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

Make the SLP store-merger less paranoid about function calls. We check for function calls when we check if it is safe to sink instructions. 

llvm-svn: 179207
This commit is contained in:
Nadav Rotem 2013-04-10 19:41:36 +00:00
parent 88dd5f7a38
commit 73dffa4184
2 changed files with 40 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
View File

@ -65,10 +65,6 @@ struct SLPVectorizer : public BasicBlockPass {
/// if we flush the chain creation every time we run into a memory barrier.
bool CollectStores(BasicBlock *BB, BoUpSLP &R) {
for (BasicBlock::iterator it = BB->begin(), e = BB->end(); it != e; ++it) {
// Can't vectorize instructions with side effects.
if (it->mayThrow())
return false;
StoreInst *SI = dyn_cast<StoreInst>(it);
if (!SI)
continue;

40
llvm/test/Transforms/SLPVectorizer/X86/barriercall.ll Normal file
View File

@ -0,0 +1,40 @@
; RUN: opt < %s -basicaa -slp-vectorizer -dce -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"
;CHECK: @foo
;CHECK: store <4 x i32>
;CHECK: ret
define i32 @foo(i32* nocapture %A, i32 %n) #0 {
entry:
%call = tail call i32 (...)* @bar() #2
%mul = mul nsw i32 %n, 5
%add = add nsw i32 %mul, 9
store i32 %add, i32* %A, align 4, !tbaa !0
%mul1 = mul nsw i32 %n, 9
%add2 = add nsw i32 %mul1, 9
%arrayidx3 = getelementptr inbounds i32* %A, i64 1
store i32 %add2, i32* %arrayidx3, align 4, !tbaa !0
%mul4 = shl i32 %n, 3
%add5 = add nsw i32 %mul4, 9
%arrayidx6 = getelementptr inbounds i32* %A, i64 2
store i32 %add5, i32* %arrayidx6, align 4, !tbaa !0
%mul7 = mul nsw i32 %n, 10
%add8 = add nsw i32 %mul7, 9
%arrayidx9 = getelementptr inbounds i32* %A, i64 3
store i32 %add8, i32* %arrayidx9, align 4, !tbaa !0
ret i32 undef
}
; We can still vectorize the stores below.
declare i32 @bar(...) #1
attributes #0 = { nounwind ssp uwtable "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf"="true" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #1 = { "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf"="true" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #2 = { nounwind }
!0 = metadata !{metadata !"int", metadata !1}
!1 = metadata !{metadata !"omnipotent char", metadata !2}
!2 = metadata !{metadata !"Simple C/C++ TBAA"}