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

80col. 

llvm-svn: 64450
This commit is contained in:
Mike Stump 2009-02-13 14:24:50 +00:00
parent 51495609df
commit 5b31ed3ff0
3 changed files with 684 additions and 342 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

633
clang/lib/Headers/emmintrin.h
View File

File diff suppressed because it is too large Load Diff

39
clang/lib/Headers/pmmintrin.h
View File

@ -30,57 +30,68 @@
#include <emmintrin.h>
static inline __m128i __attribute__((__always_inline__)) _mm_lddqu_si128(__m128i const *p)
static inline __m128i __attribute__((__always_inline__))
_mm_lddqu_si128(__m128i const *p)
{
return (__m128i)__builtin_ia32_lddqu((char const *)p);
}
static inline __m128 __attribute__((__always_inline__)) _mm_addsub_ps(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_addsub_ps(__m128 a, __m128 b)
{
return __builtin_ia32_addsubps(a, b);
}
static inline __m128 __attribute__((__always_inline__)) _mm_hadd_ps(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_hadd_ps(__m128 a, __m128 b)
{
return __builtin_ia32_haddps(a, b);
}
static inline __m128 __attribute__((__always_inline__)) _mm_hsub_ps(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_hsub_ps(__m128 a, __m128 b)
{
return __builtin_ia32_hsubps(a, b);
}
static inline __m128 __attribute__((__always_inline__)) _mm_movehdup_ps(__m128 a)
static inline __m128 __attribute__((__always_inline__))
_mm_movehdup_ps(__m128 a)
{
return __builtin_shufflevector(a, a, 1, 1, 3, 3);
}
static inline __m128 __attribute__((__always_inline__)) _mm_moveldup_ps(__m128 a)
static inline __m128 __attribute__((__always_inline__))
_mm_moveldup_ps(__m128 a)
{
return __builtin_shufflevector(a, a, 0, 0, 2, 2);
}
static inline __m128d __attribute__((__always_inline__)) _mm_addsub_pd(__m128d a, __m128d b)
static inline __m128d __attribute__((__always_inline__))
_mm_addsub_pd(__m128d a, __m128d b)
{
return __builtin_ia32_addsubpd(a, b);
}
static inline __m128d __attribute__((__always_inline__)) _mm_hadd_pd(__m128d a, __m128d b)
static inline __m128d __attribute__((__always_inline__))
_mm_hadd_pd(__m128d a, __m128d b)
{
return __builtin_ia32_haddpd(a, b);
}
static inline __m128d __attribute__((__always_inline__)) _mm_hsub_pd(__m128d a, __m128d b)
static inline __m128d __attribute__((__always_inline__))
_mm_hsub_pd(__m128d a, __m128d b)
{
return __builtin_ia32_hsubpd(a, b);
}
static inline __m128d __attribute__((__always_inline__)) _mm_loaddup_pd(double const *dp)
static inline __m128d __attribute__((__always_inline__))
_mm_loaddup_pd(double const *dp)
{
return __builtin_shufflevector(*(__m128d *)dp, *(__m128d *)dp, 0, 0);
}
static inline __m128d __attribute__((__always_inline__)) _mm_movedup_pd(__m128d a)
static inline __m128d __attribute__((__always_inline__))
_mm_movedup_pd(__m128d a)
{
return __builtin_shufflevector(a, a, 0, 0);
}
@ -93,12 +104,14 @@ static inline __m128d __attribute__((__always_inline__)) _mm_movedup_pd(__m128d
#define _MM_GET_DENORMALS_ZERO_MODE() (_mm_getcsr() & _MM_DENORMALS_ZERO_MASK)
#define _MM_SET_DENORMALS_ZERO_MODE(x) (_mm_setcsr((_mm_getcsr() & ~_MM_DENORMALS_ZERO_MASK) | (x)))
static inline void __attribute__((__always_inline__)) _mm_monitor(void const *p, unsigned extensions, unsigned hints)
static inline void __attribute__((__always_inline__))
_mm_monitor(void const *p, unsigned extensions, unsigned hints)
{
__builtin_ia32_monitor((void *)p, extensions, hints);
}
static inline void __attribute__((__always_inline__)) _mm_mwait(unsigned extensions, unsigned hints)
static inline void __attribute__((__always_inline__))
_mm_mwait(unsigned extensions, unsigned hints)
{
__builtin_ia32_mwait(extensions, hints);
}

354
clang/lib/Headers/xmmintrin.h
View File

@ -35,449 +35,537 @@ typedef float __m128 __attribute__((__vector_size__(16)));
#include <mm_malloc.h>
static inline __m128 __attribute__((__always_inline__)) _mm_add_ss(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_add_ss(__m128 a, __m128 b)
{
return __builtin_ia32_addss(a, b);
}
static inline __m128 __attribute__((__always_inline__)) _mm_add_ps(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_add_ps(__m128 a, __m128 b)
{
return a + b;
}
static inline __m128 __attribute__((__always_inline__)) _mm_sub_ss(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_sub_ss(__m128 a, __m128 b)
{
return __builtin_ia32_subss(a, b);
}
static inline __m128 __attribute__((__always_inline__)) _mm_sub_ps(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_sub_ps(__m128 a, __m128 b)
{
return a - b;
}
static inline __m128 __attribute__((__always_inline__)) _mm_mul_ss(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_mul_ss(__m128 a, __m128 b)
{
return __builtin_ia32_mulss(a, b);
}
static inline __m128 __attribute__((__always_inline__)) _mm_mul_ps(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_mul_ps(__m128 a, __m128 b)
{
return a * b;
}
static inline __m128 __attribute__((__always_inline__)) _mm_div_ss(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_div_ss(__m128 a, __m128 b)
{
return __builtin_ia32_divss(a, b);
}
static inline __m128 __attribute__((__always_inline__)) _mm_div_ps(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_div_ps(__m128 a, __m128 b)
{
return a / b;
}
static inline __m128 __attribute__((__always_inline__)) _mm_sqrt_ss(__m128 a)
static inline __m128 __attribute__((__always_inline__))
_mm_sqrt_ss(__m128 a)
{
return __builtin_ia32_sqrtss(a);
}
static inline __m128 __attribute__((__always_inline__)) _mm_sqrt_ps(__m128 a)
static inline __m128 __attribute__((__always_inline__))
_mm_sqrt_ps(__m128 a)
{
return __builtin_ia32_sqrtps(a);
}
static inline __m128 __attribute__((__always_inline__)) _mm_rcp_ss(__m128 a)
static inline __m128 __attribute__((__always_inline__))
_mm_rcp_ss(__m128 a)
{
return __builtin_ia32_rcpss(a);
}
static inline __m128 __attribute__((__always_inline__)) _mm_rcp_ps(__m128 a)
static inline __m128 __attribute__((__always_inline__))
_mm_rcp_ps(__m128 a)
{
return __builtin_ia32_rcpps(a);
}
static inline __m128 __attribute__((__always_inline__)) _mm_rsqrt_ss(__m128 a)
static inline __m128 __attribute__((__always_inline__))
_mm_rsqrt_ss(__m128 a)
{
return __builtin_ia32_rsqrtss(a);
}
static inline __m128 __attribute__((__always_inline__)) _mm_rsqrt_ps(__m128 a)
static inline __m128 __attribute__((__always_inline__))
_mm_rsqrt_ps(__m128 a)
{
return __builtin_ia32_rsqrtps(a);
}
static inline __m128 __attribute__((__always_inline__)) _mm_min_ss(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_min_ss(__m128 a, __m128 b)
{
return __builtin_ia32_minss(a, b);
}
static inline __m128 __attribute__((__always_inline__)) _mm_min_ps(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_min_ps(__m128 a, __m128 b)
{
return __builtin_ia32_minps(a, b);
}
static inline __m128 __attribute__((__always_inline__)) _mm_max_ss(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_max_ss(__m128 a, __m128 b)
{
return __builtin_ia32_maxss(a, b);
}
static inline __m128 __attribute__((__always_inline__)) _mm_max_ps(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_max_ps(__m128 a, __m128 b)
{
return __builtin_ia32_maxps(a, b);
}
static inline __m128 __attribute__((__always_inline__)) _mm_and_ps(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_and_ps(__m128 a, __m128 b)
{
return __builtin_ia32_andps(a, b);
}
static inline __m128 __attribute__((__always_inline__)) _mm_andnot_ps(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_andnot_ps(__m128 a, __m128 b)
{
return __builtin_ia32_andnps(a, b);
}
static inline __m128 __attribute__((__always_inline__)) _mm_or_ps(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_or_ps(__m128 a, __m128 b)
{
return __builtin_ia32_orps(a, b);
}
static inline __m128 __attribute__((__always_inline__)) _mm_xor_ps(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_xor_ps(__m128 a, __m128 b)
{
return __builtin_ia32_xorps(a, b);
}
static inline __m128 __attribute__((__always_inline__)) _mm_cmpeq_ss(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_cmpeq_ss(__m128 a, __m128 b)
{
return (__m128)__builtin_ia32_cmpeqss(a, b);
}
static inline __m128 __attribute__((__always_inline__)) _mm_cmpeq_ps(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_cmpeq_ps(__m128 a, __m128 b)
{
return (__m128)__builtin_ia32_cmpeqps(a, b);
}
static inline __m128 __attribute__((__always_inline__)) _mm_cmplt_ss(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_cmplt_ss(__m128 a, __m128 b)
{
return (__m128)__builtin_ia32_cmpltss(a, b);
}
static inline __m128 __attribute__((__always_inline__)) _mm_cmplt_ps(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_cmplt_ps(__m128 a, __m128 b)
{
return (__m128)__builtin_ia32_cmpltps(a, b);
}
static inline __m128 __attribute__((__always_inline__)) _mm_cmple_ss(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_cmple_ss(__m128 a, __m128 b)
{
return (__m128)__builtin_ia32_cmpless(a, b);
}
static inline __m128 __attribute__((__always_inline__)) _mm_cmple_ps(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_cmple_ps(__m128 a, __m128 b)
{
return (__m128)__builtin_ia32_cmpleps(a, b);
}
static inline __m128 __attribute__((__always_inline__)) _mm_cmpgt_ss(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_cmpgt_ss(__m128 a, __m128 b)
{
return (__m128)__builtin_ia32_cmpltss(b, a);
}
static inline __m128 __attribute__((__always_inline__)) _mm_cmpgt_ps(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_cmpgt_ps(__m128 a, __m128 b)
{
return (__m128)__builtin_ia32_cmpltps(b, a);
}
static inline __m128 __attribute__((__always_inline__)) _mm_cmpge_ss(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_cmpge_ss(__m128 a, __m128 b)
{
return (__m128)__builtin_ia32_cmpless(b, a);
}
static inline __m128 __attribute__((__always_inline__)) _mm_cmpge_ps(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_cmpge_ps(__m128 a, __m128 b)
{
return (__m128)__builtin_ia32_cmpleps(b, a);
}
static inline __m128 __attribute__((__always_inline__)) _mm_cmpneq_ss(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_cmpneq_ss(__m128 a, __m128 b)
{
return (__m128)__builtin_ia32_cmpneqss(a, b);
}
static inline __m128 __attribute__((__always_inline__)) _mm_cmpneq_ps(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_cmpneq_ps(__m128 a, __m128 b)
{
return (__m128)__builtin_ia32_cmpneqps(a, b);
}
static inline __m128 __attribute__((__always_inline__)) _mm_cmpnlt_ss(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_cmpnlt_ss(__m128 a, __m128 b)
{
return (__m128)__builtin_ia32_cmpnltss(a, b);
}
static inline __m128 __attribute__((__always_inline__)) _mm_cmpnlt_ps(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_cmpnlt_ps(__m128 a, __m128 b)
{
return (__m128)__builtin_ia32_cmpnltps(a, b);
}
static inline __m128 __attribute__((__always_inline__)) _mm_cmpnle_ss(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_cmpnle_ss(__m128 a, __m128 b)
{
return (__m128)__builtin_ia32_cmpnless(a, b);
}
static inline __m128 __attribute__((__always_inline__)) _mm_cmpnle_ps(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_cmpnle_ps(__m128 a, __m128 b)
{
return (__m128)__builtin_ia32_cmpnleps(a, b);
}
static inline __m128 __attribute__((__always_inline__)) _mm_cmpngt_ss(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_cmpngt_ss(__m128 a, __m128 b)
{
return (__m128)__builtin_ia32_cmpnltss(b, a);
}
static inline __m128 __attribute__((__always_inline__)) _mm_cmpngt_ps(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_cmpngt_ps(__m128 a, __m128 b)
{
return (__m128)__builtin_ia32_cmpnltps(b, a);
}
static inline __m128 __attribute__((__always_inline__)) _mm_cmpnge_ss(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_cmpnge_ss(__m128 a, __m128 b)
{
return (__m128)__builtin_ia32_cmpnless(b, a);
}
static inline __m128 __attribute__((__always_inline__)) _mm_cmpnge_ps(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_cmpnge_ps(__m128 a, __m128 b)
{
return (__m128)__builtin_ia32_cmpnleps(b, a);
}
static inline __m128 __attribute__((__always_inline__)) _mm_cmpord_ss(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_cmpord_ss(__m128 a, __m128 b)
{
return (__m128)__builtin_ia32_cmpordss(a, b);
}
static inline __m128 __attribute__((__always_inline__)) _mm_cmpord_ps(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_cmpord_ps(__m128 a, __m128 b)
{
return (__m128)__builtin_ia32_cmpordps(a, b);
}
static inline __m128 __attribute__((__always_inline__)) _mm_cmpunord_ss(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_cmpunord_ss(__m128 a, __m128 b)
{
return (__m128)__builtin_ia32_cmpunordss(a, b);
}
static inline __m128 __attribute__((__always_inline__)) _mm_cmpunord_ps(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_cmpunord_ps(__m128 a, __m128 b)
{
return (__m128)__builtin_ia32_cmpunordps(a, b);
}
static inline int __attribute__((__always_inline__)) _mm_comieq_ss(__m128 a, __m128 b)
static inline int __attribute__((__always_inline__))
_mm_comieq_ss(__m128 a, __m128 b)
{
return __builtin_ia32_comieq(a, b);
}
static inline int __attribute__((__always_inline__)) _mm_comilt_ss(__m128 a, __m128 b)
static inline int __attribute__((__always_inline__))
_mm_comilt_ss(__m128 a, __m128 b)
{
return __builtin_ia32_comilt(a, b);
}
static inline int __attribute__((__always_inline__)) _mm_comile_ss(__m128 a, __m128 b)
static inline int __attribute__((__always_inline__))
_mm_comile_ss(__m128 a, __m128 b)
{
return __builtin_ia32_comile(a, b);
}
static inline int __attribute__((__always_inline__)) _mm_comigt_ss(__m128 a, __m128 b)
static inline int __attribute__((__always_inline__))
_mm_comigt_ss(__m128 a, __m128 b)
{
return __builtin_ia32_comigt(a, b);
}
static inline int __attribute__((__always_inline__)) _mm_comige_ss(__m128 a, __m128 b)
static inline int __attribute__((__always_inline__))
_mm_comige_ss(__m128 a, __m128 b)
{
return __builtin_ia32_comige(a, b);
}
static inline int __attribute__((__always_inline__)) _mm_comineq_ss(__m128 a, __m128 b)
static inline int __attribute__((__always_inline__))
_mm_comineq_ss(__m128 a, __m128 b)
{
return __builtin_ia32_comineq(a, b);
}
static inline int __attribute__((__always_inline__)) _mm_ucomieq_ss(__m128 a, __m128 b)
static inline int __attribute__((__always_inline__))
_mm_ucomieq_ss(__m128 a, __m128 b)
{
return __builtin_ia32_ucomieq(a, b);
}
static inline int __attribute__((__always_inline__)) _mm_ucomilt_ss(__m128 a, __m128 b)
static inline int __attribute__((__always_inline__))
_mm_ucomilt_ss(__m128 a, __m128 b)
{
return __builtin_ia32_ucomilt(a, b);
}
static inline int __attribute__((__always_inline__)) _mm_ucomile_ss(__m128 a, __m128 b)
static inline int __attribute__((__always_inline__))
_mm_ucomile_ss(__m128 a, __m128 b)
{
return __builtin_ia32_ucomile(a, b);
}
static inline int __attribute__((__always_inline__)) _mm_ucomigt_ss(__m128 a, __m128 b)
static inline int __attribute__((__always_inline__))
_mm_ucomigt_ss(__m128 a, __m128 b)
{
return __builtin_ia32_ucomigt(a, b);
}
static inline int __attribute__((__always_inline__)) _mm_ucomige_ss(__m128 a, __m128 b)
static inline int __attribute__((__always_inline__))
_mm_ucomige_ss(__m128 a, __m128 b)
{
return __builtin_ia32_ucomige(a, b);
}
static inline int __attribute__((__always_inline__)) _mm_ucomineq_ss(__m128 a, __m128 b)
static inline int __attribute__((__always_inline__))
_mm_ucomineq_ss(__m128 a, __m128 b)
{
return __builtin_ia32_ucomineq(a, b);
}
static inline int __attribute__((__always_inline__)) _mm_cvtss_si32(__m128 a)
static inline int __attribute__((__always_inline__))
_mm_cvtss_si32(__m128 a)
{
return __builtin_ia32_cvtss2si(a);
}
static inline long long __attribute__((__always_inline__)) _mm_cvtss_si64(__m128 a)
static inline long long __attribute__((__always_inline__))
_mm_cvtss_si64(__m128 a)
{
return __builtin_ia32_cvtss2si64(a);
}
static inline __m64 __attribute__((__always_inline__)) _mm_cvtps_pi32(__m128 a)
static inline __m64 __attribute__((__always_inline__))
_mm_cvtps_pi32(__m128 a)
{
return (__m64)__builtin_ia32_cvtps2pi(a);
}
static inline int __attribute__((__always_inline__)) _mm_cvttss_si32(__m128 a)
static inline int __attribute__((__always_inline__))
_mm_cvttss_si32(__m128 a)
{
return __builtin_ia32_cvttss2si(a);
}
static inline long long __attribute__((__always_inline__)) _mm_cvttss_si64(__m128 a)
static inline long long __attribute__((__always_inline__))
_mm_cvttss_si64(__m128 a)
{
return __builtin_ia32_cvttss2si64(a);
}
static inline __m64 __attribute__((__always_inline__)) _mm_cvttps_pi32(__m128 a)
static inline __m64 __attribute__((__always_inline__))
_mm_cvttps_pi32(__m128 a)
{
return (__m64)__builtin_ia32_cvttps2pi(a);
}
static inline __m128 __attribute__((__always_inline__)) _mm_cvtsi32_ss(__m128 a, int b)
static inline __m128 __attribute__((__always_inline__))
_mm_cvtsi32_ss(__m128 a, int b)
{
return __builtin_ia32_cvtsi2ss(a, b);
}
#ifdef __x86_64__
static inline __m128 __attribute__((__always_inline__)) _mm_cvtsi64_ss(__m128 a, long long b)
static inline __m128 __attribute__((__always_inline__))
_mm_cvtsi64_ss(__m128 a, long long b)
{
return __builtin_ia32_cvtsi642ss(a, b);
}
#endif
static inline __m128 __attribute__((__always_inline__)) _mm_cvtpi32_ps(__m128 a, __m64 b)
static inline __m128 __attribute__((__always_inline__))
_mm_cvtpi32_ps(__m128 a, __m64 b)
{
return __builtin_ia32_cvtpi2ps(a, (__v2si)b);
}
static inline float __attribute__((__always_inline__)) _mm_cvtss_f32(__m128 a)
static inline float __attribute__((__always_inline__))
_mm_cvtss_f32(__m128 a)
{
return a[0];
}
static inline __m128 __attribute__((__always_inline__)) _mm_loadh_pi(__m128 a, __m64 const *p)
static inline __m128 __attribute__((__always_inline__))
_mm_loadh_pi(__m128 a, __m64 const *p)
{
return __builtin_ia32_loadhps(a, (__v2si *)p);
}
static inline __m128 __attribute__((__always_inline__)) _mm_loadl_pi(__m128 a, __m64 const *p)
static inline __m128 __attribute__((__always_inline__))
_mm_loadl_pi(__m128 a, __m64 const *p)
{
return __builtin_ia32_loadlps(a, (__v2si *)p);
}
static inline __m128 __attribute__((__always_inline__)) _mm_load_ss(float *p)
static inline __m128 __attribute__((__always_inline__))
_mm_load_ss(float *p)
{
return (__m128){ *p, 0, 0, 0 };
}
static inline __m128 __attribute__((__always_inline__)) _mm_load1_ps(float *p)
static inline __m128 __attribute__((__always_inline__))
_mm_load1_ps(float *p)
{
return (__m128){ *p, *p, *p, *p };
}
static inline __m128 __attribute__((__always_inline__)) _mm_load_ps(float *p)
static inline __m128 __attribute__((__always_inline__))
_mm_load_ps(float *p)
{
return *(__m128*)p;
}
static inline __m128 __attribute__((__always_inline__)) _mm_loadu_ps(float *p)
static inline __m128 __attribute__((__always_inline__))
_mm_loadu_ps(float *p)
{
return __builtin_ia32_loadups(p);
}
static inline __m128 __attribute__((__always_inline__)) _mm_loadr_ps(float *p)
static inline __m128 __attribute__((__always_inline__))
_mm_loadr_ps(float *p)
{
__m128 a = _mm_load_ps(p);
return __builtin_shufflevector(a, a, 3, 2, 1, 0);
}
static inline __m128 __attribute__((__always_inline__)) _mm_set_ss(float w)
static inline __m128 __attribute__((__always_inline__))
_mm_set_ss(float w)
{
return (__m128){ w, 0, 0, 0 };
}
static inline __m128 __attribute__((__always_inline__)) _mm_set1_ps(float w)
static inline __m128 __attribute__((__always_inline__))
_mm_set1_ps(float w)
{
return (__m128){ w, w, w, w };
}
// Microsoft specific.
static inline __m128 __attribute__((__always_inline__)) _mm_set_ps1(float w)
static inline __m128 __attribute__((__always_inline__))
_mm_set_ps1(float w)
{
return _mm_set1_ps(w);
}
static inline __m128 __attribute__((__always_inline__)) _mm_set_ps(float z, float y, float x, float w)
static inline __m128 __attribute__((__always_inline__))
_mm_set_ps(float z, float y, float x, float w)
{
return (__m128){ w, x, y, z };
}
static inline __m128 __attribute__((__always_inline__)) _mm_setr_ps(float z, float y, float x, float w)
static inline __m128 __attribute__((__always_inline__))
_mm_setr_ps(float z, float y, float x, float w)
{
return (__m128){ z, y, x, w };
}
static inline __m128 __attribute__((__always__inline__)) _mm_setzero_ps(void)
static inline __m128 __attribute__((__always__inline__))
_mm_setzero_ps(void)
{
return (__m128){ 0, 0, 0, 0 };
}
static inline void __attribute__((__always__inline__)) _mm_storeh_pi(__m64 *p, __m128 a)
static inline void __attribute__((__always__inline__))
_mm_storeh_pi(__m64 *p, __m128 a)
{
__builtin_ia32_storehps((__v2si *)p, a);
}
static inline void __attribute__((__always__inline__)) _mm_storel_pi(__m64 *p, __m128 a)
static inline void __attribute__((__always__inline__))
_mm_storel_pi(__m64 *p, __m128 a)
{
__builtin_ia32_storelps((__v2si *)p, a);
}
static inline void __attribute__((__always__inline__)) _mm_store_ss(float *p, __m128 a)
static inline void __attribute__((__always__inline__))
_mm_store_ss(float *p, __m128 a)
{
*p = a[0];
}
static inline void __attribute__((__always_inline__)) _mm_storeu_ps(float *p, __m128 a)
static inline void __attribute__((__always_inline__))
_mm_storeu_ps(float *p, __m128 a)
{
__builtin_ia32_storeups(p, a);
}
static inline void __attribute__((__always_inline__)) _mm_store1_ps(float *p, __m128 a)
static inline void __attribute__((__always_inline__))
_mm_store1_ps(float *p, __m128 a)
{
a = __builtin_shufflevector(a, a, 0, 0, 0, 0);
_mm_storeu_ps(p, a);
}
static inline void __attribute__((__always_inline__)) _mm_store_ps(float *p, __m128 a)
static inline void __attribute__((__always_inline__))
_mm_store_ps(float *p, __m128 a)
{
*(__m128 *)p = a;
}
static inline void __attribute__((__always_inline__)) _mm_storer_ps(float *p, __m128 a)
static inline void __attribute__((__always_inline__))
_mm_storer_ps(float *p, __m128 a)
{
a = __builtin_shufflevector(a, a, 3, 2, 1, 0);
_mm_store_ps(p, a);
@ -493,22 +581,26 @@ static inline void __attribute__((__always_inline__)) _mm_storer_ps(float *p, __
#define _mm_prefetch(a, sel) (__builtin_prefetch((void *)a, 0, sel))
static inline void __attribute__((__always_inline__)) _mm_stream_pi(__m64 *p, __m64 a)
static inline void __attribute__((__always_inline__))
_mm_stream_pi(__m64 *p, __m64 a)
{
__builtin_ia32_movntq(p, a);
}
static inline void __attribute__((__always_inline__)) _mm_stream_ps(float *p, __m128 a)
static inline void __attribute__((__always_inline__))
_mm_stream_ps(float *p, __m128 a)
{
__builtin_ia32_movntps(p, a);
}
static inline void __attribute__((__always_inline__)) _mm_sfence(void)
static inline void __attribute__((__always_inline__))
_mm_sfence(void)
{
__builtin_ia32_sfence();
}
static inline int __attribute__((__always_inline__)) _mm_extract_pi16(__m64 a, int n)
static inline int __attribute__((__always_inline__))
_mm_extract_pi16(__m64 a, int n)
{
/* FIXME:
* This should force n to be an immediate.
@ -524,102 +616,121 @@ static inline int __attribute__((__always_inline__)) _mm_extract_pi16(__m64 a, i
the already existing __builtin_shufflevector.
*/
/*
static inline __m64 __attribute__((__always_inline__)) _mm_insert_pi16(__m64 a, int d, int n)
static inline __m64 __attribute__((__always_inline__))
_mm_insert_pi16(__m64 a, int d, int n)
{
return (__m64){ 0LL };
}
*/
static inline __m64 __attribute__((__always_inline__)) _mm_max_pi16(__m64 a, __m64 b)
static inline __m64 __attribute__((__always_inline__))
_mm_max_pi16(__m64 a, __m64 b)
{
return (__m64)__builtin_ia32_pmaxsw((__v4hi)a, (__v4hi)b);
}
static inline __m64 __attribute__((__always_inline__)) _mm_max_pu8(__m64 a, __m64 b)
static inline __m64 __attribute__((__always_inline__))
_mm_max_pu8(__m64 a, __m64 b)
{
return (__m64)__builtin_ia32_pmaxub((__v8qi)a, (__v8qi)b);
}
static inline __m64 __attribute__((__always_inline__)) _mm_min_pi16(__m64 a, __m64 b)
static inline __m64 __attribute__((__always_inline__))
_mm_min_pi16(__m64 a, __m64 b)
{
return (__m64)__builtin_ia32_pminsw((__v4hi)a, (__v4hi)b);
}
static inline __m64 __attribute__((__always_inline__)) _mm_min_pu8(__m64 a, __m64 b)
static inline __m64 __attribute__((__always_inline__))
_mm_min_pu8(__m64 a, __m64 b)
{
return (__m64)__builtin_ia32_pminub((__v8qi)a, (__v8qi)b);
}
static inline int __attribute__((__always_inline__)) _mm_movemask_pi8(__m64 a)
static inline int __attribute__((__always_inline__))
_mm_movemask_pi8(__m64 a)
{
return __builtin_ia32_pmovmskb((__v8qi)a);
}
static inline __m64 __attribute__((__always_inline__)) _mm_mulhi_pu16(__m64 a, __m64 b)
static inline __m64 __attribute__((__always_inline__))
_mm_mulhi_pu16(__m64 a, __m64 b)
{
return (__m64)__builtin_ia32_pmulhuw((__v4hi)a, (__v4hi)b);
}
#define _mm_shuffle_pi16(a, n) ((__m64)__builtin_ia32_pshufw((__v4hi)a, n))
static inline void __attribute__((__always_inline__)) _mm_maskmove_si64(__m64 d, __m64 n, char *p)
static inline void __attribute__((__always_inline__))
_mm_maskmove_si64(__m64 d, __m64 n, char *p)
{
__builtin_ia32_maskmovq((__v8qi)d, (__v8qi)n, p);
}
static inline __m64 __attribute__((__always_inline__)) _mm_avg_pu8(__m64 a, __m64 b)
static inline __m64 __attribute__((__always_inline__))
_mm_avg_pu8(__m64 a, __m64 b)
{
return (__m64)__builtin_ia32_pavgb((__v8qi)a, (__v8qi)b);
}
static inline __m64 __attribute__((__always_inline__)) _mm_avg_pu16(__m64 a, __m64 b)
static inline __m64 __attribute__((__always_inline__))
_mm_avg_pu16(__m64 a, __m64 b)
{
return (__m64)__builtin_ia32_pavgw((__v4hi)a, (__v4hi)b);
}
static inline __m64 __attribute__((__always_inline___)) _mm_sad_pu8(__m64 a, __m64 b)
static inline __m64 __attribute__((__always_inline___))
_mm_sad_pu8(__m64 a, __m64 b)
{
return (__m64)__builtin_ia32_psadbw((__v8qi)a, (__v8qi)b);
}
static inline unsigned int __attribute__((__always_inline___)) _mm_getcsr(void)
static inline unsigned int __attribute__((__always_inline___))
_mm_getcsr(void)
{
return __builtin_ia32_stmxcsr();
}
static inline void __attribute__((__always_inline__)) _mm_setcsr(unsigned int i)
static inline void __attribute__((__always_inline__))
_mm_setcsr(unsigned int i)
{
__builtin_ia32_ldmxcsr(i);
}
#define _mm_shuffle_ps(a, b, mask) (__builtin_ia32_shufps(a, b, mask))
static inline __m128 __attribute__((__always_inline__)) _mm_unpackhi_ps(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_unpackhi_ps(__m128 a, __m128 b)
{
return __builtin_shufflevector(a, b, 2, 6, 3, 7);
}
static inline __m128 __attribute__((__always_inline__)) _mm_unpacklo_ps(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_unpacklo_ps(__m128 a, __m128 b)
{
return __builtin_shufflevector(a, b, 0, 4, 1, 5);
}
static inline __m128 __attribute__((__always_inline__)) _mm_move_ss(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_move_ss(__m128 a, __m128 b)
{
return __builtin_shufflevector(a, b, 4, 1, 2, 3);
}
static inline __m128 __attribute__((__always_inline__)) _mm_movehl_ps(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_movehl_ps(__m128 a, __m128 b)
{
return __builtin_shufflevector(a, b, 6, 7, 2, 3);
}
static inline __m128 __attribute__((__always_inline__)) _mm_movelh_ps(__m128 a, __m128 b)
static inline __m128 __attribute__((__always_inline__))
_mm_movelh_ps(__m128 a, __m128 b)
{
return __builtin_shufflevector(a, b, 0, 1, 4, 5);
}
static inline __m128 __attribute__((__always_inline__)) _mm_cvtpi16_ps(__m64 a)
static inline __m128 __attribute__((__always_inline__))
_mm_cvtpi16_ps(__m64 a)
{
__m64 b, c;
__m128 r;
@ -636,7 +747,8 @@ static inline __m128 __attribute__((__always_inline__)) _mm_cvtpi16_ps(__m64 a)
return r;
}
static inline __m128 __attribute__((__always_inline__)) _mm_cvtpu16_ps(__m64 a)
static inline __m128 __attribute__((__always_inline__))
_mm_cvtpu16_ps(__m64 a)
{
__m64 b, c;
__m128 r;
@ -652,7 +764,8 @@ static inline __m128 __attribute__((__always_inline__)) _mm_cvtpu16_ps(__m64 a)
return r;
}
static inline __m128 __attribute__((__always_inline__)) _mm_cvtpi8_ps(__m64 a)
static inline __m128 __attribute__((__always_inline__))
_mm_cvtpi8_ps(__m64 a)
{
__m64 b;
@ -663,7 +776,8 @@ static inline __m128 __attribute__((__always_inline__)) _mm_cvtpi8_ps(__m64 a)
return _mm_cvtpi16_ps(b);
}
static inline __m128 __attribute__((__always_inline__)) _mm_cvtpu8_ps(__m64 a)
static inline __m128 __attribute__((__always_inline__))
_mm_cvtpu8_ps(__m64 a)
{
__m64 b;
@ -673,7 +787,8 @@ static inline __m128 __attribute__((__always_inline__)) _mm_cvtpu8_ps(__m64 a)
return _mm_cvtpi16_ps(b);
}
static inline __m128 __attribute__((__always_inline__)) _mm_cvtpi32x2_ps(__m64 a, __m64 b)
static inline __m128 __attribute__((__always_inline__))
_mm_cvtpi32x2_ps(__m64 a, __m64 b)
{
__m128 c;
@ -684,7 +799,8 @@ static inline __m128 __attribute__((__always_inline__)) _mm_cvtpi32x2_ps(__m64 a
return _mm_cvtpi32_ps(c, a);
}
static inline __m64 __attribute__((__always_inline__)) _mm_cvtps_pi16(__m128 a)
static inline __m64 __attribute__((__always_inline__))
_mm_cvtps_pi16(__m128 a)
{
__m64 b, c;
@ -695,7 +811,8 @@ static inline __m64 __attribute__((__always_inline__)) _mm_cvtps_pi16(__m128 a)
return _mm_packs_pi16(b, c);
}
static inline __m64 __attribute__((__always_inline__)) _mm_cvtps_pi8(__m128 a)
static inline __m64 __attribute__((__always_inline__))
_mm_cvtps_pi8(__m128 a)
{
__m64 b, c;
@ -705,7 +822,8 @@ static inline __m64 __attribute__((__always_inline__)) _mm_cvtps_pi8(__m128 a)
return _mm_packs_pi16(b, c);
}
static inline int __attribute__((__always_inline__)) _mm_movemask_ps(__m128 a)
static inline int __attribute__((__always_inline__))
_mm_movemask_ps(__m128 a)
{
return __builtin_ia32_movmskps(a);
}