RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-26 04:32:44 +01:00
Code Issues Projects Releases Wiki Activity

[InstSimplify] Add constant fold for extractelement + splat for scalable vectors

Browse Source 
This patch allows that scalable vector can fold extractelement and constant splat
only when the lane index is lower than the minimum number of elements of the vector.

Differential Revision: https://reviews.llvm.org/D103180
This commit is contained in:
Caroline Concatto 2021-05-11 15:22:27 +01:00
parent 434526729b
commit 7714042905
3 changed files with 38 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
lib/IR/ConstantFold.cpp
View File

@ -907,14 +907,10 @@ Constant *llvm::ConstantFoldExtractElementInstruction(Constant *Val,
}
}
// CAZ of type ScalableVectorType and n < CAZ->getMinNumElements() =>
// extractelt CAZ, n -> 0
if (auto *ValSVTy = dyn_cast<ScalableVectorType>(Val->getType())) {
if (!CIdx->uge(ValSVTy->getMinNumElements())) {
if (auto *CAZ = dyn_cast<ConstantAggregateZero>(Val))
return CAZ->getElementValue(CIdx->getZExtValue());
}
return nullptr;
// Lane < Splat minimum vector width => extractelt Splat(x), Lane -> x
if (CIdx->getValue().ult(ValVTy->getElementCount().getKnownMinValue())) {
if (Constant *SplatVal = Val->getSplatValue())
return SplatVal;
}
return Val->getAggregateElement(CIdx);

2
test/Transforms/InstCombine/gep-vector-indices.ll
View File

@ -13,7 +13,7 @@ define i32* @vector_splat_indices_v2i64_ext0(i32* %a) {
define i32* @vector_splat_indices_nxv2i64_ext0(i32* %a) {
; CHECK-LABEL: @vector_splat_indices_nxv2i64_ext0(
; CHECK-NEXT: [[RES:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 extractelement (<vscale x 2 x i64> shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 4, i32 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer), i32 0)
; CHECK-NEXT: [[RES:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 4
; CHECK-NEXT: ret i32* [[RES]]
;
%tmp = insertelement <vscale x 2 x i64> poison, i64 4, i32 0

34
test/Transforms/InstSimplify/ConstProp/extractelement-vscale.ll
View File

@ -1,4 +1,4 @@
; RUN: opt -instcombine -S < %s | FileCheck %s
; RUN: opt -S -instsimplify < %s | FileCheck %s
; CHECK-LABEL: definitely_in_bounds
; CHECK: ret i8 0
@ -11,3 +11,35 @@ define i8 @definitely_in_bounds() {
define i8 @maybe_in_bounds() {
ret i8 extractelement (<vscale x 16 x i8> zeroinitializer, i64 16)
}
; Examples of extracting a lane from a splat constant
define i32 @extractconstant_shuffle_in_range(i32 %v) {
; CHECK-LABEL: @extractconstant_shuffle_in_range(
; CHECK-NEXT: ret i32 1024
;
%in = insertelement <vscale x 4 x i32> undef, i32 1024, i32 0
%splat = shufflevector <vscale x 4 x i32> %in, <vscale x 4 x i32> undef, <vscale x 4 x i32> zeroinitializer
%r = extractelement <vscale x 4 x i32> %splat, i32 1
ret i32 %r
}
define i32 @extractconstant_shuffle_maybe_out_of_range(i32 %v) {
; CHECK-LABEL: @extractconstant_shuffle_maybe_out_of_range(
; CHECK-NEXT: ret i32 extractelement (<vscale x 4 x i32> shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> undef, i32 1024, i32 0), <vscale x 4 x i32> undef, <vscale x 4 x i32> zeroinitializer), i32 4)
;
%in = insertelement <vscale x 4 x i32> undef, i32 1024, i32 0
%splat = shufflevector <vscale x 4 x i32> %in, <vscale x 4 x i32> undef, <vscale x 4 x i32> zeroinitializer
%r = extractelement <vscale x 4 x i32> %splat, i32 4
ret i32 %r
}
define i32 @extractconstant_shuffle_invalid_index(i32 %v) {
; CHECK-LABEL: @extractconstant_shuffle_invalid_index(
; CHECK-NEXT: ret i32 extractelement (<vscale x 4 x i32> shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> undef, i32 1024, i32 0), <vscale x 4 x i32> undef, <vscale x 4 x i32> zeroinitializer), i32 -1)
;
%in = insertelement <vscale x 4 x i32> undef, i32 1024, i32 0
%splat = shufflevector <vscale x 4 x i32> %in, <vscale x 4 x i32> undef, <vscale x 4 x i32> zeroinitializer
%r = extractelement <vscale x 4 x i32> %splat, i32 -1
ret i32 %r
}