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

[X86] combineX86GatherScatter - only fold scale if the index isn't extended 

As mentioned on D108539, when the gather indices are smaller than the pointer size, they are sign-extended BEFORE scale is applied, making the general fold unsafe.

If the index have sufficient sign-bits then folding the scale could be safe - I'll investigate this.
This commit is contained in:
Simon Pilgrim 2021-10-29 11:47:38 +01:00
parent 96808c69a1
commit 154c036ebb
2 changed files with 17 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -50230,16 +50230,20 @@ static SDValue combineX86GatherScatter(SDNode *N, SelectionDAG &DAG,
TargetLowering::DAGCombinerInfo &DCI,
const X86Subtarget &Subtarget) {
auto *MemOp = cast<X86MaskedGatherScatterSDNode>(N);
SDValue BasePtr = MemOp->getBasePtr();
SDValue Index = MemOp->getIndex();
SDValue Scale = MemOp->getScale();
SDValue Mask = MemOp->getMask();
// Attempt to fold an index scale into the scale value directly.
// For smaller indices, implicit sext is performed BEFORE scale, preventing
// this fold under most circumstances.
// TODO: Move this into X86DAGToDAGISel::matchVectorAddressRecursively?
if ((Index.getOpcode() == X86ISD::VSHLI ||
(Index.getOpcode() == ISD::ADD &&
Index.getOperand(0) == Index.getOperand(1))) &&
isa<ConstantSDNode>(Scale)) {
isa<ConstantSDNode>(Scale) &&
BasePtr.getScalarValueSizeInBits() == Index.getScalarValueSizeInBits()) {
unsigned ShiftAmt =
Index.getOpcode() == ISD::ADD ? 1 : Index.getConstantOperandVal(1);
uint64_t ScaleAmt = cast<ConstantSDNode>(Scale)->getZExtValue();

21
llvm/test/CodeGen/X86/masked_gather_scatter.ll
View File

@ -4992,9 +4992,9 @@ define void @splat_ptr_scatter(i32* %ptr, <4 x i1> %mask, <4 x i32> %val) {
define <8 x float> @scaleidx_x86gather(float* %base, <8 x i32> %index, <8 x i32> %imask) nounwind {
; KNL_64-LABEL: scaleidx_x86gather:
; KNL_64: # %bb.0:
; KNL_64-NEXT: vxorps %xmm2, %xmm2, %xmm2
; KNL_64-NEXT: vgatherdps %ymm1, (%rdi,%ymm0,4), %ymm2
; KNL_64-NEXT: vmovaps %ymm2, %ymm0
; KNL_64-NEXT: vpslld $2, %ymm0, %ymm2
; KNL_64-NEXT: vpxor %xmm0, %xmm0, %xmm0
; KNL_64-NEXT: vgatherdps %ymm1, (%rdi,%ymm2), %ymm0
; KNL_64-NEXT: retq
;
; KNL_32-LABEL: scaleidx_x86gather:
@ -5007,9 +5007,9 @@ define <8 x float> @scaleidx_x86gather(float* %base, <8 x i32> %index, <8 x i32>
;
; SKX-LABEL: scaleidx_x86gather:
; SKX: # %bb.0:
; SKX-NEXT: vxorps %xmm2, %xmm2, %xmm2
; SKX-NEXT: vgatherdps %ymm1, (%rdi,%ymm0,4), %ymm2
; SKX-NEXT: vmovaps %ymm2, %ymm0
; SKX-NEXT: vpslld $2, %ymm0, %ymm2
; SKX-NEXT: vpxor %xmm0, %xmm0, %xmm0
; SKX-NEXT: vgatherdps %ymm1, (%rdi,%ymm2), %ymm0
; SKX-NEXT: retq
;
; SKX_32-LABEL: scaleidx_x86gather:
@ -5068,7 +5068,8 @@ define void @scaleidx_x86scatter(<16 x float> %value, float* %base, <16 x i32> %
; KNL_64-LABEL: scaleidx_x86scatter:
; KNL_64: # %bb.0:
; KNL_64-NEXT: kmovw %esi, %k1
; KNL_64-NEXT: vscatterdps %zmm0, (%rdi,%zmm1,4) {%k1}
; KNL_64-NEXT: vpaddd %zmm1, %zmm1, %zmm1
; KNL_64-NEXT: vscatterdps %zmm0, (%rdi,%zmm1,2) {%k1}
; KNL_64-NEXT: vzeroupper
; KNL_64-NEXT: retq
;
@ -5083,7 +5084,8 @@ define void @scaleidx_x86scatter(<16 x float> %value, float* %base, <16 x i32> %
; SKX-LABEL: scaleidx_x86scatter:
; SKX: # %bb.0:
; SKX-NEXT: kmovw %esi, %k1
; SKX-NEXT: vscatterdps %zmm0, (%rdi,%zmm1,4) {%k1}
; SKX-NEXT: vpaddd %zmm1, %zmm1, %zmm1
; SKX-NEXT: vscatterdps %zmm0, (%rdi,%zmm1,2) {%k1}
; SKX-NEXT: vzeroupper
; SKX-NEXT: retq
;
@ -5129,8 +5131,9 @@ define void @scaleidx_scatter(<8 x float> %value, float* %base, <8 x i32> %index
;
; SKX-LABEL: scaleidx_scatter:
; SKX: # %bb.0:
; SKX-NEXT: vpaddd %ymm1, %ymm1, %ymm1
; SKX-NEXT: kmovw %esi, %k1
; SKX-NEXT: vscatterdps %ymm0, (%rdi,%ymm1,8) {%k1}
; SKX-NEXT: vscatterdps %ymm0, (%rdi,%ymm1,4) {%k1}
; SKX-NEXT: vzeroupper
; SKX-NEXT: retq
;