llvm/test/Transforms/LoopVectorize/X86/libm-vector-calls-finite.ll

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --filter "call.*@" --version 6
; RUN: opt -vector-library=LIBMVEC -passes=inject-tli-mappings,loop-vectorize -force-vector-width=2 -force-vector-interleave=1 -S < %s | FileCheck %s --check-prefixes=CHECK-VF2
; RUN: opt -vector-library=LIBMVEC -passes=inject-tli-mappings,loop-vectorize -force-vector-width=4 -force-vector-interleave=1 -S < %s | FileCheck %s --check-prefixes=CHECK-VF4
; RUN: opt -vector-library=LIBMVEC -passes=inject-tli-mappings,loop-vectorize -force-vector-width=8 -force-vector-interleave=1 -S < %s | FileCheck %s --check-prefixes=CHECK-VF8
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"

define void @exp_f32(ptr nocapture %varray) {
; CHECK-VF2-LABEL: define void @exp_f32(
; CHECK-VF2-SAME: ptr captures(none) [[VARRAY:%.*]]) {
; CHECK-VF2:    [[TMP2:%.*]] = tail call fast float @__expf_finite(float [[TMP1:%.*]]) #[[ATTR0:[0-9]+]]
; CHECK-VF2:    [[TMP4:%.*]] = tail call fast float @__expf_finite(float [[TMP3:%.*]]) #[[ATTR0]]
;
; CHECK-VF4-LABEL: define void @exp_f32(
; CHECK-VF4-SAME: ptr captures(none) [[VARRAY:%.*]]) {
; CHECK-VF4:    [[TMP1:%.*]] = call fast <4 x float> @_ZGVbN4v___expf_finite(<4 x float> [[TMP0:%.*]])
;
; CHECK-VF8-LABEL: define void @exp_f32(
; CHECK-VF8-SAME: ptr captures(none) [[VARRAY:%.*]]) {
; CHECK-VF8:    [[TMP1:%.*]] = call fast <8 x float> @_ZGVdN8v___expf_finite(<8 x float> [[TMP0:%.*]])
;
entry:
  br label %for.body

for.body:
  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
  %tmp = trunc i64 %indvars.iv to i32
  %conv = sitofp i32 %tmp to float
  %call = tail call fast float @__expf_finite(float %conv)
  %arrayidx = getelementptr inbounds float, ptr %varray, i64 %indvars.iv
  store float %call, ptr %arrayidx, align 4
  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
  %exitcond = icmp eq i64 %indvars.iv.next, 1000
  br i1 %exitcond, label %for.end, label %for.body

for.end:
  ret void
}

define void @exp_f64(ptr nocapture %varray) {
; CHECK-VF2-LABEL: define void @exp_f64(
; CHECK-VF2-SAME: ptr captures(none) [[VARRAY:%.*]]) {
; CHECK-VF2:    [[TMP1:%.*]] = call fast <2 x double> @_ZGVbN2v___exp_finite(<2 x double> [[TMP0:%.*]])
;
; CHECK-VF4-LABEL: define void @exp_f64(
; CHECK-VF4-SAME: ptr captures(none) [[VARRAY:%.*]]) {
; CHECK-VF4:    [[TMP1:%.*]] = call fast <4 x double> @_ZGVdN4v___exp_finite(<4 x double> [[TMP0:%.*]])
;
; CHECK-VF8-LABEL: define void @exp_f64(
; CHECK-VF8-SAME: ptr captures(none) [[VARRAY:%.*]]) {
; CHECK-VF8:    [[TMP2:%.*]] = tail call fast double @__exp_finite(double [[TMP1:%.*]]) #[[ATTR0:[0-9]+]]
; CHECK-VF8:    [[TMP4:%.*]] = tail call fast double @__exp_finite(double [[TMP3:%.*]]) #[[ATTR0]]
; CHECK-VF8:    [[TMP6:%.*]] = tail call fast double @__exp_finite(double [[TMP5:%.*]]) #[[ATTR0]]
; CHECK-VF8:    [[TMP8:%.*]] = tail call fast double @__exp_finite(double [[TMP7:%.*]]) #[[ATTR0]]
; CHECK-VF8:    [[TMP10:%.*]] = tail call fast double @__exp_finite(double [[TMP9:%.*]]) #[[ATTR0]]
; CHECK-VF8:    [[TMP12:%.*]] = tail call fast double @__exp_finite(double [[TMP11:%.*]]) #[[ATTR0]]
; CHECK-VF8:    [[TMP14:%.*]] = tail call fast double @__exp_finite(double [[TMP13:%.*]]) #[[ATTR0]]
; CHECK-VF8:    [[TMP16:%.*]] = tail call fast double @__exp_finite(double [[TMP15:%.*]]) #[[ATTR0]]
;
entry:
  br label %for.body

for.body:
  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
  %tmp = trunc i64 %indvars.iv to i32
  %conv = sitofp i32 %tmp to double
  %call = tail call fast double @__exp_finite(double %conv)
  %arrayidx = getelementptr inbounds double, ptr %varray, i64 %indvars.iv
  store double %call, ptr %arrayidx, align 4
  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
  %exitcond = icmp eq i64 %indvars.iv.next, 1000
  br i1 %exitcond, label %for.end, label %for.body

for.end:
  ret void
}

define void @log_f32(ptr nocapture %varray) {
; CHECK-VF2-LABEL: define void @log_f32(
; CHECK-VF2-SAME: ptr captures(none) [[VARRAY:%.*]]) {
; CHECK-VF2:    [[TMP2:%.*]] = tail call fast float @__logf_finite(float [[TMP1:%.*]]) #[[ATTR1:[0-9]+]]
; CHECK-VF2:    [[TMP4:%.*]] = tail call fast float @__logf_finite(float [[TMP3:%.*]]) #[[ATTR1]]
;
; CHECK-VF4-LABEL: define void @log_f32(
; CHECK-VF4-SAME: ptr captures(none) [[VARRAY:%.*]]) {
; CHECK-VF4:    [[TMP1:%.*]] = call fast <4 x float> @_ZGVbN4v___logf_finite(<4 x float> [[TMP0:%.*]])
;
; CHECK-VF8-LABEL: define void @log_f32(
; CHECK-VF8-SAME: ptr captures(none) [[VARRAY:%.*]]) {
; CHECK-VF8:    [[TMP1:%.*]] = call fast <8 x float> @_ZGVdN8v___logf_finite(<8 x float> [[TMP0:%.*]])
;
entry:
  br label %for.body

for.body:
  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
  %tmp = trunc i64 %indvars.iv to i32
  %conv = sitofp i32 %tmp to float
  %call = tail call fast float @__logf_finite(float %conv)
  %arrayidx = getelementptr inbounds float, ptr %varray, i64 %indvars.iv
  store float %call, ptr %arrayidx, align 4
  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
  %exitcond = icmp eq i64 %indvars.iv.next, 1000
  br i1 %exitcond, label %for.end, label %for.body

for.end:
  ret void
}

define void @log_f64(ptr nocapture %varray) {
; CHECK-VF2-LABEL: define void @log_f64(
; CHECK-VF2-SAME: ptr captures(none) [[VARRAY:%.*]]) {
; CHECK-VF2:    [[TMP1:%.*]] = call fast <2 x double> @_ZGVbN2v___log_finite(<2 x double> [[TMP0:%.*]])
;
; CHECK-VF4-LABEL: define void @log_f64(
; CHECK-VF4-SAME: ptr captures(none) [[VARRAY:%.*]]) {
; CHECK-VF4:    [[TMP1:%.*]] = call fast <4 x double> @_ZGVdN4v___log_finite(<4 x double> [[TMP0:%.*]])
;
; CHECK-VF8-LABEL: define void @log_f64(
; CHECK-VF8-SAME: ptr captures(none) [[VARRAY:%.*]]) {
; CHECK-VF8:    [[TMP2:%.*]] = tail call fast double @__log_finite(double [[TMP1:%.*]]) #[[ATTR1:[0-9]+]]
; CHECK-VF8:    [[TMP4:%.*]] = tail call fast double @__log_finite(double [[TMP3:%.*]]) #[[ATTR1]]
; CHECK-VF8:    [[TMP6:%.*]] = tail call fast double @__log_finite(double [[TMP5:%.*]]) #[[ATTR1]]
; CHECK-VF8:    [[TMP8:%.*]] = tail call fast double @__log_finite(double [[TMP7:%.*]]) #[[ATTR1]]
; CHECK-VF8:    [[TMP10:%.*]] = tail call fast double @__log_finite(double [[TMP9:%.*]]) #[[ATTR1]]
; CHECK-VF8:    [[TMP12:%.*]] = tail call fast double @__log_finite(double [[TMP11:%.*]]) #[[ATTR1]]
; CHECK-VF8:    [[TMP14:%.*]] = tail call fast double @__log_finite(double [[TMP13:%.*]]) #[[ATTR1]]
; CHECK-VF8:    [[TMP16:%.*]] = tail call fast double @__log_finite(double [[TMP15:%.*]]) #[[ATTR1]]
;
entry:
  br label %for.body

for.body:
  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
  %tmp = trunc i64 %indvars.iv to i32
  %conv = sitofp i32 %tmp to double
  %call = tail call fast double @__log_finite(double %conv)
  %arrayidx = getelementptr inbounds double, ptr %varray, i64 %indvars.iv
  store double %call, ptr %arrayidx, align 4
  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
  %exitcond = icmp eq i64 %indvars.iv.next, 1000
  br i1 %exitcond, label %for.end, label %for.body

for.end:
  ret void
}


define void @pow_f32(ptr nocapture %varray, ptr nocapture readonly %exp) {
; CHECK-VF2-LABEL: define void @pow_f32(
; CHECK-VF2-SAME: ptr captures(none) [[VARRAY:%.*]], ptr readonly captures(none) [[EXP:%.*]]) {
; CHECK-VF2:    [[TMP6:%.*]] = tail call fast float @__powf_finite(float [[TMP4:%.*]], float [[TMP5:%.*]]) #[[ATTR2:[0-9]+]]
; CHECK-VF2:    [[TMP9:%.*]] = tail call fast float @__powf_finite(float [[TMP7:%.*]], float [[TMP8:%.*]]) #[[ATTR2]]
; CHECK-VF2:    [[I2:%.*]] = tail call fast float @__powf_finite(float [[CONV:%.*]], float [[I1:%.*]]) #[[ATTR2]]
;
; CHECK-VF4-LABEL: define void @pow_f32(
; CHECK-VF4-SAME: ptr captures(none) [[VARRAY:%.*]], ptr readonly captures(none) [[EXP:%.*]]) {
; CHECK-VF4:    [[TMP3:%.*]] = call fast <4 x float> @_ZGVbN4vv___powf_finite(<4 x float> [[TMP1:%.*]], <4 x float> [[WIDE_LOAD:%.*]])
; CHECK-VF4:    [[I2:%.*]] = tail call fast float @__powf_finite(float [[CONV:%.*]], float [[I1:%.*]]) #[[ATTR0:[0-9]+]]
;
; CHECK-VF8-LABEL: define void @pow_f32(
; CHECK-VF8-SAME: ptr captures(none) [[VARRAY:%.*]], ptr readonly captures(none) [[EXP:%.*]]) {
; CHECK-VF8:    [[TMP3:%.*]] = call fast <8 x float> @_ZGVdN8vv___powf_finite(<8 x float> [[TMP1:%.*]], <8 x float> [[WIDE_LOAD:%.*]])
; CHECK-VF8:    [[I2:%.*]] = tail call fast float @__powf_finite(float [[CONV:%.*]], float [[I1:%.*]]) #[[ATTR2:[0-9]+]]
;
entry:
  br label %for.body

for.body:
  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
  %tmp = trunc i64 %indvars.iv to i32
  %conv = sitofp i32 %tmp to float
  %arrayidx = getelementptr inbounds float, ptr %exp, i64 %indvars.iv
  %i1 = load float, ptr %arrayidx, align 4
  %i2 = tail call fast float @__powf_finite(float %conv, float %i1)
  %arrayidx2 = getelementptr inbounds float, ptr %varray, i64 %indvars.iv
  store float %i2, ptr %arrayidx2, align 4
  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
  %exitcond = icmp eq i64 %indvars.iv.next, 1000
  br i1 %exitcond, label %for.end, label %for.body

for.end:
  ret void
}

define void @pow_f64(ptr nocapture %varray, ptr nocapture readonly %exp) {
; CHECK-VF2-LABEL: define void @pow_f64(
; CHECK-VF2-SAME: ptr captures(none) [[VARRAY:%.*]], ptr readonly captures(none) [[EXP:%.*]]) {
; CHECK-VF2:    [[TMP3:%.*]] = call fast <2 x double> @_ZGVbN2vv___pow_finite(<2 x double> [[TMP1:%.*]], <2 x double> [[WIDE_LOAD:%.*]])
; CHECK-VF2:    [[I2:%.*]] = tail call fast double @__pow_finite(double [[CONV:%.*]], double [[I1:%.*]]) #[[ATTR3:[0-9]+]]
;
; CHECK-VF4-LABEL: define void @pow_f64(
; CHECK-VF4-SAME: ptr captures(none) [[VARRAY:%.*]], ptr readonly captures(none) [[EXP:%.*]]) {
; CHECK-VF4:    [[TMP3:%.*]] = call fast <4 x double> @_ZGVdN4vv___pow_finite(<4 x double> [[TMP1:%.*]], <4 x double> [[WIDE_LOAD:%.*]])
; CHECK-VF4:    [[I2:%.*]] = tail call fast double @__pow_finite(double [[CONV:%.*]], double [[I1:%.*]]) #[[ATTR1:[0-9]+]]
;
; CHECK-VF8-LABEL: define void @pow_f64(
; CHECK-VF8-SAME: ptr captures(none) [[VARRAY:%.*]], ptr readonly captures(none) [[EXP:%.*]]) {
; CHECK-VF8:    [[TMP6:%.*]] = tail call fast double @__pow_finite(double [[TMP4:%.*]], double [[TMP5:%.*]]) #[[ATTR3:[0-9]+]]
; CHECK-VF8:    [[TMP9:%.*]] = tail call fast double @__pow_finite(double [[TMP7:%.*]], double [[TMP8:%.*]]) #[[ATTR3]]
; CHECK-VF8:    [[TMP12:%.*]] = tail call fast double @__pow_finite(double [[TMP10:%.*]], double [[TMP11:%.*]]) #[[ATTR3]]
; CHECK-VF8:    [[TMP15:%.*]] = tail call fast double @__pow_finite(double [[TMP13:%.*]], double [[TMP14:%.*]]) #[[ATTR3]]
; CHECK-VF8:    [[TMP18:%.*]] = tail call fast double @__pow_finite(double [[TMP16:%.*]], double [[TMP17:%.*]]) #[[ATTR3]]
; CHECK-VF8:    [[TMP21:%.*]] = tail call fast double @__pow_finite(double [[TMP19:%.*]], double [[TMP20:%.*]]) #[[ATTR3]]
; CHECK-VF8:    [[TMP24:%.*]] = tail call fast double @__pow_finite(double [[TMP22:%.*]], double [[TMP23:%.*]]) #[[ATTR3]]
; CHECK-VF8:    [[TMP27:%.*]] = tail call fast double @__pow_finite(double [[TMP25:%.*]], double [[TMP26:%.*]]) #[[ATTR3]]
; CHECK-VF8:    [[I2:%.*]] = tail call fast double @__pow_finite(double [[CONV:%.*]], double [[I1:%.*]]) #[[ATTR3]]
;
entry:
  br label %for.body

for.body:
  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
  %tmp = trunc i64 %indvars.iv to i32
  %conv = sitofp i32 %tmp to double
  %arrayidx = getelementptr inbounds double, ptr %exp, i64 %indvars.iv
  %i1 = load double, ptr %arrayidx, align 4
  %i2 = tail call fast double @__pow_finite(double %conv, double %i1)
  %arrayidx2 = getelementptr inbounds double, ptr %varray, i64 %indvars.iv
  store double %i2, ptr %arrayidx2, align 4
  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
  %exitcond = icmp eq i64 %indvars.iv.next, 1000
  br i1 %exitcond, label %for.end, label %for.body

for.end:
  ret void
}

declare float @__expf_finite(float) #0
declare double @__exp_finite(double) #0
declare float @__logf_finite(float) #0
declare double @__log_finite(double) #0
declare float @__powf_finite(float, float) #0
declare double @__pow_finite(double, double) #0