diff options
Diffstat (limited to 'clang/lib/Headers/tmmintrin.h')
| -rw-r--r-- | clang/lib/Headers/tmmintrin.h | 20 |
1 files changed, 11 insertions, 9 deletions
diff --git a/clang/lib/Headers/tmmintrin.h b/clang/lib/Headers/tmmintrin.h index d40f0c5..3fc9f98 100644 --- a/clang/lib/Headers/tmmintrin.h +++ b/clang/lib/Headers/tmmintrin.h @@ -23,6 +23,9 @@ #define __trunc64(x) \ (__m64) __builtin_shufflevector((__v2di)(x), __extension__(__v2di){}, 0) +#define __zext128(x) \ + (__m128i) __builtin_shufflevector((__v2si)(x), __extension__(__v2si){}, 0, \ + 1, 2, 3) #define __anyext128(x) \ (__m128i) __builtin_shufflevector((__v2si)(x), __extension__(__v2si){}, 0, \ 1, -1, -1) @@ -504,10 +507,9 @@ _mm_hsubs_pi16(__m64 __a, __m64 __b) /// \a R5 := (\a __a10 * \a __b10) + (\a __a11 * \a __b11) \n /// \a R6 := (\a __a12 * \a __b12) + (\a __a13 * \a __b13) \n /// \a R7 := (\a __a14 * \a __b14) + (\a __a15 * \a __b15) -static __inline__ __m128i __DEFAULT_FN_ATTRS -_mm_maddubs_epi16(__m128i __a, __m128i __b) -{ - return (__m128i)__builtin_ia32_pmaddubsw128((__v16qi)__a, (__v16qi)__b); +static __inline__ __m128i __DEFAULT_FN_ATTRS_CONSTEXPR +_mm_maddubs_epi16(__m128i __a, __m128i __b) { + return (__m128i)__builtin_ia32_pmaddubsw128((__v16qi)__a, (__v16qi)__b); } /// Multiplies corresponding pairs of packed 8-bit unsigned integer @@ -534,11 +536,10 @@ _mm_maddubs_epi16(__m128i __a, __m128i __b) /// \a R1 := (\a __a2 * \a __b2) + (\a __a3 * \a __b3) \n /// \a R2 := (\a __a4 * \a __b4) + (\a __a5 * \a __b5) \n /// \a R3 := (\a __a6 * \a __b6) + (\a __a7 * \a __b7) -static __inline__ __m64 __DEFAULT_FN_ATTRS -_mm_maddubs_pi16(__m64 __a, __m64 __b) -{ - return __trunc64(__builtin_ia32_pmaddubsw128((__v16qi)__anyext128(__a), - (__v16qi)__anyext128(__b))); +static __inline__ __m64 __DEFAULT_FN_ATTRS_CONSTEXPR +_mm_maddubs_pi16(__m64 __a, __m64 __b) { + return __trunc64(__builtin_ia32_pmaddubsw128((__v16qi)__zext128(__a), + (__v16qi)__zext128(__b))); } /// Multiplies packed 16-bit signed integer values, truncates the 32-bit @@ -796,6 +797,7 @@ _mm_sign_pi32(__m64 __a, __m64 __b) } #undef __anyext128 +#undef __zext128 #undef __trunc64 #undef __DEFAULT_FN_ATTRS #undef __DEFAULT_FN_ATTRS_CONSTEXPR |