X-Git-Url: http://plrg.eecs.uci.edu/git/?a=blobdiff_plain;f=test%2FCodeGen%2FX86%2Fsqrt-fastmath.ll;h=386409a674ef08c40c7ba9f06198492b9810b908;hb=b5b07c36862e772571fcbfa459fa9780615ec42b;hp=9b5179efa421c28bc43ca411cd54b65413a124dd;hpb=b704d23062aa78b00999b75dcdcb628d4d84ee3f;p=oota-llvm.git

diff --git a/test/CodeGen/X86/sqrt-fastmath.ll b/test/CodeGen/X86/sqrt-fastmath.ll
index 9b5179efa42..386409a674e 100644
--- a/test/CodeGen/X86/sqrt-fastmath.ll
+++ b/test/CodeGen/X86/sqrt-fastmath.ll
@@ -1,60 +1,142 @@
-; RUN: llc < %s -mcpu=core2 | FileCheck %s
-
-; generated using "clang -S -O2 -ffast-math -emit-llvm sqrt.c" from
-; #include <math.h>
-; 
-; double fd(double d){
-;   return sqrt(d);
-; }
-; 
-; float ff(float f){
-;   return sqrtf(f);
-; }
-; 
-; long double fld(long double ld){
-;   return sqrtl(ld);
-; }
-;
-; Tests conversion of sqrt function calls into sqrt instructions when
-; -ffast-math is in effect.
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=sse2 -recip=!sqrtf,!vec-sqrtf,!divf,!vec-divf | FileCheck %s --check-prefix=NORECIP
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx -recip=sqrtf,vec-sqrtf | FileCheck %s --check-prefix=ESTIMATE
+
+declare double @__sqrt_finite(double) #0
+declare float @__sqrtf_finite(float) #0
+declare x86_fp80 @__sqrtl_finite(x86_fp80) #0
+declare float @llvm.sqrt.f32(float) #0
+declare <4 x float> @llvm.sqrt.v4f32(<4 x float>) #0
+declare <8 x float> @llvm.sqrt.v8f32(<8 x float>) #0
 
-; ModuleID = 'sqrt.c'
-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"
 
-; Function Attrs: nounwind readnone uwtable
 define double @fd(double %d) #0 {
-entry:
-; CHECK: sqrtsd
-  %call = tail call double @__sqrt_finite(double %d) #2
+; NORECIP-LABEL: fd:
+; NORECIP:       # BB#0:
+; NORECIP-NEXT:    sqrtsd %xmm0, %xmm0
+; NORECIP-NEXT:    retq
+;
+; ESTIMATE-LABEL: fd:
+; ESTIMATE:       # BB#0:
+; ESTIMATE-NEXT:    vsqrtsd %xmm0, %xmm0, %xmm0
+; ESTIMATE-NEXT:    retq
+  %call = tail call double @__sqrt_finite(double %d) #1
   ret double %call
 }
 
-; Function Attrs: nounwind readnone
-declare double @__sqrt_finite(double) #1
 
-; Function Attrs: nounwind readnone uwtable
 define float @ff(float %f) #0 {
-entry:
-; CHECK: sqrtss
-  %call = tail call float @__sqrtf_finite(float %f) #2
+; NORECIP-LABEL: ff:
+; NORECIP:       # BB#0:
+; NORECIP-NEXT:    sqrtss %xmm0, %xmm0
+; NORECIP-NEXT:    retq
+;
+; ESTIMATE-LABEL: ff:
+; ESTIMATE:       # BB#0:
+; ESTIMATE-NEXT:    vrsqrtss %xmm0, %xmm0, %xmm1
+; ESTIMATE-NEXT:    vmulss {{.*}}(%rip), %xmm1, %xmm2
+; ESTIMATE-NEXT:    vmulss %xmm0, %xmm1, %xmm3
+; ESTIMATE-NEXT:    vmulss %xmm3, %xmm1, %xmm1
+; ESTIMATE-NEXT:    vaddss {{.*}}(%rip), %xmm1, %xmm1
+; ESTIMATE-NEXT:    vmulss %xmm0, %xmm2, %xmm2
+; ESTIMATE-NEXT:    vmulss %xmm2, %xmm1, %xmm1
+; ESTIMATE-NEXT:    vxorps %xmm2, %xmm2, %xmm2
+; ESTIMATE-NEXT:    vcmpeqss %xmm2, %xmm0, %xmm0
+; ESTIMATE-NEXT:    vandnps %xmm1, %xmm0, %xmm0
+; ESTIMATE-NEXT:    retq
+  %call = tail call float @__sqrtf_finite(float %f) #1
   ret float %call
 }
 
-; Function Attrs: nounwind readnone
-declare float @__sqrtf_finite(float) #1
 
-; Function Attrs: nounwind readnone uwtable
 define x86_fp80 @fld(x86_fp80 %ld) #0 {
-entry:
-; CHECK: fsqrt
-  %call = tail call x86_fp80 @__sqrtl_finite(x86_fp80 %ld) #2
+; NORECIP-LABEL: fld:
+; NORECIP:       # BB#0:
+; NORECIP-NEXT:    fldt {{[0-9]+}}(%rsp)
+; NORECIP-NEXT:    fsqrt
+; NORECIP-NEXT:    retq
+;
+; ESTIMATE-LABEL: fld:
+; ESTIMATE:       # BB#0:
+; ESTIMATE-NEXT:    fldt {{[0-9]+}}(%rsp)
+; ESTIMATE-NEXT:    fsqrt
+; ESTIMATE-NEXT:    retq
+  %call = tail call x86_fp80 @__sqrtl_finite(x86_fp80 %ld) #1
   ret x86_fp80 %call
 }
 
-; Function Attrs: nounwind readnone
-declare x86_fp80 @__sqrtl_finite(x86_fp80) #1
 
-attributes #0 = { nounwind readnone uwtable "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-frame-pointer-elim-non-leaf"="false" "no-infs-fp-math"="true" "no-nans-fp-math"="true" "unsafe-fp-math"="true" "use-soft-float"="false" }
-attributes #1 = { nounwind readnone "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-frame-pointer-elim-non-leaf"="false" "no-infs-fp-math"="true" "no-nans-fp-math"="true" "unsafe-fp-math"="true" "use-soft-float"="false" }
-attributes #2 = { nounwind readnone }
+
+define float @reciprocal_square_root(float %x) #0 {
+; NORECIP-LABEL: reciprocal_square_root:
+; NORECIP:       # BB#0:
+; NORECIP-NEXT:    sqrtss %xmm0, %xmm1
+; NORECIP-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
+; NORECIP-NEXT:    divss %xmm1, %xmm0
+; NORECIP-NEXT:    retq
+;
+; ESTIMATE-LABEL: reciprocal_square_root:
+; ESTIMATE:       # BB#0:
+; ESTIMATE-NEXT:    vrsqrtss %xmm0, %xmm0, %xmm1
+; ESTIMATE-NEXT:    vmulss {{.*}}(%rip), %xmm1, %xmm2
+; ESTIMATE-NEXT:    vmulss %xmm0, %xmm1, %xmm0
+; ESTIMATE-NEXT:    vmulss %xmm0, %xmm1, %xmm0
+; ESTIMATE-NEXT:    vaddss {{.*}}(%rip), %xmm0, %xmm0
+; ESTIMATE-NEXT:    vmulss %xmm2, %xmm0, %xmm0
+; ESTIMATE-NEXT:    retq
+  %sqrt = tail call float @llvm.sqrt.f32(float %x)
+  %div = fdiv fast float 1.0, %sqrt
+  ret float %div
+}
+
+define <4 x float> @reciprocal_square_root_v4f32(<4 x float> %x) #0 {
+; NORECIP-LABEL: reciprocal_square_root_v4f32:
+; NORECIP:       # BB#0:
+; NORECIP-NEXT:    sqrtps %xmm0, %xmm1
+; NORECIP-NEXT:    movaps {{.*#+}} xmm0 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
+; NORECIP-NEXT:    divps %xmm1, %xmm0
+; NORECIP-NEXT:    retq
+;
+; ESTIMATE-LABEL: reciprocal_square_root_v4f32:
+; ESTIMATE:       # BB#0:
+; ESTIMATE-NEXT:    vrsqrtps %xmm0, %xmm1
+; ESTIMATE-NEXT:    vmulps %xmm0, %xmm1, %xmm0
+; ESTIMATE-NEXT:    vmulps %xmm0, %xmm1, %xmm0
+; ESTIMATE-NEXT:    vaddps {{.*}}(%rip), %xmm0, %xmm0
+; ESTIMATE-NEXT:    vmulps {{.*}}(%rip), %xmm1, %xmm1
+; ESTIMATE-NEXT:    vmulps %xmm1, %xmm0, %xmm0
+; ESTIMATE-NEXT:    retq
+  %sqrt = tail call <4 x float> @llvm.sqrt.v4f32(<4 x float> %x)
+  %div = fdiv fast <4 x float> <float 1.0, float 1.0, float 1.0, float 1.0>, %sqrt
+  ret <4 x float> %div
+}
+
+define <8 x float> @reciprocal_square_root_v8f32(<8 x float> %x) #0 {
+; NORECIP-LABEL: reciprocal_square_root_v8f32:
+; NORECIP:       # BB#0:
+; NORECIP-NEXT:    sqrtps %xmm1, %xmm2
+; NORECIP-NEXT:    sqrtps %xmm0, %xmm3
+; NORECIP-NEXT:    movaps {{.*#+}} xmm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
+; NORECIP-NEXT:    movaps %xmm1, %xmm0
+; NORECIP-NEXT:    divps %xmm3, %xmm0
+; NORECIP-NEXT:    divps %xmm2, %xmm1
+; NORECIP-NEXT:    retq
+;
+; ESTIMATE-LABEL: reciprocal_square_root_v8f32:
+; ESTIMATE:       # BB#0:
+; ESTIMATE-NEXT:    vrsqrtps %ymm0, %ymm1
+; ESTIMATE-NEXT:    vmulps %ymm0, %ymm1, %ymm0
+; ESTIMATE-NEXT:    vmulps %ymm0, %ymm1, %ymm0
+; ESTIMATE-NEXT:    vaddps {{.*}}(%rip), %ymm0, %ymm0
+; ESTIMATE-NEXT:    vmulps {{.*}}(%rip), %ymm1, %ymm1
+; ESTIMATE-NEXT:    vmulps %ymm1, %ymm0, %ymm0
+; ESTIMATE-NEXT:    retq
+  %sqrt = tail call <8 x float> @llvm.sqrt.v8f32(<8 x float> %x)
+  %div = fdiv fast <8 x float> <float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0>, %sqrt
+  ret <8 x float> %div
+}
+
+
+attributes #0 = { "unsafe-fp-math"="true" }
+attributes #1 = { nounwind readnone }
+