev(I))) && "Worklist not sorted properly!"
) ? static_cast<void> (0) : __assert_fail ("*I && (I == CSEWorkList.begin() || !DT->dominates(*I, *std::prev(I))) && \"Worklist not sorted properly!\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5190, __PRETTY_FUNCTION__));
  BasicBlock *BB = (*I)->getBlock();
  // For all instructions in blocks containing gather sequences:
  for (BasicBlock::iterator it = BB->begin(), e = BB->end(); it != e;) {
    Instruction *In = &*it++;
    if (isDeleted(In))
      continue;
    if (!isa<InsertElementInst>(In) && !isa<ExtractElementInst>(In))
      continue;

    // Check if we can replace this instruction with any of the
    // visited instructions.
    for (Instruction *v : Visited) {
      if (In->isIdenticalTo(v) &&
          DT->dominates(v->getParent(), In->getParent())) {
        In->replaceAllUsesWith(v);
        eraseInstruction(In);
        In = nullptr;
        break;
      }
    }
    if (In) {
      assert(!is_contained(Visited, In))((!is_contained(Visited, In)) ? static_cast<void> (0) :
 __assert_fail ("!is_contained(Visited, In)", "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5212, __PRETTY_FUNCTION__));
      Visited.push_back(In);
    }
  }
}
CSEBlocks.clear();
GatherSeq.clear();
5219}

5221// Groups the instructions to a bundle (which is then a single scheduling entity)
5222// and schedules instructions until the bundle gets ready.
5223Optional<BoUpSLP::ScheduleData *>
5224BoUpSLP::BlockScheduling::tryScheduleBundle(ArrayRef<Value *> VL, BoUpSLP *SLP,
                                          const InstructionsState &S) {
if (isa<PHINode>(S.OpValue))
  return nullptr;

// Initialize the instruction bundle.
Instruction *OldScheduleEnd = ScheduleEnd;
ScheduleData *PrevInBundle = nullptr;
ScheduleData *Bundle = nullptr;
bool ReSchedule = false;
LLVM_DEBUG(dbgs() << "SLP:  bundle: " << *S.OpValue << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP:  bundle: " << *S.OpValue
 << "\n"; } } while (false);

auto &&TryScheduleBundle = [this, OldScheduleEnd, SLP](bool ReSchedule,
                                                       ScheduleData *Bundle) {
  // The scheduling region got new instructions at the lower end (or it is a
  // new region for the first bundle). This makes it necessary to
  // recalculate all dependencies.
  // It is seldom that this needs to be done a second time after adding the
  // initial bundle to the region.
  if (ScheduleEnd != OldScheduleEnd) {
    for (auto *I = ScheduleStart; I != ScheduleEnd; I = I->getNextNode())
      doForAllOpcodes(I, [](ScheduleData *SD) { SD->clearDependencies(); });
    ReSchedule = true;
  }
  if (ReSchedule) {
    resetSchedule();
    initialFillReadyList(ReadyInsts);
  }
  if (Bundle) {
    LLVM_DEBUG(dbgs() << "SLP: try schedule bundle " << *Bundledo { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: try schedule bundle " <<
 *Bundle << " in block " << BB->getName() <<
 "\n"; } } while (false)
                      << " in block " << BB->getName() << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: try schedule bundle " <<
 *Bundle << " in block " << BB->getName() <<
 "\n"; } } while (false);
    calculateDependencies(Bundle, /*InsertInReadyList=*/true, SLP);
  }

  // Now try to schedule the new bundle or (if no bundle) just calculate
  // dependencies. As soon as the bundle is "ready" it means that there are no
  // cyclic dependencies and we can schedule it. Note that's important that we
  // don't "schedule" the bundle yet (see cancelScheduling).
  while (((!Bundle && ReSchedule) || (Bundle && !Bundle->isReady())) &&
         !ReadyInsts.empty()) {
    ScheduleData *Picked = ReadyInsts.pop_back_val();
    if (Picked->isSchedulingEntity() && Picked->isReady())
      schedule(Picked, ReadyInsts);
  }
};

// Make sure that the scheduling region contains all
// instructions of the bundle.
for (Value *V : VL) {
  if (!extendSchedulingRegion(V, S)) {
    // If the scheduling region got new instructions at the lower end (or it
    // is a new region for the first bundle). This makes it necessary to
    // recalculate all dependencies.
    // Otherwise the compiler may crash trying to incorrectly calculate
    // dependencies and emit instruction in the wrong order at the actual
    // scheduling.
    TryScheduleBundle(/*ReSchedule=*/false, nullptr);
    return None;
  }
}

for (Value *V : VL) {
  ScheduleData *BundleMember = getScheduleData(V);
  assert(BundleMember &&((BundleMember && "no ScheduleData for bundle member (maybe not in same basic block)"
) ? static_cast<void> (0) : __assert_fail ("BundleMember && \"no ScheduleData for bundle member (maybe not in same basic block)\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5288, __PRETTY_FUNCTION__))
         "no ScheduleData for bundle member (maybe not in same basic block)")((BundleMember && "no ScheduleData for bundle member (maybe not in same basic block)"
) ? static_cast<void> (0) : __assert_fail ("BundleMember && \"no ScheduleData for bundle member (maybe not in same basic block)\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5288, __PRETTY_FUNCTION__));
  if (BundleMember->IsScheduled) {
    // A bundle member was scheduled as single instruction before and now
    // needs to be scheduled as part of the bundle. We just get rid of the
    // existing schedule.
    LLVM_DEBUG(dbgs() << "SLP:  reset schedule because " << *BundleMemberdo { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP:  reset schedule because " <<
 *BundleMember << " was already scheduled\n"; } } while
 (false)
                      << " was already scheduled\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP:  reset schedule because " <<
 *BundleMember << " was already scheduled\n"; } } while
 (false);
    ReSchedule = true;
  }
  assert(BundleMember->isSchedulingEntity() &&((BundleMember->isSchedulingEntity() && "bundle member already part of other bundle"
) ? static_cast<void> (0) : __assert_fail ("BundleMember->isSchedulingEntity() && \"bundle member already part of other bundle\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5298, __PRETTY_FUNCTION__))
         "bundle member already part of other bundle")((BundleMember->isSchedulingEntity() && "bundle member already part of other bundle"
) ? static_cast<void> (0) : __assert_fail ("BundleMember->isSchedulingEntity() && \"bundle member already part of other bundle\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5298, __PRETTY_FUNCTION__));
  if (PrevInBundle) {
    PrevInBundle->NextInBundle = BundleMember;
  } else {
    Bundle = BundleMember;
  }
  BundleMember->UnscheduledDepsInBundle = 0;
  Bundle->UnscheduledDepsInBundle += BundleMember->UnscheduledDeps;

  // Group the instructions to a bundle.
  BundleMember->FirstInBundle = Bundle;
  PrevInBundle = BundleMember;
}
assert(Bundle && "Failed to find schedule bundle")((Bundle && "Failed to find schedule bundle") ? static_cast
<void> (0) : __assert_fail ("Bundle && \"Failed to find schedule bundle\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5311, __PRETTY_FUNCTION__));
TryScheduleBundle(ReSchedule, Bundle);
if (!Bundle->isReady()) {
  cancelScheduling(VL, S.OpValue);
  return None;
}
return Bundle;
5318}

5320void BoUpSLP::BlockScheduling::cancelScheduling(ArrayRef<Value *> VL,
                                              Value *OpValue) {
if (isa<PHINode>(OpValue))
  return;

ScheduleData *Bundle = getScheduleData(OpValue);
LLVM_DEBUG(dbgs() << "SLP:  cancel scheduling of " << *Bundle << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP:  cancel scheduling of " <<
 *Bundle << "\n"; } } while (false);
assert(!Bundle->IsScheduled &&((!Bundle->IsScheduled && "Can't cancel bundle which is already scheduled"
) ? static_cast<void> (0) : __assert_fail ("!Bundle->IsScheduled && \"Can't cancel bundle which is already scheduled\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5328, __PRETTY_FUNCTION__))
       "Can't cancel bundle which is already scheduled")((!Bundle->IsScheduled && "Can't cancel bundle which is already scheduled"
) ? static_cast<void> (0) : __assert_fail ("!Bundle->IsScheduled && \"Can't cancel bundle which is already scheduled\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5328, __PRETTY_FUNCTION__));
assert(Bundle->isSchedulingEntity() && Bundle->isPartOfBundle() &&((Bundle->isSchedulingEntity() && Bundle->isPartOfBundle
() && "tried to unbundle something which is not a bundle"
) ? static_cast<void> (0) : __assert_fail ("Bundle->isSchedulingEntity() && Bundle->isPartOfBundle() && \"tried to unbundle something which is not a bundle\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5330, __PRETTY_FUNCTION__))
       "tried to unbundle something which is not a bundle")((Bundle->isSchedulingEntity() && Bundle->isPartOfBundle
() && "tried to unbundle something which is not a bundle"
) ? static_cast<void> (0) : __assert_fail ("Bundle->isSchedulingEntity() && Bundle->isPartOfBundle() && \"tried to unbundle something which is not a bundle\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5330, __PRETTY_FUNCTION__));

// Un-bundle: make single instructions out of the bundle.
ScheduleData *BundleMember = Bundle;
while (BundleMember) {
  assert(BundleMember->FirstInBundle == Bundle && "corrupt bundle links")((BundleMember->FirstInBundle == Bundle && "corrupt bundle links"
) ? static_cast<void> (0) : __assert_fail ("BundleMember->FirstInBundle == Bundle && \"corrupt bundle links\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5335, __PRETTY_FUNCTION__));
  BundleMember->FirstInBundle = BundleMember;
  ScheduleData *Next = BundleMember->NextInBundle;
  BundleMember->NextInBundle = nullptr;
  BundleMember->UnscheduledDepsInBundle = BundleMember->UnscheduledDeps;
  if (BundleMember->UnscheduledDepsInBundle == 0) {
    ReadyInsts.insert(BundleMember);
  }
  BundleMember = Next;
}
5345}

5347BoUpSLP::ScheduleData *BoUpSLP::BlockScheduling::allocateScheduleDataChunks() {
// Allocate a new ScheduleData for the instruction.
if (ChunkPos >= ChunkSize) {
  ScheduleDataChunks.push_back(std::make_unique<ScheduleData[]>(ChunkSize));
  ChunkPos = 0;
}
return &(ScheduleDataChunks.back()[ChunkPos++]);
5354}

5356bool BoUpSLP::BlockScheduling::extendSchedulingRegion(Value *V,
                                                    const InstructionsState &S) {
if (getScheduleData(V, isOneOf(S, V)))
  return true;
Instruction *I = dyn_cast<Instruction>(V);
assert(I && "bundle member must be an instruction")((I && "bundle member must be an instruction") ? static_cast
<void> (0) : __assert_fail ("I && \"bundle member must be an instruction\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5361, __PRETTY_FUNCTION__));
assert(!isa<PHINode>(I) && "phi nodes don't need to be scheduled")((!isa<PHINode>(I) && "phi nodes don't need to be scheduled"
) ? static_cast<void> (0) : __assert_fail ("!isa<PHINode>(I) && \"phi nodes don't need to be scheduled\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5362, __PRETTY_FUNCTION__));
auto &&CheckSheduleForI = [this, &S](Instruction *I) -> bool {
  ScheduleData *ISD = getScheduleData(I);
  if (!ISD)
    return false;
  assert(isInSchedulingRegion(ISD) &&((isInSchedulingRegion(ISD) && "ScheduleData not in scheduling region"
) ? static_cast<void> (0) : __assert_fail ("isInSchedulingRegion(ISD) && \"ScheduleData not in scheduling region\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5368, __PRETTY_FUNCTION__))
         "ScheduleData not in scheduling region")((isInSchedulingRegion(ISD) && "ScheduleData not in scheduling region"
) ? static_cast<void> (0) : __assert_fail ("isInSchedulingRegion(ISD) && \"ScheduleData not in scheduling region\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5368, __PRETTY_FUNCTION__));
  ScheduleData *SD = allocateScheduleDataChunks();
  SD->Inst = I;
  SD->init(SchedulingRegionID, S.OpValue);
  ExtraScheduleDataMap[I][S.OpValue] = SD;
  return true;
};
if (CheckSheduleForI(I))
  return true;
if (!ScheduleStart) {
  // It's the first instruction in the new region.
  initScheduleData(I, I->getNextNode(), nullptr, nullptr);
  ScheduleStart = I;
  ScheduleEnd = I->getNextNode();
  if (isOneOf(S, I) != I)
    CheckSheduleForI(I);
  assert(ScheduleEnd && "tried to vectorize a terminator?")((ScheduleEnd && "tried to vectorize a terminator?") ?
 static_cast<void> (0) : __assert_fail ("ScheduleEnd && \"tried to vectorize a terminator?\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5384, __PRETTY_FUNCTION__));
  LLVM_DEBUG(dbgs() << "SLP:  initialize schedule region to " << *I << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP:  initialize schedule region to "
 << *I << "\n"; } } while (false);
  return true;
}
// Search up and down at the same time, because we don't know if the new
// instruction is above or below the existing scheduling region.
BasicBlock::reverse_iterator UpIter =
    ++ScheduleStart->getIterator().getReverse();
BasicBlock::reverse_iterator UpperEnd = BB->rend();
BasicBlock::iterator DownIter = ScheduleEnd->getIterator();
BasicBlock::iterator LowerEnd = BB->end();
while (UpIter != UpperEnd && DownIter != LowerEnd && &*UpIter != I &&
       &*DownIter != I) {
  if (++ScheduleRegionSize > ScheduleRegionSizeLimit) {
    LLVM_DEBUG(dbgs() << "SLP:  exceeded schedule region size limit\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP:  exceeded schedule region size limit\n"
; } } while (false);
    return false;
  }

  ++UpIter;
  ++DownIter;
}
if (DownIter == LowerEnd || (UpIter != UpperEnd && &*UpIter == I)) {
  assert(I->getParent() == ScheduleStart->getParent() &&((I->getParent() == ScheduleStart->getParent() &&
 "Instruction is in wrong basic block.") ? static_cast<void
> (0) : __assert_fail ("I->getParent() == ScheduleStart->getParent() && \"Instruction is in wrong basic block.\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5407, __PRETTY_FUNCTION__))
         "Instruction is in wrong basic block.")((I->getParent() == ScheduleStart->getParent() &&
 "Instruction is in wrong basic block.") ? static_cast<void
> (0) : __assert_fail ("I->getParent() == ScheduleStart->getParent() && \"Instruction is in wrong basic block.\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5407, __PRETTY_FUNCTION__));
  initScheduleData(I, ScheduleStart, nullptr, FirstLoadStoreInRegion);
  ScheduleStart = I;
  if (isOneOf(S, I) != I)
    CheckSheduleForI(I);
  LLVM_DEBUG(dbgs() << "SLP:  extend schedule region start to " << *Ido { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP:  extend schedule region start to "
 << *I << "\n"; } } while (false)
                    << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP:  extend schedule region start to "
 << *I << "\n"; } } while (false);
  return true;
}
assert((UpIter == UpperEnd || (DownIter != LowerEnd && &*DownIter == I)) &&(((UpIter == UpperEnd || (DownIter != LowerEnd && &
*DownIter == I)) && "Expected to reach top of the basic block or instruction down the "
 "lower end.") ? static_cast<void> (0) : __assert_fail (
"(UpIter == UpperEnd || (DownIter != LowerEnd && &*DownIter == I)) && \"Expected to reach top of the basic block or instruction down the \" \"lower end.\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5418, __PRETTY_FUNCTION__))
       "Expected to reach top of the basic block or instruction down the "(((UpIter == UpperEnd || (DownIter != LowerEnd && &
*DownIter == I)) && "Expected to reach top of the basic block or instruction down the "
 "lower end.") ? static_cast<void> (0) : __assert_fail (
"(UpIter == UpperEnd || (DownIter != LowerEnd && &*DownIter == I)) && \"Expected to reach top of the basic block or instruction down the \" \"lower end.\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5418, __PRETTY_FUNCTION__))
       "lower end.")(((UpIter == UpperEnd || (DownIter != LowerEnd && &
*DownIter == I)) && "Expected to reach top of the basic block or instruction down the "
 "lower end.") ? static_cast<void> (0) : __assert_fail (
"(UpIter == UpperEnd || (DownIter != LowerEnd && &*DownIter == I)) && \"Expected to reach top of the basic block or instruction down the \" \"lower end.\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5418, __PRETTY_FUNCTION__));
assert(I->getParent() == ScheduleEnd->getParent() &&((I->getParent() == ScheduleEnd->getParent() &&
 "Instruction is in wrong basic block.") ? static_cast<void
> (0) : __assert_fail ("I->getParent() == ScheduleEnd->getParent() && \"Instruction is in wrong basic block.\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5420, __PRETTY_FUNCTION__))
       "Instruction is in wrong basic block.")((I->getParent() == ScheduleEnd->getParent() &&
 "Instruction is in wrong basic block.") ? static_cast<void
> (0) : __assert_fail ("I->getParent() == ScheduleEnd->getParent() && \"Instruction is in wrong basic block.\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5420, __PRETTY_FUNCTION__));
initScheduleData(ScheduleEnd, I->getNextNode(), LastLoadStoreInRegion,
                 nullptr);
ScheduleEnd = I->getNextNode();
if (isOneOf(S, I) != I)
  CheckSheduleForI(I);
assert(ScheduleEnd && "tried to vectorize a terminator?")((ScheduleEnd && "tried to vectorize a terminator?") ?
 static_cast<void> (0) : __assert_fail ("ScheduleEnd && \"tried to vectorize a terminator?\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5426, __PRETTY_FUNCTION__));
LLVM_DEBUG(dbgs() << "SLP:  extend schedule region end to " << *I << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP:  extend schedule region end to "
 << *I << "\n"; } } while (false);
return true;
5429}

5431void BoUpSLP::BlockScheduling::initScheduleData(Instruction *FromI,
                                              Instruction *ToI,
                                              ScheduleData *PrevLoadStore,
                                              ScheduleData *NextLoadStore) {
ScheduleData *CurrentLoadStore = PrevLoadStore;
for (Instruction *I = FromI; I != ToI; I = I->getNextNode()) {
  ScheduleData *SD = ScheduleDataMap[I];
  if (!SD) {
    SD = allocateScheduleDataChunks();
    ScheduleDataMap[I] = SD;
    SD->Inst = I;
  }
  assert(!isInSchedulingRegion(SD) &&((!isInSchedulingRegion(SD) && "new ScheduleData already in scheduling region"
) ? static_cast<void> (0) : __assert_fail ("!isInSchedulingRegion(SD) && \"new ScheduleData already in scheduling region\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5444, __PRETTY_FUNCTION__))
         "new ScheduleData already in scheduling region")((!isInSchedulingRegion(SD) && "new ScheduleData already in scheduling region"
) ? static_cast<void> (0) : __assert_fail ("!isInSchedulingRegion(SD) && \"new ScheduleData already in scheduling region\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5444, __PRETTY_FUNCTION__));
  SD->init(SchedulingRegionID, I);

  if (I->mayReadOrWriteMemory() &&
      (!isa<IntrinsicInst>(I) ||
       (cast<IntrinsicInst>(I)->getIntrinsicID() != Intrinsic::sideeffect &&
        cast<IntrinsicInst>(I)->getIntrinsicID() !=
            Intrinsic::pseudoprobe))) {
    // Update the linked list of memory accessing instructions.
    if (CurrentLoadStore) {
      CurrentLoadStore->NextLoadStore = SD;
    } else {
      FirstLoadStoreInRegion = SD;
    }
    CurrentLoadStore = SD;
  }
}
if (NextLoadStore) {
  if (CurrentLoadStore)
    CurrentLoadStore->NextLoadStore = NextLoadStore;
} else {
  LastLoadStoreInRegion = CurrentLoadStore;
}
5467}

5469void BoUpSLP::BlockScheduling::calculateDependencies(ScheduleData *SD,
                                                   bool InsertInReadyList,
                                                   BoUpSLP *SLP) {
assert(SD->isSchedulingEntity())((SD->isSchedulingEntity()) ? static_cast<void> (0) :
 __assert_fail ("SD->isSchedulingEntity()", "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5472, __PRETTY_FUNCTION__));

SmallVector<ScheduleData *, 10> WorkList;
WorkList.push_back(SD);

while (!WorkList.empty()) {
  ScheduleData *SD = WorkList.pop_back_val();

  ScheduleData *BundleMember = SD;
  while (BundleMember) {
    assert(isInSchedulingRegion(BundleMember))((isInSchedulingRegion(BundleMember)) ? static_cast<void>
 (0) : __assert_fail ("isInSchedulingRegion(BundleMember)", "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5482, __PRETTY_FUNCTION__));
    if (!BundleMember->hasValidDependencies()) {

      LLVM_DEBUG(dbgs() << "SLP:       update deps of " << *BundleMemberdo { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP:       update deps of " <<
 *BundleMember << "\n"; } } while (false)
                        << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP:       update deps of " <<
 *BundleMember << "\n"; } } while (false);
      BundleMember->Dependencies = 0;
      BundleMember->resetUnscheduledDeps();

      // Handle def-use chain dependencies.
      if (BundleMember->OpValue != BundleMember->Inst) {
        ScheduleData *UseSD = getScheduleData(BundleMember->Inst);
        if (UseSD && isInSchedulingRegion(UseSD->FirstInBundle)) {
          BundleMember->Dependencies++;
          ScheduleData *DestBundle = UseSD->FirstInBundle;
          if (!DestBundle->IsScheduled)
            BundleMember->incrementUnscheduledDeps(1);
          if (!DestBundle->hasValidDependencies())
            WorkList.push_back(DestBundle);
        }
      } else {
        for (User *U : BundleMember->Inst->users()) {
          if (isa<Instruction>(U)) {
            ScheduleData *UseSD = getScheduleData(U);
            if (UseSD && isInSchedulingRegion(UseSD->FirstInBundle)) {
              BundleMember->Dependencies++;
              ScheduleData *DestBundle = UseSD->FirstInBundle;
              if (!DestBundle->IsScheduled)
                BundleMember->incrementUnscheduledDeps(1);
              if (!DestBundle->hasValidDependencies())
                WorkList.push_back(DestBundle);
            }
          } else {
            // I'm not sure if this can ever happen. But we need to be safe.
            // This lets the instruction/bundle never be scheduled and
            // eventually disable vectorization.
            BundleMember->Dependencies++;
            BundleMember->incrementUnscheduledDeps(1);
          }
        }
      }

      // Handle the memory dependencies.
      ScheduleData *DepDest = BundleMember->NextLoadStore;
      if (DepDest) {
        Instruction *SrcInst = BundleMember->Inst;
        MemoryLocation SrcLoc = getLocation(SrcInst, SLP->AA);
        bool SrcMayWrite = BundleMember->Inst->mayWriteToMemory();
        unsigned numAliased = 0;
        unsigned DistToSrc = 1;

        while (DepDest) {
          assert(isInSchedulingRegion(DepDest))((isInSchedulingRegion(DepDest)) ? static_cast<void> (0
) : __assert_fail ("isInSchedulingRegion(DepDest)", "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5533, __PRETTY_FUNCTION__));

          // We have two limits to reduce the complexity:
          // 1) AliasedCheckLimit: It's a small limit to reduce calls to
          //    SLP->isAliased (which is the expensive part in this loop).
          // 2) MaxMemDepDistance: It's for very large blocks and it aborts
          //    the whole loop (even if the loop is fast, it's quadratic).
          //    It's important for the loop break condition (see below) to
          //    check this limit even between two read-only instructions.
          if (DistToSrc >= MaxMemDepDistance ||
                  ((SrcMayWrite || DepDest->Inst->mayWriteToMemory()) &&
                   (numAliased >= AliasedCheckLimit ||
                    SLP->isAliased(SrcLoc, SrcInst, DepDest->Inst)))) {

            // We increment the counter only if the locations are aliased
            // (instead of counting all alias checks). This gives a better
            // balance between reduced runtime and accurate dependencies.
            numAliased++;

            DepDest->MemoryDependencies.push_back(BundleMember);
            BundleMember->Dependencies++;
            ScheduleData *DestBundle = DepDest->FirstInBundle;
            if (!DestBundle->IsScheduled) {
              BundleMember->incrementUnscheduledDeps(1);
            }
            if (!DestBundle->hasValidDependencies()) {
              WorkList.push_back(DestBundle);
            }
          }
          DepDest = DepDest->NextLoadStore;

          // Example, explaining the loop break condition: Let's assume our
          // starting instruction is i0 and MaxMemDepDistance = 3.
          //
          //                      +--------v--v--v
          //             i0,i1,i2,i3,i4,i5,i6,i7,i8
          //             +--------^--^--^
          //
          // MaxMemDepDistance let us stop alias-checking at i3 and we add
          // dependencies from i0 to i3,i4,.. (even if they are not aliased).
          // Previously we already added dependencies from i3 to i6,i7,i8
          // (because of MaxMemDepDistance). As we added a dependency from
          // i0 to i3, we have transitive dependencies from i0 to i6,i7,i8
          // and we can abort this loop at i6.
          if (DistToSrc >= 2 * MaxMemDepDistance)
            break;
          DistToSrc++;
        }
      }
    }
    BundleMember = BundleMember->NextInBundle;
  }
  if (InsertInReadyList && SD->isReady()) {
    ReadyInsts.push_back(SD);
    LLVM_DEBUG(dbgs() << "SLP:     gets ready on update: " << *SD->Instdo { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP:     gets ready on update: " <<
 *SD->Inst << "\n"; } } while (false)
                      << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP:     gets ready on update: " <<
 *SD->Inst << "\n"; } } while (false);
  }
}
5591}

5593void BoUpSLP::BlockScheduling::resetSchedule() {
assert(ScheduleStart &&((ScheduleStart && "tried to reset schedule on block which has not been scheduled"
) ? static_cast<void> (0) : __assert_fail ("ScheduleStart && \"tried to reset schedule on block which has not been scheduled\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5595, __PRETTY_FUNCTION__))
       "tried to reset schedule on block which has not been scheduled")((ScheduleStart && "tried to reset schedule on block which has not been scheduled"
) ? static_cast<void> (0) : __assert_fail ("ScheduleStart && \"tried to reset schedule on block which has not been scheduled\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5595, __PRETTY_FUNCTION__));
for (Instruction *I = ScheduleStart; I != ScheduleEnd; I = I->getNextNode()) {
  doForAllOpcodes(I, [&](ScheduleData *SD) {
    assert(isInSchedulingRegion(SD) &&((isInSchedulingRegion(SD) && "ScheduleData not in scheduling region"
) ? static_cast<void> (0) : __assert_fail ("isInSchedulingRegion(SD) && \"ScheduleData not in scheduling region\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5599, __PRETTY_FUNCTION__))
           "ScheduleData not in scheduling region")((isInSchedulingRegion(SD) && "ScheduleData not in scheduling region"
) ? static_cast<void> (0) : __assert_fail ("isInSchedulingRegion(SD) && \"ScheduleData not in scheduling region\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5599, __PRETTY_FUNCTION__));
    SD->IsScheduled = false;
    SD->resetUnscheduledDeps();
  });
}
ReadyInsts.clear();
5605}

5607void BoUpSLP::scheduleBlock(BlockScheduling *BS) {
if (!BS->ScheduleStart)
  return;

LLVM_DEBUG(dbgs() << "SLP: schedule block " << BS->BB->getName() << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: schedule block " << BS
->BB->getName() << "\n"; } } while (false);

BS->resetSchedule();

// For the real scheduling we use a more sophisticated ready-list: it is
// sorted by the original instruction location. This lets the final schedule
// be as  close as possible to the original instruction order.
struct ScheduleDataCompare {
  bool operator()(ScheduleData *SD1, ScheduleData *SD2) const {
    return SD2->SchedulingPriority < SD1->SchedulingPriority;
  }
};
std::set<ScheduleData *, ScheduleDataCompare> ReadyInsts;

// Ensure that all dependency data is updated and fill the ready-list with
// initial instructions.
int Idx = 0;
int NumToSchedule = 0;
for (auto *I = BS->ScheduleStart; I != BS->ScheduleEnd;
     I = I->getNextNode()) {
  BS->doForAllOpcodes(I, [this, &Idx, &NumToSchedule, BS](ScheduleData *SD) {
    assert(SD->isPartOfBundle() ==((SD->isPartOfBundle() == (getTreeEntry(SD->Inst) != nullptr
) && "scheduler and vectorizer bundle mismatch") ? static_cast
<void> (0) : __assert_fail ("SD->isPartOfBundle() == (getTreeEntry(SD->Inst) != nullptr) && \"scheduler and vectorizer bundle mismatch\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5634, __PRETTY_FUNCTION__))
               (getTreeEntry(SD->Inst) != nullptr) &&((SD->isPartOfBundle() == (getTreeEntry(SD->Inst) != nullptr
) && "scheduler and vectorizer bundle mismatch") ? static_cast
<void> (0) : __assert_fail ("SD->isPartOfBundle() == (getTreeEntry(SD->Inst) != nullptr) && \"scheduler and vectorizer bundle mismatch\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5634, __PRETTY_FUNCTION__))
           "scheduler and vectorizer bundle mismatch")((SD->isPartOfBundle() == (getTreeEntry(SD->Inst) != nullptr
) && "scheduler and vectorizer bundle mismatch") ? static_cast
<void> (0) : __assert_fail ("SD->isPartOfBundle() == (getTreeEntry(SD->Inst) != nullptr) && \"scheduler and vectorizer bundle mismatch\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5634, __PRETTY_FUNCTION__));
    SD->FirstInBundle->SchedulingPriority = Idx++;
    if (SD->isSchedulingEntity()) {
      BS->calculateDependencies(SD, false, this);
      NumToSchedule++;
    }
  });
}
BS->initialFillReadyList(ReadyInsts);

Instruction *LastScheduledInst = BS->ScheduleEnd;

// Do the "real" scheduling.
while (!ReadyInsts.empty()) {
  ScheduleData *picked = *ReadyInsts.begin();
  ReadyInsts.erase(ReadyInsts.begin());

  // Move the scheduled instruction(s) to their dedicated places, if not
  // there yet.
  ScheduleData *BundleMember = picked;
  while (BundleMember) {
    Instruction *pickedInst = BundleMember->Inst;
    if (LastScheduledInst->getNextNode() != pickedInst) {
      BS->BB->getInstList().remove(pickedInst);
      BS->BB->getInstList().insert(LastScheduledInst->getIterator(),
                                   pickedInst);
    }
    LastScheduledInst = pickedInst;
    BundleMember = BundleMember->NextInBundle;
  }

  BS->schedule(picked, ReadyInsts);
  NumToSchedule--;
}
assert(NumToSchedule == 0 && "could not schedule all instructions")((NumToSchedule == 0 && "could not schedule all instructions"
) ? static_cast<void> (0) : __assert_fail ("NumToSchedule == 0 && \"could not schedule all instructions\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5668, __PRETTY_FUNCTION__));

// Avoid duplicate scheduling of the block.
BS->ScheduleStart = nullptr;
5672}

5674unsigned BoUpSLP::getVectorElementSize(Value *V) {
// If V is a store, just return the width of the stored value (or value
// truncated just before storing) without traversing the expression tree.
// This is the common case.
if (auto *Store = dyn_cast<StoreInst>(V)) {
  if (auto *Trunc = dyn_cast<TruncInst>(Store->getValueOperand()))
    return DL->getTypeSizeInBits(Trunc->getSrcTy());
  return DL->getTypeSizeInBits(Store->getValueOperand()->getType());
}

auto E = InstrElementSize.find(V);
if (E != InstrElementSize.end())
  return E->second;

// If V is not a store, we can traverse the expression tree to find loads
// that feed it. The type of the loaded value may indicate a more suitable
// width than V's type. We want to base the vector element size on the width
// of memory operations where possible.
SmallVector<std::pair<Instruction *, BasicBlock *>, 16> Worklist;
SmallPtrSet<Instruction *, 16> Visited;
if (auto *I = dyn_cast<Instruction>(V)) {
  Worklist.emplace_back(I, I->getParent());
  Visited.insert(I);
}

// Traverse the expression tree in bottom-up order looking for loads. If we
// encounter an instruction we don't yet handle, we give up.
auto Width = 0u;
while (!Worklist.empty()) {
  Instruction *I;
  BasicBlock *Parent;
  std::tie(I, Parent) = Worklist.pop_back_val();

  // We should only be looking at scalar instructions here. If the current
  // instruction has a vector type, skip.
  auto *Ty = I->getType();
  if (isa<VectorType>(Ty))
    continue;

  // If the current instruction is a load, update MaxWidth to reflect the
  // width of the loaded value.
  if (isa<LoadInst>(I) || isa<ExtractElementInst>(I) ||
      isa<ExtractValueInst>(I))
    Width = std::max<unsigned>(Width, DL->getTypeSizeInBits(Ty));

  // Otherwise, we need to visit the operands of the instruction. We only
  // handle the interesting cases from buildTree here. If an operand is an
  // instruction we haven't yet visited and from the same basic block as the
  // user or the use is a PHI node, we add it to the worklist.
  else if (isa<PHINode>(I) || isa<CastInst>(I) || isa<GetElementPtrInst>(I) ||
           isa<CmpInst>(I) || isa<SelectInst>(I) || isa<BinaryOperator>(I) ||
           isa<UnaryOperator>(I)) {
    for (Use &U : I->operands())
      if (auto *J = dyn_cast<Instruction>(U.get()))
        if (Visited.insert(J).second &&
            (isa<PHINode>(I) || J->getParent() == Parent))
          Worklist.emplace_back(J, J->getParent());
  } else {
    break;
  }
}

// If we didn't encounter a memory access in the expression tree, or if we
// gave up for some reason, just return the width of V. Otherwise, return the
// maximum width we found.
if (!Width) {
  if (auto *CI = dyn_cast<CmpInst>(V))
    V = CI->getOperand(0);
  Width = DL->getTypeSizeInBits(V->getType());
}

for (Instruction *I : Visited)
  InstrElementSize[I] = Width;

return Width;
5749}

5751// Determine if a value V in a vectorizable expression Expr can be demoted to a
5752// smaller type with a truncation. We collect the values that will be demoted
5753// in ToDemote and additional roots that require investigating in Roots.
5754static bool collectValuesToDemote(Value *V, SmallPtrSetImpl<Value *> &Expr,
                                SmallVectorImpl<Value *> &ToDemote,
                                SmallVectorImpl<Value *> &Roots) {
// We can always demote constants.
if (isa<Constant>(V)) {
  ToDemote.push_back(V);
  return true;
}

// If the value is not an instruction in the expression with only one use, it
// cannot be demoted.
auto *I = dyn_cast<Instruction>(V);
if (!I || !I->hasOneUse() || !Expr.count(I))
  return false;

switch (I->getOpcode()) {

// We can always demote truncations and extensions. Since truncations can
// seed additional demotion, we save the truncated value.
case Instruction::Trunc:
  Roots.push_back(I->getOperand(0));
  break;
case Instruction::ZExt:
case Instruction::SExt:
  break;

// We can demote certain binary operations if we can demote both of their
// operands.
case Instruction::Add:
case Instruction::Sub:
case Instruction::Mul:
case Instruction::And:
case Instruction::Or:
case Instruction::Xor:
  if (!collectValuesToDemote(I->getOperand(0), Expr, ToDemote, Roots) ||
      !collectValuesToDemote(I->getOperand(1), Expr, ToDemote, Roots))
    return false;
  break;

// We can demote selects if we can demote their true and false values.
case Instruction::Select: {
  SelectInst *SI = cast<SelectInst>(I);
  if (!collectValuesToDemote(SI->getTrueValue(), Expr, ToDemote, Roots) ||
      !collectValuesToDemote(SI->getFalseValue(), Expr, ToDemote, Roots))
    return false;
  break;
}

// We can demote phis if we can demote all their incoming operands. Note that
// we don't need to worry about cycles since we ensure single use above.
case Instruction::PHI: {
  PHINode *PN = cast<PHINode>(I);
  for (Value *IncValue : PN->incoming_values())
    if (!collectValuesToDemote(IncValue, Expr, ToDemote, Roots))
      return false;
  break;
}

// Otherwise, conservatively give up.
default:
  return false;
}

// Record the value that we can demote.
ToDemote.push_back(V);
return true;
5820}

5822void BoUpSLP::computeMinimumValueSizes() {
// If there are no external uses, the expression tree must be rooted by a
// store. We can't demote in-memory values, so there is nothing to do here.
if (ExternalUses.empty())
  return;

// We only attempt to truncate integer expressions.
auto &TreeRoot = VectorizableTree[0]->Scalars;
auto *TreeRootIT = dyn_cast<IntegerType>(TreeRoot[0]->getType());
if (!TreeRootIT)
  return;

// If the expression is not rooted by a store, these roots should have
// external uses. We will rely on InstCombine to rewrite the expression in
// the narrower type. However, InstCombine only rewrites single-use values.
// This means that if a tree entry other than a root is used externally, it
// must have multiple uses and InstCombine will not rewrite it. The code
// below ensures that only the roots are used externally.
SmallPtrSet<Value *, 32> Expr(TreeRoot.begin(), TreeRoot.end());
for (auto &EU : ExternalUses)
  if (!Expr.erase(EU.Scalar))
    return;
if (!Expr.empty())
  return;

// Collect the scalar values of the vectorizable expression. We will use this
// context to determine which values can be demoted. If we see a truncation,
// we mark it as seeding another demotion.
for (auto &EntryPtr : VectorizableTree)
  Expr.insert(EntryPtr->Scalars.begin(), EntryPtr->Scalars.end());

// Ensure the roots of the vectorizable tree don't form a cycle. They must
// have a single external user that is not in the vectorizable tree.
for (auto *Root : TreeRoot)
  if (!Root->hasOneUse() || Expr.count(*Root->user_begin()))
    return;

// Conservatively determine if we can actually truncate the roots of the
// expression. Collect the values that can be demoted in ToDemote and
// additional roots that require investigating in Roots.
SmallVector<Value *, 32> ToDemote;
SmallVector<Value *, 4> Roots;
for (auto *Root : TreeRoot)
  if (!collectValuesToDemote(Root, Expr, ToDemote, Roots))
    return;

// The maximum bit width required to represent all the values that can be
// demoted without loss of precision. It would be safe to truncate the roots
// of the expression to this width.
auto MaxBitWidth = 8u;

// We first check if all the bits of the roots are demanded. If they're not,
// we can truncate the roots to this narrower type.
for (auto *Root : TreeRoot) {
  auto Mask = DB->getDemandedBits(cast<Instruction>(Root));
  MaxBitWidth = std::max<unsigned>(
      Mask.getBitWidth() - Mask.countLeadingZeros(), MaxBitWidth);
}

// True if the roots can be zero-extended back to their original type, rather
// than sign-extended. We know that if the leading bits are not demanded, we
// can safely zero-extend. So we initialize IsKnownPositive to True.
bool IsKnownPositive = true;

// If all the bits of the roots are demanded, we can try a little harder to
// compute a narrower type. This can happen, for example, if the roots are
// getelementptr indices. InstCombine promotes these indices to the pointer
// width. Thus, all their bits are technically demanded even though the
// address computation might be vectorized in a smaller type.
//
// We start by looking at each entry that can be demoted. We compute the
// maximum bit width required to store the scalar by using ValueTracking to
// compute the number of high-order bits we can truncate.
if (MaxBitWidth == DL->getTypeSizeInBits(TreeRoot[0]->getType()) &&
    llvm::all_of(TreeRoot, [](Value *R) {
      assert(R->hasOneUse() && "Root should have only one use!")((R->hasOneUse() && "Root should have only one use!"
) ? static_cast<void> (0) : __assert_fail ("R->hasOneUse() && \"Root should have only one use!\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 5897, __PRETTY_FUNCTION__));
      return isa<GetElementPtrInst>(R->user_back());
    })) {
  MaxBitWidth = 8u;

  // Determine if the sign bit of all the roots is known to be zero. If not,
  // IsKnownPositive is set to False.
  IsKnownPositive = llvm::all_of(TreeRoot, [&](Value *R) {
    KnownBits Known = computeKnownBits(R, *DL);
    return Known.isNonNegative();
  });

  // Determine the maximum number of bits required to store the scalar
  // values.
  for (auto *Scalar : ToDemote) {
    auto NumSignBits = ComputeNumSignBits(Scalar, *DL, 0, AC, nullptr, DT);
    auto NumTypeBits = DL->getTypeSizeInBits(Scalar->getType());
    MaxBitWidth = std::max<unsigned>(NumTypeBits - NumSignBits, MaxBitWidth);
  }

  // If we can't prove that the sign bit is zero, we must add one to the
  // maximum bit width to account for the unknown sign bit. This preserves
  // the existing sign bit so we can safely sign-extend the root back to the
  // original type. Otherwise, if we know the sign bit is zero, we will
  // zero-extend the root instead.
  //
  // FIXME: This is somewhat suboptimal, as there will be cases where adding
  //        one to the maximum bit width will yield a larger-than-necessary
  //        type. In general, we need to add an extra bit only if we can't
  //        prove that the upper bit of the original type is equal to the
  //        upper bit of the proposed smaller type. If these two bits are the
  //        same (either zero or one) we know that sign-extending from the
  //        smaller type will result in the same value. Here, since we can't
  //        yet prove this, we are just making the proposed smaller type
  //        larger to ensure correctness.
  if (!IsKnownPositive)
    ++MaxBitWidth;
}

// Round MaxBitWidth up to the next power-of-two.
if (!isPowerOf2_64(MaxBitWidth))
  MaxBitWidth = NextPowerOf2(MaxBitWidth);

// If the maximum bit width we compute is less than the with of the roots'
// type, we can proceed with the narrowing. Otherwise, do nothing.
if (MaxBitWidth >= TreeRootIT->getBitWidth())
  return;

// If we can truncate the root, we must collect additional values that might
// be demoted as a result. That is, those seeded by truncations we will
// modify.
while (!Roots.empty())
  collectValuesToDemote(Roots.pop_back_val(), Expr, ToDemote, Roots);

// Finally, map the values we can demote to the maximum bit with we computed.
for (auto *Scalar : ToDemote)
  MinBWs[Scalar] = std::make_pair(MaxBitWidth, !IsKnownPositive);
5954}

5956namespace {

5958/// The SLPVectorizer Pass.
5959struct SLPVectorizer : public FunctionPass {
SLPVectorizerPass Impl;

/// Pass identification, replacement for typeid
static char ID;

explicit SLPVectorizer() : FunctionPass(ID) {
  initializeSLPVectorizerPass(*PassRegistry::getPassRegistry());
}

bool doInitialization(Module &M) override {
  return false;
}

bool runOnFunction(Function &F) override {
  if (skipFunction(F))
    return false;

  auto *SE = &getAnalysis<ScalarEvolutionWrapperPass>().getSE();
  auto *TTI = &getAnalysis<TargetTransformInfoWrapperPass>().getTTI(F);
  auto *TLIP = getAnalysisIfAvailable<TargetLibraryInfoWrapperPass>();
  auto *TLI = TLIP ? &TLIP->getTLI(F) : nullptr;
  auto *AA = &getAnalysis<AAResultsWrapperPass>().getAAResults();
  auto *LI = &getAnalysis<LoopInfoWrapperPass>().getLoopInfo();
  auto *DT = &getAnalysis<DominatorTreeWrapperPass>().getDomTree();
  auto *AC = &getAnalysis<AssumptionCacheTracker>().getAssumptionCache(F);
  auto *DB = &getAnalysis<DemandedBitsWrapperPass>().getDemandedBits();
  auto *ORE = &getAnalysis<OptimizationRemarkEmitterWrapperPass>().getORE();

  return Impl.runImpl(F, SE, TTI, TLI, AA, LI, DT, AC, DB, ORE);
}

void getAnalysisUsage(AnalysisUsage &AU) const override {
  FunctionPass::getAnalysisUsage(AU);
  AU.addRequired<AssumptionCacheTracker>();
  AU.addRequired<ScalarEvolutionWrapperPass>();
  AU.addRequired<AAResultsWrapperPass>();
  AU.addRequired<TargetTransformInfoWrapperPass>();
  AU.addRequired<LoopInfoWrapperPass>();
  AU.addRequired<DominatorTreeWrapperPass>();
  AU.addRequired<DemandedBitsWrapperPass>();
  AU.addRequired<OptimizationRemarkEmitterWrapperPass>();
  AU.addRequired<InjectTLIMappingsLegacy>();
  AU.addPreserved<LoopInfoWrapperPass>();
  AU.addPreserved<DominatorTreeWrapperPass>();
  AU.addPreserved<AAResultsWrapperPass>();
  AU.addPreserved<GlobalsAAWrapperPass>();
  AU.setPreservesCFG();
}
6008};

6010} // end anonymous namespace

6012PreservedAnalyses SLPVectorizerPass::run(Function &F, FunctionAnalysisManager &AM) {
auto *SE = &AM.getResult<ScalarEvolutionAnalysis>(F);
auto *TTI = &AM.getResult<TargetIRAnalysis>(F);
auto *TLI = AM.getCachedResult<TargetLibraryAnalysis>(F);
auto *AA = &AM.getResult<AAManager>(F);
auto *LI = &AM.getResult<LoopAnalysis>(F);
auto *DT = &AM.getResult<DominatorTreeAnalysis>(F);
auto *AC = &AM.getResult<AssumptionAnalysis>(F);
auto *DB = &AM.getResult<DemandedBitsAnalysis>(F);
auto *ORE = &AM.getResult<OptimizationRemarkEmitterAnalysis>(F);

bool Changed = runImpl(F, SE, TTI, TLI, AA, LI, DT, AC, DB, ORE);
if (!Changed)
  return PreservedAnalyses::all();

PreservedAnalyses PA;
PA.preserveSet<CFGAnalyses>();
PA.preserve<AAManager>();
PA.preserve<GlobalsAA>();
return PA;
6032}

6034bool SLPVectorizerPass::runImpl(Function &F, ScalarEvolution *SE_,
                              TargetTransformInfo *TTI_,
                              TargetLibraryInfo *TLI_, AAResults *AA_,
                              LoopInfo *LI_, DominatorTree *DT_,
                              AssumptionCache *AC_, DemandedBits *DB_,
                              OptimizationRemarkEmitter *ORE_) {
if (!RunSLPVectorization)
  return false;
SE = SE_;
TTI = TTI_;
TLI = TLI_;
AA = AA_;
LI = LI_;
DT = DT_;
AC = AC_;
DB = DB_;
DL = &F.getParent()->getDataLayout();

Stores.clear();
GEPs.clear();
bool Changed = false;

// If the target claims to have no vector registers don't attempt
// vectorization.
if (!TTI->getNumberOfRegisters(TTI->getRegisterClassForType(true)))
  return false;

// Don't vectorize when the attribute NoImplicitFloat is used.
if (F.hasFnAttribute(Attribute::NoImplicitFloat))
  return false;

LLVM_DEBUG(dbgs() << "SLP: Analyzing blocks in " << F.getName() << ".\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Analyzing blocks in " <<
 F.getName() << ".\n"; } } while (false);

// Use the bottom up slp vectorizer to construct chains that start with
// store instructions.
BoUpSLP R(&F, SE, TTI, TLI, AA, LI, DT, AC, DB, DL, ORE_);

// A general note: the vectorizer must use BoUpSLP::eraseInstruction() to
// delete instructions.

// Scan the blocks in the function in post order.
for (auto BB : post_order(&F.getEntryBlock())) {
  collectSeedInstructions(BB);

  // Vectorize trees that end at stores.
  if (!Stores.empty()) {
    LLVM_DEBUG(dbgs() << "SLP: Found stores for " << Stores.size()do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Found stores for " << Stores
.size() << " underlying objects.\n"; } } while (false)
                      << " underlying objects.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Found stores for " << Stores
.size() << " underlying objects.\n"; } } while (false);
    Changed |= vectorizeStoreChains(R);
  }

  // Vectorize trees that end at reductions.
  Changed |= vectorizeChainsInBlock(BB, R);

  // Vectorize the index computations of getelementptr instructions. This
  // is primarily intended to catch gather-like idioms ending at
  // non-consecutive loads.
  if (!GEPs.empty()) {
    LLVM_DEBUG(dbgs() << "SLP: Found GEPs for " << GEPs.size()do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Found GEPs for " << GEPs
.size() << " underlying objects.\n"; } } while (false)
                      << " underlying objects.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Found GEPs for " << GEPs
.size() << " underlying objects.\n"; } } while (false);
    Changed |= vectorizeGEPIndices(BB, R);
  }
}

if (Changed) {
  R.optimizeGatherSequence();
  LLVM_DEBUG(dbgs() << "SLP: vectorized \"" << F.getName() << "\"\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: vectorized \"" << F.getName
() << "\"\n"; } } while (false);
}
return Changed;
6103}

6105bool SLPVectorizerPass::vectorizeStoreChain(ArrayRef<Value *> Chain, BoUpSLP &R,
                                          unsigned Idx) {
LLVM_DEBUG(dbgs() << "SLP: Analyzing a store chain of length " << Chain.size()do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Analyzing a store chain of length "
 << Chain.size() << "\n"; } } while (false)
                  << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Analyzing a store chain of length "
 << Chain.size() << "\n"; } } while (false);
const unsigned Sz = R.getVectorElementSize(Chain[0]);
const unsigned MinVF = R.getMinVecRegSize() / Sz;
unsigned VF = Chain.size();

if (!isPowerOf2_32(Sz) || !isPowerOf2_32(VF) || VF < 2 || VF < MinVF)
  return false;

LLVM_DEBUG(dbgs() << "SLP: Analyzing " << VF << " stores at offset " << Idxdo { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Analyzing " << VF <<
 " stores at offset " << Idx << "\n"; } } while (
false)
                  << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Analyzing " << VF <<
 " stores at offset " << Idx << "\n"; } } while (
false);

R.buildTree(Chain);
Optional<ArrayRef<unsigned>> Order = R.bestOrder();
// TODO: Handle orders of size less than number of elements in the vector.
if (Order && Order->size() == Chain.size()) {
  // TODO: reorder tree nodes without tree rebuilding.
  SmallVector<Value *, 4> ReorderedOps(Chain.rbegin(), Chain.rend());
  llvm::transform(*Order, ReorderedOps.begin(),
                  [Chain](const unsigned Idx) { return Chain[Idx]; });
  R.buildTree(ReorderedOps);
}
if (R.isTreeTinyAndNotFullyVectorizable())
  return false;
if (R.isLoadCombineCandidate())
  return false;

R.computeMinimumValueSizes();

InstructionCost Cost = R.getTreeCost();

LLVM_DEBUG(dbgs() << "SLP: Found cost = " << Cost << " for VF =" << VF << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Found cost = " << Cost
 << " for VF =" << VF << "\n"; } } while (false
);
if (Cost < -SLPCostThreshold) {
  LLVM_DEBUG(dbgs() << "SLP: Decided to vectorize cost = " << Cost << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Decided to vectorize cost = "
 << Cost << "\n"; } } while (false);

  using namespace ore;

  R.getORE()->emit(OptimizationRemark(SV_NAME"slp-vectorizer", "StoresVectorized",
                                      cast<StoreInst>(Chain[0]))
                   << "Stores SLP vectorized with cost " << NV("Cost", Cost)
                   << " and with tree size "
                   << NV("TreeSize", R.getTreeSize()));

  R.vectorizeTree();
  return true;
}

return false;
6155}

6157bool SLPVectorizerPass::vectorizeStores(ArrayRef<StoreInst *> Stores,
                                      BoUpSLP &R) {
// We may run into multiple chains that merge into a single chain. We mark the
// stores that we vectorized so that we don't visit the same store twice.
BoUpSLP::ValueSet VectorizedStores;
bool Changed = false;

int E = Stores.size();
SmallBitVector Tails(E, false);
int MaxIter = MaxStoreLookup.getValue();
SmallVector<std::pair<int, int>, 16> ConsecutiveChain(
    E, std::make_pair(E, INT_MAX2147483647));
SmallVector<SmallBitVector, 4> CheckedPairs(E, SmallBitVector(E, false));
int IterCnt;
auto &&FindConsecutiveAccess = [this, &Stores, &Tails, &IterCnt, MaxIter,
                                &CheckedPairs,
                                &ConsecutiveChain](int K, int Idx) {
  if (IterCnt >= MaxIter)
    return true;
  if (CheckedPairs[Idx].test(K))
    return ConsecutiveChain[K].second == 1 &&
           ConsecutiveChain[K].first == Idx;
  ++IterCnt;
  CheckedPairs[Idx].set(K);
  CheckedPairs[K].set(Idx);
  Optional<int> Diff = getPointersDiff(Stores[K]->getPointerOperand(),
                                       Stores[Idx]->getPointerOperand(), *DL,
                                       *SE, /*StrictCheck=*/true);
  if (!Diff || *Diff == 0)
    return false;
  int Val = *Diff;
  if (Val < 0) {
    if (ConsecutiveChain[Idx].second > -Val) {
      Tails.set(K);
      ConsecutiveChain[Idx] = std::make_pair(K, -Val);
    }
    return false;
  }
  if (ConsecutiveChain[K].second <= Val)
    return false;

  Tails.set(Idx);
  ConsecutiveChain[K] = std::make_pair(Idx, Val);
  return Val == 1;
};
// Do a quadratic search on all of the given stores in reverse order and find
// all of the pairs of stores that follow each other.
for (int Idx = E - 1; Idx >= 0; --Idx) {
  // If a store has multiple consecutive store candidates, search according
  // to the sequence: Idx-1, Idx+1, Idx-2, Idx+2, ...
  // This is because usually pairing with immediate succeeding or preceding
  // candidate create the best chance to find slp vectorization opportunity.
  const int MaxLookDepth = std::max(E - Idx, Idx + 1);
  IterCnt = 0;
  for (int Offset = 1, F = MaxLookDepth; Offset < F; ++Offset)
    if ((Idx >= Offset && FindConsecutiveAccess(Idx - Offset, Idx)) ||
        (Idx + Offset < E && FindConsecutiveAccess(Idx + Offset, Idx)))
      break;
}

// Tracks if we tried to vectorize stores starting from the given tail
// already.
SmallBitVector TriedTails(E, false);
// For stores that start but don't end a link in the chain:
for (int Cnt = E; Cnt > 0; --Cnt) {
  int I = Cnt - 1;
  if (ConsecutiveChain[I].first == E || Tails.test(I))
    continue;
  // We found a store instr that starts a chain. Now follow the chain and try
  // to vectorize it.
  BoUpSLP::ValueList Operands;
  // Collect the chain into a list.
  while (I != E && !VectorizedStores.count(Stores[I])) {
    Operands.push_back(Stores[I]);
    Tails.set(I);
    if (ConsecutiveChain[I].second != 1) {
      // Mark the new end in the chain and go back, if required. It might be
      // required if the original stores come in reversed order, for example.
      if (ConsecutiveChain[I].first != E &&
          Tails.test(ConsecutiveChain[I].first) && !TriedTails.test(I) &&
          !VectorizedStores.count(Stores[ConsecutiveChain[I].first])) {
        TriedTails.set(I);
        Tails.reset(ConsecutiveChain[I].first);
        if (Cnt < ConsecutiveChain[I].first + 2)
          Cnt = ConsecutiveChain[I].first + 2;
      }
      break;
    }
    // Move to the next value in the chain.
    I = ConsecutiveChain[I].first;
  }
  assert(!Operands.empty() && "Expected non-empty list of stores.")((!Operands.empty() && "Expected non-empty list of stores."
) ? static_cast<void> (0) : __assert_fail ("!Operands.empty() && \"Expected non-empty list of stores.\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 6248, __PRETTY_FUNCTION__));

  unsigned MaxVecRegSize = R.getMaxVecRegSize();
  unsigned EltSize = R.getVectorElementSize(Operands[0]);
  unsigned MaxElts = llvm::PowerOf2Floor(MaxVecRegSize / EltSize);

  unsigned MinVF = std::max(2U, R.getMinVecRegSize() / EltSize);
  unsigned MaxVF = std::min(R.getMaximumVF(EltSize, Instruction::Store),
                            MaxElts);

  // FIXME: Is division-by-2 the correct step? Should we assert that the
  // register size is a power-of-2?
  unsigned StartIdx = 0;
  for (unsigned Size = MaxVF; Size >= MinVF; Size /= 2) {
    for (unsigned Cnt = StartIdx, E = Operands.size(); Cnt + Size <= E;) {
      ArrayRef<Value *> Slice = makeArrayRef(Operands).slice(Cnt, Size);
      if (!VectorizedStores.count(Slice.front()) &&
          !VectorizedStores.count(Slice.back()) &&
          vectorizeStoreChain(Slice, R, Cnt)) {
        // Mark the vectorized stores so that we don't vectorize them again.
        VectorizedStores.insert(Slice.begin(), Slice.end());
        Changed = true;
        // If we vectorized initial block, no need to try to vectorize it
        // again.
        if (Cnt == StartIdx)
          StartIdx += Size;
        Cnt += Size;
        continue;
      }
      ++Cnt;
    }
    // Check if the whole array was vectorized already - exit.
    if (StartIdx >= Operands.size())
      break;
  }
}

return Changed;
6286}

6288void SLPVectorizerPass::collectSeedInstructions(BasicBlock *BB) {
// Initialize the collections. We will make a single pass over the block.
Stores.clear();
GEPs.clear();

// Visit the store and getelementptr instructions in BB and organize them in
// Stores and GEPs according to the underlying objects of their pointer
// operands.
for (Instruction &I : *BB) {
  // Ignore store instructions that are volatile or have a pointer operand
  // that doesn't point to a scalar type.
  if (auto *SI = dyn_cast<StoreInst>(&I)) {
    if (!SI->isSimple())
      continue;
    if (!isValidElementType(SI->getValueOperand()->getType()))
      continue;
    Stores[getUnderlyingObject(SI->getPointerOperand())].push_back(SI);
  }

  // Ignore getelementptr instructions that have more than one index, a
  // constant index, or a pointer operand that doesn't point to a scalar
  // type.
  else if (auto *GEP = dyn_cast<GetElementPtrInst>(&I)) {
    auto Idx = GEP->idx_begin()->get();
    if (GEP->getNumIndices() > 1 || isa<Constant>(Idx))
      continue;
    if (!isValidElementType(Idx->getType()))
      continue;
    if (GEP->getType()->isVectorTy())
      continue;
    GEPs[GEP->getPointerOperand()].push_back(GEP);
  }
}
6321}

6323bool SLPVectorizerPass::tryToVectorizePair(Value *A, Value *B, BoUpSLP &R) {
if (!A || !B)
  return false;
Value *VL[] = {A, B};
return tryToVectorizeList(VL, R, /*AllowReorder=*/true);
6328}

6330bool SLPVectorizerPass::tryToVectorizeList(ArrayRef<Value *> VL, BoUpSLP &R,
                                         bool AllowReorder,
                                         ArrayRef<Value *> InsertUses) {
if (VL.size() < 2)
  return false;

LLVM_DEBUG(dbgs() << "SLP: Trying to vectorize a list of length = "do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Trying to vectorize a list of length = "
 << VL.size() << ".\n"; } } while (false)
                  << VL.size() << ".\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Trying to vectorize a list of length = "
 << VL.size() << ".\n"; } } while (false);

// Check that all of the parts are instructions of the same type,
// we permit an alternate opcode via InstructionsState.
InstructionsState S = getSameOpcode(VL);
if (!S.getOpcode())
  return false;

Instruction *I0 = cast<Instruction>(S.OpValue);
// Make sure invalid types (including vector type) are rejected before
// determining vectorization factor for scalar instructions.
for (Value *V : VL) {
  Type *Ty = V->getType();
  if (!isValidElementType(Ty)) {
    // NOTE: the following will give user internal llvm type name, which may
    // not be useful.
    R.getORE()->emit([&]() {
      std::string type_str;
      llvm::raw_string_ostream rso(type_str);
      Ty->print(rso);
      return OptimizationRemarkMissed(SV_NAME"slp-vectorizer", "UnsupportedType", I0)
             << "Cannot SLP vectorize list: type "
             << rso.str() + " is unsupported by vectorizer";
    });
    return false;
  }
}

unsigned Sz = R.getVectorElementSize(I0);
unsigned MinVF = std::max(2U, R.getMinVecRegSize() / Sz);
unsigned MaxVF = std::max<unsigned>(PowerOf2Floor(VL.size()), MinVF);
MaxVF = std::min(R.getMaximumVF(Sz, S.getOpcode()), MaxVF);
if (MaxVF < 2) {
  R.getORE()->emit([&]() {
    return OptimizationRemarkMissed(SV_NAME"slp-vectorizer", "SmallVF", I0)
           << "Cannot SLP vectorize list: vectorization factor "
           << "less than 2 is not supported";
  });
  return false;
}

bool Changed = false;
bool CandidateFound = false;
InstructionCost MinCost = SLPCostThreshold.getValue();

bool CompensateUseCost =
    !InsertUses.empty() && llvm::all_of(InsertUses, [](const Value *V) {
      return V && isa<InsertElementInst>(V);
    });
assert((!CompensateUseCost || InsertUses.size() == VL.size()) &&(((!CompensateUseCost || InsertUses.size() == VL.size()) &&
 "Each scalar expected to have an associated InsertElement user."
) ? static_cast<void> (0) : __assert_fail ("(!CompensateUseCost || InsertUses.size() == VL.size()) && \"Each scalar expected to have an associated InsertElement user.\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 6387, __PRETTY_FUNCTION__))
       "Each scalar expected to have an associated InsertElement user.")(((!CompensateUseCost || InsertUses.size() == VL.size()) &&
 "Each scalar expected to have an associated InsertElement user."
) ? static_cast<void> (0) : __assert_fail ("(!CompensateUseCost || InsertUses.size() == VL.size()) && \"Each scalar expected to have an associated InsertElement user.\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 6387, __PRETTY_FUNCTION__));

unsigned NextInst = 0, MaxInst = VL.size();
for (unsigned VF = MaxVF; NextInst + 1 < MaxInst && VF >= MinVF; VF /= 2) {
  // No actual vectorization should happen, if number of parts is the same as
  // provided vectorization factor (i.e. the scalar type is used for vector
  // code during codegen).
  auto *VecTy = FixedVectorType::get(VL[0]->getType(), VF);
  if (TTI->getNumberOfParts(VecTy) == VF)
    continue;
  for (unsigned I = NextInst; I < MaxInst; ++I) {
    unsigned OpsWidth = 0;

    if (I + VF > MaxInst)
      OpsWidth = MaxInst - I;
    else
      OpsWidth = VF;

    if (!isPowerOf2_32(OpsWidth) || OpsWidth < 2)
      break;

    ArrayRef<Value *> Ops = VL.slice(I, OpsWidth);
    // Check that a previous iteration of this loop did not delete the Value.
    if (llvm::any_of(Ops, [&R](Value *V) {
          auto *I = dyn_cast<Instruction>(V);
          return I && R.isDeleted(I);
        }))
      continue;

    LLVM_DEBUG(dbgs() << "SLP: Analyzing " << OpsWidth << " operations "do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Analyzing " << OpsWidth
 << " operations " << "\n"; } } while (false)
                      << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Analyzing " << OpsWidth
 << " operations " << "\n"; } } while (false);

    R.buildTree(Ops);
    Optional<ArrayRef<unsigned>> Order = R.bestOrder();
    // TODO: check if we can allow reordering for more cases.
    if (AllowReorder && Order) {
      // TODO: reorder tree nodes without tree rebuilding.
      // Conceptually, there is nothing actually preventing us from trying to
      // reorder a larger list. In fact, we do exactly this when vectorizing
      // reductions. However, at this point, we only expect to get here when
      // there are exactly two operations.
      assert(Ops.size() == 2)((Ops.size() == 2) ? static_cast<void> (0) : __assert_fail
 ("Ops.size() == 2", "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 6428, __PRETTY_FUNCTION__));
      Value *ReorderedOps[] = {Ops[1], Ops[0]};
      R.buildTree(ReorderedOps, None);
    }
    if (R.isTreeTinyAndNotFullyVectorizable())
      continue;

    R.computeMinimumValueSizes();
    InstructionCost Cost = R.getTreeCost();
    CandidateFound = true;
    if (CompensateUseCost) {
      // TODO: Use TTI's getScalarizationOverhead for sequence of inserts
      // rather than sum of single inserts as the latter may overestimate
      // cost. This work should imply improving cost estimation for extracts
      // that added in for external (for vectorization tree) users,i.e. that
      // part should also switch to same interface.
      // For example, the following case is projected code after SLP:
      //  %4 = extractelement <4 x i64> %3, i32 0
      //  %v0 = insertelement <4 x i64> poison, i64 %4, i32 0
      //  %5 = extractelement <4 x i64> %3, i32 1
      //  %v1 = insertelement <4 x i64> %v0, i64 %5, i32 1
      //  %6 = extractelement <4 x i64> %3, i32 2
      //  %v2 = insertelement <4 x i64> %v1, i64 %6, i32 2
      //  %7 = extractelement <4 x i64> %3, i32 3
      //  %v3 = insertelement <4 x i64> %v2, i64 %7, i32 3
      //
      // Extracts here added by SLP in order to feed users (the inserts) of
      // original scalars and contribute to "ExtractCost" at cost evaluation.
      // The inserts in turn form sequence to build an aggregate that
      // detected by findBuildAggregate routine.
      // SLP makes an assumption that such sequence will be optimized away
      // later (instcombine) so it tries to compensate ExctractCost with
      // cost of insert sequence.
      // Current per element cost calculation approach is not quite accurate
      // and tends to create bias toward favoring vectorization.
      // Switching to the TTI interface might help a bit.
      // Alternative solution could be pattern-match to detect a no-op or
      // shuffle.
      InstructionCost UserCost = 0;
      for (unsigned Lane = 0; Lane < OpsWidth; Lane++) {
        auto *IE = cast<InsertElementInst>(InsertUses[I + Lane]);
        if (auto *CI = dyn_cast<ConstantInt>(IE->getOperand(2)))
          UserCost += TTI->getVectorInstrCost(
              Instruction::InsertElement, IE->getType(), CI->getZExtValue());
      }
      LLVM_DEBUG(dbgs() << "SLP: Compensate cost of users by: " << UserCostdo { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Compensate cost of users by: "
 << UserCost << ".\n"; } } while (false)
                        << ".\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Compensate cost of users by: "
 << UserCost << ".\n"; } } while (false);
      Cost -= UserCost;
    }

    MinCost = std::min(MinCost, Cost);

    if (Cost < -SLPCostThreshold) {
      LLVM_DEBUG(dbgs() << "SLP: Vectorizing list at cost:" << Cost << ".\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Vectorizing list at cost:" <<
 Cost << ".\n"; } } while (false);
      R.getORE()->emit(OptimizationRemark(SV_NAME"slp-vectorizer", "VectorizedList",
                                                  cast<Instruction>(Ops[0]))
                               << "SLP vectorized with cost " << ore::NV("Cost", Cost)
                               << " and with tree size "
                               << ore::NV("TreeSize", R.getTreeSize()));

      R.vectorizeTree();
      // Move to the next bundle.
      I += VF - 1;
      NextInst = I + 1;
      Changed = true;
    }
  }
}

if (!Changed && CandidateFound) {
  R.getORE()->emit([&]() {
    return OptimizationRemarkMissed(SV_NAME"slp-vectorizer", "NotBeneficial", I0)
           << "List vectorization was possible but not beneficial with cost "
           << ore::NV("Cost", MinCost) << " >= "
           << ore::NV("Treshold", -SLPCostThreshold);
  });
} else if (!Changed) {
  R.getORE()->emit([&]() {
    return OptimizationRemarkMissed(SV_NAME"slp-vectorizer", "NotPossible", I0)
           << "Cannot SLP vectorize list: vectorization was impossible"
           << " with available vectorization factors";
  });
}
return Changed;
6512}

6514bool SLPVectorizerPass::tryToVectorize(Instruction *I, BoUpSLP &R) {
if (!I)
  return false;

if (!isa<BinaryOperator>(I) && !isa<CmpInst>(I))
  return false;

Value *P = I->getParent();

// Vectorize in current basic block only.
auto *Op0 = dyn_cast<Instruction>(I->getOperand(0));
auto *Op1 = dyn_cast<Instruction>(I->getOperand(1));
if (!Op0 || !Op1 || Op0->getParent() != P || Op1->getParent() != P)
  return false;

// Try to vectorize V.
if (tryToVectorizePair(Op0, Op1, R))
  return true;

auto *A = dyn_cast<BinaryOperator>(Op0);
auto *B = dyn_cast<BinaryOperator>(Op1);
// Try to skip B.
if (B && B->hasOneUse()) {
  auto *B0 = dyn_cast<BinaryOperator>(B->getOperand(0));
  auto *B1 = dyn_cast<BinaryOperator>(B->getOperand(1));
  if (B0 && B0->getParent() == P && tryToVectorizePair(A, B0, R))
    return true;
  if (B1 && B1->getParent() == P && tryToVectorizePair(A, B1, R))
    return true;
}

// Try to skip A.
if (A && A->hasOneUse()) {
  auto *A0 = dyn_cast<BinaryOperator>(A->getOperand(0));
  auto *A1 = dyn_cast<BinaryOperator>(A->getOperand(1));
  if (A0 && A0->getParent() == P && tryToVectorizePair(A0, B, R))
    return true;
  if (A1 && A1->getParent() == P && tryToVectorizePair(A1, B, R))
    return true;
}
return false;
6555}

6557namespace {

6559/// Model horizontal reductions.
6560///
6561/// A horizontal reduction is a tree of reduction instructions that has values
6562/// that can be put into a vector as its leaves. For example:
6563///
6564/// mul mul mul mul
6565///  \  /    \  /
6566///   +       +
6567///    \     /
6568///       +
6569/// This tree has "mul" as its leaf values and "+" as its reduction
6570/// instructions. A reduction can feed into a store or a binary operation
6571/// feeding a phi.
6572///    ...
6573///    \  /
6574///     +
6575///     |
6576///  phi +=
6577///
6578///  Or:
6579///    ...
6580///    \  /
6581///     +
6582///     |
6583///   *p =
6584///
6585class HorizontalReduction {
using ReductionOpsType = SmallVector<Value *, 16>;
using ReductionOpsListType = SmallVector<ReductionOpsType, 2>;
ReductionOpsListType ReductionOps;
SmallVector<Value *, 32> ReducedVals;
// Use map vector to make stable output.
MapVector<Instruction *, Value *> ExtraArgs;
WeakTrackingVH ReductionRoot;
/// The type of reduction operation.
RecurKind RdxKind;

/// Checks if instruction is associative and can be vectorized.
static bool isVectorizable(RecurKind Kind, Instruction *I) {
  if (Kind == RecurKind::None)
    return false;
  if (RecurrenceDescriptor::isIntMinMaxRecurrenceKind(Kind))
    return true;

  if (Kind == RecurKind::FMax || Kind == RecurKind::FMin) {
    // FP min/max are associative except for NaN and -0.0. We do not
    // have to rule out -0.0 here because the intrinsic semantics do not
    // specify a fixed result for it.
    return I->getFastMathFlags().noNaNs();
  }

  return I->isAssociative();
}

/// Checks if the ParentStackElem.first should be marked as a reduction
/// operation with an extra argument or as extra argument itself.
void markExtraArg(std::pair<Instruction *, unsigned> &ParentStackElem,
                  Value *ExtraArg) {
  if (ExtraArgs.count(ParentStackElem.first)) {
    ExtraArgs[ParentStackElem.first] = nullptr;
    // We ran into something like:
    // ParentStackElem.first = ExtraArgs[ParentStackElem.first] + ExtraArg.
    // The whole ParentStackElem.first should be considered as an extra value
    // in this case.
    // Do not perform analysis of remaining operands of ParentStackElem.first
    // instruction, this whole instruction is an extra argument.
    ParentStackElem.second = getNumberOfOperands(ParentStackElem.first);
  } else {
    // We ran into something like:
    // ParentStackElem.first += ... + ExtraArg + ...
    ExtraArgs[ParentStackElem.first] = ExtraArg;
  }
}

/// Creates reduction operation with the current opcode.
static Value *createOp(IRBuilder<> &Builder, RecurKind Kind, Value *LHS,
                       Value *RHS, const Twine &Name, bool UseSelect) {
  unsigned RdxOpcode = RecurrenceDescriptor::getOpcode(Kind);
  switch (Kind) {
  case RecurKind::Add:
  case RecurKind::Mul:
  case RecurKind::Or:
  case RecurKind::And:
  case RecurKind::Xor:
  case RecurKind::FAdd:
  case RecurKind::FMul:
    return Builder.CreateBinOp((Instruction::BinaryOps)RdxOpcode, LHS, RHS,
                               Name);
  case RecurKind::FMax:
    return Builder.CreateBinaryIntrinsic(Intrinsic::maxnum, LHS, RHS);
  case RecurKind::FMin:
    return Builder.CreateBinaryIntrinsic(Intrinsic::minnum, LHS, RHS);
  case RecurKind::SMax:
    if (UseSelect) {
      Value *Cmp = Builder.CreateICmpSGT(LHS, RHS, Name);
      return Builder.CreateSelect(Cmp, LHS, RHS, Name);
    }
    return Builder.CreateBinaryIntrinsic(Intrinsic::smax, LHS, RHS);
  case RecurKind::SMin:
    if (UseSelect) {
      Value *Cmp = Builder.CreateICmpSLT(LHS, RHS, Name);
      return Builder.CreateSelect(Cmp, LHS, RHS, Name);
    }
    return Builder.CreateBinaryIntrinsic(Intrinsic::smin, LHS, RHS);
  case RecurKind::UMax:
    if (UseSelect) {
      Value *Cmp = Builder.CreateICmpUGT(LHS, RHS, Name);
      return Builder.CreateSelect(Cmp, LHS, RHS, Name);
    }
    return Builder.CreateBinaryIntrinsic(Intrinsic::umax, LHS, RHS);
  case RecurKind::UMin:
    if (UseSelect) {
      Value *Cmp = Builder.CreateICmpULT(LHS, RHS, Name);
      return Builder.CreateSelect(Cmp, LHS, RHS, Name);
    }
    return Builder.CreateBinaryIntrinsic(Intrinsic::umin, LHS, RHS);
  default:
    llvm_unreachable("Unknown reduction operation.")::llvm::llvm_unreachable_internal("Unknown reduction operation."
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 6676);
  }
}

/// Creates reduction operation with the current opcode with the IR flags
/// from \p ReductionOps.
static Value *createOp(IRBuilder<> &Builder, RecurKind RdxKind, Value *LHS,
                       Value *RHS, const Twine &Name,
                       const ReductionOpsListType &ReductionOps) {
  bool UseSelect = ReductionOps.size() == 2;
  assert((!UseSelect || isa<SelectInst>(ReductionOps[1][0])) &&(((!UseSelect || isa<SelectInst>(ReductionOps[1][0])) &&
 "Expected cmp + select pairs for reduction") ? static_cast<
void> (0) : __assert_fail ("(!UseSelect || isa<SelectInst>(ReductionOps[1][0])) && \"Expected cmp + select pairs for reduction\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 6687, __PRETTY_FUNCTION__))
         "Expected cmp + select pairs for reduction")(((!UseSelect || isa<SelectInst>(ReductionOps[1][0])) &&
 "Expected cmp + select pairs for reduction") ? static_cast<
void> (0) : __assert_fail ("(!UseSelect || isa<SelectInst>(ReductionOps[1][0])) && \"Expected cmp + select pairs for reduction\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 6687, __PRETTY_FUNCTION__));
  Value *Op = createOp(Builder, RdxKind, LHS, RHS, Name, UseSelect);
  if (RecurrenceDescriptor::isIntMinMaxRecurrenceKind(RdxKind)) {
    if (auto *Sel = dyn_cast<SelectInst>(Op)) {
      propagateIRFlags(Sel->getCondition(), ReductionOps[0]);
      propagateIRFlags(Op, ReductionOps[1]);
      return Op;
    }
  }
  propagateIRFlags(Op, ReductionOps[0]);
  return Op;
}
/// Creates reduction operation with the current opcode with the IR flags
/// from \p I.
static Value *createOp(IRBuilder<> &Builder, RecurKind RdxKind, Value *LHS,
                       Value *RHS, const Twine &Name, Instruction *I) {
  auto *SelI = dyn_cast<SelectInst>(I);
1
Assuming 'I' is not a 'SelectInst'→
2
←
'SelI' initialized to a null pointer value→
  Value *Op = createOp(Builder, RdxKind, LHS, RHS, Name, SelI != nullptr);
  if (RecurrenceDescriptor::isIntMinMaxRecurrenceKind(RdxKind)) {
3
←
Calling 'RecurrenceDescriptor::isIntMinMaxRecurrenceKind'→
5
←
Returning from 'RecurrenceDescriptor::isIntMinMaxRecurrenceKind'→
6
←
Taking true branch→
    if (auto *Sel7.1
'Sel' is non-null
1
'Sel' is non-null
 = dyn_cast<SelectInst>(Op))
7
←
Assuming 'Op' is a 'SelectInst'→
8
←
Taking true branch→
        propagateIRFlags(Sel->getCondition(), SelI->getCondition());
9
←
Called C++ object pointer is null
  }
  propagateIRFlags(Op, I);
  return Op;
}

static RecurKind getRdxKind(Instruction *I) {
  assert(I && "Expected instruction for reduction matching")((I && "Expected instruction for reduction matching")
 ? static_cast<void> (0) : __assert_fail ("I && \"Expected instruction for reduction matching\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 6714, __PRETTY_FUNCTION__));
  TargetTransformInfo::ReductionFlags RdxFlags;
  if (match(I, m_Add(m_Value(), m_Value())))
    return RecurKind::Add;
  if (match(I, m_Mul(m_Value(), m_Value())))
    return RecurKind::Mul;
  if (match(I, m_And(m_Value(), m_Value())))
    return RecurKind::And;
  if (match(I, m_Or(m_Value(), m_Value())))
    return RecurKind::Or;
  if (match(I, m_Xor(m_Value(), m_Value())))
    return RecurKind::Xor;
  if (match(I, m_FAdd(m_Value(), m_Value())))
    return RecurKind::FAdd;
  if (match(I, m_FMul(m_Value(), m_Value())))
    return RecurKind::FMul;

  if (match(I, m_Intrinsic<Intrinsic::maxnum>(m_Value(), m_Value())))
    return RecurKind::FMax;
  if (match(I, m_Intrinsic<Intrinsic::minnum>(m_Value(), m_Value())))
    return RecurKind::FMin;

  // This matches either cmp+select or intrinsics. SLP is expected to handle
  // either form.
  // TODO: If we are canonicalizing to intrinsics, we can remove several
  //       special-case paths that deal with selects.
  if (match(I, m_SMax(m_Value(), m_Value())))
    return RecurKind::SMax;
  if (match(I, m_SMin(m_Value(), m_Value())))
    return RecurKind::SMin;
  if (match(I, m_UMax(m_Value(), m_Value())))
    return RecurKind::UMax;
  if (match(I, m_UMin(m_Value(), m_Value())))
    return RecurKind::UMin;

  if (auto *Select = dyn_cast<SelectInst>(I)) {
    // Try harder: look for min/max pattern based on instructions producing
    // same values such as: select ((cmp Inst1, Inst2), Inst1, Inst2).
    // During the intermediate stages of SLP, it's very common to have
    // pattern like this (since optimizeGatherSequence is run only once
    // at the end):
    // %1 = extractelement <2 x i32> %a, i32 0
    // %2 = extractelement <2 x i32> %a, i32 1
    // %cond = icmp sgt i32 %1, %2
    // %3 = extractelement <2 x i32> %a, i32 0
    // %4 = extractelement <2 x i32> %a, i32 1
    // %select = select i1 %cond, i32 %3, i32 %4
    CmpInst::Predicate Pred;
    Instruction *L1;
    Instruction *L2;

    Value *LHS = Select->getTrueValue();
    Value *RHS = Select->getFalseValue();
    Value *Cond = Select->getCondition();

    // TODO: Support inverse predicates.
    if (match(Cond, m_Cmp(Pred, m_Specific(LHS), m_Instruction(L2)))) {
      if (!isa<ExtractElementInst>(RHS) ||
          !L2->isIdenticalTo(cast<Instruction>(RHS)))
        return RecurKind::None;
    } else if (match(Cond, m_Cmp(Pred, m_Instruction(L1), m_Specific(RHS)))) {
      if (!isa<ExtractElementInst>(LHS) ||
          !L1->isIdenticalTo(cast<Instruction>(LHS)))
        return RecurKind::None;
    } else {
      if (!isa<ExtractElementInst>(LHS) || !isa<ExtractElementInst>(RHS))
        return RecurKind::None;
      if (!match(Cond, m_Cmp(Pred, m_Instruction(L1), m_Instruction(L2))) ||
          !L1->isIdenticalTo(cast<Instruction>(LHS)) ||
          !L2->isIdenticalTo(cast<Instruction>(RHS)))
        return RecurKind::None;
    }

    TargetTransformInfo::ReductionFlags RdxFlags;
    switch (Pred) {
    default:
      return RecurKind::None;
    case CmpInst::ICMP_SGT:
    case CmpInst::ICMP_SGE:
      return RecurKind::SMax;
    case CmpInst::ICMP_SLT:
    case CmpInst::ICMP_SLE:
      return RecurKind::SMin;
    case CmpInst::ICMP_UGT:
    case CmpInst::ICMP_UGE:
      return RecurKind::UMax;
    case CmpInst::ICMP_ULT:
    case CmpInst::ICMP_ULE:
      return RecurKind::UMin;
    }
  }
  return RecurKind::None;
}

/// Get the index of the first operand.
static unsigned getFirstOperandIndex(Instruction *I) {
  return isa<SelectInst>(I) ? 1 : 0;
}

/// Total number of operands in the reduction operation.
static unsigned getNumberOfOperands(Instruction *I) {
  return isa<SelectInst>(I) ? 3 : 2;
}

/// Checks if the instruction is in basic block \p BB.
/// For a min/max reduction check that both compare and select are in \p BB.
static bool hasSameParent(Instruction *I, BasicBlock *BB, bool IsRedOp) {
  auto *Sel = dyn_cast<SelectInst>(I);
  if (IsRedOp && Sel) {
    auto *Cmp = cast<Instruction>(Sel->getCondition());
    return Sel->getParent() == BB && Cmp->getParent() == BB;
  }
  return I->getParent() == BB;
}

/// Expected number of uses for reduction operations/reduced values.
static bool hasRequiredNumberOfUses(bool MatchCmpSel, Instruction *I) {
  // SelectInst must be used twice while the condition op must have single
  // use only.
  if (MatchCmpSel) {
    if (auto *Sel = dyn_cast<SelectInst>(I))
      return Sel->hasNUses(2) && Sel->getCondition()->hasOneUse();
    return I->hasNUses(2);
  }

  // Arithmetic reduction operation must be used once only.
  return I->hasOneUse();
}

/// Initializes the list of reduction operations.
void initReductionOps(Instruction *I) {
  if (isa<SelectInst>(I))
    ReductionOps.assign(2, ReductionOpsType());
  else
    ReductionOps.assign(1, ReductionOpsType());
}

/// Add all reduction operations for the reduction instruction \p I.
void addReductionOps(Instruction *I) {
  if (auto *Sel = dyn_cast<SelectInst>(I)) {
    ReductionOps[0].emplace_back(Sel->getCondition());
    ReductionOps[1].emplace_back(Sel);
  } else {
    ReductionOps[0].emplace_back(I);
  }
}

static Value *getLHS(RecurKind Kind, Instruction *I) {
  if (Kind == RecurKind::None)
    return nullptr;
  return I->getOperand(getFirstOperandIndex(I));
}
static Value *getRHS(RecurKind Kind, Instruction *I) {
  if (Kind == RecurKind::None)
    return nullptr;
  return I->getOperand(getFirstOperandIndex(I) + 1);
}

6872public:
HorizontalReduction() = default;

/// Try to find a reduction tree.
bool matchAssociativeReduction(PHINode *Phi, Instruction *B) {
  assert((!Phi || is_contained(Phi->operands(), B)) &&(((!Phi || is_contained(Phi->operands(), B)) && "Phi needs to use the binary operator"
) ? static_cast<void> (0) : __assert_fail ("(!Phi || is_contained(Phi->operands(), B)) && \"Phi needs to use the binary operator\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 6878, __PRETTY_FUNCTION__))
         "Phi needs to use the binary operator")(((!Phi || is_contained(Phi->operands(), B)) && "Phi needs to use the binary operator"
) ? static_cast<void> (0) : __assert_fail ("(!Phi || is_contained(Phi->operands(), B)) && \"Phi needs to use the binary operator\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 6878, __PRETTY_FUNCTION__));

  RdxKind = getRdxKind(B);

  // We could have a initial reductions that is not an add.
  //  r *= v1 + v2 + v3 + v4
  // In such a case start looking for a tree rooted in the first '+'.
  if (Phi) {
    if (getLHS(RdxKind, B) == Phi) {
      Phi = nullptr;
      B = dyn_cast<Instruction>(getRHS(RdxKind, B));
      if (!B)
        return false;
      RdxKind = getRdxKind(B);
    } else if (getRHS(RdxKind, B) == Phi) {
      Phi = nullptr;
      B = dyn_cast<Instruction>(getLHS(RdxKind, B));
      if (!B)
        return false;
      RdxKind = getRdxKind(B);
    }
  }

  if (!isVectorizable(RdxKind, B))
    return false;

  // Analyze "regular" integer/FP types for reductions - no target-specific
  // types or pointers.
  Type *Ty = B->getType();
  if (!isValidElementType(Ty) || Ty->isPointerTy())
    return false;

  // Though the ultimate reduction may have multiple uses, its condition must
  // have only single use.
  if (auto *SI = dyn_cast<SelectInst>(B))
    if (!SI->getCondition()->hasOneUse())
      return false;

  ReductionRoot = B;

  // The opcode for leaf values that we perform a reduction on.
  // For example: load(x) + load(y) + load(z) + fptoui(w)
  // The leaf opcode for 'w' does not match, so we don't include it as a
  // potential candidate for the reduction.
  unsigned LeafOpcode = 0;

  // Post order traverse the reduction tree starting at B. We only handle true
  // trees containing only binary operators.
  SmallVector<std::pair<Instruction *, unsigned>, 32> Stack;
  Stack.push_back(std::make_pair(B, getFirstOperandIndex(B)));
  initReductionOps(B);
  while (!Stack.empty()) {
    Instruction *TreeN = Stack.back().first;
    unsigned EdgeToVisit = Stack.back().second++;
    const RecurKind TreeRdxKind = getRdxKind(TreeN);
    bool IsReducedValue = TreeRdxKind != RdxKind;

    // Postorder visit.
    if (IsReducedValue || EdgeToVisit == getNumberOfOperands(TreeN)) {
      if (IsReducedValue)
        ReducedVals.push_back(TreeN);
      else {
        auto ExtraArgsIter = ExtraArgs.find(TreeN);
        if (ExtraArgsIter != ExtraArgs.end() && !ExtraArgsIter->second) {
          // Check if TreeN is an extra argument of its parent operation.
          if (Stack.size() <= 1) {
            // TreeN can't be an extra argument as it is a root reduction
            // operation.
            return false;
          }
          // Yes, TreeN is an extra argument, do not add it to a list of
          // reduction operations.
          // Stack[Stack.size() - 2] always points to the parent operation.
          markExtraArg(Stack[Stack.size() - 2], TreeN);
          ExtraArgs.erase(TreeN);
        } else
          addReductionOps(TreeN);
      }
      // Retract.
      Stack.pop_back();
      continue;
    }

    // Visit left or right.
    Value *EdgeVal = TreeN->getOperand(EdgeToVisit);
    auto *EdgeInst = dyn_cast<Instruction>(EdgeVal);
    if (!EdgeInst) {
      // Edge value is not a reduction instruction or a leaf instruction.
      // (It may be a constant, function argument, or something else.)
      markExtraArg(Stack.back(), EdgeVal);
      continue;
    }
    RecurKind EdgeRdxKind = getRdxKind(EdgeInst);
    // Continue analysis if the next operand is a reduction operation or
    // (possibly) a leaf value. If the leaf value opcode is not set,
    // the first met operation != reduction operation is considered as the
    // leaf opcode.
    // Only handle trees in the current basic block.
    // Each tree node needs to have minimal number of users except for the
    // ultimate reduction.
    const bool IsRdxInst = EdgeRdxKind == RdxKind;
    if (EdgeInst != Phi && EdgeInst != B &&
        hasSameParent(EdgeInst, B->getParent(), IsRdxInst) &&
        hasRequiredNumberOfUses(isa<SelectInst>(B), EdgeInst) &&
        (!LeafOpcode || LeafOpcode == EdgeInst->getOpcode() || IsRdxInst)) {
      if (IsRdxInst) {
        // We need to be able to reassociate the reduction operations.
        if (!isVectorizable(EdgeRdxKind, EdgeInst)) {
          // I is an extra argument for TreeN (its parent operation).
          markExtraArg(Stack.back(), EdgeInst);
          continue;
        }
      } else if (!LeafOpcode) {
        LeafOpcode = EdgeInst->getOpcode();
      }
      Stack.push_back(
          std::make_pair(EdgeInst, getFirstOperandIndex(EdgeInst)));
      continue;
    }
    // I is an extra argument for TreeN (its parent operation).
    markExtraArg(Stack.back(), EdgeInst);
  }
  return true;
}

/// Attempt to vectorize the tree found by matchAssociativeReduction.
bool tryToReduce(BoUpSLP &V, TargetTransformInfo *TTI) {
  // If there are a sufficient number of reduction values, reduce
  // to a nearby power-of-2. We can safely generate oversized
  // vectors and rely on the backend to split them to legal sizes.
  unsigned NumReducedVals = ReducedVals.size();
  if (NumReducedVals < 4)
    return false;

  // Intersect the fast-math-flags from all reduction operations.
  FastMathFlags RdxFMF;
  RdxFMF.set();
  for (ReductionOpsType &RdxOp : ReductionOps) {
    for (Value *RdxVal : RdxOp) {
      if (auto *FPMO = dyn_cast<FPMathOperator>(RdxVal))
        RdxFMF &= FPMO->getFastMathFlags();
    }
  }

  IRBuilder<> Builder(cast<Instruction>(ReductionRoot));
  Builder.setFastMathFlags(RdxFMF);

  BoUpSLP::ExtraValueToDebugLocsMap ExternallyUsedValues;
  // The same extra argument may be used several times, so log each attempt
  // to use it.
  for (const std::pair<Instruction *, Value *> &Pair : ExtraArgs) {
    assert(Pair.first && "DebugLoc must be set.")((Pair.first && "DebugLoc must be set.") ? static_cast
<void> (0) : __assert_fail ("Pair.first && \"DebugLoc must be set.\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 7029, __PRETTY_FUNCTION__));
    ExternallyUsedValues[Pair.second].push_back(Pair.first);
  }

  // The compare instruction of a min/max is the insertion point for new
  // instructions and may be replaced with a new compare instruction.
  auto getCmpForMinMaxReduction = [](Instruction *RdxRootInst) {
    assert(isa<SelectInst>(RdxRootInst) &&((isa<SelectInst>(RdxRootInst) && "Expected min/max reduction to have select root instruction"
) ? static_cast<void> (0) : __assert_fail ("isa<SelectInst>(RdxRootInst) && \"Expected min/max reduction to have select root instruction\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 7037, __PRETTY_FUNCTION__))
           "Expected min/max reduction to have select root instruction")((isa<SelectInst>(RdxRootInst) && "Expected min/max reduction to have select root instruction"
) ? static_cast<void> (0) : __assert_fail ("isa<SelectInst>(RdxRootInst) && \"Expected min/max reduction to have select root instruction\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 7037, __PRETTY_FUNCTION__));
    Value *ScalarCond = cast<SelectInst>(RdxRootInst)->getCondition();
    assert(isa<Instruction>(ScalarCond) &&((isa<Instruction>(ScalarCond) && "Expected min/max reduction to have compare condition"
) ? static_cast<void> (0) : __assert_fail ("isa<Instruction>(ScalarCond) && \"Expected min/max reduction to have compare condition\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 7040, __PRETTY_FUNCTION__))
           "Expected min/max reduction to have compare condition")((isa<Instruction>(ScalarCond) && "Expected min/max reduction to have compare condition"
) ? static_cast<void> (0) : __assert_fail ("isa<Instruction>(ScalarCond) && \"Expected min/max reduction to have compare condition\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 7040, __PRETTY_FUNCTION__));
    return cast<Instruction>(ScalarCond);
  };

  // The reduction root is used as the insertion point for new instructions,
  // so set it as externally used to prevent it from being deleted.
  ExternallyUsedValues[ReductionRoot];
  SmallVector<Value *, 16> IgnoreList;
  for (ReductionOpsType &RdxOp : ReductionOps)
    IgnoreList.append(RdxOp.begin(), RdxOp.end());

  unsigned ReduxWidth = PowerOf2Floor(NumReducedVals);
  if (NumReducedVals > ReduxWidth) {
    // In the loop below, we are building a tree based on a window of
    // 'ReduxWidth' values.
    // If the operands of those values have common traits (compare predicate,
    // constant operand, etc), then we want to group those together to
    // minimize the cost of the reduction.

    // TODO: This should be extended to count common operands for
    //       compares and binops.

    // Step 1: Count the number of times each compare predicate occurs.
    SmallDenseMap<unsigned, unsigned> PredCountMap;
    for (Value *RdxVal : ReducedVals) {
      CmpInst::Predicate Pred;
      if (match(RdxVal, m_Cmp(Pred, m_Value(), m_Value())))
        ++PredCountMap[Pred];
    }
    // Step 2: Sort the values so the most common predicates come first.
    stable_sort(ReducedVals, [&PredCountMap](Value *A, Value *B) {
      CmpInst::Predicate PredA, PredB;
      if (match(A, m_Cmp(PredA, m_Value(), m_Value())) &&
          match(B, m_Cmp(PredB, m_Value(), m_Value()))) {
        return PredCountMap[PredA] > PredCountMap[PredB];
      }
      return false;
    });
  }

  Value *VectorizedTree = nullptr;
  unsigned i = 0;
  while (i < NumReducedVals - ReduxWidth + 1 && ReduxWidth > 2) {
    ArrayRef<Value *> VL(&ReducedVals[i], ReduxWidth);
    V.buildTree(VL, ExternallyUsedValues, IgnoreList);
    Optional<ArrayRef<unsigned>> Order = V.bestOrder();
    if (Order) {
      assert(Order->size() == VL.size() &&((Order->size() == VL.size() && "Order size must be the same as number of vectorized "
 "instructions.") ? static_cast<void> (0) : __assert_fail
 ("Order->size() == VL.size() && \"Order size must be the same as number of vectorized \" \"instructions.\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 7089, __PRETTY_FUNCTION__))
             "Order size must be the same as number of vectorized "((Order->size() == VL.size() && "Order size must be the same as number of vectorized "
 "instructions.") ? static_cast<void> (0) : __assert_fail
 ("Order->size() == VL.size() && \"Order size must be the same as number of vectorized \" \"instructions.\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 7089, __PRETTY_FUNCTION__))
             "instructions.")((Order->size() == VL.size() && "Order size must be the same as number of vectorized "
 "instructions.") ? static_cast<void> (0) : __assert_fail
 ("Order->size() == VL.size() && \"Order size must be the same as number of vectorized \" \"instructions.\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 7089, __PRETTY_FUNCTION__));
      // TODO: reorder tree nodes without tree rebuilding.
      SmallVector<Value *, 4> ReorderedOps(VL.size());
      llvm::transform(*Order, ReorderedOps.begin(),
                      [VL](const unsigned Idx) { return VL[Idx]; });
      V.buildTree(ReorderedOps, ExternallyUsedValues, IgnoreList);
    }
    if (V.isTreeTinyAndNotFullyVectorizable())
      break;
    if (V.isLoadCombineReductionCandidate(RdxKind))
      break;

    V.computeMinimumValueSizes();

    // Estimate cost.
    InstructionCost TreeCost = V.getTreeCost();
    InstructionCost ReductionCost =
        getReductionCost(TTI, ReducedVals[i], ReduxWidth);
    InstructionCost Cost = TreeCost + ReductionCost;
    if (!Cost.isValid()) {
      LLVM_DEBUG(dbgs() << "Encountered invalid baseline cost.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "Encountered invalid baseline cost.\n"
; } } while (false);
      return false;
    }
    if (Cost >= -SLPCostThreshold) {
      V.getORE()->emit([&]() {
        return OptimizationRemarkMissed(SV_NAME"slp-vectorizer", "HorSLPNotBeneficial",
                                        cast<Instruction>(VL[0]))
               << "Vectorizing horizontal reduction is possible"
               << "but not beneficial with cost " << ore::NV("Cost", Cost)
               << " and threshold "
               << ore::NV("Threshold", -SLPCostThreshold);
      });
      break;
    }

    LLVM_DEBUG(dbgs() << "SLP: Vectorizing horizontal reduction at cost:"do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Vectorizing horizontal reduction at cost:"
 << Cost << ". (HorRdx)\n"; } } while (false)
                      << Cost << ". (HorRdx)\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Vectorizing horizontal reduction at cost:"
 << Cost << ". (HorRdx)\n"; } } while (false);
    V.getORE()->emit([&]() {
      return OptimizationRemark(SV_NAME"slp-vectorizer", "VectorizedHorizontalReduction",
                                cast<Instruction>(VL[0]))
             << "Vectorized horizontal reduction with cost "
             << ore::NV("Cost", Cost) << " and with tree size "
             << ore::NV("TreeSize", V.getTreeSize());
    });

    // Vectorize a tree.
    DebugLoc Loc = cast<Instruction>(ReducedVals[i])->getDebugLoc();
    Value *VectorizedRoot = V.vectorizeTree(ExternallyUsedValues);

    // Emit a reduction. If the root is a select (min/max idiom), the insert
    // point is the compare condition of that select.
    Instruction *RdxRootInst = cast<Instruction>(ReductionRoot);
    if (isa<SelectInst>(RdxRootInst))
      Builder.SetInsertPoint(getCmpForMinMaxReduction(RdxRootInst));
    else
      Builder.SetInsertPoint(RdxRootInst);

    Value *ReducedSubTree =
        emitReduction(VectorizedRoot, Builder, ReduxWidth, TTI);

    if (!VectorizedTree) {
      // Initialize the final value in the reduction.
      VectorizedTree = ReducedSubTree;
    } else {
      // Update the final value in the reduction.
      Builder.SetCurrentDebugLocation(Loc);
      VectorizedTree = createOp(Builder, RdxKind, VectorizedTree,
                                ReducedSubTree, "op.rdx", ReductionOps);
    }
    i += ReduxWidth;
    ReduxWidth = PowerOf2Floor(NumReducedVals - i);
  }

  if (VectorizedTree) {
    // Finish the reduction.
    for (; i < NumReducedVals; ++i) {
      auto *I = cast<Instruction>(ReducedVals[i]);
      Builder.SetCurrentDebugLocation(I->getDebugLoc());
      VectorizedTree =
          createOp(Builder, RdxKind, VectorizedTree, I, "", ReductionOps);
    }
    for (auto &Pair : ExternallyUsedValues) {
      // Add each externally used value to the final reduction.
      for (auto *I : Pair.second) {
        Builder.SetCurrentDebugLocation(I->getDebugLoc());
        VectorizedTree = createOp(Builder, RdxKind, VectorizedTree,
                                  Pair.first, "op.extra", I);
      }
    }

    ReductionRoot->replaceAllUsesWith(VectorizedTree);

    // Mark all scalar reduction ops for deletion, they are replaced by the
    // vector reductions.
    V.eraseInstructions(IgnoreList);
  }
  return VectorizedTree != nullptr;
}

unsigned numReductionValues() const { return ReducedVals.size(); }

7190private:
/// Calculate the cost of a reduction.
InstructionCost getReductionCost(TargetTransformInfo *TTI,
                                 Value *FirstReducedVal,
                                 unsigned ReduxWidth) {
  Type *ScalarTy = FirstReducedVal->getType();
  FixedVectorType *VectorTy = FixedVectorType::get(ScalarTy, ReduxWidth);
  InstructionCost VectorCost, ScalarCost;
  switch (RdxKind) {
  case RecurKind::Add:
  case RecurKind::Mul:
  case RecurKind::Or:
  case RecurKind::And:
  case RecurKind::Xor:
  case RecurKind::FAdd:
  case RecurKind::FMul: {
    unsigned RdxOpcode = RecurrenceDescriptor::getOpcode(RdxKind);
    VectorCost = TTI->getArithmeticReductionCost(RdxOpcode, VectorTy,
                                                 /*IsPairwiseForm=*/false);
    ScalarCost = TTI->getArithmeticInstrCost(RdxOpcode, ScalarTy);
    break;
  }
  case RecurKind::FMax:
  case RecurKind::FMin: {
    auto *VecCondTy = cast<VectorType>(CmpInst::makeCmpResultType(VectorTy));
    VectorCost =
        TTI->getMinMaxReductionCost(VectorTy, VecCondTy,
                                    /*pairwise=*/false, /*unsigned=*/false);
    ScalarCost =
        TTI->getCmpSelInstrCost(Instruction::FCmp, ScalarTy) +
        TTI->getCmpSelInstrCost(Instruction::Select, ScalarTy,
                                CmpInst::makeCmpResultType(ScalarTy));
    break;
  }
  case RecurKind::SMax:
  case RecurKind::SMin:
  case RecurKind::UMax:
  case RecurKind::UMin: {
    auto *VecCondTy = cast<VectorType>(CmpInst::makeCmpResultType(VectorTy));
    bool IsUnsigned =
        RdxKind == RecurKind::UMax || RdxKind == RecurKind::UMin;
    VectorCost =
        TTI->getMinMaxReductionCost(VectorTy, VecCondTy,
                                    /*IsPairwiseForm=*/false, IsUnsigned);
    ScalarCost =
        TTI->getCmpSelInstrCost(Instruction::ICmp, ScalarTy) +
        TTI->getCmpSelInstrCost(Instruction::Select, ScalarTy,
                                CmpInst::makeCmpResultType(ScalarTy));
    break;
  }
  default:
    llvm_unreachable("Expected arithmetic or min/max reduction operation")::llvm::llvm_unreachable_internal("Expected arithmetic or min/max reduction operation"
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 7241);
  }

  // Scalar cost is repeated for N-1 elements.
  ScalarCost *= (ReduxWidth - 1);
  LLVM_DEBUG(dbgs() << "SLP: Adding cost " << VectorCost - ScalarCostdo { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Adding cost " << VectorCost
 - ScalarCost << " for reduction that starts with " <<
 *FirstReducedVal << " (It is a splitting reduction)\n"
; } } while (false)
                    << " for reduction that starts with " << *FirstReducedValdo { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Adding cost " << VectorCost
 - ScalarCost << " for reduction that starts with " <<
 *FirstReducedVal << " (It is a splitting reduction)\n"
; } } while (false)
                    << " (It is a splitting reduction)\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Adding cost " << VectorCost
 - ScalarCost << " for reduction that starts with " <<
 *FirstReducedVal << " (It is a splitting reduction)\n"
; } } while (false);
  return VectorCost - ScalarCost;
}

/// Emit a horizontal reduction of the vectorized value.
Value *emitReduction(Value *VectorizedValue, IRBuilder<> &Builder,
                     unsigned ReduxWidth, const TargetTransformInfo *TTI) {
  assert(VectorizedValue && "Need to have a vectorized tree node")((VectorizedValue && "Need to have a vectorized tree node"
) ? static_cast<void> (0) : __assert_fail ("VectorizedValue && \"Need to have a vectorized tree node\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 7255, __PRETTY_FUNCTION__));
  assert(isPowerOf2_32(ReduxWidth) &&((isPowerOf2_32(ReduxWidth) && "We only handle power-of-two reductions for now"
) ? static_cast<void> (0) : __assert_fail ("isPowerOf2_32(ReduxWidth) && \"We only handle power-of-two reductions for now\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 7257, __PRETTY_FUNCTION__))
         "We only handle power-of-two reductions for now")((isPowerOf2_32(ReduxWidth) && "We only handle power-of-two reductions for now"
) ? static_cast<void> (0) : __assert_fail ("isPowerOf2_32(ReduxWidth) && \"We only handle power-of-two reductions for now\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 7257, __PRETTY_FUNCTION__));

  return createSimpleTargetReduction(Builder, TTI, VectorizedValue, RdxKind,
                                     ReductionOps.back());
}
7262};

7264} // end anonymous namespace

7266static Optional<unsigned> getAggregateSize(Instruction *InsertInst) {
if (auto *IE = dyn_cast<InsertElementInst>(InsertInst))
  return cast<FixedVectorType>(IE->getType())->getNumElements();

unsigned AggregateSize = 1;
auto *IV = cast<InsertValueInst>(InsertInst);
Type *CurrentType = IV->getType();
do {
  if (auto *ST = dyn_cast<StructType>(CurrentType)) {
    for (auto *Elt : ST->elements())
      if (Elt != ST->getElementType(0)) // check homogeneity
        return None;
    AggregateSize *= ST->getNumElements();
    CurrentType = ST->getElementType(0);
  } else if (auto *AT = dyn_cast<ArrayType>(CurrentType)) {
    AggregateSize *= AT->getNumElements();
    CurrentType = AT->getElementType();
  } else if (auto *VT = dyn_cast<FixedVectorType>(CurrentType)) {
    AggregateSize *= VT->getNumElements();
    return AggregateSize;
  } else if (CurrentType->isSingleValueType()) {
    return AggregateSize;
  } else {
    return None;
  }
} while (true);
7292}

7294static Optional<unsigned> getOperandIndex(Instruction *InsertInst,
                                        unsigned OperandOffset) {
unsigned OperandIndex = OperandOffset;
if (auto *IE = dyn_cast<InsertElementInst>(InsertInst)) {
  if (auto *CI = dyn_cast<ConstantInt>(IE->getOperand(2))) {
    auto *VT = cast<FixedVectorType>(IE->getType());
    OperandIndex *= VT->getNumElements();
    OperandIndex += CI->getZExtValue();
    return OperandIndex;
  }
  return None;
}

auto *IV = cast<InsertValueInst>(InsertInst);
Type *CurrentType = IV->getType();
for (unsigned int Index : IV->indices()) {
  if (auto *ST = dyn_cast<StructType>(CurrentType)) {
    OperandIndex *= ST->getNumElements();
    CurrentType = ST->getElementType(Index);
  } else if (auto *AT = dyn_cast<ArrayType>(CurrentType)) {
    OperandIndex *= AT->getNumElements();
    CurrentType = AT->getElementType();
  } else {
    return None;
  }
  OperandIndex += Index;
}
return OperandIndex;
7322}

7324static bool findBuildAggregate_rec(Instruction *LastInsertInst,
                                 TargetTransformInfo *TTI,
                                 SmallVectorImpl<Value *> &BuildVectorOpds,
                                 SmallVectorImpl<Value *> &InsertElts,
                                 unsigned OperandOffset) {
do {
  Value *InsertedOperand = LastInsertInst->getOperand(1);
  Optional<unsigned> OperandIndex =
      getOperandIndex(LastInsertInst, OperandOffset);
  if (!OperandIndex)
    return false;
  if (isa<InsertElementInst>(InsertedOperand) ||
      isa<InsertValueInst>(InsertedOperand)) {
    if (!findBuildAggregate_rec(cast<Instruction>(InsertedOperand), TTI,
                                BuildVectorOpds, InsertElts, *OperandIndex))
      return false;
  } else {
    BuildVectorOpds[*OperandIndex] = InsertedOperand;
    InsertElts[*OperandIndex] = LastInsertInst;
  }
  if (isa<UndefValue>(LastInsertInst->getOperand(0)))
    return true;
  LastInsertInst = dyn_cast<Instruction>(LastInsertInst->getOperand(0));
} while (LastInsertInst != nullptr &&
         (isa<InsertValueInst>(LastInsertInst) ||
          isa<InsertElementInst>(LastInsertInst)) &&
         LastInsertInst->hasOneUse());
return false;
7352}

7354/// Recognize construction of vectors like
7355///  %ra = insertelement <4 x float> poison, float %s0, i32 0
7356///  %rb = insertelement <4 x float> %ra, float %s1, i32 1
7357///  %rc = insertelement <4 x float> %rb, float %s2, i32 2
7358///  %rd = insertelement <4 x float> %rc, float %s3, i32 3
7359///  starting from the last insertelement or insertvalue instruction.
7360///
7361/// Also recognize homogeneous aggregates like {<2 x float>, <2 x float>},
7362/// {{float, float}, {float, float}}, [2 x {float, float}] and so on.
7363/// See llvm/test/Transforms/SLPVectorizer/X86/pr42022.ll for examples.
7364///
7365/// Assume LastInsertInst is of InsertElementInst or InsertValueInst type.
7366///
7367/// \return true if it matches.
7368static bool findBuildAggregate(Instruction *LastInsertInst,
                             TargetTransformInfo *TTI,
                             SmallVectorImpl<Value *> &BuildVectorOpds,
                             SmallVectorImpl<Value *> &InsertElts) {

assert((isa<InsertElementInst>(LastInsertInst) ||(((isa<InsertElementInst>(LastInsertInst) || isa<InsertValueInst
>(LastInsertInst)) && "Expected insertelement or insertvalue instruction!"
) ? static_cast<void> (0) : __assert_fail ("(isa<InsertElementInst>(LastInsertInst) || isa<InsertValueInst>(LastInsertInst)) && \"Expected insertelement or insertvalue instruction!\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 7375, __PRETTY_FUNCTION__))
        isa<InsertValueInst>(LastInsertInst)) &&(((isa<InsertElementInst>(LastInsertInst) || isa<InsertValueInst
>(LastInsertInst)) && "Expected insertelement or insertvalue instruction!"
) ? static_cast<void> (0) : __assert_fail ("(isa<InsertElementInst>(LastInsertInst) || isa<InsertValueInst>(LastInsertInst)) && \"Expected insertelement or insertvalue instruction!\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 7375, __PRETTY_FUNCTION__))
       "Expected insertelement or insertvalue instruction!")(((isa<InsertElementInst>(LastInsertInst) || isa<InsertValueInst
>(LastInsertInst)) && "Expected insertelement or insertvalue instruction!"
) ? static_cast<void> (0) : __assert_fail ("(isa<InsertElementInst>(LastInsertInst) || isa<InsertValueInst>(LastInsertInst)) && \"Expected insertelement or insertvalue instruction!\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 7375, __PRETTY_FUNCTION__));

assert((BuildVectorOpds.empty() && InsertElts.empty()) &&(((BuildVectorOpds.empty() && InsertElts.empty()) &&
 "Expected empty result vectors!") ? static_cast<void> (
0) : __assert_fail ("(BuildVectorOpds.empty() && InsertElts.empty()) && \"Expected empty result vectors!\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 7378, __PRETTY_FUNCTION__))
       "Expected empty result vectors!")(((BuildVectorOpds.empty() && InsertElts.empty()) &&
 "Expected empty result vectors!") ? static_cast<void> (
0) : __assert_fail ("(BuildVectorOpds.empty() && InsertElts.empty()) && \"Expected empty result vectors!\""
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 7378, __PRETTY_FUNCTION__));

Optional<unsigned> AggregateSize = getAggregateSize(LastInsertInst);
if (!AggregateSize)
  return false;
BuildVectorOpds.resize(*AggregateSize);
InsertElts.resize(*AggregateSize);

if (findBuildAggregate_rec(LastInsertInst, TTI, BuildVectorOpds, InsertElts,
                           0)) {
  llvm::erase_value(BuildVectorOpds, nullptr);
  llvm::erase_value(InsertElts, nullptr);
  if (BuildVectorOpds.size() >= 2)
    return true;
}

return false;
7395}

7397static bool PhiTypeSorterFunc(Value *V, Value *V2) {
return V->getType() < V2->getType();
7399}

7401/// Try and get a reduction value from a phi node.
7402///
7403/// Given a phi node \p P in a block \p ParentBB, consider possible reductions
7404/// if they come from either \p ParentBB or a containing loop latch.
7405///
7406/// \returns A candidate reduction value if possible, or \code nullptr \endcode
7407/// if not possible.
7408static Value *getReductionValue(const DominatorTree *DT, PHINode *P,
                              BasicBlock *ParentBB, LoopInfo *LI) {
// There are situations where the reduction value is not dominated by the
// reduction phi. Vectorizing such cases has been reported to cause
// miscompiles. See PR25787.
auto DominatedReduxValue = [&](Value *R) {
  return isa<Instruction>(R) &&
         DT->dominates(P->getParent(), cast<Instruction>(R)->getParent());
};

Value *Rdx = nullptr;

// Return the incoming value if it comes from the same BB as the phi node.
if (P->getIncomingBlock(0) == ParentBB) {
  Rdx = P->getIncomingValue(0);
} else if (P->getIncomingBlock(1) == ParentBB) {
  Rdx = P->getIncomingValue(1);
}

if (Rdx && DominatedReduxValue(Rdx))
  return Rdx;

// Otherwise, check whether we have a loop latch to look at.
Loop *BBL = LI->getLoopFor(ParentBB);
if (!BBL)
  return nullptr;
BasicBlock *BBLatch = BBL->getLoopLatch();
if (!BBLatch)
  return nullptr;

// There is a loop latch, return the incoming value if it comes from
// that. This reduction pattern occasionally turns up.
if (P->getIncomingBlock(0) == BBLatch) {
  Rdx = P->getIncomingValue(0);
} else if (P->getIncomingBlock(1) == BBLatch) {
  Rdx = P->getIncomingValue(1);
}

if (Rdx && DominatedReduxValue(Rdx))
  return Rdx;

return nullptr;
7450}

7452static bool matchRdxBop(Instruction *I, Value *&V0, Value *&V1) {
if (match(I, m_BinOp(m_Value(V0), m_Value(V1))))
  return true;
if (match(I, m_Intrinsic<Intrinsic::maxnum>(m_Value(V0), m_Value(V1))))
  return true;
if (match(I, m_Intrinsic<Intrinsic::minnum>(m_Value(V0), m_Value(V1))))
  return true;
if (match(I, m_Intrinsic<Intrinsic::smax>(m_Value(V0), m_Value(V1))))
  return true;
if (match(I, m_Intrinsic<Intrinsic::smin>(m_Value(V0), m_Value(V1))))
  return true;
if (match(I, m_Intrinsic<Intrinsic::umax>(m_Value(V0), m_Value(V1))))
  return true;
if (match(I, m_Intrinsic<Intrinsic::umin>(m_Value(V0), m_Value(V1))))
  return true;
return false;
7468}

7470/// Attempt to reduce a horizontal reduction.
7471/// If it is legal to match a horizontal reduction feeding the phi node \a P
7472/// with reduction operators \a Root (or one of its operands) in a basic block
7473/// \a BB, then check if it can be done. If horizontal reduction is not found
7474/// and root instruction is a binary operation, vectorization of the operands is
7475/// attempted.
7476/// \returns true if a horizontal reduction was matched and reduced or operands
7477/// of one of the binary instruction were vectorized.
7478/// \returns false if a horizontal reduction was not matched (or not possible)
7479/// or no vectorization of any binary operation feeding \a Root instruction was
7480/// performed.
7481static bool tryToVectorizeHorReductionOrInstOperands(
  PHINode *P, Instruction *Root, BasicBlock *BB, BoUpSLP &R,
  TargetTransformInfo *TTI,
  const function_ref<bool(Instruction *, BoUpSLP &)> Vectorize) {
if (!ShouldVectorizeHor)
  return false;

if (!Root)
  return false;

if (Root->getParent() != BB || isa<PHINode>(Root))
  return false;
// Start analysis starting from Root instruction. If horizontal reduction is
// found, try to vectorize it. If it is not a horizontal reduction or
// vectorization is not possible or not effective, and currently analyzed
// instruction is a binary operation, try to vectorize the operands, using
// pre-order DFS traversal order. If the operands were not vectorized, repeat
// the same procedure considering each operand as a possible root of the
// horizontal reduction.
// Interrupt the process if the Root instruction itself was vectorized or all
// sub-trees not higher that RecursionMaxDepth were analyzed/vectorized.
// Skip the analysis of CmpInsts.Compiler implements postanalysis of the
// CmpInsts so we can skip extra attempts in
// tryToVectorizeHorReductionOrInstOperands and save compile time.
SmallVector<std::pair<Instruction *, unsigned>, 8> Stack(1, {Root, 0});
SmallPtrSet<Value *, 8> VisitedInstrs;
bool Res = false;
while (!Stack.empty()) {
  Instruction *Inst;
  unsigned Level;
  std::tie(Inst, Level) = Stack.pop_back_val();
  Value *B0, *B1;
  bool IsBinop = matchRdxBop(Inst, B0, B1);
  bool IsSelect = match(Inst, m_Select(m_Value(), m_Value(), m_Value()));
  if (IsBinop || IsSelect) {
    HorizontalReduction HorRdx;
    if (HorRdx.matchAssociativeReduction(P, Inst)) {
      if (HorRdx.tryToReduce(R, TTI)) {
        Res = true;
        // Set P to nullptr to avoid re-analysis of phi node in
        // matchAssociativeReduction function unless this is the root node.
        P = nullptr;
        continue;
      }
    }
    if (P && IsBinop) {
      Inst = dyn_cast<Instruction>(B0);
      if (Inst == P)
        Inst = dyn_cast<Instruction>(B1);
      if (!Inst) {
        // Set P to nullptr to avoid re-analysis of phi node in
        // matchAssociativeReduction function unless this is the root node.
        P = nullptr;
        continue;
      }
    }
  }
  // Set P to nullptr to avoid re-analysis of phi node in
  // matchAssociativeReduction function unless this is the root node.
  P = nullptr;
  // Do not try to vectorize CmpInst operands, this is done separately.
  if (!isa<CmpInst>(Inst) && Vectorize(Inst, R)) {
    Res = true;
    continue;
  }

  // Try to vectorize operands.
  // Continue analysis for the instruction from the same basic block only to
  // save compile time.
  if (++Level < RecursionMaxDepth)
    for (auto *Op : Inst->operand_values())
      if (VisitedInstrs.insert(Op).second)
        if (auto *I = dyn_cast<Instruction>(Op))
          // Do not try to vectorize CmpInst operands,  this is done
          // separately.
          if (!isa<PHINode>(I) && !isa<CmpInst>(I) && !R.isDeleted(I) &&
              I->getParent() == BB)
            Stack.emplace_back(I, Level);
}
return Res;
7561}

7563bool SLPVectorizerPass::vectorizeRootInstruction(PHINode *P, Value *V,
                                               BasicBlock *BB, BoUpSLP &R,
                                               TargetTransformInfo *TTI) {
auto *I = dyn_cast_or_null<Instruction>(V);
if (!I)
  return false;

if (!isa<BinaryOperator>(I))
  P = nullptr;
// Try to match and vectorize a horizontal reduction.
auto &&ExtraVectorization = [this](Instruction *I, BoUpSLP &R) -> bool {
  return tryToVectorize(I, R);
};
return tryToVectorizeHorReductionOrInstOperands(P, I, BB, R, TTI,
                                                ExtraVectorization);
7578}

7580bool SLPVectorizerPass::vectorizeInsertValueInst(InsertValueInst *IVI,
                                               BasicBlock *BB, BoUpSLP &R) {
const DataLayout &DL = BB->getModule()->getDataLayout();
if (!R.canMapToVector(IVI->getType(), DL))
  return false;

SmallVector<Value *, 16> BuildVectorOpds;
SmallVector<Value *, 16> BuildVectorInsts;
if (!findBuildAggregate(IVI, TTI, BuildVectorOpds, BuildVectorInsts))
  return false;

LLVM_DEBUG(dbgs() << "SLP: array mappable to vector: " << *IVI << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: array mappable to vector: " <<
 *IVI << "\n"; } } while (false);
// Aggregate value is unlikely to be processed in vector register, we need to
// extract scalars into scalar registers, so NeedExtraction is set true.
return tryToVectorizeList(BuildVectorOpds, R, /*AllowReorder=*/false,
                          BuildVectorInsts);
7596}

7598bool SLPVectorizerPass::vectorizeInsertElementInst(InsertElementInst *IEI,
                                                 BasicBlock *BB, BoUpSLP &R) {
SmallVector<Value *, 16> BuildVectorInsts;
SmallVector<Value *, 16> BuildVectorOpds;
SmallVector<int> Mask;
if (!findBuildAggregate(IEI, TTI, BuildVectorOpds, BuildVectorInsts) ||
    (llvm::all_of(BuildVectorOpds,
                  [](Value *V) { return isa<ExtractElementInst>(V); }) &&
     isShuffle(BuildVectorOpds, Mask)))
  return false;

// Vectorize starting with the build vector operands ignoring the BuildVector
// instructions for the purpose of scheduling and user extraction.
return tryToVectorizeList(BuildVectorOpds, R, /*AllowReorder=*/false,
                          BuildVectorInsts);
7613}

7615bool SLPVectorizerPass::vectorizeSimpleInstructions(
  SmallVectorImpl<Instruction *> &Instructions, BasicBlock *BB, BoUpSLP &R,
  bool AtTerminator) {
bool OpsChanged = false;
SmallVector<Instruction *, 4> PostponedCmps;
for (auto *I : reverse(Instructions)) {
  if (R.isDeleted(I))
    continue;
  if (auto *LastInsertValue = dyn_cast<InsertValueInst>(I))
    OpsChanged |= vectorizeInsertValueInst(LastInsertValue, BB, R);
  else if (auto *LastInsertElem = dyn_cast<InsertElementInst>(I))
    OpsChanged |= vectorizeInsertElementInst(LastInsertElem, BB, R);
  else if (isa<CmpInst>(I))
    PostponedCmps.push_back(I);
}
if (AtTerminator) {
  // Try to find reductions first.
  for (Instruction *I : PostponedCmps) {
    if (R.isDeleted(I))
      continue;
    for (Value *Op : I->operands())
      OpsChanged |= vectorizeRootInstruction(nullptr, Op, BB, R, TTI);
  }
  // Try to vectorize operands as vector bundles.
  for (Instruction *I : PostponedCmps) {
    if (R.isDeleted(I))
      continue;
    OpsChanged |= tryToVectorize(I, R);
  }
  Instructions.clear();
} else {
  // Insert in reverse order since the PostponedCmps vector was filled in
  // reverse order.
  Instructions.assign(PostponedCmps.rbegin(), PostponedCmps.rend());
}
return OpsChanged;
7651}

7653bool SLPVectorizerPass::vectorizeChainsInBlock(BasicBlock *BB, BoUpSLP &R) {
bool Changed = false;
SmallVector<Value *, 4> Incoming;
SmallPtrSet<Value *, 16> VisitedInstrs;

bool HaveVectorizedPhiNodes = true;
while (HaveVectorizedPhiNodes) {
  HaveVectorizedPhiNodes = false;

  // Collect the incoming values from the PHIs.
  Incoming.clear();
  for (Instruction &I : *BB) {
    PHINode *P = dyn_cast<PHINode>(&I);
    if (!P)
      break;

    if (!VisitedInstrs.count(P) && !R.isDeleted(P))
      Incoming.push_back(P);
  }

  // Sort by type.
  llvm::stable_sort(Incoming, PhiTypeSorterFunc);

  // Try to vectorize elements base on their type.
  for (SmallVector<Value *, 4>::iterator IncIt = Incoming.begin(),
                                         E = Incoming.end();
       IncIt != E;) {

    // Look for the next elements with the same type.
    SmallVector<Value *, 4>::iterator SameTypeIt = IncIt;
    while (SameTypeIt != E &&
           (*SameTypeIt)->getType() == (*IncIt)->getType()) {
      VisitedInstrs.insert(*SameTypeIt);
      ++SameTypeIt;
    }

    // Try to vectorize them.
    unsigned NumElts = (SameTypeIt - IncIt);
    LLVM_DEBUG(dbgs() << "SLP: Trying to vectorize starting at PHIs ("do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Trying to vectorize starting at PHIs ("
 << NumElts << ")\n"; } } while (false)
                      << NumElts << ")\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Trying to vectorize starting at PHIs ("
 << NumElts << ")\n"; } } while (false);
    // The order in which the phi nodes appear in the program does not matter.
    // So allow tryToVectorizeList to reorder them if it is beneficial. This
    // is done when there are exactly two elements since tryToVectorizeList
    // asserts that there are only two values when AllowReorder is true.
    bool AllowReorder = NumElts == 2;
    if (NumElts > 1 &&
        tryToVectorizeList(makeArrayRef(IncIt, NumElts), R, AllowReorder)) {
      // Success start over because instructions might have been changed.
      HaveVectorizedPhiNodes = true;
      Changed = true;
      break;
    }

    // Start over at the next instruction of a different type (or the end).
    IncIt = SameTypeIt;
  }
}

VisitedInstrs.clear();

SmallVector<Instruction *, 8> PostProcessInstructions;
SmallDenseSet<Instruction *, 4> KeyNodes;
for (BasicBlock::iterator it = BB->begin(), e = BB->end(); it != e; ++it) {
  // Skip instructions with scalable type. The num of elements is unknown at
  // compile-time for scalable type.
  if (isa<ScalableVectorType>(it->getType()))
    continue;

  // Skip instructions marked for the deletion.
  if (R.isDeleted(&*it))
    continue;
  // We may go through BB multiple times so skip the one we have checked.
  if (!VisitedInstrs.insert(&*it).second) {
    if (it->use_empty() && KeyNodes.contains(&*it) &&
        vectorizeSimpleInstructions(PostProcessInstructions, BB, R,
                                    it->isTerminator())) {
      // We would like to start over since some instructions are deleted
      // and the iterator may become invalid value.
      Changed = true;
      it = BB->begin();
      e = BB->end();
    }
    continue;
  }

  if (isa<DbgInfoIntrinsic>(it))
    continue;

  // Try to vectorize reductions that use PHINodes.
  if (PHINode *P = dyn_cast<PHINode>(it)) {
    // Check that the PHI is a reduction PHI.
    if (P->getNumIncomingValues() == 2) {
      // Try to match and vectorize a horizontal reduction.
      if (vectorizeRootInstruction(P, getReductionValue(DT, P, BB, LI), BB, R,
                                   TTI)) {
        Changed = true;
        it = BB->begin();
        e = BB->end();
        continue;
      }
    }
    // Try to vectorize the incoming values of the PHI, to catch reductions
    // that feed into PHIs.
    for (unsigned I = 0, E = P->getNumIncomingValues(); I != E; I++) {
      // Skip if the incoming block is the current BB for now. Also, bypass
      // unreachable IR for efficiency and to avoid crashing.
      // TODO: Collect the skipped incoming values and try to vectorize them
      // after processing BB.
      if (BB == P->getIncomingBlock(I) ||
          !DT->isReachableFromEntry(P->getIncomingBlock(I)))
        continue;

      Changed |= vectorizeRootInstruction(nullptr, P->getIncomingValue(I),
                                          P->getIncomingBlock(I), R, TTI);
    }
    continue;
  }

  // Ran into an instruction without users, like terminator, or function call
  // with ignored return value, store. Ignore unused instructions (basing on
  // instruction type, except for CallInst and InvokeInst).
  if (it->use_empty() && (it->getType()->isVoidTy() || isa<CallInst>(it) ||
                          isa<InvokeInst>(it))) {
    KeyNodes.insert(&*it);
    bool OpsChanged = false;
    if (ShouldStartVectorizeHorAtStore || !isa<StoreInst>(it)) {
      for (auto *V : it->operand_values()) {
        // Try to match and vectorize a horizontal reduction.
        OpsChanged |= vectorizeRootInstruction(nullptr, V, BB, R, TTI);
      }
    }
    // Start vectorization of post-process list of instructions from the
    // top-tree instructions to try to vectorize as many instructions as
    // possible.
    OpsChanged |= vectorizeSimpleInstructions(PostProcessInstructions, BB, R,
                                              it->isTerminator());
    if (OpsChanged) {
      // We would like to start over since some instructions are deleted
      // and the iterator may become invalid value.
      Changed = true;
      it = BB->begin();
      e = BB->end();
      continue;
    }
  }

  if (isa<InsertElementInst>(it) || isa<CmpInst>(it) ||
      isa<InsertValueInst>(it))
    PostProcessInstructions.push_back(&*it);
}

return Changed;
7805}

7807bool SLPVectorizerPass::vectorizeGEPIndices(BasicBlock *BB, BoUpSLP &R) {
auto Changed = false;
for (auto &Entry : GEPs) {
  // If the getelementptr list has fewer than two elements, there's nothing
  // to do.
  if (Entry.second.size() < 2)
    continue;

  LLVM_DEBUG(dbgs() << "SLP: Analyzing a getelementptr list of length "do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Analyzing a getelementptr list of length "
 << Entry.second.size() << ".\n"; } } while (false
)
                    << Entry.second.size() << ".\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Analyzing a getelementptr list of length "
 << Entry.second.size() << ".\n"; } } while (false
);

  // Process the GEP list in chunks suitable for the target's supported
  // vector size. If a vector register can't hold 1 element, we are done. We
  // are trying to vectorize the index computations, so the maximum number of
  // elements is based on the size of the index expression, rather than the
  // size of the GEP itself (the target's pointer size).
  unsigned MaxVecRegSize = R.getMaxVecRegSize();
  unsigned EltSize = R.getVectorElementSize(*Entry.second[0]->idx_begin());
  if (MaxVecRegSize < EltSize)
    continue;

  unsigned MaxElts = MaxVecRegSize / EltSize;
  for (unsigned BI = 0, BE = Entry.second.size(); BI < BE; BI += MaxElts) {
    auto Len = std::min<unsigned>(BE - BI, MaxElts);
    ArrayRef<GetElementPtrInst *> GEPList(&Entry.second[BI], Len);

    // Initialize a set a candidate getelementptrs. Note that we use a
    // SetVector here to preserve program order. If the index computations
    // are vectorizable and begin with loads, we want to minimize the chance
    // of having to reorder them later.
    SetVector<Value *> Candidates(GEPList.begin(), GEPList.end());

    // Some of the candidates may have already been vectorized after we
    // initially collected them. If so, they are marked as deleted, so remove
    // them from the set of candidates.
    Candidates.remove_if(
        [&R](Value *I) { return R.isDeleted(cast<Instruction>(I)); });

    // Remove from the set of candidates all pairs of getelementptrs with
    // constant differences. Such getelementptrs are likely not good
    // candidates for vectorization in a bottom-up phase since one can be
    // computed from the other. We also ensure all candidate getelementptr
    // indices are unique.
    for (int I = 0, E = GEPList.size(); I < E && Candidates.size() > 1; ++I) {
      auto *GEPI = GEPList[I];
      if (!Candidates.count(GEPI))
        continue;
      auto *SCEVI = SE->getSCEV(GEPList[I]);
      for (int J = I + 1; J < E && Candidates.size() > 1; ++J) {
        auto *GEPJ = GEPList[J];
        auto *SCEVJ = SE->getSCEV(GEPList[J]);
        if (isa<SCEVConstant>(SE->getMinusSCEV(SCEVI, SCEVJ))) {
          Candidates.remove(GEPI);
          Candidates.remove(GEPJ);
        } else if (GEPI->idx_begin()->get() == GEPJ->idx_begin()->get()) {
          Candidates.remove(GEPJ);
        }
      }
    }

    // We break out of the above computation as soon as we know there are
    // fewer than two candidates remaining.
    if (Candidates.size() < 2)
      continue;

    // Add the single, non-constant index of each candidate to the bundle. We
    // ensured the indices met these constraints when we originally collected
    // the getelementptrs.
    SmallVector<Value *, 16> Bundle(Candidates.size());
    auto BundleIndex = 0u;
    for (auto *V : Candidates) {
      auto *GEP = cast<GetElementPtrInst>(V);
      auto *GEPIdx = GEP->idx_begin()->get();
      assert(GEP->getNumIndices() == 1 || !isa<Constant>(GEPIdx))((GEP->getNumIndices() == 1 || !isa<Constant>(GEPIdx
)) ? static_cast<void> (0) : __assert_fail ("GEP->getNumIndices() == 1 || !isa<Constant>(GEPIdx)"
, "/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp"
, 7880, __PRETTY_FUNCTION__));
      Bundle[BundleIndex++] = GEPIdx;
    }

    // Try and vectorize the indices. We are currently only interested in
    // gather-like cases of the form:
    //
    // ... = g[a[0] - b[0]] + g[a[1] - b[1]] + ...
    //
    // where the loads of "a", the loads of "b", and the subtractions can be
    // performed in parallel. It's likely that detecting this pattern in a
    // bottom-up phase will be simpler and less costly than building a
    // full-blown top-down phase beginning at the consecutive loads.
    Changed |= tryToVectorizeList(Bundle, R);
  }
}
return Changed;
7897}

7899bool SLPVectorizerPass::vectorizeStoreChains(BoUpSLP &R) {
bool Changed = false;
// Attempt to sort and vectorize each of the store-groups.
for (StoreListMap::iterator it = Stores.begin(), e = Stores.end(); it != e;
     ++it) {
  if (it->second.size() < 2)
    continue;

  LLVM_DEBUG(dbgs() << "SLP: Analyzing a store chain of length "do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Analyzing a store chain of length "
 << it->second.size() << ".\n"; } } while (false
)
                    << it->second.size() << ".\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("SLP")) { dbgs() << "SLP: Analyzing a store chain of length "
 << it->second.size() << ".\n"; } } while (false
);

  Changed |= vectorizeStores(it->second, R);
}
return Changed;
7913}

7915char SLPVectorizer::ID = 0;

7917static const char lv_name[] = "SLP Vectorizer";

7919INITIALIZE_PASS_BEGIN(SLPVectorizer, SV_NAME, lv_name, false, false)static void *initializeSLPVectorizerPassOnce(PassRegistry &
Registry) {
7920INITIALIZE_PASS_DEPENDENCY(AAResultsWrapperPass)initializeAAResultsWrapperPassPass(Registry);
7921INITIALIZE_PASS_DEPENDENCY(TargetTransformInfoWrapperPass)initializeTargetTransformInfoWrapperPassPass(Registry);
7922INITIALIZE_PASS_DEPENDENCY(AssumptionCacheTracker)initializeAssumptionCacheTrackerPass(Registry);
7923INITIALIZE_PASS_DEPENDENCY(ScalarEvolutionWrapperPass)initializeScalarEvolutionWrapperPassPass(Registry);
7924INITIALIZE_PASS_DEPENDENCY(LoopSimplify)initializeLoopSimplifyPass(Registry);
7925INITIALIZE_PASS_DEPENDENCY(DemandedBitsWrapperPass)initializeDemandedBitsWrapperPassPass(Registry);
7926INITIALIZE_PASS_DEPENDENCY(OptimizationRemarkEmitterWrapperPass)initializeOptimizationRemarkEmitterWrapperPassPass(Registry);
7927INITIALIZE_PASS_DEPENDENCY(InjectTLIMappingsLegacy)initializeInjectTLIMappingsLegacyPass(Registry);
7928INITIALIZE_PASS_END(SLPVectorizer, SV_NAME, lv_name, false, false)PassInfo *PI = new PassInfo( lv_name, "slp-vectorizer", &
SLPVectorizer::ID, PassInfo::NormalCtor_t(callDefaultCtor<
SLPVectorizer>), false, false); Registry.registerPass(*PI,
 true); return PI; } static llvm::once_flag InitializeSLPVectorizerPassFlag
; void llvm::initializeSLPVectorizerPass(PassRegistry &Registry
) { llvm::call_once(InitializeSLPVectorizerPassFlag, initializeSLPVectorizerPassOnce
, std::ref(Registry)); }

7930Pass *llvm::createSLPVectorizerPass() { return new SLPVectorizer(); }

←

/build/llvm-toolchain-snapshot-13~++20210413100635+64c24f493e5f/llvm/include/llvm/Analysis/IVDescriptors.h

1//===- llvm/Analysis/IVDescriptors.h - IndVar Descriptors -------*- C++ -*-===//
2//
3// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
4// See https://llvm.org/LICENSE.txt for license information.
5// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
6//
7//===----------------------------------------------------------------------===//
8//
9// This file "describes" induction and recurrence variables.
10//
11//===----------------------------------------------------------------------===//

13#ifndef LLVM_ANALYSIS_IVDESCRIPTORS_H
14#define LLVM_ANALYSIS_IVDESCRIPTORS_H

16#include "llvm/ADT/DenseMap.h"
17#include "llvm/ADT/SmallPtrSet.h"
18#include "llvm/ADT/SmallVector.h"
19#include "llvm/ADT/StringRef.h"
20#include "llvm/IR/InstrTypes.h"
21#include "llvm/IR/Instruction.h"
22#include "llvm/IR/Operator.h"
23#include "llvm/IR/ValueHandle.h"
24#include "llvm/Support/Casting.h"

26namespace llvm {

28class DemandedBits;
29class AssumptionCache;
30class Loop;
31class PredicatedScalarEvolution;
32class ScalarEvolution;
33class SCEV;
34class DominatorTree;

36/// These are the kinds of recurrences that we support.
37enum class RecurKind {
None,   ///< Not a recurrence.
Add,    ///< Sum of integers.
Mul,    ///< Product of integers.
Or,     ///< Bitwise or logical OR of integers.
And,    ///< Bitwise or logical AND of integers.
Xor,    ///< Bitwise or logical XOR of integers.
SMin,   ///< Signed integer min implemented in terms of select(cmp()).
SMax,   ///< Signed integer max implemented in terms of select(cmp()).
UMin,   ///< Unisgned integer min implemented in terms of select(cmp()).
UMax,   ///< Unsigned integer max implemented in terms of select(cmp()).
FAdd,   ///< Sum of floats.
FMul,   ///< Product of floats.
FMin,   ///< FP min implemented in terms of select(cmp()).
FMax    ///< FP max implemented in terms of select(cmp()).
52};

54/// The RecurrenceDescriptor is used to identify recurrences variables in a
55/// loop. Reduction is a special case of recurrence that has uses of the
56/// recurrence variable outside the loop. The method isReductionPHI identifies
57/// reductions that are basic recurrences.
58///
59/// Basic recurrences are defined as the summation, product, OR, AND, XOR, min,
60/// or max of a set of terms. For example: for(i=0; i<n; i++) { total +=
61/// array[i]; } is a summation of array elements. Basic recurrences are a
62/// special case of chains of recurrences (CR). See ScalarEvolution for CR
63/// references.

65/// This struct holds information about recurrence variables.
66class RecurrenceDescriptor {
67public:
RecurrenceDescriptor() = default;

RecurrenceDescriptor(Value *Start, Instruction *Exit, RecurKind K,
                     FastMathFlags FMF, Instruction *ExactFP, Type *RT,
                     bool Signed, bool Ordered,
                     SmallPtrSetImpl<Instruction *> &CI)
    : StartValue(Start), LoopExitInstr(Exit), Kind(K), FMF(FMF),
      ExactFPMathInst(ExactFP), RecurrenceType(RT), IsSigned(Signed),
      IsOrdered(Ordered) {
  CastInsts.insert(CI.begin(), CI.end());
}

/// This POD struct holds information about a potential recurrence operation.
class InstDesc {
public:
  InstDesc(bool IsRecur, Instruction *I, Instruction *ExactFP = nullptr)
      : IsRecurrence(IsRecur), PatternLastInst(I),
        RecKind(RecurKind::None), ExactFPMathInst(ExactFP) {}

  InstDesc(Instruction *I, RecurKind K, Instruction *ExactFP = nullptr)
      : IsRecurrence(true), PatternLastInst(I), RecKind(K),
        ExactFPMathInst(ExactFP) {}

  bool isRecurrence() const { return IsRecurrence; }

  bool needsExactFPMath() const { return ExactFPMathInst != nullptr; }

  Instruction *getExactFPMathInst() const { return ExactFPMathInst; }

  RecurKind getRecKind() const { return RecKind; }

  Instruction *getPatternInst() const { return PatternLastInst; }

private:
  // Is this instruction a recurrence candidate.
  bool IsRecurrence;
  // The last instruction in a min/max pattern (select of the select(icmp())
  // pattern), or the current recurrence instruction otherwise.
  Instruction *PatternLastInst;
  // If this is a min/max pattern.
  RecurKind RecKind;
  // Recurrence does not allow floating-point reassociation.
  Instruction *ExactFPMathInst;
};

/// Returns a struct describing if the instruction 'I' can be a recurrence
/// variable of type 'Kind'. If the recurrence is a min/max pattern of
/// select(icmp()) this function advances the instruction pointer 'I' from the
/// compare instruction to the select instruction and stores this pointer in
/// 'PatternLastInst' member of the returned struct.
static InstDesc isRecurrenceInstr(Instruction *I, RecurKind Kind,
                                  InstDesc &Prev, FastMathFlags FMF);

/// Returns true if instruction I has multiple uses in Insts
static bool hasMultipleUsesOf(Instruction *I,
                              SmallPtrSetImpl<Instruction *> &Insts,
                              unsigned MaxNumUses);

/// Returns true if all uses of the instruction I is within the Set.
static bool areAllUsesIn(Instruction *I, SmallPtrSetImpl<Instruction *> &Set);

/// Returns a struct describing if the instruction is a
/// Select(ICmp(X, Y), X, Y) instruction pattern corresponding to a min(X, Y)
/// or max(X, Y). \p Prev specifies the description of an already processed
/// select instruction, so its corresponding cmp can be matched to it.
static InstDesc isMinMaxSelectCmpPattern(Instruction *I,
                                         const InstDesc &Prev);

/// Returns a struct describing if the instruction is a
/// Select(FCmp(X, Y), (Z = X op PHINode), PHINode) instruction pattern.
static InstDesc isConditionalRdxPattern(RecurKind Kind, Instruction *I);

/// Returns identity corresponding to the RecurrenceKind.
static Constant *getRecurrenceIdentity(RecurKind K, Type *Tp,
                                       FastMathFlags FMF);

/// Returns the opcode corresponding to the RecurrenceKind.
static unsigned getOpcode(RecurKind Kind);

/// Returns true if Phi is a reduction of type Kind and adds it to the
/// RecurrenceDescriptor. If either \p DB is non-null or \p AC and \p DT are
/// non-null, the minimal bit width needed to compute the reduction will be
/// computed.
static bool AddReductionVar(PHINode *Phi, RecurKind Kind, Loop *TheLoop,
                            FastMathFlags FMF,
                            RecurrenceDescriptor &RedDes,
                            DemandedBits *DB = nullptr,
                            AssumptionCache *AC = nullptr,
                            DominatorTree *DT = nullptr);

/// Returns true if Phi is a reduction in TheLoop. The RecurrenceDescriptor
/// is returned in RedDes. If either \p DB is non-null or \p AC and \p DT are
/// non-null, the minimal bit width needed to compute the reduction will be
/// computed.
static bool isReductionPHI(PHINode *Phi, Loop *TheLoop,
                           RecurrenceDescriptor &RedDes,
                           DemandedBits *DB = nullptr,
                           AssumptionCache *AC = nullptr,
                           DominatorTree *DT = nullptr);

/// Returns true if Phi is a first-order recurrence. A first-order recurrence
/// is a non-reduction recurrence relation in which the value of the
/// recurrence in the current loop iteration equals a value defined in the
/// previous iteration. \p SinkAfter includes pairs of instructions where the
/// first will be rescheduled to appear after the second if/when the loop is
/// vectorized. It may be augmented with additional pairs if needed in order
/// to handle Phi as a first-order recurrence.
static bool
isFirstOrderRecurrence(PHINode *Phi, Loop *TheLoop,
                       DenseMap<Instruction *, Instruction *> &SinkAfter,
                       DominatorTree *DT);

RecurKind getRecurrenceKind() const { return Kind; }

unsigned getOpcode() const { return getOpcode(getRecurrenceKind()); }

FastMathFlags getFastMathFlags() const { return FMF; }

TrackingVH<Value> getRecurrenceStartValue() const { return StartValue; }

Instruction *getLoopExitInstr() const { return LoopExitInstr; }

/// Returns true if the recurrence has floating-point math that requires
/// precise (ordered) operations.
bool hasExactFPMath() const { return ExactFPMathInst != nullptr; }

/// Returns 1st non-reassociative FP instruction in the PHI node's use-chain.
Instruction *getExactFPMathInst() const { return ExactFPMathInst; }

/// Returns true if the recurrence kind is an integer kind.
static bool isIntegerRecurrenceKind(RecurKind Kind);

/// Returns true if the recurrence kind is a floating point kind.
static bool isFloatingPointRecurrenceKind(RecurKind Kind);

/// Returns true if the recurrence kind is an arithmetic kind.
static bool isArithmeticRecurrenceKind(RecurKind Kind);

/// Returns true if the recurrence kind is an integer min/max kind.
static bool isIntMinMaxRecurrenceKind(RecurKind Kind) {
  return Kind3.1
'Kind' is equal to UMin
1
'Kind' is equal to UMin
 == RecurKind::UMin || Kind == RecurKind::UMax ||
4
←
Returning the value 1, which participates in a condition later→
         Kind == RecurKind::SMin || Kind == RecurKind::SMax;
}

/// Returns true if the recurrence kind is a floating-point min/max kind.
static bool isFPMinMaxRecurrenceKind(RecurKind Kind) {
  return Kind == RecurKind::FMin || Kind == RecurKind::FMax;
}

/// Returns true if the recurrence kind is any min/max kind.
static bool isMinMaxRecurrenceKind(RecurKind Kind) {
  return isIntMinMaxRecurrenceKind(Kind) || isFPMinMaxRecurrenceKind(Kind);
}

/// Returns the type of the recurrence. This type can be narrower than the
/// actual type of the Phi if the recurrence has been type-promoted.
Type *getRecurrenceType() const { return RecurrenceType; }

/// Returns a reference to the instructions used for type-promoting the
/// recurrence.
const SmallPtrSet<Instruction *, 8> &getCastInsts() const { return CastInsts; }

/// Returns true if all source operands of the recurrence are SExtInsts.
bool isSigned() const { return IsSigned; }

/// Expose an ordered FP reduction to the instance users.
bool isOrdered() const { return IsOrdered; }

/// Attempts to find a chain of operations from Phi to LoopExitInst that can
/// be treated as a set of reductions instructions for in-loop reductions.
SmallVector<Instruction *, 4> getReductionOpChain(PHINode *Phi,
                                                  Loop *L) const;

241private:
// The starting value of the recurrence.
// It does not have to be zero!
TrackingVH<Value> StartValue;
// The instruction who's value is used outside the loop.
Instruction *LoopExitInstr = nullptr;
// The kind of the recurrence.
RecurKind Kind = RecurKind::None;
// The fast-math flags on the recurrent instructions.  We propagate these
// fast-math flags into the vectorized FP instructions we generate.
FastMathFlags FMF;
// First instance of non-reassociative floating-point in the PHI's use-chain.
Instruction *ExactFPMathInst = nullptr;
// The type of the recurrence.
Type *RecurrenceType = nullptr;
// True if all source operands of the recurrence are SExtInsts.
bool IsSigned = false;
// True if this recurrence can be treated as an in-order reduction.
// Currently only a non-reassociative FAdd can be considered in-order,
// if it is also the only FAdd in the PHI's use chain.
bool IsOrdered = false;
// Instructions used for type-promoting the recurrence.
SmallPtrSet<Instruction *, 8> CastInsts;
264};

266/// A struct for saving information about induction variables.
267class InductionDescriptor {
268public:
/// This enum represents the kinds of inductions that we support.
enum InductionKind {
  IK_NoInduction,  ///< Not an induction variable.
  IK_IntInduction, ///< Integer induction variable. Step = C.
  IK_PtrInduction, ///< Pointer induction var. Step = C / sizeof(elem).
  IK_FpInduction   ///< Floating point induction variable.
};

277public:
/// Default constructor - creates an invalid induction.
InductionDescriptor() = default;

Value *getStartValue() const { return StartValue; }
InductionKind getKind() const { return IK; }
const SCEV *getStep() const { return Step; }
BinaryOperator *getInductionBinOp() const { return InductionBinOp; }
ConstantInt *getConstIntStepValue() const;

/// Returns true if \p Phi is an induction in the loop \p L. If \p Phi is an
/// induction, the induction descriptor \p D will contain the data describing
/// this induction. If by some other means the caller has a better SCEV
/// expression for \p Phi than the one returned by the ScalarEvolution
/// analysis, it can be passed through \p Expr. If the def-use chain
/// associated with the phi includes casts (that we know we can ignore
/// under proper runtime checks), they are passed through \p CastsToIgnore.
static bool
isInductionPHI(PHINode *Phi, const Loop *L, ScalarEvolution *SE,
               InductionDescriptor &D, const SCEV *Expr = nullptr,
               SmallVectorImpl<Instruction *> *CastsToIgnore = nullptr);

/// Returns true if \p Phi is a floating point induction in the loop \p L.
/// If \p Phi is an induction, the induction descriptor \p D will contain
/// the data describing this induction.
static bool isFPInductionPHI(PHINode *Phi, const Loop *L, ScalarEvolution *SE,
                             InductionDescriptor &D);

/// Returns true if \p Phi is a loop \p L induction, in the context associated
/// with the run-time predicate of PSE. If \p Assume is true, this can add
/// further SCEV predicates to \p PSE in order to prove that \p Phi is an
/// induction.
/// If \p Phi is an induction, \p D will contain the data describing this
/// induction.
static bool isInductionPHI(PHINode *Phi, const Loop *L,
                           PredicatedScalarEvolution &PSE,
                           InductionDescriptor &D, bool Assume = false);

/// Returns floating-point induction operator that does not allow
/// reassociation (transforming the induction requires an override of normal
/// floating-point rules).
Instruction *getExactFPMathInst() {
  if (IK == IK_FpInduction && InductionBinOp &&
      !InductionBinOp->hasAllowReassoc())
    return InductionBinOp;
  return nullptr;
}

/// Returns binary opcode of the induction operator.
Instruction::BinaryOps getInductionOpcode() const {
  return InductionBinOp ? InductionBinOp->getOpcode()
                        : Instruction::BinaryOpsEnd;
}

/// Returns a reference to the type cast instructions in the induction
/// update chain, that are redundant when guarded with a runtime
/// SCEV overflow check.
const SmallVectorImpl<Instruction *> &getCastInsts() const {
  return RedundantCasts;
}

338private:
/// Private constructor - used by \c isInductionPHI.
InductionDescriptor(Value *Start, InductionKind K, const SCEV *Step,
                    BinaryOperator *InductionBinOp = nullptr,
                    SmallVectorImpl<Instruction *> *Casts = nullptr);

/// Start value.
TrackingVH<Value> StartValue;
/// Induction kind.
InductionKind IK = IK_NoInduction;
/// Step value.
const SCEV *Step = nullptr;
// Instruction that advances induction variable.
BinaryOperator *InductionBinOp = nullptr;
// Instructions used for type-casts of the induction variable,
// that are redundant when guarded with a runtime SCEV overflow check.
SmallVector<Instruction *, 2> RedundantCasts;
355};

357} // end namespace llvm

359#endif // LLVM_ANALYSIS_IVDESCRIPTORS_H