Lines Matching defs:__X
3002 /// 128-bit vector of [4 x float] in \a __X to all elements of the result's
3009 /// \param __X
3013 _mm_broadcastss_ps(__m128 __X)
3015 return (__m128)__builtin_shufflevector((__v4sf)__X, (__v4sf)__X, 0, 0, 0, 0);
3036 /// 128-bit vector of [4 x float] in \a __X to all elements of the
3043 /// \param __X
3047 _mm256_broadcastss_ps(__m128 __X)
3049 return (__m256)__builtin_shufflevector((__v4sf)__X, (__v4sf)__X, 0, 0, 0, 0, 0, 0, 0, 0);
3053 /// 128-bit vector of [2 x double] in \a __X to all elements of the
3060 /// \param __X
3064 _mm256_broadcastsd_pd(__m128d __X)
3066 return (__m256d)__builtin_shufflevector((__v2df)__X, (__v2df)__X, 0, 0, 0, 0);
3069 /// Broadcasts the 128-bit integer data from \a __X to both the lower and
3076 /// \param __X
3080 _mm256_broadcastsi128_si256(__m128i __X)
3082 return (__m256i)__builtin_shufflevector((__v2di)__X, (__v2di)__X, 0, 1, 0, 1);
3161 /// Broadcasts the low byte from the 128-bit integer vector in \a __X to all
3168 /// \param __X
3172 _mm256_broadcastb_epi8(__m128i __X)
3174 return (__m256i)__builtin_shufflevector((__v16qi)__X, (__v16qi)__X, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0);
3177 /// Broadcasts the low element from the 128-bit vector of [8 x i16] in \a __X
3184 /// \param __X
3188 _mm256_broadcastw_epi16(__m128i __X)
3190 return (__m256i)__builtin_shufflevector((__v8hi)__X, (__v8hi)__X, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0);
3193 /// Broadcasts the low element from the 128-bit vector of [4 x i32] in \a __X
3200 /// \param __X
3204 _mm256_broadcastd_epi32(__m128i __X)
3206 return (__m256i)__builtin_shufflevector((__v4si)__X, (__v4si)__X, 0, 0, 0, 0, 0, 0, 0, 0);
3209 /// Broadcasts the low element from the 128-bit vector of [2 x i64] in \a __X
3216 /// \param __X
3220 _mm256_broadcastq_epi64(__m128i __X)
3222 return (__m256i)__builtin_shufflevector((__v2di)__X, (__v2di)__X, 0, 0, 0, 0);
3225 /// Broadcasts the low byte from the 128-bit integer vector in \a __X to all
3232 /// \param __X
3236 _mm_broadcastb_epi8(__m128i __X)
3238 return (__m128i)__builtin_shufflevector((__v16qi)__X, (__v16qi)__X, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0);
3242 /// \a __X to all elements of the result's 128-bit vector of [8 x i16].
3248 /// \param __X
3252 _mm_broadcastw_epi16(__m128i __X)
3254 return (__m128i)__builtin_shufflevector((__v8hi)__X, (__v8hi)__X, 0, 0, 0, 0, 0, 0, 0, 0);
3257 /// Broadcasts the low element from the 128-bit vector of [4 x i32] in \a __X
3264 /// \param __X
3268 _mm_broadcastd_epi32(__m128i __X)
3270 return (__m128i)__builtin_shufflevector((__v4si)__X, (__v4si)__X, 0, 0, 0, 0);
3273 /// Broadcasts the low element from the 128-bit vector of [2 x i64] in \a __X
3280 /// \param __X
3284 _mm_broadcastq_epi64(__m128i __X)
3286 return (__m128i)__builtin_shufflevector((__v2di)__X, (__v2di)__X, 0, 0);
3495 /// Conditionally loads eight 32-bit integer elements from memory \a __X, if
3504 /// result[j+31:j] := Load32(__X+(i*4))
3515 /// \param __X
3522 _mm256_maskload_epi32(int const *__X, __m256i __M)
3524 return (__m256i)__builtin_ia32_maskloadd256((const __v8si *)__X, (__v8si)__M);
3527 /// Conditionally loads four 64-bit integer elements from memory \a __X, if
3536 /// result[j+63:j] := Load64(__X+(i*8))
3547 /// \param __X
3554 _mm256_maskload_epi64(long long const *__X, __m256i __M)
3556 return (__m256i)__builtin_ia32_maskloadq256((const __v4di *)__X, (__v4di)__M);
3559 /// Conditionally loads four 32-bit integer elements from memory \a __X, if
3568 /// result[j+31:j] := Load32(__X+(i*4))
3579 /// \param __X
3586 _mm_maskload_epi32(int const *__X, __m128i __M)
3588 return (__m128i)__builtin_ia32_maskloadd((const __v4si *)__X, (__v4si)__M);
3591 /// Conditionally loads two 64-bit integer elements from memory \a __X, if
3600 /// result[j+63:j] := Load64(__X+(i*8))
3611 /// \param __X
3618 _mm_maskload_epi64(long long const *__X, __m128i __M)
3620 return (__m128i)__builtin_ia32_maskloadq((const __v2di *)__X, (__v2di)__M);
3624 /// of [8 x i32] in \a __Y to memory \a __X, if the most significant bit of
3632 /// Store32(__X+(i*4), __Y[j+31:j])
3641 /// \param __X
3648 _mm256_maskstore_epi32(int *__X, __m256i __M, __m256i __Y)
3650 __builtin_ia32_maskstored256((__v8si *)__X, (__v8si)__M, (__v8si)__Y);
3654 /// of [4 x i64] in \a __Y to memory \a __X, if the most significant bit of
3662 /// Store64(__X+(i*8), __Y[j+63:j])
3671 /// \param __X
3678 _mm256_maskstore_epi64(long long *__X, __m256i __M, __m256i __Y)
3680 __builtin_ia32_maskstoreq256((__v4di *)__X, (__v4di)__M, (__v4di)__Y);
3684 /// of [4 x i32] in \a __Y to memory \a __X, if the most significant bit of
3692 /// Store32(__X+(i*4), __Y[j+31:j])
3701 /// \param __X
3708 _mm_maskstore_epi32(int *__X, __m128i __M, __m128i __Y)
3710 __builtin_ia32_maskstored((__v4si *)__X, (__v4si)__M, (__v4si)__Y);
3714 /// of [2 x i64] in \a __Y to memory \a __X, if the most significant bit of
3722 /// Store64(__X+(i*8), __Y[j+63:j])
3731 /// \param __X
3738 _mm_maskstore_epi64(long long *__X, __m128i __M, __m128i __Y)
3740 __builtin_ia32_maskstoreq(( __v2di *)__X, (__v2di)__M, (__v2di)__Y);
3743 /// Shifts each 32-bit element of the 256-bit vector of [8 x i32] in \a __X
3753 /// \param __X
3760 _mm256_sllv_epi32(__m256i __X, __m256i __Y)
3762 return (__m256i)__builtin_ia32_psllv8si((__v8si)__X, (__v8si)__Y);
3765 /// Shifts each 32-bit element of the 128-bit vector of [4 x i32] in \a __X
3775 /// \param __X
3782 _mm_sllv_epi32(__m128i __X, __m128i __Y)
3784 return (__m128i)__builtin_ia32_psllv4si((__v4si)__X, (__v4si)__Y);
3787 /// Shifts each 64-bit element of the 256-bit vector of [4 x i64] in \a __X
3797 /// \param __X
3804 _mm256_sllv_epi64(__m256i __X, __m256i __Y)
3806 return (__m256i)__builtin_ia32_psllv4di((__v4di)__X, (__v4di)__Y);
3809 /// Shifts each 64-bit element of the 128-bit vector of [2 x i64] in \a __X
3819 /// \param __X
3826 _mm_sllv_epi64(__m128i __X, __m128i __Y)
3828 return (__m128i)__builtin_ia32_psllv2di((__v2di)__X, (__v2di)__Y);
3831 /// Shifts each 32-bit element of the 256-bit vector of [8 x i32] in \a __X
3842 /// \param __X
3849 _mm256_srav_epi32(__m256i __X, __m256i __Y)
3851 return (__m256i)__builtin_ia32_psrav8si((__v8si)__X, (__v8si)__Y);
3854 /// Shifts each 32-bit element of the 128-bit vector of [4 x i32] in \a __X
3865 /// \param __X
3872 _mm_srav_epi32(__m128i __X, __m128i __Y)
3874 return (__m128i)__builtin_ia32_psrav4si((__v4si)__X, (__v4si)__Y);
3877 /// Shifts each 32-bit element of the 256-bit vector of [8 x i32] in \a __X
3887 /// \param __X
3894 _mm256_srlv_epi32(__m256i __X, __m256i __Y)
3896 return (__m256i)__builtin_ia32_psrlv8si((__v8si)__X, (__v8si)__Y);
3899 /// Shifts each 32-bit element of the 128-bit vector of [4 x i32] in \a __X
3909 /// \param __X
3916 _mm_srlv_epi32(__m128i __X, __m128i __Y)
3918 return (__m128i)__builtin_ia32_psrlv4si((__v4si)__X, (__v4si)__Y);
3921 /// Shifts each 64-bit element of the 256-bit vector of [4 x i64] in \a __X
3931 /// \param __X
3938 _mm256_srlv_epi64(__m256i __X, __m256i __Y)
3940 return (__m256i)__builtin_ia32_psrlv4di((__v4di)__X, (__v4di)__Y);
3943 /// Shifts each 64-bit element of the 128-bit vector of [2 x i64] in \a __X
3953 /// \param __X
3960 _mm_srlv_epi64(__m128i __X, __m128i __Y)
3962 return (__m128i)__builtin_ia32_psrlv2di((__v2di)__X, (__v2di)__Y);