maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

Continue slp vectorization even the BB already has vectorized store radar://16641956 

llvm-svn: 207572
This commit is contained in:
Yi Jiang 2014-04-29 19:37:20 +00:00
parent 4e234aa790
commit 1a3f18b161
2 changed files with 32 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
View File

@ -2116,7 +2116,7 @@ unsigned SLPVectorizer::collectStores(BasicBlock *BB, BoUpSLP &R) {
// Check that the pointer points to scalars. // Check that the pointer points to scalars.
Type *Ty = SI->getValueOperand()->getType(); Type *Ty = SI->getValueOperand()->getType();
if (Ty->isAggregateType() || Ty->isVectorTy()) if (Ty->isAggregateType() || Ty->isVectorTy())
return 0; continue;
// Find the base pointer. // Find the base pointer.
Value *Ptr = GetUnderlyingObject(SI->getPointerOperand(), DL); Value *Ptr = GetUnderlyingObject(SI->getPointerOperand(), DL);

31
llvm/test/Transforms/SLPVectorizer/X86/continue_vectorizing.ll Normal file
View File

@ -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
}