llvm-for-llvmta/test/Transforms/SLPVectorizer/X86/opt.ll

51 lines
2.6 KiB
LLVM
Raw Permalink Normal View History

2022-04-25 10:02:23 +02:00
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -O3 -S -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx | FileCheck %s --check-prefix=SLP
; RUN: opt < %s -O3 -vectorize-slp=false -S -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx | FileCheck %s --check-prefix=NOSLP
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
target triple = "x86_64-apple-macosx10.8.0"
; Make sure we can disable slp vectorization in opt.
define void @test1(double* %a, double* %b, double* %c) {
; SLP-LABEL: @test1(
; SLP-NEXT: entry:
; SLP-NEXT: [[TMP0:%.*]] = bitcast double* [[A:%.*]] to <2 x double>*
; SLP-NEXT: [[TMP1:%.*]] = load <2 x double>, <2 x double>* [[TMP0]], align 8
; SLP-NEXT: [[TMP2:%.*]] = bitcast double* [[B:%.*]] to <2 x double>*
; SLP-NEXT: [[TMP3:%.*]] = load <2 x double>, <2 x double>* [[TMP2]], align 8
; SLP-NEXT: [[TMP4:%.*]] = fmul <2 x double> [[TMP1]], [[TMP3]]
; SLP-NEXT: [[TMP5:%.*]] = bitcast double* [[C:%.*]] to <2 x double>*
; SLP-NEXT: store <2 x double> [[TMP4]], <2 x double>* [[TMP5]], align 8
; SLP-NEXT: ret void
;
; NOSLP-LABEL: @test1(
; NOSLP-NEXT: entry:
; NOSLP-NEXT: [[I0:%.*]] = load double, double* [[A:%.*]], align 8
; NOSLP-NEXT: [[I1:%.*]] = load double, double* [[B:%.*]], align 8
; NOSLP-NEXT: [[MUL:%.*]] = fmul double [[I0]], [[I1]]
; NOSLP-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds double, double* [[A]], i64 1
; NOSLP-NEXT: [[I3:%.*]] = load double, double* [[ARRAYIDX3]], align 8
; NOSLP-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds double, double* [[B]], i64 1
; NOSLP-NEXT: [[I4:%.*]] = load double, double* [[ARRAYIDX4]], align 8
; NOSLP-NEXT: [[MUL5:%.*]] = fmul double [[I3]], [[I4]]
; NOSLP-NEXT: store double [[MUL]], double* [[C:%.*]], align 8
; NOSLP-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds double, double* [[C]], i64 1
; NOSLP-NEXT: store double [[MUL5]], double* [[ARRAYIDX5]], align 8
; NOSLP-NEXT: ret void
;
entry:
%i0 = load double, double* %a, align 8
%i1 = load double, double* %b, align 8
%mul = fmul double %i0, %i1
%arrayidx3 = getelementptr inbounds double, double* %a, i64 1
%i3 = load double, double* %arrayidx3, align 8
%arrayidx4 = getelementptr inbounds double, double* %b, i64 1
%i4 = load double, double* %arrayidx4, align 8
%mul5 = fmul double %i3, %i4
store double %mul, double* %c, align 8
%arrayidx5 = getelementptr inbounds double, double* %c, i64 1
store double %mul5, double* %arrayidx5, align 8
ret void
}