Google Git
Sign in
llvm / llvm / afe472d270f95026062dfcb33a0c9e043ab9f94e / . / test / Transforms / SLPVectorizer / X86 / intrinsic.ll
blob: fbce7551b00b2c872736d12cbb244b4f79578df0 [file] [log] [blame]
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -basicaa -slp-vectorizer -slp-threshold=-999 -dce -S -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx | FileCheck %s
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"
declare double @llvm.fabs.f64(double) nounwind readnone
define void @vec_fabs_f64(double* %a, double* %b, double* %c) {
; CHECK-LABEL: @vec_fabs_f64(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = bitcast double* [[A:%.*]] to <2 x double>*
; CHECK-NEXT: [[TMP1:%.*]] = load <2 x double>, <2 x double>* [[TMP0]], align 8
; CHECK-NEXT: [[TMP2:%.*]] = bitcast double* [[B:%.*]] to <2 x double>*
; CHECK-NEXT: [[TMP3:%.*]] = load <2 x double>, <2 x double>* [[TMP2]], align 8
; CHECK-NEXT: [[TMP4:%.*]] = fmul <2 x double> [[TMP1]], [[TMP3]]
; CHECK-NEXT: [[TMP5:%.*]] = call <2 x double> @llvm.fabs.v2f64(<2 x double> [[TMP4]])
; CHECK-NEXT: [[TMP6:%.*]] = bitcast double* [[C:%.*]] to <2 x double>*
; CHECK-NEXT: store <2 x double> [[TMP5]], <2 x double>* [[TMP6]], align 8
; CHECK-NEXT: ret void
;
entry:
%i0 = load double, double* %a, align 8
%i1 = load double, double* %b, align 8
%mul = fmul double %i0, %i1
%call = tail call double @llvm.fabs.f64(double %mul) nounwind readnone
%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
%call5 = tail call double @llvm.fabs.f64(double %mul5) nounwind readnone
store double %call, double* %c, align 8
%arrayidx5 = getelementptr inbounds double, double* %c, i64 1
store double %call5, double* %arrayidx5, align 8
ret void
}
declare float @llvm.copysign.f32(float, float) nounwind readnone
define void @vec_copysign_f32(float* %a, float* %b, float* noalias %c) {
; CHECK-LABEL: @vec_copysign_f32(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = bitcast float* [[A:%.*]] to <4 x float>*
; CHECK-NEXT: [[TMP1:%.*]] = load <4 x float>, <4 x float>* [[TMP0]], align 4
; CHECK-NEXT: [[TMP2:%.*]] = bitcast float* [[B:%.*]] to <4 x float>*
; CHECK-NEXT: [[TMP3:%.*]] = load <4 x float>, <4 x float>* [[TMP2]], align 4
; CHECK-NEXT: [[TMP4:%.*]] = call <4 x float> @llvm.copysign.v4f32(<4 x float> [[TMP1]], <4 x float> [[TMP3]])
; CHECK-NEXT: [[TMP5:%.*]] = bitcast float* [[C:%.*]] to <4 x float>*
; CHECK-NEXT: store <4 x float> [[TMP4]], <4 x float>* [[TMP5]], align 4
; CHECK-NEXT: ret void
;
entry:
%0 = load float, float* %a, align 4
%1 = load float, float* %b, align 4
%call0 = tail call float @llvm.copysign.f32(float %0, float %1) nounwind readnone
store float %call0, float* %c, align 4
%ix2 = getelementptr inbounds float, float* %a, i64 1
%2 = load float, float* %ix2, align 4
%ix3 = getelementptr inbounds float, float* %b, i64 1
%3 = load float, float* %ix3, align 4
%call1 = tail call float @llvm.copysign.f32(float %2, float %3) nounwind readnone
%c1 = getelementptr inbounds float, float* %c, i64 1
store float %call1, float* %c1, align 4
%ix4 = getelementptr inbounds float, float* %a, i64 2
%4 = load float, float* %ix4, align 4
%ix5 = getelementptr inbounds float, float* %b, i64 2
%5 = load float, float* %ix5, align 4
%call2 = tail call float @llvm.copysign.f32(float %4, float %5) nounwind readnone
%c2 = getelementptr inbounds float, float* %c, i64 2
store float %call2, float* %c2, align 4
%ix6 = getelementptr inbounds float, float* %a, i64 3
%6 = load float, float* %ix6, align 4
%ix7 = getelementptr inbounds float, float* %b, i64 3
%7 = load float, float* %ix7, align 4
%call3 = tail call float @llvm.copysign.f32(float %6, float %7) nounwind readnone
%c3 = getelementptr inbounds float, float* %c, i64 3
store float %call3, float* %c3, align 4
ret void
}
declare i32 @llvm.bswap.i32(i32) nounwind readnone
define void @vec_bswap_i32(i32* %a, i32* %b, i32* %c) {
; CHECK-LABEL: @vec_bswap_i32(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[A:%.*]] to <4 x i32>*
; CHECK-NEXT: [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4
; CHECK-NEXT: [[TMP2:%.*]] = bitcast i32* [[B:%.*]] to <4 x i32>*
; CHECK-NEXT: [[TMP3:%.*]] = load <4 x i32>, <4 x i32>* [[TMP2]], align 4
; CHECK-NEXT: [[TMP4:%.*]] = add <4 x i32> [[TMP1]], [[TMP3]]
; CHECK-NEXT: [[TMP5:%.*]] = call <4 x i32> @llvm.bswap.v4i32(<4 x i32> [[TMP4]])
; CHECK-NEXT: [[TMP6:%.*]] = bitcast i32* [[C:%.*]] to <4 x i32>*
; CHECK-NEXT: store <4 x i32> [[TMP5]], <4 x i32>* [[TMP6]], align 4
; CHECK-NEXT: ret void
;
entry:
%i0 = load i32, i32* %a, align 4
%i1 = load i32, i32* %b, align 4
%add1 = add i32 %i0, %i1
%call1 = tail call i32 @llvm.bswap.i32(i32 %add1) nounwind readnone
%arrayidx2 = getelementptr inbounds i32, i32* %a, i32 1
%i2 = load i32, i32* %arrayidx2, align 4
%arrayidx3 = getelementptr inbounds i32, i32* %b, i32 1
%i3 = load i32, i32* %arrayidx3, align 4
%add2 = add i32 %i2, %i3
%call2 = tail call i32 @llvm.bswap.i32(i32 %add2) nounwind readnone
%arrayidx4 = getelementptr inbounds i32, i32* %a, i32 2
%i4 = load i32, i32* %arrayidx4, align 4
%arrayidx5 = getelementptr inbounds i32, i32* %b, i32 2
%i5 = load i32, i32* %arrayidx5, align 4
%add3 = add i32 %i4, %i5
%call3 = tail call i32 @llvm.bswap.i32(i32 %add3) nounwind readnone
%arrayidx6 = getelementptr inbounds i32, i32* %a, i32 3
%i6 = load i32, i32* %arrayidx6, align 4
%arrayidx7 = getelementptr inbounds i32, i32* %b, i32 3
%i7 = load i32, i32* %arrayidx7, align 4
%add4 = add i32 %i6, %i7
%call4 = tail call i32 @llvm.bswap.i32(i32 %add4) nounwind readnone
store i32 %call1, i32* %c, align 4
%arrayidx8 = getelementptr inbounds i32, i32* %c, i32 1
store i32 %call2, i32* %arrayidx8, align 4
%arrayidx9 = getelementptr inbounds i32, i32* %c, i32 2
store i32 %call3, i32* %arrayidx9, align 4
%arrayidx10 = getelementptr inbounds i32, i32* %c, i32 3
store i32 %call4, i32* %arrayidx10, align 4
ret void
}
declare i32 @llvm.ctlz.i32(i32,i1) nounwind readnone
define void @vec_ctlz_i32(i32* %a, i32* %b, i32* %c, i1) {
; CHECK-LABEL: @vec_ctlz_i32(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP1:%.*]] = bitcast i32* [[A:%.*]] to <4 x i32>*
; CHECK-NEXT: [[TMP2:%.*]] = load <4 x i32>, <4 x i32>* [[TMP1]], align 4
; CHECK-NEXT: [[TMP3:%.*]] = bitcast i32* [[B:%.*]] to <4 x i32>*
; CHECK-NEXT: [[TMP4:%.*]] = load <4 x i32>, <4 x i32>* [[TMP3]], align 4
; CHECK-NEXT: [[TMP5:%.*]] = add <4 x i32> [[TMP2]], [[TMP4]]
; CHECK-NEXT: [[TMP6:%.*]] = call <4 x i32> @llvm.ctlz.v4i32(<4 x i32> [[TMP5]], i1 true)
; CHECK-NEXT: [[TMP7:%.*]] = bitcast i32* [[C:%.*]] to <4 x i32>*
; CHECK-NEXT: store <4 x i32> [[TMP6]], <4 x i32>* [[TMP7]], align 4
; CHECK-NEXT: ret void
;
entry:
%i0 = load i32, i32* %a, align 4
%i1 = load i32, i32* %b, align 4
%add1 = add i32 %i0, %i1
%call1 = tail call i32 @llvm.ctlz.i32(i32 %add1,i1 true) nounwind readnone
%arrayidx2 = getelementptr inbounds i32, i32* %a, i32 1
%i2 = load i32, i32* %arrayidx2, align 4
%arrayidx3 = getelementptr inbounds i32, i32* %b, i32 1
%i3 = load i32, i32* %arrayidx3, align 4
%add2 = add i32 %i2, %i3
%call2 = tail call i32 @llvm.ctlz.i32(i32 %add2,i1 true) nounwind readnone
%arrayidx4 = getelementptr inbounds i32, i32* %a, i32 2
%i4 = load i32, i32* %arrayidx4, align 4
%arrayidx5 = getelementptr inbounds i32, i32* %b, i32 2
%i5 = load i32, i32* %arrayidx5, align 4
%add3 = add i32 %i4, %i5
%call3 = tail call i32 @llvm.ctlz.i32(i32 %add3,i1 true) nounwind readnone
%arrayidx6 = getelementptr inbounds i32, i32* %a, i32 3
%i6 = load i32, i32* %arrayidx6, align 4
%arrayidx7 = getelementptr inbounds i32, i32* %b, i32 3
%i7 = load i32, i32* %arrayidx7, align 4
%add4 = add i32 %i6, %i7
%call4 = tail call i32 @llvm.ctlz.i32(i32 %add4,i1 true) nounwind readnone
store i32 %call1, i32* %c, align 4
%arrayidx8 = getelementptr inbounds i32, i32* %c, i32 1
store i32 %call2, i32* %arrayidx8, align 4
%arrayidx9 = getelementptr inbounds i32, i32* %c, i32 2
store i32 %call3, i32* %arrayidx9, align 4
%arrayidx10 = getelementptr inbounds i32, i32* %c, i32 3
store i32 %call4, i32* %arrayidx10, align 4
ret void
}
define void @vec_ctlz_i32_neg(i32* %a, i32* %b, i32* %c, i1) {
; CHECK-LABEL: @vec_ctlz_i32_neg(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[I0:%.*]] = load i32, i32* [[A:%.*]], align 4
; CHECK-NEXT: [[I1:%.*]] = load i32, i32* [[B:%.*]], align 4
; CHECK-NEXT: [[ADD1:%.*]] = add i32 [[I0]], [[I1]]
; CHECK-NEXT: [[CALL1:%.*]] = tail call i32 @llvm.ctlz.i32(i32 [[ADD1]], i1 true) #3
; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, i32* [[A]], i32 1
; CHECK-NEXT: [[I2:%.*]] = load i32, i32* [[ARRAYIDX2]], align 4
; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, i32* [[B]], i32 1
; CHECK-NEXT: [[I3:%.*]] = load i32, i32* [[ARRAYIDX3]], align 4
; CHECK-NEXT: [[ADD2:%.*]] = add i32 [[I2]], [[I3]]
; CHECK-NEXT: [[CALL2:%.*]] = tail call i32 @llvm.ctlz.i32(i32 [[ADD2]], i1 false) #3
; CHECK-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds i32, i32* [[A]], i32 2
; CHECK-NEXT: [[I4:%.*]] = load i32, i32* [[ARRAYIDX4]], align 4
; CHECK-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds i32, i32* [[B]], i32 2
; CHECK-NEXT: [[I5:%.*]] = load i32, i32* [[ARRAYIDX5]], align 4
; CHECK-NEXT: [[ADD3:%.*]] = add i32 [[I4]], [[I5]]
; CHECK-NEXT: [[CALL3:%.*]] = tail call i32 @llvm.ctlz.i32(i32 [[ADD3]], i1 true) #3
; CHECK-NEXT: [[ARRAYIDX6:%.*]] = getelementptr inbounds i32, i32* [[A]], i32 3
; CHECK-NEXT: [[I6:%.*]] = load i32, i32* [[ARRAYIDX6]], align 4
; CHECK-NEXT: [[ARRAYIDX7:%.*]] = getelementptr inbounds i32, i32* [[B]], i32 3
; CHECK-NEXT: [[I7:%.*]] = load i32, i32* [[ARRAYIDX7]], align 4
; CHECK-NEXT: [[ADD4:%.*]] = add i32 [[I6]], [[I7]]
; CHECK-NEXT: [[CALL4:%.*]] = tail call i32 @llvm.ctlz.i32(i32 [[ADD4]], i1 false) #3
; CHECK-NEXT: store i32 [[CALL1]], i32* [[C:%.*]], align 4
; CHECK-NEXT: [[ARRAYIDX8:%.*]] = getelementptr inbounds i32, i32* [[C]], i32 1
; CHECK-NEXT: store i32 [[CALL2]], i32* [[ARRAYIDX8]], align 4
; CHECK-NEXT: [[ARRAYIDX9:%.*]] = getelementptr inbounds i32, i32* [[C]], i32 2
; CHECK-NEXT: store i32 [[CALL3]], i32* [[ARRAYIDX9]], align 4
; CHECK-NEXT: [[ARRAYIDX10:%.*]] = getelementptr inbounds i32, i32* [[C]], i32 3
; CHECK-NEXT: store i32 [[CALL4]], i32* [[ARRAYIDX10]], align 4
; CHECK-NEXT: ret void
;
entry:
%i0 = load i32, i32* %a, align 4
%i1 = load i32, i32* %b, align 4
%add1 = add i32 %i0, %i1
%call1 = tail call i32 @llvm.ctlz.i32(i32 %add1,i1 true) nounwind readnone
%arrayidx2 = getelementptr inbounds i32, i32* %a, i32 1
%i2 = load i32, i32* %arrayidx2, align 4
%arrayidx3 = getelementptr inbounds i32, i32* %b, i32 1
%i3 = load i32, i32* %arrayidx3, align 4
%add2 = add i32 %i2, %i3
%call2 = tail call i32 @llvm.ctlz.i32(i32 %add2,i1 false) nounwind readnone
%arrayidx4 = getelementptr inbounds i32, i32* %a, i32 2
%i4 = load i32, i32* %arrayidx4, align 4
%arrayidx5 = getelementptr inbounds i32, i32* %b, i32 2
%i5 = load i32, i32* %arrayidx5, align 4
%add3 = add i32 %i4, %i5
%call3 = tail call i32 @llvm.ctlz.i32(i32 %add3,i1 true) nounwind readnone
%arrayidx6 = getelementptr inbounds i32, i32* %a, i32 3
%i6 = load i32, i32* %arrayidx6, align 4
%arrayidx7 = getelementptr inbounds i32, i32* %b, i32 3
%i7 = load i32, i32* %arrayidx7, align 4
%add4 = add i32 %i6, %i7
%call4 = tail call i32 @llvm.ctlz.i32(i32 %add4,i1 false) nounwind readnone
store i32 %call1, i32* %c, align 4
%arrayidx8 = getelementptr inbounds i32, i32* %c, i32 1
store i32 %call2, i32* %arrayidx8, align 4
%arrayidx9 = getelementptr inbounds i32, i32* %c, i32 2
store i32 %call3, i32* %arrayidx9, align 4
%arrayidx10 = getelementptr inbounds i32, i32* %c, i32 3
store i32 %call4, i32* %arrayidx10, align 4
ret void
}
declare i32 @llvm.cttz.i32(i32,i1) nounwind readnone
define void @vec_cttz_i32(i32* %a, i32* %b, i32* %c, i1) {
; CHECK-LABEL: @vec_cttz_i32(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP1:%.*]] = bitcast i32* [[A:%.*]] to <4 x i32>*
; CHECK-NEXT: [[TMP2:%.*]] = load <4 x i32>, <4 x i32>* [[TMP1]], align 4
; CHECK-NEXT: [[TMP3:%.*]] = bitcast i32* [[B:%.*]] to <4 x i32>*
; CHECK-NEXT: [[TMP4:%.*]] = load <4 x i32>, <4 x i32>* [[TMP3]], align 4
; CHECK-NEXT: [[TMP5:%.*]] = add <4 x i32> [[TMP2]], [[TMP4]]
; CHECK-NEXT: [[TMP6:%.*]] = call <4 x i32> @llvm.cttz.v4i32(<4 x i32> [[TMP5]], i1 true)
; CHECK-NEXT: [[TMP7:%.*]] = bitcast i32* [[C:%.*]] to <4 x i32>*
; CHECK-NEXT: store <4 x i32> [[TMP6]], <4 x i32>* [[TMP7]], align 4
; CHECK-NEXT: ret void
;
entry:
%i0 = load i32, i32* %a, align 4
%i1 = load i32, i32* %b, align 4
%add1 = add i32 %i0, %i1
%call1 = tail call i32 @llvm.cttz.i32(i32 %add1,i1 true) nounwind readnone
%arrayidx2 = getelementptr inbounds i32, i32* %a, i32 1
%i2 = load i32, i32* %arrayidx2, align 4
%arrayidx3 = getelementptr inbounds i32, i32* %b, i32 1
%i3 = load i32, i32* %arrayidx3, align 4
%add2 = add i32 %i2, %i3
%call2 = tail call i32 @llvm.cttz.i32(i32 %add2,i1 true) nounwind readnone
%arrayidx4 = getelementptr inbounds i32, i32* %a, i32 2
%i4 = load i32, i32* %arrayidx4, align 4
%arrayidx5 = getelementptr inbounds i32, i32* %b, i32 2
%i5 = load i32, i32* %arrayidx5, align 4
%add3 = add i32 %i4, %i5
%call3 = tail call i32 @llvm.cttz.i32(i32 %add3,i1 true) nounwind readnone
%arrayidx6 = getelementptr inbounds i32, i32* %a, i32 3
%i6 = load i32, i32* %arrayidx6, align 4
%arrayidx7 = getelementptr inbounds i32, i32* %b, i32 3
%i7 = load i32, i32* %arrayidx7, align 4
%add4 = add i32 %i6, %i7
%call4 = tail call i32 @llvm.cttz.i32(i32 %add4,i1 true) nounwind readnone
store i32 %call1, i32* %c, align 4
%arrayidx8 = getelementptr inbounds i32, i32* %c, i32 1
store i32 %call2, i32* %arrayidx8, align 4
%arrayidx9 = getelementptr inbounds i32, i32* %c, i32 2
store i32 %call3, i32* %arrayidx9, align 4
%arrayidx10 = getelementptr inbounds i32, i32* %c, i32 3
store i32 %call4, i32* %arrayidx10, align 4
ret void
}
define void @vec_cttz_i32_neg(i32* %a, i32* %b, i32* %c, i1) {
; CHECK-LABEL: @vec_cttz_i32_neg(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[I0:%.*]] = load i32, i32* [[A:%.*]], align 4
; CHECK-NEXT: [[I1:%.*]] = load i32, i32* [[B:%.*]], align 4
; CHECK-NEXT: [[ADD1:%.*]] = add i32 [[I0]], [[I1]]
; CHECK-NEXT: [[CALL1:%.*]] = tail call i32 @llvm.cttz.i32(i32 [[ADD1]], i1 true) #3
; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, i32* [[A]], i32 1
; CHECK-NEXT: [[I2:%.*]] = load i32, i32* [[ARRAYIDX2]], align 4
; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, i32* [[B]], i32 1
; CHECK-NEXT: [[I3:%.*]] = load i32, i32* [[ARRAYIDX3]], align 4
; CHECK-NEXT: [[ADD2:%.*]] = add i32 [[I2]], [[I3]]
; CHECK-NEXT: [[CALL2:%.*]] = tail call i32 @llvm.cttz.i32(i32 [[ADD2]], i1 false) #3
; CHECK-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds i32, i32* [[A]], i32 2
; CHECK-NEXT: [[I4:%.*]] = load i32, i32* [[ARRAYIDX4]], align 4
; CHECK-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds i32, i32* [[B]], i32 2
; CHECK-NEXT: [[I5:%.*]] = load i32, i32* [[ARRAYIDX5]], align 4
; CHECK-NEXT: [[ADD3:%.*]] = add i32 [[I4]], [[I5]]
; CHECK-NEXT: [[CALL3:%.*]] = tail call i32 @llvm.cttz.i32(i32 [[ADD3]], i1 true) #3
; CHECK-NEXT: [[ARRAYIDX6:%.*]] = getelementptr inbounds i32, i32* [[A]], i32 3
; CHECK-NEXT: [[I6:%.*]] = load i32, i32* [[ARRAYIDX6]], align 4
; CHECK-NEXT: [[ARRAYIDX7:%.*]] = getelementptr inbounds i32, i32* [[B]], i32 3
; CHECK-NEXT: [[I7:%.*]] = load i32, i32* [[ARRAYIDX7]], align 4
; CHECK-NEXT: [[ADD4:%.*]] = add i32 [[I6]], [[I7]]
; CHECK-NEXT: [[CALL4:%.*]] = tail call i32 @llvm.cttz.i32(i32 [[ADD4]], i1 false) #3
; CHECK-NEXT: store i32 [[CALL1]], i32* [[C:%.*]], align 4
; CHECK-NEXT: [[ARRAYIDX8:%.*]] = getelementptr inbounds i32, i32* [[C]], i32 1
; CHECK-NEXT: store i32 [[CALL2]], i32* [[ARRAYIDX8]], align 4
; CHECK-NEXT: [[ARRAYIDX9:%.*]] = getelementptr inbounds i32, i32* [[C]], i32 2
; CHECK-NEXT: store i32 [[CALL3]], i32* [[ARRAYIDX9]], align 4
; CHECK-NEXT: [[ARRAYIDX10:%.*]] = getelementptr inbounds i32, i32* [[C]], i32 3
; CHECK-NEXT: store i32 [[CALL4]], i32* [[ARRAYIDX10]], align 4
; CHECK-NEXT: ret void
;
entry:
%i0 = load i32, i32* %a, align 4
%i1 = load i32, i32* %b, align 4
%add1 = add i32 %i0, %i1
%call1 = tail call i32 @llvm.cttz.i32(i32 %add1,i1 true) nounwind readnone
%arrayidx2 = getelementptr inbounds i32, i32* %a, i32 1
%i2 = load i32, i32* %arrayidx2, align 4
%arrayidx3 = getelementptr inbounds i32, i32* %b, i32 1
%i3 = load i32, i32* %arrayidx3, align 4
%add2 = add i32 %i2, %i3
%call2 = tail call i32 @llvm.cttz.i32(i32 %add2,i1 false) nounwind readnone
%arrayidx4 = getelementptr inbounds i32, i32* %a, i32 2
%i4 = load i32, i32* %arrayidx4, align 4
%arrayidx5 = getelementptr inbounds i32, i32* %b, i32 2
%i5 = load i32, i32* %arrayidx5, align 4
%add3 = add i32 %i4, %i5
%call3 = tail call i32 @llvm.cttz.i32(i32 %add3,i1 true) nounwind readnone
%arrayidx6 = getelementptr inbounds i32, i32* %a, i32 3
%i6 = load i32, i32* %arrayidx6, align 4
%arrayidx7 = getelementptr inbounds i32, i32* %b, i32 3
%i7 = load i32, i32* %arrayidx7, align 4
%add4 = add i32 %i6, %i7
%call4 = tail call i32 @llvm.cttz.i32(i32 %add4,i1 false) nounwind readnone
store i32 %call1, i32* %c, align 4
%arrayidx8 = getelementptr inbounds i32, i32* %c, i32 1
store i32 %call2, i32* %arrayidx8, align 4
%arrayidx9 = getelementptr inbounds i32, i32* %c, i32 2
store i32 %call3, i32* %arrayidx9, align 4
%arrayidx10 = getelementptr inbounds i32, i32* %c, i32 3
store i32 %call4, i32* %arrayidx10, align 4
ret void
}
declare float @llvm.powi.f32(float, i32)
define void @vec_powi_f32(float* %a, float* %b, float* %c, i32 %P) {
; CHECK-LABEL: @vec_powi_f32(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = bitcast float* [[A:%.*]] to <4 x float>*
; CHECK-NEXT: [[TMP1:%.*]] = load <4 x float>, <4 x float>* [[TMP0]], align 4
; CHECK-NEXT: [[TMP2:%.*]] = bitcast float* [[B:%.*]] to <4 x float>*
; CHECK-NEXT: [[TMP3:%.*]] = load <4 x float>, <4 x float>* [[TMP2]], align 4
; CHECK-NEXT: [[TMP4:%.*]] = fadd <4 x float> [[TMP1]], [[TMP3]]
; CHECK-NEXT: [[TMP5:%.*]] = call <4 x float> @llvm.powi.v4f32(<4 x float> [[TMP4]], i32 [[P:%.*]])
; CHECK-NEXT: [[TMP6:%.*]] = bitcast float* [[C:%.*]] to <4 x float>*
; CHECK-NEXT: store <4 x float> [[TMP5]], <4 x float>* [[TMP6]], align 4
; CHECK-NEXT: ret void
;
entry:
%i0 = load float, float* %a, align 4
%i1 = load float, float* %b, align 4
%add1 = fadd float %i0, %i1
%call1 = tail call float @llvm.powi.f32(float %add1,i32 %P) nounwind readnone
%arrayidx2 = getelementptr inbounds float, float* %a, i32 1
%i2 = load float, float* %arrayidx2, align 4
%arrayidx3 = getelementptr inbounds float, float* %b, i32 1
%i3 = load float, float* %arrayidx3, align 4
%add2 = fadd float %i2, %i3
%call2 = tail call float @llvm.powi.f32(float %add2,i32 %P) nounwind readnone
%arrayidx4 = getelementptr inbounds float, float* %a, i32 2
%i4 = load float, float* %arrayidx4, align 4
%arrayidx5 = getelementptr inbounds float, float* %b, i32 2
%i5 = load float, float* %arrayidx5, align 4
%add3 = fadd float %i4, %i5
%call3 = tail call float @llvm.powi.f32(float %add3,i32 %P) nounwind readnone
%arrayidx6 = getelementptr inbounds float, float* %a, i32 3
%i6 = load float, float* %arrayidx6, align 4
%arrayidx7 = getelementptr inbounds float, float* %b, i32 3
%i7 = load float, float* %arrayidx7, align 4
%add4 = fadd float %i6, %i7
%call4 = tail call float @llvm.powi.f32(float %add4,i32 %P) nounwind readnone
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
}
define void @vec_powi_f32_neg(float* %a, float* %b, float* %c, i32 %P, i32 %Q) {
; CHECK-LABEL: @vec_powi_f32_neg(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[I0:%.*]] = load float, float* [[A:%.*]], align 4
; CHECK-NEXT: [[I1:%.*]] = load float, float* [[B:%.*]], align 4
; CHECK-NEXT: [[ADD1:%.*]] = fadd float [[I0]], [[I1]]
; CHECK-NEXT: [[CALL1:%.*]] = tail call float @llvm.powi.f32(float [[ADD1]], i32 [[P:%.*]]) #3
; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds float, float* [[A]], i32 1
; CHECK-NEXT: [[I2:%.*]] = load float, float* [[ARRAYIDX2]], align 4
; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds float, float* [[B]], i32 1
; CHECK-NEXT: [[I3:%.*]] = load float, float* [[ARRAYIDX3]], align 4
; CHECK-NEXT: [[ADD2:%.*]] = fadd float [[I2]], [[I3]]
; CHECK-NEXT: [[CALL2:%.*]] = tail call float @llvm.powi.f32(float [[ADD2]], i32 [[Q:%.*]]) #3
; CHECK-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds float, float* [[A]], i32 2
; CHECK-NEXT: [[I4:%.*]] = load float, float* [[ARRAYIDX4]], align 4
; CHECK-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds float, float* [[B]], i32 2
; CHECK-NEXT: [[I5:%.*]] = load float, float* [[ARRAYIDX5]], align 4
; CHECK-NEXT: [[ADD3:%.*]] = fadd float [[I4]], [[I5]]
; CHECK-NEXT: [[CALL3:%.*]] = tail call float @llvm.powi.f32(float [[ADD3]], i32 [[P]]) #3
; CHECK-NEXT: [[ARRAYIDX6:%.*]] = getelementptr inbounds float, float* [[A]], i32 3
; CHECK-NEXT: [[I6:%.*]] = load float, float* [[ARRAYIDX6]], align 4
; CHECK-NEXT: [[ARRAYIDX7:%.*]] = getelementptr inbounds float, float* [[B]], i32 3
; CHECK-NEXT: [[I7:%.*]] = load float, float* [[ARRAYIDX7]], align 4
; CHECK-NEXT: [[ADD4:%.*]] = fadd float [[I6]], [[I7]]
; CHECK-NEXT: [[CALL4:%.*]] = tail call float @llvm.powi.f32(float [[ADD4]], i32 [[Q]]) #3
; 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
%i1 = load float, float* %b, align 4
%add1 = fadd float %i0, %i1
%call1 = tail call float @llvm.powi.f32(float %add1,i32 %P) nounwind readnone
%arrayidx2 = getelementptr inbounds float, float* %a, i32 1
%i2 = load float, float* %arrayidx2, align 4
%arrayidx3 = getelementptr inbounds float, float* %b, i32 1
%i3 = load float, float* %arrayidx3, align 4
%add2 = fadd float %i2, %i3
%call2 = tail call float @llvm.powi.f32(float %add2,i32 %Q) nounwind readnone
%arrayidx4 = getelementptr inbounds float, float* %a, i32 2
%i4 = load float, float* %arrayidx4, align 4
%arrayidx5 = getelementptr inbounds float, float* %b, i32 2
%i5 = load float, float* %arrayidx5, align 4
%add3 = fadd float %i4, %i5
%call3 = tail call float @llvm.powi.f32(float %add3,i32 %P) nounwind readnone
%arrayidx6 = getelementptr inbounds float, float* %a, i32 3
%i6 = load float, float* %arrayidx6, align 4
%arrayidx7 = getelementptr inbounds float, float* %b, i32 3
%i7 = load float, float* %arrayidx7, align 4
%add4 = fadd float %i6, %i7
%call4 = tail call float @llvm.powi.f32(float %add4,i32 %Q) nounwind readnone
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
}