From 935d08fcd38b9e1399f0d7b3f42646ec04b7f3e1 Mon Sep 17 00:00:00 2001 From: Tyler Nowicki Date: Thu, 20 Aug 2015 16:19:55 -0700 Subject: [PATCH 4/4] Modifiy vectorization requirement test for memcheck threshold to allopw vectorize(enable) pragma to override the small threshold. --- lib/Transforms/Vectorize/LoopVectorize.cpp | 21 ++++++++++++++++----- test/Transforms/LoopVectorize/runtime-limit.ll | 18 ++++++++++++++++-- 2 files changed, 32 insertions(+), 7 deletions(-) diff --git a/lib/Transforms/Vectorize/LoopVectorize.cpp b/lib/Transforms/Vectorize/LoopVectorize.cpp index 13cc665..f387411 100644 --- a/lib/Transforms/Vectorize/LoopVectorize.cpp +++ b/lib/Transforms/Vectorize/LoopVectorize.cpp @@ -214,6 +214,11 @@ static cl::opt MaxNestedScalarReductionIC( cl::desc("The maximum interleave count to use when interleaving a scalar " "reduction in a nested loop.")); +static cl::opt PragmaVectorizeMemoryCheckThreshold( + "pragma-vectorize-memory-check-threshold", cl::init(128), cl::Hidden, + cl::desc("The maximum allowed number of runtime memory checks with a " + "vectorize(enable) pragma.")); + namespace { // Forward declarations. @@ -926,6 +931,9 @@ public: return DiagnosticInfo::AlwaysPrint; return LV_NAME; } + bool allowReordering() const { + return getForce() == LoopVectorizeHints::FK_Enabled || getWidth() > 1; + } private: /// Find hints specified in the loop metadata and update local values. @@ -1505,9 +1513,7 @@ public: bool doesNotMeet(Function *F, Loop *L, const LoopVectorizeHints &Hints) { const char *Name = Hints.vectorizeAnalysisPassName(); bool Failed = false; - if (UnsafeAlgebraInst && - Hints.getForce() == LoopVectorizeHints::FK_Undefined && - Hints.getWidth() == 0) { + if (UnsafeAlgebraInst && !Hints.allowReordering()) { emitOptimizationRemarkAnalysisFPCommute( F->getContext(), Name, *F, UnsafeAlgebraInst->getDebugLoc(), VectorizationReport() << "cannot prove it is safe to reorder " @@ -1515,8 +1521,13 @@ public: Failed = true; } - if (NumRuntimePointerChecks > - VectorizerParams::RuntimeMemoryCheckThreshold) { + // Test if runtime memcheck thresholds are exceeded. + bool PragmaThresholdReached = + NumRuntimePointerChecks > PragmaVectorizeMemoryCheckThreshold; + bool ThresholdReached = NumRuntimePointerChecks > + VectorizerParams::RuntimeMemoryCheckThreshold && + !Hints.allowReordering(); + if (ThresholdReached || PragmaThresholdReached) { emitOptimizationRemarkAnalysisAliasing( F->getContext(), Name, *F, L->getStartLoc(), VectorizationReport() diff --git a/test/Transforms/LoopVectorize/runtime-limit.ll b/test/Transforms/LoopVectorize/runtime-limit.ll index a2593eb..e583e6b 100644 --- a/test/Transforms/LoopVectorize/runtime-limit.ll +++ b/test/Transforms/LoopVectorize/runtime-limit.ll @@ -1,4 +1,6 @@ ; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -dce -instcombine -pass-remarks=loop-vectorize -pass-remarks-missed=loop-vectorize -S 2>&1 | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-width=4 -force-vector-interleave=1 -dce -instcombine -pass-remarks=loop-vectorize -pass-remarks-missed=loop-vectorize -S 2>&1 | FileCheck %s -check-prefix=OVERRIDE +; RUN: opt < %s -loop-vectorize -force-vector-width=4 -force-vector-interleave=1 -pragma-vectorize-memory-check-threshold=6 -dce -instcombine -pass-remarks=loop-vectorize -pass-remarks-missed=loop-vectorize -S 2>&1 | FileCheck %s target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128" target triple = "x86_64-apple-macosx10.8.0" @@ -8,10 +10,18 @@ target triple = "x86_64-apple-macosx10.8.0" ; Second loop produces diagnostic analysis remark. ;CHECK: remark: {{.*}}:0:0: loop not vectorized: cannot prove it is safe to reorder memory operations +; First loop produced diagnostic pass remark. +;OVERRIDE: remark: {{.*}}:0:0: vectorized loop (vectorization width: {{[0-9]}}, interleaved count: 1) +; Second loop produces diagnostic pass remark. +;OVERRIDE: remark: {{.*}}:0:0: vectorized loop (vectorization width: {{[0-9]}}, interleaved count: 1) + ; We are vectorizing with 6 runtime checks. ;CHECK-LABEL: func1x6( -;CHECK: <4 x i32> +;CHECK: <{{[0-9]}} x i32> ;CHECK: ret +;OVERRIDE-LABEL: func1x6( +;OVERRIDE: <4 x i32> +;OVERRIDE: ret define i32 @func1x6(i32* nocapture %out, i32* nocapture %A, i32* nocapture %B, i32* nocapture %C, i32* nocapture %D, i32* nocapture %E, i32* nocapture %F) { entry: br label %for.body @@ -44,8 +54,12 @@ for.end: ; preds = %for.body ; We are not vectorizing with 12 runtime checks. ;CHECK-LABEL: func2x6( -;CHECK-NOT: <4 x i32> +;CHECK-NOT: <{{[0-9]}} x i32> ;CHECK: ret +; We vectorize with 12 checks if a vectorization hint is provided. +;OVERRIDE-LABEL: func2x6( +;OVERRIDE: <4 x i32> +;OVERRIDE: ret define i32 @func2x6(i32* nocapture %out, i32* nocapture %out2, i32* nocapture %A, i32* nocapture %B, i32* nocapture %C, i32* nocapture %D, i32* nocapture %E, i32* nocapture %F) { entry: br label %for.body -- 2.3.2 (Apple Git-55)