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

Implement the AVX cmp builtins as macros instead of static inlines. 

Patch by Syoyo Fujita!  Reviewed by Chris Lattner!  Checked in by me!

llvm-svn: 128984
This commit is contained in:
John McCall 2011-04-06 03:37:51 +00:00
parent c5e6b97523
commit 91a528841b
2 changed files with 59 additions and 30 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

42
clang/lib/Headers/avxintrin.h
View File

@ -385,41 +385,23 @@ _mm256_dp_ps(__m256 a, __m256 b, const int c)
#define _CMP_GT_OQ 0x1e /* Greater-than (ordered, non-signaling) */
#define _CMP_TRUE_US 0x1f /* True (unordered, signaling) */
static __inline __m128d __attribute__((__always_inline__, __nodebug__))
_mm_cmp_pd(__m128d a, __m128d b, const int c)
{
return (__m128d)__builtin_ia32_cmppd((__v2df)a, (__v2df)b, c);
}
#define _mm_cmp_pd(a, b, c) \
(__m128d)__builtin_ia32_cmppd((__v2df)(a), (__v2df)(b), (c))
static __inline __m128 __attribute__((__always_inline__, __nodebug__))
_mm_cmp_ps(__m128 a, __m128 b, const int c)
{
return (__m128)__builtin_ia32_cmpps((__v4sf)a, (__v4sf)b, c);
}
#define _mm_cmp_ps(a, b, c) \
(__m128)__builtin_ia32_cmpps((__v4sf)(a), (__v4sf)(b), (c))
static __inline __m256d __attribute__((__always_inline__, __nodebug__))
_mm256_cmp_pd(__m256d a, __m256d b, const int c)
{
return (__m256d)__builtin_ia32_cmppd256((__v4df)a, (__v4df)b, c);
}
#define _mm256_cmp_pd(a, b, c) \
(__m256d)__builtin_ia32_cmppd256((__v4df)(a), (__v4df)(b), (c))
static __inline __m256 __attribute__((__always_inline__, __nodebug__))
_mm256_cmp_ps(__m256 a, __m256 b, const int c)
{
return (__m256)__builtin_ia32_cmpps256((__v8sf)a, (__v8sf)b, c);
}
#define _mm256_cmp_ps(a, b, c) \
(__m256)__builtin_ia32_cmpps256((__v8sf)(a), (__v8sf)(b), (c))
static __inline __m128d __attribute__((__always_inline__, __nodebug__))
_mm_cmp_sd(__m128d a, __m128d b, const int c)
{
return (__m128d)__builtin_ia32_cmpsd((__v2df)a, (__v2df)b, c);
}
#define _mm_cmp_sd(a, b, c) \
(__m128d)__builtin_ia32_cmpsd((__v2df)(a), (__v2df)(b), (c))
static __inline __m128 __attribute__((__always_inline__, __nodebug__))
_mm_cmp_ss(__m128 a, __m128 b, const int c)
{
return (__m128)__builtin_ia32_cmpss((__v4sf)a, (__v4sf)b, c);
}
#define _mm_cmp_ss(a, b, c) \
(__m128)__builtin_ia32_cmpss((__v4sf)(a), (__v4sf)(b), (c))
/* Vector extract */
static __inline __m128d __attribute__((__always_inline__, __nodebug__))

47
clang/test/CodeGen/avx-cmp-builtins.c Normal file
View File

@ -0,0 +1,47 @@
// RUN: %clang -mavx -c -emit-llvm %s -o - | llvm-dis | FileCheck %s
#include <immintrin.h>
//
// Test if third argument of cmp_XY function in LLVM IR form has immediate value.
//
void test_cmp_ps256() {
__m256 a, b, c;
a = _mm256_cmp_ps(b, c, _CMP_GE_OS);
// CHECK: @test_cmp_ps256
// CHECK: %0 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %tmp, <8 x float> %tmp1, i8 13)
}
void test_cmp_pd256() {
__m256d a, b, c;
a = _mm256_cmp_pd(b, c, _CMP_GE_OS);
// CHECK: @test_cmp_pd256
// CHECK: %0 = call <4 x double> @llvm.x86.avx.cmp.pd.256(<4 x double> %tmp, <4 x double> %tmp1, i8 13)
}
void test_cmp_ps() {
__m128 a, b, c;
a = _mm_cmp_ps(b, c, _CMP_GE_OS);
// CHECK: @test_cmp_ps
// CHECK: %cmpps = call <4 x float> @llvm.x86.sse.cmp.ps(<4 x float> %tmp, <4 x float> %tmp1, i8 13)
}
void test_cmp_pd() {
__m128d a, b, c;
a = _mm_cmp_pd(b, c, _CMP_GE_OS);
// CHECK: @test_cmp_pd
// CHECK: %cmppd = call <2 x double> @llvm.x86.sse2.cmp.pd(<2 x double> %tmp, <2 x double> %tmp1, i8 13)
}
void test_cmp_sd() {
__m128d a, b, c;
a = _mm_cmp_sd(b, c, _CMP_GE_OS);
// CHECK: @test_cmp_sd
// CHECK: %cmpsd = call <2 x double> @llvm.x86.sse2.cmp.sd(<2 x double> %tmp, <2 x double> %tmp1, i8 13)
}
void test_cmp_ss() {
__m128 a, b, c;
a = _mm_cmp_ss(b, c, _CMP_GE_OS);
// CHECK: @test_cmp_ss
// CHECK: %cmpss = call <4 x float> @llvm.x86.sse.cmp.ss(<4 x float> %tmp, <4 x float> %tmp1, i8 13)
}