/external/libgav1/libgav1/src/dsp/x86/ |
D | intrapred_cfl_sse4.cc | 68 StoreUnaligned16(luma_ptr, result); in StoreLumaResults8_420() 115 StoreUnaligned16(dst, res); in CflIntraPredictor_SSE4_1() 120 StoreUnaligned16(dst + 16, res); in CflIntraPredictor_SSE4_1() 241 StoreUnaligned16(luma_ptr, samples0); in CflSubsampler444_8xH_SSE4_1() 254 StoreUnaligned16(luma_ptr, samples1); in CflSubsampler444_8xH_SSE4_1() 264 StoreUnaligned16(luma_ptr, samples1); in CflSubsampler444_8xH_SSE4_1() 268 StoreUnaligned16(luma_ptr, samples1); in CflSubsampler444_8xH_SSE4_1() 287 StoreUnaligned16(luma_ptr, _mm_sub_epi16(samples, averages)); in CflSubsampler444_8xH_SSE4_1() 358 StoreUnaligned16(luma_ptr, samples0); in CflSubsampler444_SSE4_1() 359 StoreUnaligned16(luma_ptr + 8, samples1); in CflSubsampler444_SSE4_1() [all …]
|
D | intra_edge_sse4.cc | 74 StoreUnaligned16(dest, result); in ComputeKernel1Store12() 114 StoreUnaligned16(dest, result); in ComputeKernel2Store12() 228 StoreUnaligned16(pixel_buffer - 1, result_lo); in IntraEdgeUpsampler_SSE4_1() 240 StoreUnaligned16(pixel_buffer + 15, result_hi); in IntraEdgeUpsampler_SSE4_1()
|
D | distance_weighted_blend_sse4.cc | 148 StoreUnaligned16(dst + x, _mm_packus_epi16(res_lo, res_hi)); in DistanceWeightedBlendLarge_SSE4_1() 326 StoreUnaligned16(dst, res0); in DistanceWeightedBlend8xH_SSE4_1() 328 StoreUnaligned16(dst, res1); in DistanceWeightedBlend8xH_SSE4_1() 356 StoreUnaligned16(dst + x, res_lo); in DistanceWeightedBlendLarge_SSE4_1() 358 StoreUnaligned16(dst + x, res_hi); in DistanceWeightedBlendLarge_SSE4_1()
|
D | warp_sse4.cc | 98 StoreUnaligned16(intermediate_result_row, sum); in HorizontalFilter() 130 StoreUnaligned16(static_cast<int16_t*>(dst_row), sum); in WriteVerticalFilter() 161 StoreUnaligned16(static_cast<int16_t*>(dst_row), sum); in WriteVerticalFilter() 234 StoreUnaligned16(dst_row, sum); in WarpRegion1()
|
D | convolve_sse4.cc | 115 StoreUnaligned16(&dest16[x], v_sum); in FilterHorizontal() 376 StoreUnaligned16(dst16_x, results); in FilterVertical() 507 StoreUnaligned16(&dest[x], v_dest_lo); in ConvolveCompoundCopy_SSE4() 508 StoreUnaligned16(&dest[x + 8], v_dest_hi); in ConvolveCompoundCopy_SSE4() 520 StoreUnaligned16(&dest[0], v_dest); in ConvolveCompoundCopy_SSE4() 1157 StoreUnaligned16(dest16_y + x, sums); in ConvolveVerticalScale() 1348 StoreUnaligned16(dst, _mm_avg_epu8(left, right)); in HalfAddHorizontal() 1522 StoreUnaligned16(dst, _mm_avg_epu8(row[0], below[0])); in IntraBlockCopyVertical() 1526 StoreUnaligned16(dst, _mm_avg_epu8(row[1], below[1])); in IntraBlockCopyVertical() 1530 StoreUnaligned16(dst, _mm_avg_epu8(row[2], below[2])); in IntraBlockCopyVertical() [all …]
|
D | inverse_transform_sse4.cc | 49 StoreUnaligned16(&dst[i * stride + idx], s[i]); in StoreDst() 50 StoreUnaligned16(&dst[(i + 1) * stride + idx], s[i + 1]); in StoreDst() 51 StoreUnaligned16(&dst[(i + 2) * stride + idx], s[i + 2]); in StoreDst() 52 StoreUnaligned16(&dst[(i + 3) * stride + idx], s[i + 3]); in StoreDst() 255 StoreUnaligned16(dst, xy_shifted); in DctDcOnly() 280 StoreUnaligned16(&dst[i], xy); in DctDcOnlyColumn() 1251 StoreUnaligned16(dst, _mm_packs_epi32(b, b1)); in Adst8DcOnly() 1549 StoreUnaligned16(&dst[i * 8], _mm_packs_epi32(b, b1)); in Adst16DcOnly() 1600 StoreUnaligned16(&dst[i * step], _mm_packs_epi32(b, b_hi)); in Identity4_SSE4_1() 1609 StoreUnaligned16(&dst[i * step], b); in Identity4_SSE4_1() [all …]
|
D | convolve_avx2.cc | 278 StoreUnaligned16(&dest8[0], _mm256_castsi256_si128(packed_result)); in FilterHorizontal() 279 StoreUnaligned16(&dest8[pred_stride], in FilterHorizontal() 314 StoreUnaligned16(&dest16[0], _mm256_castsi256_si128(result)); in FilterHorizontal() 315 StoreUnaligned16(&dest16[pred_stride], in FilterHorizontal() 521 StoreUnaligned16(dst8_x, packed_sum); in Filter2DVertical16xH() 938 StoreUnaligned16(dst8, this_dst); in FilterVertical16xH() 939 StoreUnaligned16(dst8 + dst_stride, next_dst); in FilterVertical16xH() 1026 StoreUnaligned16(dst16, this_dst); in FilterVertical8xH() 1027 StoreUnaligned16(dst16 + dst_stride, next_dst); in FilterVertical8xH() 1098 StoreUnaligned16(dst16, results); in FilterVertical8xH()
|
D | common_avx2.h | 70 using avx2::StoreUnaligned16;
|
D | obmc_sse4.cc | 178 StoreUnaligned16(pred, _mm_packus_epi16(result_lo, result_hi)); in OverlapBlendFromLeft_SSE4_1() 295 StoreUnaligned16(pred + x, _mm_packus_epi16(result_lo, result_hi)); in OverlapBlendFromTop_SSE4_1() 431 StoreUnaligned16(pred, _mm_packus_epi32(result_lo, result_hi)); in OverlapBlendFromLeft10bpp_SSE4_1() 570 StoreUnaligned16(pred + x, _mm_packus_epi32(result_lo, result_hi)); in OverlapBlendFromTop10bpp_SSE4_1()
|
D | intrapred_sse4.cc | 238 StoreUnaligned16(dst, dc_dup); in DcStore16xH_SSE4_1() 241 StoreUnaligned16(dst, dc_dup); in DcStore16xH_SSE4_1() 252 StoreUnaligned16(dst, dc_dup); in DcStore32xH_SSE4_1() 253 StoreUnaligned16(dst + 16, dc_dup); in DcStore32xH_SSE4_1() 256 StoreUnaligned16(dst, dc_dup); in DcStore32xH_SSE4_1() 257 StoreUnaligned16(dst + 16, dc_dup); in DcStore32xH_SSE4_1() 268 StoreUnaligned16(dst, dc_dup); in DcStore64xH_SSE4_1() 269 StoreUnaligned16(dst + 16, dc_dup); in DcStore64xH_SSE4_1() 270 StoreUnaligned16(dst + 32, dc_dup); in DcStore64xH_SSE4_1() 271 StoreUnaligned16(dst + 48, dc_dup); in DcStore64xH_SSE4_1() [all …]
|
D | loop_filter_sse4.cc | 1095 StoreUnaligned16(dst - 8 + 0 * stride, x0); in Vertical14() 1096 StoreUnaligned16(dst - 8 + 1 * stride, x1); in Vertical14() 1097 StoreUnaligned16(dst - 8 + 2 * stride, x2); in Vertical14() 1098 StoreUnaligned16(dst - 8 + 3 * stride, x3); in Vertical14() 1844 StoreUnaligned16(dst - 4 + 0 * stride, x0); in Vertical8() 1845 StoreUnaligned16(dst - 4 + 1 * stride, x1); in Vertical8() 1846 StoreUnaligned16(dst - 4 + 2 * stride, x2); in Vertical8() 1847 StoreUnaligned16(dst - 4 + 3 * stride, x3); in Vertical8() 2177 StoreUnaligned16(dst - 8 + 0 * stride, x0); in Vertical14() 2178 StoreUnaligned16(dst - 8 + 1 * stride, x1); in Vertical14() [all …]
|
D | common_sse4.h | 123 using sse4::StoreUnaligned16;
|
D | convolve_sse4.inc | 246 StoreUnaligned16(dst16_x, sum); 308 StoreUnaligned16(dst16, sum); 474 StoreUnaligned16(dst16, results); 521 StoreUnaligned16(dst16, results); 580 StoreUnaligned16(dst16, results); 651 StoreUnaligned16(dst16, results);
|
D | average_blend_sse4.cc | 69 StoreUnaligned16(dest + x, _mm_packus_epi16(res0, res1)); in AverageBlendLargeRow() 177 StoreUnaligned16(dst + offset, result); in AverageBlendRow()
|
D | intrapred_directional_sse4.cc | 1277 StoreUnaligned16(dest + x, pred); in DirectionalZone1_Large() 1315 StoreUnaligned16(dest + x, pred); in DirectionalZone1_Large() 1384 StoreUnaligned16(dest + x, pred); in DirectionalIntraPredictorZone1_SSE4_1() 1434 StoreUnaligned16(dest + x, pred); in DirectionalIntraPredictorZone1_SSE4_1()
|
D | common_sse4.inc | 152 inline void StoreUnaligned16(void* a, const __m128i v) {
|
D | mask_blend_sse4.cc | 717 StoreUnaligned16(dst + x, result); in MaskBlend10bpp_SSE4_1() 893 StoreUnaligned16(dst + x, _mm_packus_epi32(shift_0, shift_1)); in InterIntraMaskBlend10bpp_SSE4_1()
|
D | film_grain_sse4.cc | 69 StoreUnaligned16(dest, data); in StoreUnsigned()
|
D | intrapred_smooth_sse4.cc | 108 StoreUnaligned16(dest, _mm_packus_epi16(pred1, pred2)); in WriteSmoothDirectionalSum16()
|
/external/libgav1/libgav1/src/utils/ |
D | entropy_decoder.cc | 350 inline void StoreUnaligned16(void* a, const __m128i v) { in StoreUnaligned16() function 398 StoreUnaligned16(cdf, cdf_vec); in UpdateCdf7To9() 434 StoreUnaligned16(cdf + 2, cdf_vec); in UpdateCdf11() 445 StoreUnaligned16(cdf + 2, cdf_vec); in UpdateCdf11() 476 StoreUnaligned16(cdf + 4, cdf_vec1); in UpdateCdf13() 497 StoreUnaligned16(cdf, cdf_vec0); in UpdateCdf16() 508 StoreUnaligned16(cdf + 8, cdf_vec1); in UpdateCdf16()
|