From 4d62f2e039428042ffb87e129fc173071dacfb6b Mon Sep 17 00:00:00 2001 From: Tyler Nowicki Date: Mon, 10 Aug 2015 19:14:16 +0000 Subject: [PATCH] Modify diagnostic messages to clearly indicate the why interleaving wasn't done. Sometimes interleaving is not beneficial, as determined by the cost-model and sometimes it is disabled by a loop hint (by the user). This patch modifies the diagnostic messages to make it clear why interleaving wasn't done. llvm-svn: 244485 --- llvm/lib/Transforms/Vectorize/LoopVectorize.cpp | 91 ++++++++++++---- .../X86/vectorization-remarks-missed.ll | 2 +- .../X86/vectorization-remarks-profitable.ll | 114 +++++++++++++++++++++ .../LoopVectorize/X86/vectorization-remarks.ll | 4 +- 4 files changed, 186 insertions(+), 25 deletions(-) create mode 100644 llvm/test/Transforms/LoopVectorize/X86/vectorization-remarks-profitable.ll diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp index 53074b0..47e7436 100644 --- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp +++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp @@ -1577,11 +1577,17 @@ struct LoopVectorize : public FunctionPass { } if (Hints.getWidth() == 1 && Hints.getInterleave() == 1) { + // FIXME: Add a separate metadata to indicate when the loop has already + // been vectorized instead of setting width and count to 1. DEBUG(dbgs() << "LV: Not vectorizing: Disabled/already vectorized.\n"); + // FIXME: Add interleave.disable metadata. This will allow + // vectorize.disable to be used without disabling the pass and errors + // to differentiate between disabled vectorization and a width of 1. emitOptimizationRemarkAnalysis( F->getContext(), DEBUG_TYPE, *F, L->getStartLoc(), - "loop not vectorized: vector width and interleave count are " - "explicitly set to 1"); + "loop not vectorized: vectorization and interleaving are explicitly " + "disabled, or vectorize width and interleave count are both set to " + "1"); return false; } @@ -1652,28 +1658,74 @@ struct LoopVectorize : public FunctionPass { // Select the interleave count. unsigned IC = CM.selectInterleaveCount(OptForSize, VF.Width, VF.Cost); - DEBUG(dbgs() << "LV: Found a vectorizable loop (" << VF.Width << ") in " - << DebugLocStr << '\n'); - DEBUG(dbgs() << "LV: Interleave Count is " << IC << '\n'); + // Get user interleave count. + unsigned UserIC = Hints.getInterleave(); + + // Identify the diagnostic messages that should be produced. + std::string VecDiagMsg, IntDiagMsg; + bool VectorizeLoop = true, InterleaveLoop = true; if (VF.Width == 1) { - DEBUG(dbgs() << "LV: Vectorization is possible but not beneficial\n"); + DEBUG(dbgs() << "LV: Vectorization is possible but not beneficial.\n"); + VecDiagMsg = + "the cost-model indicates that vectorization is not beneficial"; + VectorizeLoop = false; + } - if (IC == 1) { - emitOptimizationRemarkAnalysis( - F->getContext(), DEBUG_TYPE, *F, L->getStartLoc(), - "not beneficial to vectorize and user disabled interleaving"); - return false; - } - DEBUG(dbgs() << "LV: Trying to at least unroll the loops.\n"); + if (IC == 1 && UserIC <= 1) { + // Tell the user interleaving is not beneficial. + DEBUG(dbgs() << "LV: Interleaving is not beneficial.\n"); + IntDiagMsg = + "the cost-model indicates that interleaving is not beneficial"; + InterleaveLoop = false; + if (UserIC == 1) + IntDiagMsg += + " and is explicitly disabled or interleave count is set to 1"; + } else if (IC > 1 && UserIC == 1) { + // Tell the user interleaving is beneficial, but it explicitly disabled. + DEBUG(dbgs() + << "LV: Interleaving is beneficial but is explicitly disabled."); + IntDiagMsg = "the cost-model indicates that interleaving is beneficial " + "but is explicitly disabled or interleave count is set to 1"; + InterleaveLoop = false; + } - // Report the unrolling decision. - emitOptimizationRemark(F->getContext(), DEBUG_TYPE, *F, L->getStartLoc(), - Twine("interleaved by " + Twine(IC) + - " (vectorization not beneficial)")); + // Override IC if user provided an interleave count. + IC = UserIC > 0 ? UserIC : IC; + // Emit diagnostic messages, if any. + if (!VectorizeLoop && !InterleaveLoop) { + // Do not vectorize or interleaving the loop. + emitOptimizationRemarkAnalysis(F->getContext(), DEBUG_TYPE, *F, + L->getStartLoc(), VecDiagMsg); + emitOptimizationRemarkAnalysis(F->getContext(), DEBUG_TYPE, *F, + L->getStartLoc(), IntDiagMsg); + return false; + } else if (!VectorizeLoop && InterleaveLoop) { + DEBUG(dbgs() << "LV: Interleave Count is " << IC << '\n'); + emitOptimizationRemarkAnalysis(F->getContext(), DEBUG_TYPE, *F, + L->getStartLoc(), VecDiagMsg); + } else if (VectorizeLoop && !InterleaveLoop) { + DEBUG(dbgs() << "LV: Found a vectorizable loop (" << VF.Width << ") in " + << DebugLocStr << '\n'); + emitOptimizationRemarkAnalysis(F->getContext(), DEBUG_TYPE, *F, + L->getStartLoc(), IntDiagMsg); + } else if (VectorizeLoop && InterleaveLoop) { + DEBUG(dbgs() << "LV: Found a vectorizable loop (" << VF.Width << ") in " + << DebugLocStr << '\n'); + DEBUG(dbgs() << "LV: Interleave Count is " << IC << '\n'); + } + + if (!VectorizeLoop) { + assert(IC > 1 && "interleave count should not be 1 or 0"); + // If we decided that it is not legal to vectorize the loop then + // interleave it. InnerLoopUnroller Unroller(L, SE, LI, DT, TLI, TTI, IC); Unroller.vectorize(&LVL); + + emitOptimizationRemark(F->getContext(), DEBUG_TYPE, *F, L->getStartLoc(), + Twine("interleaved loop (interleaved count: ") + + Twine(IC) + ")"); } else { // If we decided that it is *legal* to vectorize the loop then do it. InnerLoopVectorizer LB(L, SE, LI, DT, TLI, TTI, VF.Width, IC); @@ -4635,11 +4687,6 @@ unsigned LoopVectorizationCostModel::selectInterleaveCount(bool OptForSize, // 3. We don't interleave if we think that we will spill registers to memory // due to the increased register pressure. - // Use the user preference, unless 'auto' is selected. - int UserUF = Hints->getInterleave(); - if (UserUF != 0) - return UserUF; - // When we optimize for size, we don't interleave. if (OptForSize) return 1; diff --git a/llvm/test/Transforms/LoopVectorize/X86/vectorization-remarks-missed.ll b/llvm/test/Transforms/LoopVectorize/X86/vectorization-remarks-missed.ll index 02b61dc..92b3dba 100644 --- a/llvm/test/Transforms/LoopVectorize/X86/vectorization-remarks-missed.ll +++ b/llvm/test/Transforms/LoopVectorize/X86/vectorization-remarks-missed.ll @@ -25,7 +25,7 @@ ; File, line, and column should match those specified in the metadata ; CHECK: remark: source.cpp:4:5: loop not vectorized: could not determine number of loop iterations ; CHECK: remark: source.cpp:4:5: loop not vectorized: use -Rpass-analysis=loop-vectorize for more info -; CHECK: remark: source.cpp:13:5: loop not vectorized: vector width and interleave count are explicitly set to 1 +; CHECK: remark: source.cpp:13:5: loop not vectorized: vectorization and interleaving are explicitly disabled, or vectorize width and interleave count are both set to 1 ; CHECK: remark: source.cpp:19:5: loop not vectorized: cannot identify array bounds ; CHECK: remark: source.cpp:19:5: loop not vectorized: use -Rpass-analysis=loop-vectorize for more info ; CHECK: warning: source.cpp:19:5: loop not vectorized: failed explicitly specified loop vectorization diff --git a/llvm/test/Transforms/LoopVectorize/X86/vectorization-remarks-profitable.ll b/llvm/test/Transforms/LoopVectorize/X86/vectorization-remarks-profitable.ll new file mode 100644 index 0000000..a8f256b --- /dev/null +++ b/llvm/test/Transforms/LoopVectorize/X86/vectorization-remarks-profitable.ll @@ -0,0 +1,114 @@ +; RUN: opt < %s -loop-vectorize -pass-remarks-analysis='loop-vectorize' -mtriple=x86_64-unknown-linux -S 2>&1 | FileCheck %s + +; Verify analysis remarks are generated when interleaving is not beneficial. +; CHECK: remark: vectorization-remarks-profitable.c:4:14: the cost-model indicates that vectorization is not beneficial +; CHECK: remark: vectorization-remarks-profitable.c:4:14: the cost-model indicates that interleaving is not beneficial and is explicitly disabled or interleave count is set to 1 +; CHECK: remark: vectorization-remarks-profitable.c:11:14: the cost-model indicates that vectorization is not beneficial +; CHECK: remark: vectorization-remarks-profitable.c:11:14: the cost-model indicates that interleaving is not beneficial + +; First loop. +; #pragma clang loop interleave(disable) unroll(disable) +; for(int i = 0; i < n; i++) { +; out[i] = in[i]; +; } + +; Second loop. +; #pragma clang loop unroll(disable) +; for(int i = 0; i < n; i++) { +; out[i] = in[i]; +; } + +target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128" +target triple = "x86_64-apple-macosx10.10.0" + +; Function Attrs: nounwind ssp uwtable +define void @do_not_interleave(float* nocapture %out, float* nocapture readonly %in, i32 %n) #0 { +entry: + %cmp.7 = icmp sgt i32 %n, 0, !dbg !3 + br i1 %cmp.7, label %for.body.preheader, label %for.cond.cleanup, !dbg !8 + +for.body.preheader: ; preds = %entry + br label %for.body, !dbg !9 + +for.cond.cleanup.loopexit: ; preds = %for.body + br label %for.cond.cleanup, !dbg !10 + +for.cond.cleanup: ; preds = %for.cond.cleanup.loopexit, %entry + ret void, !dbg !10 + +for.body: ; preds = %for.body.preheader, %for.body + %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %for.body.preheader ] + %arrayidx = getelementptr inbounds float, float* %in, i64 %indvars.iv, !dbg !9 + %0 = bitcast float* %arrayidx to i32*, !dbg !9 + %1 = load i32, i32* %0, align 4, !dbg !9, !tbaa !11 + %arrayidx2 = getelementptr inbounds float, float* %out, i64 %indvars.iv, !dbg !15 + %2 = bitcast float* %arrayidx2 to i32*, !dbg !16 + store i32 %1, i32* %2, align 4, !dbg !16, !tbaa !11 + %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1, !dbg !8 + %lftr.wideiv = trunc i64 %indvars.iv.next to i32, !dbg !8 + %exitcond = icmp eq i32 %lftr.wideiv, %n, !dbg !8 + br i1 %exitcond, label %for.cond.cleanup.loopexit, label %for.body, !dbg !8, !llvm.loop !17 +} + +; Function Attrs: nounwind ssp uwtable +define void @interleave_not_profitable(float* nocapture %out, float* nocapture readonly %in, i32 %n) #0 { +entry: + %cmp.7 = icmp sgt i32 %n, 0, !dbg !20 + br i1 %cmp.7, label %for.body.preheader, label %for.cond.cleanup, !dbg !22 + +for.body.preheader: ; preds = %entry + br label %for.body, !dbg !23 + +for.cond.cleanup.loopexit: ; preds = %for.body + br label %for.cond.cleanup, !dbg !24 + +for.cond.cleanup: ; preds = %for.cond.cleanup.loopexit, %entry + ret void, !dbg !24 + +for.body: ; preds = %for.body.preheader, %for.body + %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %for.body.preheader ] + %arrayidx = getelementptr inbounds float, float* %in, i64 %indvars.iv, !dbg !23 + %0 = bitcast float* %arrayidx to i32*, !dbg !23 + %1 = load i32, i32* %0, align 4, !dbg !23, !tbaa !11 + %arrayidx2 = getelementptr inbounds float, float* %out, i64 %indvars.iv, !dbg !25 + %2 = bitcast float* %arrayidx2 to i32*, !dbg !26 + store i32 %1, i32* %2, align 4, !dbg !26, !tbaa !11 + %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1, !dbg !22 + %lftr.wideiv = trunc i64 %indvars.iv.next to i32, !dbg !22 + %exitcond = icmp eq i32 %lftr.wideiv, %n, !dbg !22 + br i1 %exitcond, label %for.cond.cleanup.loopexit, label %for.body, !dbg !22, !llvm.loop !27 +} + +attributes #0 = { nounwind } + +!llvm.module.flags = !{!0, !1} +!llvm.ident = !{!2} + +!0 = !{i32 2, !"Debug Info Version", i32 3} +!1 = !{i32 1, !"PIC Level", i32 2} +!2 = !{!"clang version 3.7.0"} +!3 = !DILocation(line: 3, column: 20, scope: !4) +!4 = !DISubprogram(name: "do_not_interleave", scope: !5, file: !5, line: 1, type: !6, isLocal: false, isDefinition: true, scopeLine: 1, flags: DIFlagPrototyped, isOptimized: true, function: void (float*, float*, i32)* @do_not_interleave, variables: !7) +!5 = !DIFile(filename: "vectorization-remarks-profitable.c", directory: "") +!6 = !DISubroutineType(types: !7) +!7 = !{} +!8 = !DILocation(line: 3, column: 3, scope: !4) +!9 = !DILocation(line: 4, column: 14, scope: !4) +!10 = !DILocation(line: 6, column: 1, scope: !4) +!11 = !{!12, !12, i64 0} +!12 = !{!"float", !13, i64 0} +!13 = !{!"omnipotent char", !14, i64 0} +!14 = !{!"Simple C/C++ TBAA"} +!15 = !DILocation(line: 4, column: 5, scope: !4) +!16 = !DILocation(line: 4, column: 12, scope: !4) +!17 = distinct !{!17, !18, !19} +!18 = !{!"llvm.loop.interleave.count", i32 1} +!19 = !{!"llvm.loop.unroll.disable"} +!20 = !DILocation(line: 10, column: 20, scope: !21) +!21 = !DISubprogram(name: "interleave_not_profitable", scope: !5, file: !5, line: 8, type: !6, isLocal: false, isDefinition: true, scopeLine: 8, flags: DIFlagPrototyped, isOptimized: true, function: void (float*, float*, i32)* @interleave_not_profitable, variables: !7) +!22 = !DILocation(line: 10, column: 3, scope: !21) +!23 = !DILocation(line: 11, column: 14, scope: !21) +!24 = !DILocation(line: 13, column: 1, scope: !21) +!25 = !DILocation(line: 11, column: 5, scope: !21) +!26 = !DILocation(line: 11, column: 12, scope: !21) +!27 = distinct !{!27, !19} diff --git a/llvm/test/Transforms/LoopVectorize/X86/vectorization-remarks.ll b/llvm/test/Transforms/LoopVectorize/X86/vectorization-remarks.ll index 8640950..a4a2fd2 100644 --- a/llvm/test/Transforms/LoopVectorize/X86/vectorization-remarks.ll +++ b/llvm/test/Transforms/LoopVectorize/X86/vectorization-remarks.ll @@ -9,9 +9,9 @@ ; DEBUG-OUTPUT-NOT: .loc ; DEBUG-OUTPUT-NOT: {{.*}}.debug_info -; NONE: remark: vectorization-remarks.c:17:8: loop not vectorized: vector width and interleave count are explicitly set to 1 ; VECTORIZED: remark: vectorization-remarks.c:17:8: vectorized loop (vectorization width: 4, interleaved count: 1) -; UNROLLED: remark: vectorization-remarks.c:17:8: interleaved by 4 (vectorization not beneficial) +; UNROLLED: remark: vectorization-remarks.c:17:8: interleaved loop (interleaved count: 4) +; NONE: remark: vectorization-remarks.c:17:8: loop not vectorized: vectorization and interleaving are explicitly disabled, or vectorize width and interleave count are both set to 1 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128" -- 2.7.4