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

[AArch64][InstCombine] Fold MLOAD and zero extensions into MLOAD 

Accord the discussion in D122281, we missing an ISD::AND combine for MLOAD
because it relies on BuildVectorSDNode is fails for scalable vectors.
This patch is intend to handle that, so we can circle back the type MVT::nxv2i32

Reviewed By: paulwalker-arm

Differential Revision: https://reviews.llvm.org/D122703
This commit is contained in:
zhongyunde 2022-04-06 20:47:32 +08:00
parent e27a122b3a
commit 19e5235147
3 changed files with 13 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
View File

@ -6067,18 +6067,17 @@ SDValue DAGCombiner::visitAND(SDNode *N) {
if (ISD::isConstantSplatVectorAllOnes(N1.getNode()))
return N0;
// fold (and (masked_load) (build_vec (x, ...))) to zext_masked_load
// fold (and (masked_load) (splat_vec (x, ...))) to zext_masked_load
auto *MLoad = dyn_cast<MaskedLoadSDNode>(N0);
auto *BVec = dyn_cast<BuildVectorSDNode>(N1);
if (MLoad && BVec && MLoad->getExtensionType() == ISD::EXTLOAD &&
N0.hasOneUse() && N1.hasOneUse()) {
ConstantSDNode *Splat = isConstOrConstSplat(N1, true, true);
if (MLoad && MLoad->getExtensionType() == ISD::EXTLOAD && N0.hasOneUse() &&
Splat && N1.hasOneUse()) {
EVT LoadVT = MLoad->getMemoryVT();
EVT ExtVT = VT;
if (TLI.isLoadExtLegal(ISD::ZEXTLOAD, ExtVT, LoadVT)) {
// For this AND to be a zero extension of the masked load the elements
// of the BuildVec must mask the bottom bits of the extended element
// type
if (ConstantSDNode *Splat = BVec->getConstantSplatNode()) {
uint64_t ElementSize =
LoadVT.getVectorElementType().getScalarSizeInBits();
if (Splat->getAPIntValue().isMask(ElementSize)) {
@ -6091,7 +6090,6 @@ SDValue DAGCombiner::visitAND(SDNode *N) {
}
}
}
}
// fold (and x, -1) -> x
if (isAllOnesConstant(N1))

1
llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
View File

@ -1230,7 +1230,6 @@ AArch64TargetLowering::AArch64TargetLowering(const TargetMachine &TM,
setLoadExtAction(Op, MVT::nxv2i64, MVT::nxv2i16, Legal);
setLoadExtAction(Op, MVT::nxv2i64, MVT::nxv2i32, Legal);
setLoadExtAction(Op, MVT::nxv4i32, MVT::nxv4i8, Legal);
setLoadExtAction(Op, MVT::nxv2i32, MVT::nxv2i16, Legal);
setLoadExtAction(Op, MVT::nxv4i32, MVT::nxv4i16, Legal);
setLoadExtAction(Op, MVT::nxv8i16, MVT::nxv8i8, Legal);
}

2
llvm/test/CodeGen/AArch64/sve-masked-ldst-zext.ll
View File

@ -97,7 +97,7 @@ define <vscale x 2 x double> @masked_zload_2i16_2f64(<vscale x 2 x i16>* noalias
; CHECK-LABEL: masked_zload_2i16_2f64:
; CHECK: ld1h { z0.d }, p0/z, [x0]
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: ucvtf z0.d, p0/m, z0.s
; CHECK-NEXT: ucvtf z0.d, p0/m, z0.d
; CHECK-NEXT: ret
%wide.load = call <vscale x 2 x i16> @llvm.masked.load.nxv2i16(<vscale x 2 x i16>* %in, i32 2, <vscale x 2 x i1> %mask, <vscale x 2 x i16> undef)
%zext = zext <vscale x 2 x i16> %wide.load to <vscale x 2 x i32>