diff options
author | Quentin Neill <quentin.neill@amd.com> | 2011-11-05 02:31:29 +0000 |
---|---|---|
committer | Harsha Jagasia <hjagasia@gcc.gnu.org> | 2011-11-05 02:31:29 +0000 |
commit | 87ca01b7be3297716a55bbec92ba9f31a7181912 (patch) | |
tree | 0af794118b8a861f7988e67283ae7603887fbe6a /gcc | |
parent | a73c1a724d3bfa9e64840437bd1d95e019ff4017 (diff) | |
download | gcc-87ca01b7be3297716a55bbec92ba9f31a7181912.zip gcc-87ca01b7be3297716a55bbec92ba9f31a7181912.tar.gz gcc-87ca01b7be3297716a55bbec92ba9f31a7181912.tar.bz2 |
Piledriver f16cintrin.h fix.
2011-11-04 Quentin Neill <quentin.neill@amd.com>
Piledriver f16cintrin.h fix.
* config/i386/f16cintrin.h: Contents moved from immintrin.h.
* config/config.gcc: Add f16cintrin.h.
From-SVN: r180999
Diffstat (limited to 'gcc')
-rw-r--r-- | gcc/ChangeLog | 6 | ||||
-rw-r--r-- | gcc/config/i386/f16cintrin.h | 94 | ||||
-rw-r--r-- | gcc/config/i386/immintrin.h | 63 |
3 files changed, 104 insertions, 59 deletions
diff --git a/gcc/ChangeLog b/gcc/ChangeLog index c0bdc1a..fbe7606 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,3 +1,9 @@ +2011-11-05 Quentin Neill <quentin.neill@amd.com> + + Piledriver f16cintrin.h fix. + * config/i386/f16cintrin.h: Contents moved from immintrin.h. + * config/config.gcc: Add f16cintrin.h. + 2011-11-04 Eric Botcazou <ebotcazou@adacore.com> PR c++/50608 diff --git a/gcc/config/i386/f16cintrin.h b/gcc/config/i386/f16cintrin.h new file mode 100644 index 0000000..5ff836b --- /dev/null +++ b/gcc/config/i386/f16cintrin.h @@ -0,0 +1,94 @@ +/* Copyright (C) 2011 + Free Software Foundation, Inc. + + This file is part of GCC. + + GCC is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 3, or (at your option) + any later version. + + GCC is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + Under Section 7 of GPL version 3, you are granted additional + permissions described in the GCC Runtime Library Exception, version + 3.1, as published by the Free Software Foundation. + + You should have received a copy of the GNU General Public License and + a copy of the GCC Runtime Library Exception along with this program; + see the files COPYING3 and COPYING.RUNTIME respectively. If not, see + <http://www.gnu.org/licenses/>. */ + +#ifndef _X86INTRIN_H_INCLUDED +#if (!defined(_X86INTRIN_H_INCLUDED) && !defined(_IMMINTRIN_H_INCLUDED)) +# error "Never use <f16intrin.h> directly; include <x86intrin.h> or <immintrin.h> instead." +#endif + +#ifndef __F16C__ +# error "F16C instruction set not enabled" +#else + +#ifndef _F16CINTRIN_H_INCLUDED +#define _F16CINTRIN_H_INCLUDED + +extern __inline float __attribute__((__gnu_inline__, __always_inline__, __artificial__)) +_cvtsh_ss (unsigned short __S) +{ + __v8hi __H = __extension__ (__v8hi){ __S, 0, 0, 0, 0, 0, 0, 0 }; + __v4sf __A = __builtin_ia32_vcvtph2ps (__H); + return __builtin_ia32_vec_ext_v4sf (__A, 0); +} + +extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__)) +_mm_cvtph_ps (__m128i __A) +{ + return (__m128) __builtin_ia32_vcvtph2ps ((__v8hi) __A); +} + +extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__)) +_mm256_cvtph_ps (__m128i __A) +{ + return (__m256) __builtin_ia32_vcvtph2ps256 ((__v8hi) __A); +} + +#ifdef __OPTIMIZE__ +extern __inline unsigned short __attribute__((__gnu_inline__, __always_inline__, __artificial__)) +_cvtss_sh (float __F, const int __I) +{ + __v4sf __A = __extension__ (__v4sf){ __F, 0, 0, 0 }; + __v8hi __H = __builtin_ia32_vcvtps2ph (__A, __I); + return (unsigned short) __builtin_ia32_vec_ext_v8hi (__H, 0); +} + +extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__)) +_mm_cvtps_ph (__m128 __A, const int __I) +{ + return (__m128i) __builtin_ia32_vcvtps2ph ((__v4sf) __A, __I); +} + +extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__)) +_mm256_cvtps_ph (__m256 __A, const int __I) +{ + return (__m128i) __builtin_ia32_vcvtps2ph256 ((__v8sf) __A, __I); +} +#else +#define _cvtss_sh(__F, __I) \ + (__extension__ \ + ({ \ + __v4sf __A = __extension__ (__v4sf){ __F, 0, 0, 0 }; \ + __v8hi __H = __builtin_ia32_vcvtps2ph (__A, __I); \ + (unsigned short) __builtin_ia32_vec_ext_v8hi (__H, 0); \ + })) + +#define _mm_cvtps_ph(A, I) \ + ((__m128i) __builtin_ia32_vcvtps2ph ((__v4sf)(__m128) A, (int) (I))) + +#define _mm256_cvtps_ph(A, I) \ + ((__m128i) __builtin_ia32_vcvtps2ph256 ((__v8sf)(__m256) A, (int) (I))) +#endif + +#endif /* __F16C__ */ +#endif diff --git a/gcc/config/i386/immintrin.h b/gcc/config/i386/immintrin.h index 102814e..986a573d 100644 --- a/gcc/config/i386/immintrin.h +++ b/gcc/config/i386/immintrin.h @@ -76,6 +76,10 @@ #include <fmaintrin.h> #endif +#ifdef __F16C__ +#include <f16cintrin.h> +#endif + #ifdef __RDRND__ extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__)) @@ -161,63 +165,4 @@ _rdrand64_step (unsigned long long *__P) #endif /* __RDRND__ */ #endif /* __x86_64__ */ -#ifdef __F16C__ -extern __inline float __attribute__((__gnu_inline__, __always_inline__, __artificial__)) -_cvtsh_ss (unsigned short __S) -{ - __v8hi __H = __extension__ (__v8hi){ __S, 0, 0, 0, 0, 0, 0, 0 }; - __v4sf __A = __builtin_ia32_vcvtph2ps (__H); - return __builtin_ia32_vec_ext_v4sf (__A, 0); -} - -extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__)) -_mm_cvtph_ps (__m128i __A) -{ - return (__m128) __builtin_ia32_vcvtph2ps ((__v8hi) __A); -} - -extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__)) -_mm256_cvtph_ps (__m128i __A) -{ - return (__m256) __builtin_ia32_vcvtph2ps256 ((__v8hi) __A); -} - -#ifdef __OPTIMIZE__ -extern __inline unsigned short __attribute__((__gnu_inline__, __always_inline__, __artificial__)) -_cvtss_sh (float __F, const int __I) -{ - __v4sf __A = __extension__ (__v4sf){ __F, 0, 0, 0 }; - __v8hi __H = __builtin_ia32_vcvtps2ph (__A, __I); - return (unsigned short) __builtin_ia32_vec_ext_v8hi (__H, 0); -} - -extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__)) -_mm_cvtps_ph (__m128 __A, const int __I) -{ - return (__m128i) __builtin_ia32_vcvtps2ph ((__v4sf) __A, __I); -} - -extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__)) -_mm256_cvtps_ph (__m256 __A, const int __I) -{ - return (__m128i) __builtin_ia32_vcvtps2ph256 ((__v8sf) __A, __I); -} -#else -#define _cvtss_sh(__F, __I) \ - (__extension__ \ - ({ \ - __v4sf __A = __extension__ (__v4sf){ __F, 0, 0, 0 }; \ - __v8hi __H = __builtin_ia32_vcvtps2ph (__A, __I); \ - (unsigned short) __builtin_ia32_vec_ext_v8hi (__H, 0); \ - })) - -#define _mm_cvtps_ph(A, I) \ - ((__m128i) __builtin_ia32_vcvtps2ph ((__v4sf)(__m128) A, (int) (I))) - -#define _mm256_cvtps_ph(A, I) \ - ((__m128i) __builtin_ia32_vcvtps2ph256 ((__v8sf)(__m256) A, (int) (I))) -#endif - -#endif /* __F16C__ */ - #endif /* _IMMINTRIN_H_INCLUDED */ |