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

[X86] Teach selectScalarSSELoad to not narrow volatile loads. 

llvm-svn: 364498
This commit is contained in:
Craig Topper 2019-06-27 05:51:56 +00:00
parent 9f69052394
commit 9ea5a32251
2 changed files with 41 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
llvm/lib/Target/X86/X86ISelDAGToDAG.cpp
View File

@ -2283,12 +2283,14 @@ bool X86DAGToDAGISel::selectScalarSSELoad(SDNode *Root, SDNode *Parent,
if (!hasSingleUsesFromRoot(Root, Parent))
return false;
// We can allow a full vector load here since narrowing a load is ok.
// We can allow a full vector load here since narrowing a load is ok unless
// it's volatile.
if (ISD::isNON_EXTLoad(N.getNode())) {
PatternNodeWithChain = N;
if (IsProfitableToFold(PatternNodeWithChain, N.getNode(), Root) &&
IsLegalToFold(PatternNodeWithChain, Parent, Root, OptLevel)) {
LoadSDNode *LD = cast<LoadSDNode>(PatternNodeWithChain);
LoadSDNode *LD = cast<LoadSDNode>(N);
if (!LD->isVolatile() &&
IsProfitableToFold(N, LD, Root) &&
IsLegalToFold(N, Parent, Root, OptLevel)) {
PatternNodeWithChain = N;
return selectAddr(LD, LD->getBasePtr(), Base, Scale, Index, Disp,
Segment);
}

34
llvm/test/CodeGen/X86/fold-load-unops.ll
View File

@ -179,6 +179,23 @@ define <4 x float> @sqrtss_full_size(<4 x float>* %a) optsize{
ret <4 x float> %res
}
define <4 x float> @sqrtss_full_size_volatile(<4 x float>* %a) optsize{
; SSE-LABEL: sqrtss_full_size_volatile:
; SSE: # %bb.0:
; SSE-NEXT: movaps (%rdi), %xmm0
; SSE-NEXT: sqrtss %xmm0, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: sqrtss_full_size_volatile:
; AVX: # %bb.0:
; AVX-NEXT: vmovaps (%rdi), %xmm0
; AVX-NEXT: vsqrtss %xmm0, %xmm0, %xmm0
; AVX-NEXT: retq
%ld = load volatile <4 x float>, <4 x float>* %a
%res = tail call <4 x float> @llvm.x86.sse.sqrt.ss(<4 x float> %ld)
ret <4 x float> %res
}
define double @sqrtsd_size(double* %a) optsize {
; SSE-LABEL: sqrtsd_size:
; SSE: # %bb.0:
@ -213,6 +230,23 @@ define <2 x double> @sqrtsd_full_size(<2 x double>* %a) optsize {
ret <2 x double> %res
}
define <2 x double> @sqrtsd_full_size_volatile(<2 x double>* %a) optsize {
; SSE-LABEL: sqrtsd_full_size_volatile:
; SSE: # %bb.0:
; SSE-NEXT: movapd (%rdi), %xmm0
; SSE-NEXT: sqrtsd %xmm0, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: sqrtsd_full_size_volatile:
; AVX: # %bb.0:
; AVX-NEXT: vmovapd (%rdi), %xmm0
; AVX-NEXT: vsqrtsd %xmm0, %xmm0, %xmm0
; AVX-NEXT: retq
%ld = load volatile <2 x double>, <2 x double>* %a
%res = tail call <2 x double> @llvm.x86.sse2.sqrt.sd(<2 x double> %ld)
ret <2 x double> %res
}
declare <4 x float> @llvm.x86.sse.rcp.ss(<4 x float>) nounwind readnone
declare <4 x float> @llvm.x86.sse.rsqrt.ss(<4 x float>) nounwind readnone
declare <4 x float> @llvm.x86.sse.sqrt.ss(<4 x float>) nounwind readnone