maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

X86 SSE Intrinsics: update header for sqrt_ss, rsqrt_ss and rcp_ss. 

There intrinsics pass through the upper FP values from the input.
rdar://12558838

llvm-svn: 166743
This commit is contained in:
Manman Ren 2012-10-26 00:25:10 +00:00
parent 375c7f3859
commit 5750c1c07e
2 changed files with 37 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
clang/lib/Headers/xmmintrin.h
View File

@ -95,7 +95,8 @@ _mm_div_ps(__m128 a, __m128 b)
static __inline__ __m128 __attribute__((__always_inline__, __nodebug__))
_mm_sqrt_ss(__m128 a)
{
return __builtin_ia32_sqrtss(a);
__m128 c = __builtin_ia32_sqrtss(a);
return (__m128) { c[0], a[1], a[2], a[3] };
}
static __inline__ __m128 __attribute__((__always_inline__, __nodebug__))
@ -107,7 +108,8 @@ _mm_sqrt_ps(__m128 a)
static __inline__ __m128 __attribute__((__always_inline__, __nodebug__))
_mm_rcp_ss(__m128 a)
{
return __builtin_ia32_rcpss(a);
__m128 c = __builtin_ia32_rcpss(a);
return (__m128) { c[0], a[1], a[2], a[3] };
}
static __inline__ __m128 __attribute__((__always_inline__, __nodebug__))
@ -119,7 +121,8 @@ _mm_rcp_ps(__m128 a)
static __inline__ __m128 __attribute__((__always_inline__, __nodebug__))
_mm_rsqrt_ss(__m128 a)
{
return __builtin_ia32_rsqrtss(a);
__m128 c = __builtin_ia32_rsqrtss(a);
return (__m128) { c[0], a[1], a[2], a[3] };
}
static __inline__ __m128 __attribute__((__always_inline__, __nodebug__))

31
clang/test/CodeGen/sse-builtins.c
View File

@ -1,8 +1,39 @@
// RUN: %clang_cc1 -ffreestanding -triple i386-apple-darwin9 -target-cpu pentium4 -target-feature +sse4.1 -g -emit-llvm %s -o - | FileCheck %s
#include <xmmintrin.h>
#include <emmintrin.h>
#include <smmintrin.h>
__m128 test_rsqrt_ss(__m128 x) {
// CHECK: define {{.*}} @test_rsqrt_ss
// CHECK: call <4 x float> @llvm.x86.sse.rsqrt.ss
// CHECK: extractelement <4 x float> {{.*}}, i32 0
// CHECK: extractelement <4 x float> {{.*}}, i32 1
// CHECK: extractelement <4 x float> {{.*}}, i32 2
// CHECK: extractelement <4 x float> {{.*}}, i32 3
return _mm_rsqrt_ss(x);
}
__m128 test_rcp_ss(__m128 x) {
// CHECK: define {{.*}} @test_rcp_ss
// CHECK: call <4 x float> @llvm.x86.sse.rcp.ss
// CHECK: extractelement <4 x float> {{.*}}, i32 0
// CHECK: extractelement <4 x float> {{.*}}, i32 1
// CHECK: extractelement <4 x float> {{.*}}, i32 2
// CHECK: extractelement <4 x float> {{.*}}, i32 3
return _mm_rcp_ss(x);
}
__m128 test_sqrt_ss(__m128 x) {
// CHECK: define {{.*}} @test_sqrt_ss
// CHECK: call <4 x float> @llvm.x86.sse.sqrt.ss
// CHECK: extractelement <4 x float> {{.*}}, i32 0
// CHECK: extractelement <4 x float> {{.*}}, i32 1
// CHECK: extractelement <4 x float> {{.*}}, i32 2
// CHECK: extractelement <4 x float> {{.*}}, i32 3
return _mm_sqrt_ss(x);
}
__m128 test_loadl_pi(__m128 x, void* y) {
// CHECK: define {{.*}} @test_loadl_pi
// CHECK: load <2 x float>* {{.*}}, align 1{{$}}