RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-25 12:12:47 +01:00
Code Issues Projects Releases Wiki Activity

[InstCombine] Add instcombine fold for extractelement + splat for scalable vectors

Browse Source 
This patch allows that scalable vector can also use the fold that already
exists for fixed vector, only when the lane index is lower than the minimum
number of elements of the vector.

Differential Revision: https://reviews.llvm.org/D102404
This commit is contained in:
Caroline Concatto 2021-05-11 15:22:27 +01:00
parent 7a134236e4
commit dcc4b87d6f
4 changed files with 9 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
lib/Analysis/InstructionSimplify.cpp
View File

@ -4495,9 +4495,13 @@ static Value *SimplifyExtractElementInst(Value *Vec, Value *Idx,
// find a previously computed scalar that was inserted into the vector.
if (auto *IdxC = dyn_cast<ConstantInt>(Idx)) {
// For fixed-length vector, fold into undef if index is out of bounds.
if (isa<FixedVectorType>(VecVTy) &&
IdxC->getValue().uge(cast<FixedVectorType>(VecVTy)->getNumElements()))
unsigned MinNumElts = VecVTy->getElementCount().getKnownMinValue();
if (isa<FixedVectorType>(VecVTy) && IdxC->getValue().uge(MinNumElts))
return PoisonValue::get(VecVTy->getElementType());
// Handle case where an element is extracted from a splat.
if (IdxC->getValue().ult(MinNumElts))
if (auto *Splat = getSplatValue(Vec))
return Splat;
if (Value *Elt = findScalarElement(Vec, IdxC->getZExtValue()))
return Elt;
}

5
test/Transforms/InstCombine/gep-vector-indices.ll
View File

@ -61,10 +61,7 @@ define i32* @vector_splat_ptrs_v2i64_ext0(i32* %a, i64 %index) {
define i32* @vector_splat_ptrs_nxv2i64_ext0(i32* %a, i64 %index) {
; CHECK-LABEL: @vector_splat_ptrs_nxv2i64_ext0(
; CHECK-NEXT: [[TMP:%.*]] = insertelement <vscale x 2 x i32*> poison, i32* [[A:%.*]], i32 0
; CHECK-NEXT: [[SPLATOFA:%.*]] = shufflevector <vscale x 2 x i32*> [[TMP]], <vscale x 2 x i32*> poison, <vscale x 2 x i32> zeroinitializer
; CHECK-NEXT: [[TMP0:%.*]] = extractelement <vscale x 2 x i32*> [[SPLATOFA]], i32 0
; CHECK-NEXT: [[RES:%.*]] = getelementptr i32, i32* [[TMP0]], i64 [[INDEX:%.*]]
; CHECK-NEXT: [[RES:%.*]] = getelementptr i32, i32* [[A:%.*]], i64 [[INDEX:%.*]]
; CHECK-NEXT: ret i32* [[RES]]
;
%tmp = insertelement <vscale x 2 x i32*> poison, i32* %a, i32 0

6
test/Transforms/InstCombine/vscale_extractelement-inseltpoison.ll
View File

@ -55,13 +55,9 @@ define i8 @extractelement_bitcast_wrong_insert(<vscale x 2 x i32> %a, i32 %x) {
ret i8 %r
}
; TODO: Instcombine could optimize to return %v.
define i32 @extractelement_shuffle_in_range(i32 %v) {
; CHECK-LABEL: @extractelement_shuffle_in_range(
; CHECK-NEXT: [[IN:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[V:%.*]], i32 0
; CHECK-NEXT: [[SPLAT:%.*]] = shufflevector <vscale x 4 x i32> [[IN]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
; CHECK-NEXT: [[R:%.*]] = extractelement <vscale x 4 x i32> [[SPLAT]], i32 1
; CHECK-NEXT: ret i32 [[R]]
; CHECK-NEXT: ret i32 %v
;
%in = insertelement <vscale x 4 x i32> poison, i32 %v, i32 0
%splat = shufflevector <vscale x 4 x i32> %in, <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer

6
test/Transforms/InstCombine/vscale_extractelement.ll
View File

@ -55,13 +55,9 @@ define i8 @extractelement_bitcast_wrong_insert(<vscale x 2 x i32> %a, i32 %x) {
ret i8 %r
}
; TODO: Instcombine could optimize to return %v.
define i32 @extractelement_shuffle_in_range(i32 %v) {
; CHECK-LABEL: @extractelement_shuffle_in_range(
; CHECK-NEXT: [[IN:%.*]] = insertelement <vscale x 4 x i32> undef, i32 [[V:%.*]], i32 0
; CHECK-NEXT: [[SPLAT:%.*]] = shufflevector <vscale x 4 x i32> [[IN]], <vscale x 4 x i32> undef, <vscale x 4 x i32> zeroinitializer
; CHECK-NEXT: [[R:%.*]] = extractelement <vscale x 4 x i32> [[SPLAT]], i32 1
; CHECK-NEXT: ret i32 [[R]]
; CHECK-NEXT: ret i32 %v
;
%in = insertelement <vscale x 4 x i32> undef, i32 %v, i32 0
%splat = shufflevector <vscale x 4 x i32> %in, <vscale x 4 x i32> undef, <vscale x 4 x i32> zeroinitializer