From bbea6143f2a7632978f35328c12db581de35d7aa Mon Sep 17 00:00:00 2001 From: Yi Jiang Date: Tue, 29 Apr 2014 19:37:20 +0000 Subject: [PATCH] Continue slp vectorization even the BB already has vectorized store radar://16641956 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207572 91177308-0d34-0410-b5e6-96231b3b80d8 --- lib/Transforms/Vectorize/SLPVectorizer.cpp | 2 +- .../SLPVectorizer/X86/continue_vectorizing.ll | 31 +++++++++++++++++++ 2 files changed, 32 insertions(+), 1 deletion(-) create mode 100644 test/Transforms/SLPVectorizer/X86/continue_vectorizing.ll diff --git a/lib/Transforms/Vectorize/SLPVectorizer.cpp b/lib/Transforms/Vectorize/SLPVectorizer.cpp index 21a727bfb3b..53feb959c80 100644 --- a/lib/Transforms/Vectorize/SLPVectorizer.cpp +++ b/lib/Transforms/Vectorize/SLPVectorizer.cpp @@ -2116,7 +2116,7 @@ unsigned SLPVectorizer::collectStores(BasicBlock *BB, BoUpSLP &R) { // Check that the pointer points to scalars. Type *Ty = SI->getValueOperand()->getType(); if (Ty->isAggregateType() || Ty->isVectorTy()) - return 0; + continue; // Find the base pointer. Value *Ptr = GetUnderlyingObject(SI->getPointerOperand(), DL); diff --git a/test/Transforms/SLPVectorizer/X86/continue_vectorizing.ll b/test/Transforms/SLPVectorizer/X86/continue_vectorizing.ll new file mode 100644 index 00000000000..ed225743a6e --- /dev/null +++ b/test/Transforms/SLPVectorizer/X86/continue_vectorizing.ll @@ -0,0 +1,31 @@ +; RUN: opt < %s -basicaa -slp-vectorizer -S -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx | 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" + +; We will keep trying to vectorize the basic block even we already find vectorized store. +; CHECK: test1 +; CHECK: store <2 x double> +; CHECK: ret +define void @test1(double* %a, double* %b, double* %c, double* %d) { +entry: + %i0 = load double* %a, align 8 + %i1 = load double* %b, align 8 + %mul = fmul double %i0, %i1 + %arrayidx3 = getelementptr inbounds double* %a, i64 1 + %i3 = load double* %arrayidx3, align 8 + %arrayidx4 = getelementptr inbounds double* %b, i64 1 + %i4 = load double* %arrayidx4, align 8 + %mul5 = fmul double %i3, %i4 + store double %mul, double* %c, align 8 + %arrayidx5 = getelementptr inbounds double* %c, i64 1 + store double %mul5, double* %arrayidx5, align 8 + %0 = bitcast double* %a to <4 x i32>* + %1 = load <4 x i32>* %0, align 8 + %2 = bitcast double* %b to <4 x i32>* + %3 = load <4 x i32>* %2, align 8 + %4 = mul <4 x i32> %1, %3 + %5 = bitcast double* %d to <4 x i32>* + store <4 x i32> %4, <4 x i32>* %5, align 8 + ret void +} -- 2.34.1