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

Fix pattern for memory form of PSHUFD for use with FP vectors to remove bitcast to an integer vector that normal code wouldn't have. Also remove bitcasts from code that turns splat vector loads into a shuffle as it was making the broken pattern necessary. 

llvm-svn: 149232
This commit is contained in:
Craig Topper 2012-01-30 07:50:31 +00:00
parent b9556acc9e
commit 516cba3380
3 changed files with 16 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -4846,21 +4846,16 @@ X86TargetLowering::LowerAsSplatVectorLoad(SDValue SrcOp, EVT VT, DebugLoc dl,
int EltNo = (Offset - StartOffset) >> 2;
int NumElems = VT.getVectorNumElements();
EVT CanonVT = VT.getSizeInBits() == 128 ? MVT::v4i32 : MVT::v8i32;
EVT NVT = EVT::getVectorVT(*DAG.getContext(), PVT, NumElems);
SDValue V1 = DAG.getLoad(NVT, dl, Chain, Ptr,
LD->getPointerInfo().getWithOffset(StartOffset),
false, false, false, 0);
// Canonicalize it to a v4i32 or v8i32 shuffle.
SmallVector<int, 8> Mask;
for (int i = 0; i < NumElems; ++i)
Mask.push_back(EltNo);
V1 = DAG.getNode(ISD::BITCAST, dl, CanonVT, V1);
return DAG.getNode(ISD::BITCAST, dl, NVT,
DAG.getVectorShuffle(CanonVT, dl, V1,
DAG.getUNDEF(CanonVT),&Mask[0]));
return DAG.getVectorShuffle(NVT, dl, V1, DAG.getUNDEF(NVT), &Mask[0]);
}
return SDValue();

6
llvm/lib/Target/X86/X86InstrSSE.td
View File

@ -3998,8 +3998,7 @@ let Predicates = [HasAVX] in {
def : Pat<(v4i32 (X86PShufd (bc_v4i32 (memopv2i64 addr:$src1)),
(i8 imm:$imm))),
(VPSHUFDmi addr:$src1, imm:$imm)>;
def : Pat<(v4i32 (X86PShufd (bc_v4i32 (memopv4f32 addr:$src1)),
(i8 imm:$imm))),
def : Pat<(v4f32 (X86PShufd (memopv4f32 addr:$src1), (i8 imm:$imm))),
(VPSHUFDmi addr:$src1, imm:$imm)>;
def : Pat<(v4f32 (X86PShufd VR128:$src1, (i8 imm:$imm))),
(VPSHUFDri VR128:$src1, imm:$imm)>;
@ -4051,8 +4050,7 @@ let Predicates = [HasSSE2] in {
def : Pat<(v4i32 (X86PShufd (bc_v4i32 (memopv2i64 addr:$src1)),
(i8 imm:$imm))),
(PSHUFDmi addr:$src1, imm:$imm)>;
def : Pat<(v4i32 (X86PShufd (bc_v4i32 (memopv4f32 addr:$src1)),
(i8 imm:$imm))),
def : Pat<(v4f32 (X86PShufd (memopv4f32 addr:$src1), (i8 imm:$imm))),
(PSHUFDmi addr:$src1, imm:$imm)>;
def : Pat<(v4f32 (X86PShufd VR128:$src1, (i8 imm:$imm))),
(PSHUFDri VR128:$src1, imm:$imm)>;

13
llvm/test/CodeGen/X86/avx-shuffle.ll
View File

@ -96,3 +96,16 @@ define i32 @test10(<4 x i32> %a) nounwind {
%r = extractelement <8 x i32> %b, i32 2
ret i32 %r
}
define <4 x float> @test11(<4 x float> %a) nounwind {
; CHECK: pshufd $27
%tmp1 = shufflevector <4 x float> %a, <4 x float> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
ret <4 x float> %tmp1
}
define <4 x float> @test12(<4 x float>* %a) nounwind {
; CHECK: pshufd $27, (
%tmp0 = load <4 x float>* %a
%tmp1 = shufflevector <4 x float> %tmp0, <4 x float> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
ret <4 x float> %tmp1
}