diff --git a/llvm/lib/Target/RISCV/RISCVInsertVSETVLI.cpp b/llvm/lib/Target/RISCV/RISCVInsertVSETVLI.cpp --- a/llvm/lib/Target/RISCV/RISCVInsertVSETVLI.cpp +++ b/llvm/lib/Target/RISCV/RISCVInsertVSETVLI.cpp @@ -334,6 +334,10 @@ return false; } + bool operator!=(const VSETVLIInfo &Other) const { + return !(*this == Other); + } + // Calculate the VSETVLIInfo visible to a block assuming this and Other are // both predecessors. VSETVLIInfo intersect(const VSETVLIInfo &Other) const { @@ -1096,6 +1100,17 @@ CurInfo = VSETVLIInfo::getUnknown(); PrevVSETVLIMI = nullptr; } + + // If we reach the end of the block and our current info doesn't match the + // expected info, insert a vsetvli to correct. + if (MI.isTerminator()) { + const VSETVLIInfo &ExitInfo = BlockInfo[MBB.getNumber()].Exit; + if (CurInfo.isValid() && ExitInfo.isValid() && !ExitInfo.isUnknown() && + CurInfo != ExitInfo) { + insertVSETVLI(MBB, MI, ExitInfo, CurInfo); + CurInfo = ExitInfo; + } + } } } diff --git a/llvm/test/CodeGen/RISCV/rvv/vsetvli-insert-crossbb.mir b/llvm/test/CodeGen/RISCV/rvv/vsetvli-insert-crossbb.mir --- a/llvm/test/CodeGen/RISCV/rvv/vsetvli-insert-crossbb.mir +++ b/llvm/test/CodeGen/RISCV/rvv/vsetvli-insert-crossbb.mir @@ -592,12 +592,10 @@ ; CHECK-NEXT: [[PseudoVADD_VX_M1_:%[0-9]+]]:vr = PseudoVADD_VX_M1 [[PseudoVID_V_M1_]], [[PHI]], -1, 6, implicit $vl, implicit $vtype ; CHECK-NEXT: [[MUL:%[0-9]+]]:gpr = MUL [[PHI]], [[SRLI]] ; CHECK-NEXT: [[ADD:%[0-9]+]]:gpr = ADD [[COPY]], [[MUL]] - ; FIXME: We insert a SEW=32,LMUL=1/2 VSETVLI here but no SEW=64,LMUL=1 - ; VSETVLI before the VADD above. This misconfigures the VADD in the case that - ; the loop takes its backedge. ; CHECK-NEXT: dead $x0 = PseudoVSETVLIX0 killed $x0, 87, implicit-def $vl, implicit-def $vtype, implicit $vl ; CHECK-NEXT: PseudoVSE32_V_MF2 killed [[PseudoVADD_VX_M1_]], killed [[ADD]], -1, 5, implicit $vl, implicit $vtype ; CHECK-NEXT: [[ADDI:%[0-9]+]]:gpr = ADDI [[PHI]], 1 + ; CHECK-NEXT: dead $x0 = PseudoVSETVLIX0 killed $x0, 88, implicit-def $vl, implicit-def $vtype, implicit $vl ; CHECK-NEXT: BLTU [[ADDI]], [[COPY1]], %bb.1 ; CHECK-NEXT: PseudoBR %bb.2 ; CHECK-NEXT: {{ $}}