From 739ded16a551fc06cd8dfc0fc909c395e8126745 Mon Sep 17 00:00:00 2001 From: Alexey Samsonov Date: Wed, 1 Jul 2015 22:18:30 +0000 Subject: [PATCH] [LoopVectorize] Use ReplaceInstWithInst() helper where appropriate. This is mostly an NFC, which increases code readability (instead of saving old terminator, generating new one in front of old, and deleting old, we just call a function). However, it would additionaly copy the debug location from old instruction to replacement, which would help PR23837. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@241197 91177308-0d34-0410-b5e6-96231b3b80d8 --- lib/Transforms/Vectorize/LoopVectorize.cpp | 37 +++++++-------- .../Transforms/LoopVectorize/runtime-check.ll | 45 ++++++++++++------- 2 files changed, 45 insertions(+), 37 deletions(-) diff --git a/lib/Transforms/Vectorize/LoopVectorize.cpp b/lib/Transforms/Vectorize/LoopVectorize.cpp index eff7c03c7f7..5ba14174ac7 100644 --- a/lib/Transforms/Vectorize/LoopVectorize.cpp +++ b/lib/Transforms/Vectorize/LoopVectorize.cpp @@ -2415,9 +2415,8 @@ void InnerLoopVectorizer::scalarizeInstruction(Instruction *Instr, bool IfPredic LoopVectorBody.push_back(NewIfBlock); VectorLp->addBasicBlockToLoop(NewIfBlock, *LI); Builder.SetInsertPoint(InsertPt); - Instruction *OldBr = IfBlock->getTerminator(); - BranchInst::Create(CondBlock, NewIfBlock, Cmp, OldBr); - OldBr->eraseFromParent(); + ReplaceInstWithInst(IfBlock->getTerminator(), + BranchInst::Create(CondBlock, NewIfBlock, Cmp)); IfBlock = NewIfBlock; } } @@ -2660,9 +2659,9 @@ void InnerLoopVectorizer::createEmptyLoop() { if (ParentLoop) ParentLoop->addBasicBlockToLoop(CheckBlock, *LI); LoopBypassBlocks.push_back(CheckBlock); - Instruction *OldTerm = LastBypassBlock->getTerminator(); - BranchInst::Create(ScalarPH, CheckBlock, CheckBCOverflow, OldTerm); - OldTerm->eraseFromParent(); + ReplaceInstWithInst( + LastBypassBlock->getTerminator(), + BranchInst::Create(ScalarPH, CheckBlock, CheckBCOverflow)); LastBypassBlock = CheckBlock; } @@ -2684,9 +2683,8 @@ void InnerLoopVectorizer::createEmptyLoop() { // Replace the branch into the memory check block with a conditional branch // for the "few elements case". - Instruction *OldTerm = LastBypassBlock->getTerminator(); - BranchInst::Create(MiddleBlock, CheckBlock, Cmp, OldTerm); - OldTerm->eraseFromParent(); + ReplaceInstWithInst(LastBypassBlock->getTerminator(), + BranchInst::Create(MiddleBlock, CheckBlock, Cmp)); Cmp = StrideCheck; LastBypassBlock = CheckBlock; @@ -2709,17 +2707,15 @@ void InnerLoopVectorizer::createEmptyLoop() { // Replace the branch into the memory check block with a conditional branch // for the "few elements case". - Instruction *OldTerm = LastBypassBlock->getTerminator(); - BranchInst::Create(MiddleBlock, CheckBlock, Cmp, OldTerm); - OldTerm->eraseFromParent(); + ReplaceInstWithInst(LastBypassBlock->getTerminator(), + BranchInst::Create(MiddleBlock, CheckBlock, Cmp)); Cmp = MemRuntimeCheck; LastBypassBlock = CheckBlock; } - LastBypassBlock->getTerminator()->eraseFromParent(); - BranchInst::Create(MiddleBlock, VectorPH, Cmp, - LastBypassBlock); + ReplaceInstWithInst(LastBypassBlock->getTerminator(), + BranchInst::Create(MiddleBlock, VectorPH, Cmp)); // We are going to resume the execution of the scalar loop. // Go over all of the induction variables that we found and fix the @@ -2856,10 +2852,8 @@ void InnerLoopVectorizer::createEmptyLoop() { Value *CmpN = CmpInst::Create(Instruction::ICmp, CmpInst::ICMP_EQ, IdxEnd, ResumeIndex, "cmp.n", MiddleBlock->getTerminator()); - - BranchInst::Create(ExitBlock, ScalarPH, CmpN, MiddleBlock->getTerminator()); - // Remove the old terminator. - MiddleBlock->getTerminator()->eraseFromParent(); + ReplaceInstWithInst(MiddleBlock->getTerminator(), + BranchInst::Create(ExitBlock, ScalarPH, CmpN)); // Create i+1 and fill the PHINode. Value *NextIdx = Builder.CreateAdd(Induction, Step, "index.next"); @@ -5513,9 +5507,8 @@ void InnerLoopUnroller::scalarizeInstruction(Instruction *Instr, LoopVectorBody.push_back(NewIfBlock); VectorLp->addBasicBlockToLoop(NewIfBlock, *LI); Builder.SetInsertPoint(InsertPt); - Instruction *OldBr = IfBlock->getTerminator(); - BranchInst::Create(CondBlock, NewIfBlock, Cmp, OldBr); - OldBr->eraseFromParent(); + ReplaceInstWithInst(IfBlock->getTerminator(), + BranchInst::Create(CondBlock, NewIfBlock, Cmp)); IfBlock = NewIfBlock; } } diff --git a/test/Transforms/LoopVectorize/runtime-check.ll b/test/Transforms/LoopVectorize/runtime-check.ll index b1c5d402c45..1f07d3f6959 100644 --- a/test/Transforms/LoopVectorize/runtime-check.ll +++ b/test/Transforms/LoopVectorize/runtime-check.ll @@ -9,30 +9,31 @@ target triple = "x86_64-apple-macosx10.9.0" ; a[i] = b[i] * 3; ; } +;CHECK-LABEL: define i32 @foo ;CHECK: for.body.preheader: -;CHECK: br i1 %cmp.zero, label %middle.block, label %vector.memcheck +;CHECK: br i1 %cmp.zero, label %middle.block, label %vector.memcheck, !dbg [[BODY_LOC:![0-9]+]] ;CHECK: vector.memcheck: -;CHECK: br i1 %memcheck.conflict, label %middle.block, label %vector.ph +;CHECK: br i1 %memcheck.conflict, label %middle.block, label %vector.ph, !dbg [[BODY_LOC]] ;CHECK: load <4 x float> define i32 @foo(float* nocapture %a, float* nocapture %b, i32 %n) nounwind uwtable ssp { entry: - %cmp6 = icmp sgt i32 %n, 0 - br i1 %cmp6, label %for.body, label %for.end + %cmp6 = icmp sgt i32 %n, 0, !dbg !6 + br i1 %cmp6, label %for.body, label %for.end, !dbg !6 for.body: ; preds = %entry, %for.body - %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ] - %arrayidx = getelementptr inbounds float, float* %b, i64 %indvars.iv - %0 = load float, float* %arrayidx, align 4 - %mul = fmul float %0, 3.000000e+00 - %arrayidx2 = getelementptr inbounds float, float* %a, i64 %indvars.iv - store float %mul, float* %arrayidx2, align 4 - %indvars.iv.next = add i64 %indvars.iv, 1 - %lftr.wideiv = trunc i64 %indvars.iv.next to i32 - %exitcond = icmp eq i32 %lftr.wideiv, %n - br i1 %exitcond, label %for.end, label %for.body + %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ], !dbg !7 + %arrayidx = getelementptr inbounds float, float* %b, i64 %indvars.iv, !dbg !7 + %0 = load float, float* %arrayidx, align 4, !dbg !7 + %mul = fmul float %0, 3.000000e+00, !dbg !7 + %arrayidx2 = getelementptr inbounds float, float* %a, i64 %indvars.iv, !dbg !7 + store float %mul, float* %arrayidx2, align 4, !dbg !7 + %indvars.iv.next = add i64 %indvars.iv, 1, !dbg !7 + %lftr.wideiv = trunc i64 %indvars.iv.next to i32, !dbg !7 + %exitcond = icmp eq i32 %lftr.wideiv, %n, !dbg !7 + br i1 %exitcond, label %for.end, label %for.body, !dbg !7 for.end: ; preds = %for.body, %entry - ret i32 undef + ret i32 undef, !dbg !8 } ; Make sure that we try to vectorize loops with a runtime check if the @@ -62,3 +63,17 @@ for.body: loopexit: ret void } + +; CHECK: [[BODY_LOC]] = !DILocation(line: 101, column: 1, scope: !{{.*}}) + +!llvm.module.flags = !{!0, !1} +!0 = !{i32 2, !"Dwarf Version", i32 4} +!1 = !{i32 2, !"Debug Info Version", i32 3} + +!2 = !{} +!3 = !DISubroutineType(types: !2) +!4 = !DIFile(filename: "test.cpp", directory: "/tmp") +!5 = !DISubprogram(name: "foo", scope: !4, file: !4, line: 99, type: !3, isLocal: false, isDefinition: true, scopeLine: 100, flags: DIFlagPrototyped, isOptimized: false, variables: !2) +!6 = !DILocation(line: 100, column: 1, scope: !5) +!7 = !DILocation(line: 101, column: 1, scope: !5) +!8 = !DILocation(line: 102, column: 1, scope: !5) -- 2.34.1