path: root/test/Transforms/LoopVectorize/intrinsic.ll

; RUN: opt < %s  -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S | 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-unknown-linux-gnu"

;CHECK: @sqrt_f32
;CHECK: llvm.sqrt.v4f32
;CHECK: ret void
define void @sqrt_f32(i32 %n, float* noalias %y, float* noalias %x) nounwind uwtable {
entry:
  %cmp6 = icmp sgt i32 %n, 0
  br i1 %cmp6, label %for.body, label %for.end

for.body:                                         ; preds = %entry, %for.body
  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
  %arrayidx = getelementptr inbounds float* %y, i64 %indvars.iv
  %0 = load float* %arrayidx, align 4
  %call = tail call float @llvm.sqrt.f32(float %0) nounwind readnone
  %arrayidx2 = getelementptr inbounds float* %x, i64 %indvars.iv
  store float %call, float* %arrayidx2, align 4
  %indvars.iv.next = add i64 %indvars.iv, 1
  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
  %exitcond = icmp eq i32 %lftr.wideiv, %n
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body, %entry
  ret void
}

declare float @llvm.sqrt.f32(float) nounwind readnone

;CHECK: @sqrt_f64
;CHECK: llvm.sqrt.v4f64
;CHECK: ret void
define void @sqrt_f64(i32 %n, double* noalias %y, double* noalias %x) nounwind uwtable {
entry:
  %cmp6 = icmp sgt i32 %n, 0
  br i1 %cmp6, label %for.body, label %for.end

for.body:                                         ; preds = %entry, %for.body
  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
  %arrayidx = getelementptr inbounds double* %y, i64 %indvars.iv
  %0 = load double* %arrayidx, align 8
  %call = tail call double @llvm.sqrt.f64(double %0) nounwind readnone
  %arrayidx2 = getelementptr inbounds double* %x, i64 %indvars.iv
  store double %call, double* %arrayidx2, align 8
  %indvars.iv.next = add i64 %indvars.iv, 1
  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
  %exitcond = icmp eq i32 %lftr.wideiv, %n
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body, %entry
  ret void
}

declare double @llvm.sqrt.f64(double) nounwind readnone

;CHECK: @sin_f32
;CHECK: llvm.sin.v4f32
;CHECK: ret void
define void @sin_f32(i32 %n, float* noalias %y, float* noalias %x) nounwind uwtable {
entry:
  %cmp6 = icmp sgt i32 %n, 0
  br i1 %cmp6, label %for.body, label %for.end

for.body:                                         ; preds = %entry, %for.body
  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
  %arrayidx = getelementptr inbounds float* %y, i64 %indvars.iv
  %0 = load float* %arrayidx, align 4
  %call = tail call float @llvm.sin.f32(float %0) nounwind readnone
  %arrayidx2 = getelementptr inbounds float* %x, i64 %indvars.iv
  store float %call, float* %arrayidx2, align 4
  %indvars.iv.next = add i64 %indvars.iv, 1
  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
  %exitcond = icmp eq i32 %lftr.wideiv, %n
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body, %entry
  ret void
}

declare float @llvm.sin.f32(float) nounwind readnone

;CHECK: @sin_f64
;CHECK: llvm.sin.v4f64
;CHECK: ret void
define void @sin_f64(i32 %n, double* noalias %y, double* noalias %x) nounwind uwtable {
entry:
  %cmp6 = icmp sgt i32 %n, 0
  br i1 %cmp6, label %for.body, label %for.end

for.body:                                         ; preds = %entry, %for.body
  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
  %arrayidx = getelementptr inbounds double* %y, i64 %indvars.iv
  %0 = load double* %arrayidx, align 8
  %call =