Searched refs:_mm256_loadu_si256 (Results 1 – 13 of 13) sorted by relevance
23 ref1_reg = _mm256_loadu_si256((__m256i const *)ref_ptr); \24 ref2_reg = _mm256_loadu_si256((__m256i const *)(ref_ptr + 32)); \26 ref1_reg, _mm256_loadu_si256((__m256i const *)src_ptr)); \28 ref2_reg, _mm256_loadu_si256((__m256i const *)(src_ptr + 32))); \54 ref1_reg = _mm256_loadu_si256((__m256i const *)ref_ptr); \55 ref2_reg = _mm256_loadu_si256((__m256i const *)(ref_ptr + ref_stride)); \57 ref1_reg, _mm256_loadu_si256((__m256i const *)src_ptr)); \60 _mm256_loadu_si256((__m256i const *)(src_ptr + src_stride))); \101 ref1_reg = _mm256_loadu_si256((__m256i const *)ref_ptr); \102 ref2_reg = _mm256_loadu_si256((__m256i const *)(ref_ptr + 32)); \[all …]
33 src_reg = _mm256_loadu_si256((const __m256i *)src); in vpx_sad32x32x4d_avx2()34 ref0_reg = _mm256_loadu_si256((const __m256i *)ref0); in vpx_sad32x32x4d_avx2()35 ref1_reg = _mm256_loadu_si256((const __m256i *)ref1); in vpx_sad32x32x4d_avx2()36 ref2_reg = _mm256_loadu_si256((const __m256i *)ref2); in vpx_sad32x32x4d_avx2()37 ref3_reg = _mm256_loadu_si256((const __m256i *)ref3); in vpx_sad32x32x4d_avx2()103 src_reg = _mm256_loadu_si256((const __m256i *)src); in vpx_sad64x64x4d_avx2()104 srcnext_reg = _mm256_loadu_si256((const __m256i *)(src + 32)); in vpx_sad64x64x4d_avx2()105 ref0_reg = _mm256_loadu_si256((const __m256i *)ref0); in vpx_sad64x64x4d_avx2()106 ref0next_reg = _mm256_loadu_si256((const __m256i *)(ref0 + 32)); in vpx_sad64x64x4d_avx2()107 ref1_reg = _mm256_loadu_si256((const __m256i *)ref1); in vpx_sad64x64x4d_avx2()[all …]
33 const __m256i p0 = _mm256_loadu_si256((const __m256i *)src); in vpx_highbd_convolve_copy_avx2()34 const __m256i p1 = _mm256_loadu_si256((const __m256i *)(src + 16)); in vpx_highbd_convolve_copy_avx2()35 const __m256i p2 = _mm256_loadu_si256((const __m256i *)(src + 32)); in vpx_highbd_convolve_copy_avx2()36 const __m256i p3 = _mm256_loadu_si256((const __m256i *)(src + 48)); in vpx_highbd_convolve_copy_avx2()47 const __m256i p0 = _mm256_loadu_si256((const __m256i *)src); in vpx_highbd_convolve_copy_avx2()48 const __m256i p1 = _mm256_loadu_si256((const __m256i *)(src + 16)); in vpx_highbd_convolve_copy_avx2()58 p0 = _mm256_loadu_si256((const __m256i *)src); in vpx_highbd_convolve_copy_avx2()60 p1 = _mm256_loadu_si256((const __m256i *)src); in vpx_highbd_convolve_copy_avx2()115 p0 = _mm256_loadu_si256((const __m256i *)src); in vpx_highbd_convolve_avg_avx2()116 p1 = _mm256_loadu_si256((const __m256i *)(src + 16)); in vpx_highbd_convolve_avg_avx2()[all …]
155 src = _mm256_loadu_si256((__m256i const *)(src_ptr)); in vpx_get32x32var_avx2()157 ref = _mm256_loadu_si256((__m256i const *)(ref_ptr)); in vpx_get32x32var_avx2()251 src_reg = _mm256_loadu_si256((__m256i const *)(src)); \252 dst_reg = _mm256_loadu_si256((__m256i const *)(dst));255 src_next_reg = _mm256_loadu_si256((__m256i const *)(src + size_stride)); \260 src_next_reg = _mm256_loadu_si256((__m256i const *)(src + size_stride)); \370 src_reg = _mm256_loadu_si256((__m256i const *)(src)); in vpx_sub_pixel_variance32xh_avx2()394 src_reg = _mm256_loadu_si256((__m256i const *)(src)); in vpx_sub_pixel_variance32xh_avx2()431 src_reg = _mm256_loadu_si256((__m256i const *)(src)); in vpx_sub_pixel_variance32xh_avx2()461 src_reg = _mm256_loadu_si256((__m256i const *)(src)); in vpx_sub_pixel_variance32xh_avx2()[all …]
23 const __m256i a_low = _mm256_loadu_si256((const __m256i *)a); in load_tran_low()26 return _mm256_loadu_si256((const __m256i *)a); in load_tran_low()
117 const __m256i ina0 = _mm256_loadu_si256((const __m256i *)(ina)); in FDCT32x32_2D_AVX2()119 _mm256_loadu_si256((const __m256i *)(ina + str1)); in FDCT32x32_2D_AVX2()121 _mm256_loadu_si256((const __m256i *)(ina + str2)); in FDCT32x32_2D_AVX2()123 _mm256_loadu_si256((const __m256i *)(ina + str3)); in FDCT32x32_2D_AVX2()125 _mm256_loadu_si256((const __m256i *)(inb - str3)); in FDCT32x32_2D_AVX2()127 _mm256_loadu_si256((const __m256i *)(inb - str2)); in FDCT32x32_2D_AVX2()129 _mm256_loadu_si256((const __m256i *)(inb - str1)); in FDCT32x32_2D_AVX2()130 const __m256i inb0 = _mm256_loadu_si256((const __m256i *)(inb)); in FDCT32x32_2D_AVX2()153 const __m256i ina0 = _mm256_loadu_si256((const __m256i *)(ina)); in FDCT32x32_2D_AVX2()155 _mm256_loadu_si256((const __m256i *)(ina + str1)); in FDCT32x32_2D_AVX2()[all …]
58 _mm256_loadu_si256((const __m256i*)(srcRows[i+0] + x*4)), in convolve_vertically()59 _mm256_loadu_si256((const __m256i*)(srcRows[i+1] + x*4))); in convolve_vertically()63 _mm256_loadu_si256((const __m256i*)(srcRows[i] + x*4)), in convolve_vertically()
242 result.lo = _mm256_loadu_si256(&m[0].lo); in _simd16_loadu_si()243 result.hi = _mm256_loadu_si256(&m[0].hi); in _simd16_loadu_si()
618 #define _simd_loadu_si _mm256_loadu_si256
489 return _mm256_loadu_si256(A); in test_mm256_loadu_si256()
219 …adu<Packet8i>(const int* from) { EIGEN_DEBUG_UNALIGNED_LOAD return _mm256_loadu_si256(reinterpret_…
2387 _mm256_loadu_si256(__m256i const *__p) in _mm256_loadu_si256() function
395 result.x = _mm256_loadu_si256(reinterpret_cast<const __m256i*>(from));