summaryrefslogtreecommitdiffstats
path: root/llvm/test/CodeGen/X86/vector-sqrt.ll
diff options
context:
space:
mode:
Diffstat (limited to 'llvm/test/CodeGen/X86/vector-sqrt.ll')
-rw-r--r--llvm/test/CodeGen/X86/vector-sqrt.ll77
1 files changed, 77 insertions, 0 deletions
diff --git a/llvm/test/CodeGen/X86/vector-sqrt.ll b/llvm/test/CodeGen/X86/vector-sqrt.ll
new file mode 100644
index 00000000000..71043379334
--- /dev/null
+++ b/llvm/test/CodeGen/X86/vector-sqrt.ll
@@ -0,0 +1,77 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefix=CHECK
+
+; ModuleID = 'vector-sqrt.c'
+source_filename = "vector-sqrt.c"
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+; Function Attrs: nounwind readonly uwtable
+define <2 x double> @sqrtd2(double* nocapture readonly %v) local_unnamed_addr #0 {
+; CHECK-LABEL: sqrtd2:
+; CHECK: # BB#0: # %entry
+; CHECK-NEXT: vsqrtsd (%rdi), %xmm0, %xmm0
+; CHECK-NEXT: vsqrtsd 8(%rdi), %xmm1, %xmm1
+; CHECK-NEXT: vunpcklpd {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; CHECK-NEXT: retq
+entry:
+ %0 = load double, double* %v, align 8, !tbaa !1
+ %call = tail call double @sqrt(double %0) #2
+ %arrayidx1 = getelementptr inbounds double, double* %v, i64 1
+ %1 = load double, double* %arrayidx1, align 8, !tbaa !1
+ %call2 = tail call double @sqrt(double %1) #2
+ %vecinit.i = insertelement <2 x double> undef, double %call, i32 0
+ %vecinit1.i = insertelement <2 x double> %vecinit.i, double %call2, i32 1
+ ret <2 x double> %vecinit1.i
+}
+
+; Function Attrs: nounwind readnone
+declare double @sqrt(double) local_unnamed_addr #1
+
+; Function Attrs: nounwind readonly uwtable
+define <4 x float> @sqrtf4(float* nocapture readonly %v) local_unnamed_addr #0 {
+; CHECK-LABEL: sqrtf4:
+; CHECK: # BB#0: # %entry
+; CHECK-NEXT: vsqrtss (%rdi), %xmm0, %xmm0
+; CHECK-NEXT: vsqrtss 4(%rdi), %xmm1, %xmm1
+; CHECK-NEXT: vsqrtss 8(%rdi), %xmm2, %xmm2
+; CHECK-NEXT: vsqrtss 12(%rdi), %xmm3, %xmm3
+; CHECK-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[2,3]
+; CHECK-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0,1],xmm2[0],xmm0[3]
+; CHECK-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0,1,2],xmm3[0]
+; CHECK-NEXT: retq
+entry:
+ %0 = load float, float* %v, align 4, !tbaa !5
+ %call = tail call float @sqrtf(float %0) #2
+ %arrayidx1 = getelementptr inbounds float, float* %v, i64 1
+ %1 = load float, float* %arrayidx1, align 4, !tbaa !5
+ %call2 = tail call float @sqrtf(float %1) #2
+ %arrayidx3 = getelementptr inbounds float, float* %v, i64 2
+ %2 = load float, float* %arrayidx3, align 4, !tbaa !5
+ %call4 = tail call float @sqrtf(float %2) #2
+ %arrayidx5 = getelementptr inbounds float, float* %v, i64 3
+ %3 = load float, float* %arrayidx5, align 4, !tbaa !5
+ %call6 = tail call float @sqrtf(float %3) #2
+ %vecinit.i = insertelement <4 x float> undef, float %call, i32 0
+ %vecinit1.i = insertelement <4 x float> %vecinit.i, float %call2, i32 1
+ %vecinit2.i = insertelement <4 x float> %vecinit1.i, float %call4, i32 2
+ %vecinit3.i = insertelement <4 x float> %vecinit2.i, float %call6, i32 3
+ ret <4 x float> %vecinit3.i
+}
+
+; Function Attrs: nounwind readnone
+declare float @sqrtf(float) local_unnamed_addr #1
+
+attributes #0 = { nounwind readonly uwtable "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="haswell" "target-features"="+aes,+avx,+avx2,+bmi,+bmi2,+cx16,+f16c,+fma,+fsgsbase,+fxsr,+lzcnt,+mmx,+movbe,+pclmul,+popcnt,+rdrnd,+rtm,+sse,+sse2,+sse3,+sse4.1,+sse4.2,+ssse3,+x87,+xsave,+xsaveopt" "unsafe-fp-math"="false" "use-soft-float"="false" }
+attributes #1 = { nounwind readnone "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="haswell" "target-features"="+aes,+avx,+avx2,+bmi,+bmi2,+cx16,+f16c,+fma,+fsgsbase,+fxsr,+lzcnt,+mmx,+movbe,+pclmul,+popcnt,+rdrnd,+rtm,+sse,+sse2,+sse3,+sse4.1,+sse4.2,+ssse3,+x87,+xsave,+xsaveopt" "unsafe-fp-math"="false" "use-soft-float"="false" }
+attributes #2 = { nounwind readnone }
+
+!llvm.ident = !{!0}
+
+!0 = !{!"clang version 4.0.0 (trunk 289787)"}
+!1 = !{!2, !2, i64 0}
+!2 = !{!"double", !3, i64 0}
+!3 = !{!"omnipotent char", !4, i64 0}
+!4 = !{!"Simple C/C++ TBAA"}
+!5 = !{!6, !6, i64 0}
+!6 = !{!"float", !3, i64 0}
OpenPOWER on IntegriCloud