Stephen Hines | 51a0ffb | 2014-02-14 00:25:07 -0800 | [diff] [blame] | 1 | /*===---- ammintrin.h - SSE4a intrinsics -----------------------------------=== |
| 2 | * |
| 3 | * Permission is hereby granted, free of charge, to any person obtaining a copy |
| 4 | * of this software and associated documentation files (the "Software"), to deal |
| 5 | * in the Software without restriction, including without limitation the rights |
| 6 | * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell |
| 7 | * copies of the Software, and to permit persons to whom the Software is |
| 8 | * furnished to do so, subject to the following conditions: |
| 9 | * |
| 10 | * The above copyright notice and this permission notice shall be included in |
| 11 | * all copies or substantial portions of the Software. |
| 12 | * |
| 13 | * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR |
| 14 | * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, |
| 15 | * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE |
| 16 | * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER |
| 17 | * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, |
| 18 | * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN |
| 19 | * THE SOFTWARE. |
| 20 | * |
| 21 | *===-----------------------------------------------------------------------=== |
| 22 | */ |
| 23 | |
| 24 | #ifndef __AMMINTRIN_H |
| 25 | #define __AMMINTRIN_H |
| 26 | |
| 27 | #ifndef __SSE4A__ |
| 28 | #error "SSE4A instruction set not enabled" |
| 29 | #else |
| 30 | |
| 31 | #include <pmmintrin.h> |
| 32 | |
| 33 | #define _mm_extracti_si64(x, len, idx) \ |
| 34 | ((__m128i)__builtin_ia32_extrqi((__v2di)(__m128i)(x), \ |
| 35 | (char)(len), (char)(idx))) |
| 36 | |
| 37 | static __inline__ __m128i __attribute__((__always_inline__, __nodebug__)) |
| 38 | _mm_extract_si64(__m128i __x, __m128i __y) |
| 39 | { |
| 40 | return (__m128i)__builtin_ia32_extrq((__v2di)__x, (__v16qi)__y); |
| 41 | } |
| 42 | |
| 43 | #define _mm_inserti_si64(x, y, len, idx) \ |
| 44 | ((__m128i)__builtin_ia32_insertqi((__v2di)(__m128i)(x), \ |
| 45 | (__v2di)(__m128i)(y), \ |
| 46 | (char)(len), (char)(idx))) |
| 47 | |
| 48 | static __inline__ __m128i __attribute__((__always_inline__, __nodebug__)) |
| 49 | _mm_insert_si64(__m128i __x, __m128i __y) |
| 50 | { |
| 51 | return (__m128i)__builtin_ia32_insertq((__v2di)__x, (__v2di)__y); |
| 52 | } |
| 53 | |
| 54 | static __inline__ void __attribute__((__always_inline__, __nodebug__)) |
| 55 | _mm_stream_sd(double *__p, __m128d __a) |
| 56 | { |
| 57 | __builtin_ia32_movntsd(__p, (__v2df)__a); |
| 58 | } |
| 59 | |
| 60 | static __inline__ void __attribute__((__always_inline__, __nodebug__)) |
| 61 | _mm_stream_ss(float *__p, __m128 __a) |
| 62 | { |
| 63 | __builtin_ia32_movntss(__p, (__v4sf)__a); |
| 64 | } |
| 65 | |
| 66 | #endif /* __SSE4A__ */ |
| 67 | |
| 68 | #endif /* __AMMINTRIN_H */ |