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

Do not throw away alignment when generating the DAG for 

memset; we may need it to decide between MOVAPS and MOVUPS
later.  Adjust a test that was looking for wrong code.
PR 3866 / 8675131.

llvm-svn: 119605
This commit is contained in:
Dale Johannesen 2010-11-18 01:35:23 +00:00
parent a2f30cc121
commit ed0d840838
3 changed files with 17 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
View File

@ -3487,7 +3487,7 @@ static SDValue getMemsetStores(SelectionDAG &DAG, DebugLoc dl,
SDValue Store = DAG.getStore(Chain, dl, Value, SDValue Store = DAG.getStore(Chain, dl, Value,
getMemBasePlusOffset(Dst, DstOff, DAG), getMemBasePlusOffset(Dst, DstOff, DAG),
DstPtrInfo.getWithOffset(DstOff), DstPtrInfo.getWithOffset(DstOff),
isVol, false, 0); isVol, false, Align);
OutChains.push_back(Store); OutChains.push_back(Store);
DstOff += VTSize; DstOff += VTSize;
} }

2
llvm/test/CodeGen/X86/memset64-on-x86-32.ll
View File

@ -1,4 +1,4 @@
; RUN: llc < %s -mtriple=i386-apple-darwin -mcpu=nehalem | grep movaps | count 5 ; RUN: llc < %s -mtriple=i386-apple-darwin -mcpu=nehalem | grep movups | count 5
; RUN: llc < %s -mtriple=i386-apple-darwin -mcpu=core2 | grep movl | count 20 ; RUN: llc < %s -mtriple=i386-apple-darwin -mcpu=core2 | grep movl | count 20
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=core2 | grep movq | count 10 ; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=core2 | grep movq | count 10

15
llvm/test/CodeGen/X86/misaligned-memset.ll Normal file
View File

@ -0,0 +1,15 @@
; RUN: llc -mtriple=x86_64-apple-darwin -mcpu=nehalem < %s | FileCheck %s
@a = common global [3 x i64] zeroinitializer, align 16
define i32 @main() nounwind ssp {
; CHECK: movups
entry:
%retval = alloca i32, align 4
store i32 0, i32* %retval
call void @llvm.memset.p0i8.i64(i8* bitcast (i64* getelementptr inbounds ([3 x i64]* @a, i32 0, i64 1) to i8*), i8 0, i64 16, i32 1, i1 false)
%0 = load i32* %retval
ret i32 %0
}
declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind