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

[SLPVectorizer][SVE] Skip scalable-vector instructions before vectorizeSimpleInstructions. 

For scalable type, the aggregated size is unknown at compile-time.
Skip instructions with scalable type to ensure the list of instructions
for vectorizeSimpleInstructions does not contains any scalable-vector instructions.

Reviewed By: RKSimon

Differential Revision: https://reviews.llvm.org/D87550
This commit is contained in:
Huihui Zhang 2020-09-15 13:09:56 -07:00
parent 00ba1a3de7
commit 3b7f5166bd
2 changed files with 49 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
View File

@ -7508,6 +7508,11 @@ bool SLPVectorizerPass::vectorizeChainsInBlock(BasicBlock *BB, BoUpSLP &R) {
SmallVector<Instruction *, 8> PostProcessInstructions;
SmallDenseSet<Instruction *, 4> KeyNodes;
for (BasicBlock::iterator it = BB->begin(), e = BB->end(); it != e; ++it) {
// Skip instructions with scalable type. The num of elements is unknown at
// compile-time for scalable type.
if (isa<ScalableVectorType>(it->getType()))
continue;
// Skip instructions marked for the deletion.
if (R.isDeleted(&*it))
continue;

44
llvm/test/Transforms/SLPVectorizer/AArch64/insertelement.ll Normal file
View File

@ -0,0 +1,44 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -slp-vectorizer -S 2>%t | FileCheck %s
; RUN: FileCheck --check-prefix=WARN --allow-empty %s <%t
; WARN-NOT: warning
target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
target triple = "aarch64-unknown-linux-gnu"
define <2 x float> @insertelement-fixed-vector() {
; CHECK-LABEL: @insertelement-fixed-vector(
; CHECK-NEXT: [[TMP1:%.*]] = call fast <2 x float> @llvm.fabs.v2f32(<2 x float> undef)
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <2 x float> [[TMP1]], i32 0
; CHECK-NEXT: [[I0:%.*]] = insertelement <2 x float> undef, float [[TMP2]], i32 0
; CHECK-NEXT: [[TMP3:%.*]] = extractelement <2 x float> [[TMP1]], i32 1
; CHECK-NEXT: [[I1:%.*]] = insertelement <2 x float> [[I0]], float [[TMP3]], i32 1
; CHECK-NEXT: ret <2 x float> [[I1]]
;
%f0 = tail call fast float @llvm.fabs.f32(float undef)
%f1 = tail call fast float @llvm.fabs.f32(float undef)
%i0 = insertelement <2 x float> undef, float %f0, i32 0
%i1 = insertelement <2 x float> %i0, float %f1, i32 1
ret <2 x float> %i1
}
; TODO: llvm.fabs could be optimized in vector form. It's legal to extract
; elements from fixed-length vector and insert into scalable vector.
define <vscale x 2 x float> @insertelement-scalable-vector() {
; CHECK-LABEL: @insertelement-scalable-vector(
; CHECK-NEXT: [[F0:%.*]] = tail call fast float @llvm.fabs.f32(float undef)
; CHECK-NEXT: [[F1:%.*]] = tail call fast float @llvm.fabs.f32(float undef)
; CHECK-NEXT: [[I0:%.*]] = insertelement <vscale x 2 x float> undef, float [[F0]], i32 0
; CHECK-NEXT: [[I1:%.*]] = insertelement <vscale x 2 x float> [[I0]], float [[F1]], i32 1
; CHECK-NEXT: ret <vscale x 2 x float> [[I1]]
;
%f0 = tail call fast float @llvm.fabs.f32(float undef)
%f1 = tail call fast float @llvm.fabs.f32(float undef)
%i0 = insertelement <vscale x 2 x float> undef, float %f0, i32 0
%i1 = insertelement <vscale x 2 x float> %i0, float %f1, i32 1
ret <vscale x 2 x float> %i1
}
; Function Attrs: nounwind readnone speculatable willreturn
declare float @llvm.fabs.f32(float)