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

[SLP][NFCAdd a test for vector intrinsic with scalar parameter, NFC.

This commit is contained in:
Alexey Bataev 2021-11-12 13:45:38 -08:00
parent 12ab3e6c84
commit e2a86ab847
1 changed files with 52 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

52
llvm/test/Transforms/SLPVectorizer/X86/intrinsic_with_scalar_param.ll Normal file
View File

@ -0,0 +1,52 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -slp-vectorizer -S -mtriple=x86_64-apple-macosx10.8.0 -slp-threshold=-8 | FileCheck %s
declare float @llvm.powi.f32.i32(float, i32)
define void @vec_powi_f32(float* %a, float* %c, i32 %P) {
; CHECK-LABEL: @vec_powi_f32(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[I0:%.*]] = load float, float* [[A:%.*]], align 4
; CHECK-NEXT: [[CALL1:%.*]] = tail call float @llvm.powi.f32.i32(float [[I0]], i32 [[P:%.*]])
; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds float, float* [[A]], i32 1
; CHECK-NEXT: [[I2:%.*]] = load float, float* [[ARRAYIDX2]], align 4
; CHECK-NEXT: [[CALL2:%.*]] = tail call float @llvm.powi.f32.i32(float [[I2]], i32 [[P]])
; CHECK-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds float, float* [[A]], i32 2
; CHECK-NEXT: [[I4:%.*]] = load float, float* [[ARRAYIDX4]], align 4
; CHECK-NEXT: [[CALL3:%.*]] = tail call float @llvm.powi.f32.i32(float [[I4]], i32 [[P]])
; CHECK-NEXT: [[ARRAYIDX6:%.*]] = getelementptr inbounds float, float* [[A]], i32 3
; CHECK-NEXT: [[I6:%.*]] = load float, float* [[ARRAYIDX6]], align 4
; CHECK-NEXT: [[CALL4:%.*]] = tail call float @llvm.powi.f32.i32(float [[I6]], i32 [[P]])
; CHECK-NEXT: store float [[CALL1]], float* [[C:%.*]], align 4
; CHECK-NEXT: [[ARRAYIDX8:%.*]] = getelementptr inbounds float, float* [[C]], i32 1
; CHECK-NEXT: store float [[CALL2]], float* [[ARRAYIDX8]], align 4
; CHECK-NEXT: [[ARRAYIDX9:%.*]] = getelementptr inbounds float, float* [[C]], i32 2
; CHECK-NEXT: store float [[CALL3]], float* [[ARRAYIDX9]], align 4
; CHECK-NEXT: [[ARRAYIDX10:%.*]] = getelementptr inbounds float, float* [[C]], i32 3
; CHECK-NEXT: store float [[CALL4]], float* [[ARRAYIDX10]], align 4
; CHECK-NEXT: ret void
;
entry:
%i0 = load float, float* %a, align 4
%call1 = tail call float @llvm.powi.f32.i32(float %i0,i32 %P)
%arrayidx2 = getelementptr inbounds float, float* %a, i32 1
%i2 = load float, float* %arrayidx2, align 4
%call2 = tail call float @llvm.powi.f32.i32(float %i2,i32 %P)
%arrayidx4 = getelementptr inbounds float, float* %a, i32 2
%i4 = load float, float* %arrayidx4, align 4
%call3 = tail call float @llvm.powi.f32.i32(float %i4,i32 %P)
%arrayidx6 = getelementptr inbounds float, float* %a, i32 3
%i6 = load float, float* %arrayidx6, align 4
%call4 = tail call float @llvm.powi.f32.i32(float %i6,i32 %P)
store float %call1, float* %c, align 4
%arrayidx8 = getelementptr inbounds float, float* %c, i32 1
store float %call2, float* %arrayidx8, align 4
%arrayidx9 = getelementptr inbounds float, float* %c, i32 2
store float %call3, float* %arrayidx9, align 4
%arrayidx10 = getelementptr inbounds float, float* %c, i32 3
store float %call4, float* %arrayidx10, align 4
ret void
}