/external/libgav1/libgav1/src/dsp/x86/ |
D | convolve_sse4.cc | 120 StoreLo8(&dest8[x], result); in FilterHorizontal() 141 StoreLo8(dest16, v_sum); in FilterHorizontal() 381 StoreLo8(dst8_x, _mm_packus_epi16(results, results)); in FilterVertical() 532 StoreLo8(&dest[0], v_dest); in ConvolveCompoundCopy_SSE4() 938 StoreLo8(intermediate, RightShiftWithRounding_S16( in ConvolveHorizontalScale() 1117 StoreLo8(dest16_y, sums); in ConvolveVerticalScale() 1159 StoreLo8(dest_y + x, _mm_packus_epi16(sums, sums)); in ConvolveVerticalScale() 1419 StoreLo8(dest, _mm_avg_epu8(left, right)); in ConvolveIntraBlockCopyHorizontal_SSE4_1() 1586 StoreLo8(dest, _mm_avg_epu8(row, below)); in ConvolveIntraBlockCopyVertical_SSE4_1() 1690 StoreLo8(dst, AddU16RightShift2AndPack(row[0], below_0)); in IntraBlockCopy2D() [all …]
|
D | loop_filter_sse4.cc | 722 StoreLo8(dst - 4 + 0 * stride, x0); in Vertical8() 723 StoreLo8(dst - 4 + 1 * stride, x1); in Vertical8() 724 StoreLo8(dst - 4 + 2 * stride, x2); in Vertical8() 725 StoreLo8(dst - 4 + 3 * stride, x3); in Vertical8() 1294 StoreLo8(dst - 2 * stride, oqp1); in Horizontal4() 1295 StoreLo8(dst - 1 * stride, oqp0); in Horizontal4() 1345 StoreLo8(dst - 2 + 0 * stride, op0p1); in Vertical4() 1347 StoreLo8(dst - 2 + 2 * stride, oq1q0); in Vertical4() 1469 StoreLo8(dst - 2 * stride, oqp1); in Horizontal6() 1470 StoreLo8(dst - 1 * stride, oqp0); in Horizontal6() [all …]
|
D | common_avx2.h | 69 using avx2::StoreLo8;
|
D | intrapred_cfl_sse4.cc | 56 StoreLo8(luma_ptr, result); in StoreLumaResults4_420() 109 StoreLo8(dst, res); in CflIntraPredictor_SSE4_1() 148 StoreLo8(luma_ptr, samples); in CflSubsampler444_4xH_SSE4_1() 163 StoreLo8(luma_ptr, samples); in CflSubsampler444_4xH_SSE4_1() 184 StoreLo8(luma_ptr, _mm_sub_epi16(samples, averages)); in CflSubsampler444_4xH_SSE4_1() 491 StoreLo8(luma_ptr, final_fill); in CflSubsampler420_4xH_SSE4_1() 506 StoreLo8(luma_ptr, _mm_sub_epi16(samples, averages)); in CflSubsampler420_4xH_SSE4_1() 993 StoreLo8(dst, res); in CflIntraPredictor_10bpp_SSE4_1() 1063 StoreLo8(luma_ptr, _mm_sub_epi16(samples, averages)); in CflSubsampler444_4xH_SSE4_1() 1072 StoreLo8(luma_ptr, _mm_sub_epi16(samples, averages)); in CflSubsampler444_4xH_SSE4_1() [all …]
|
D | distance_weighted_blend_sse4.cc | 120 StoreLo8(dst, result_pixels); in DistanceWeightedBlend8xH_SSE4_1() 290 StoreLo8(dst, res0); in DistanceWeightedBlend4xH_SSE4_1() 294 StoreLo8(dst, res1); in DistanceWeightedBlend4xH_SSE4_1()
|
D | intrapred_directional_sse4.cc | 191 StoreLo8(dest + x, _mm_packus_epi16(vals, vals)); in DirectionalZone1_Large() 234 StoreLo8(dest + x, _mm_packus_epi16(vals, vals)); in DirectionalZone1_Large() 294 StoreLo8(dest + x, _mm_packus_epi16(vals, vals)); in DirectionalZone1_SSE4_1() 349 StoreLo8(dest + x, _mm_packus_epi16(vals, vals)); in DirectionalZone1_SSE4_1() 363 StoreLo8(dest + x, _mm_packus_epi16(vals, vals)); in DirectionalZone1_SSE4_1() 456 StoreLo8(dest, _mm_packus_epi16(result_block[y], result_block[y])); in DirectionalZone3_8xH() 569 StoreLo8(dest, _mm_packus_epi16(blended_vals, blended_vals)); in DirectionalBlend8_SSE4_1() 667 StoreLo8(dst, _mm_packus_epi16(vals, vals)); in DirectionalZone2FromLeftCol_8x8_SSE4_1() 1197 StoreLo8(dst, pred); in DirectionalZone1_4xH()
|
D | inverse_transform_sse4.cc | 57 StoreLo8(&dst[i * stride + idx], s[i]); in StoreDst() 58 StoreLo8(&dst[(i + 1) * stride + idx], s[i + 1]); in StoreDst() 59 StoreLo8(&dst[(i + 2) * stride + idx], s[i + 2]); in StoreDst() 60 StoreLo8(&dst[(i + 3) * stride + idx], s[i + 3]); in StoreDst() 252 StoreLo8(dst, xy_shifted); in DctDcOnly() 274 StoreLo8(dst, xy); in DctDcOnlyColumn() 1060 StoreLo8(dst, c); in Adst4DcOnly() 1089 StoreLo8(&dst[i], dst_0_1); in Adst4DcOnlyColumn() 1091 StoreLo8(&dst[i + width * 2], dst_2_3); in Adst4DcOnlyColumn() 1302 StoreLo8(&dst[j * width], x[j]); in Adst8DcOnlyColumn() [all …]
|
D | motion_field_projection_sse4.cc | 132 StoreLo8(skip_64, skip); in GetPosition() 217 StoreLo8(&early_skip, skip_r); in MotionFieldProjectionKernel_SSE4_1() 276 StoreLo8(&early_skip, skip_r); in MotionFieldProjectionKernel_SSE4_1()
|
D | obmc_sse4.cc | 127 StoreLo8(pred, _mm_packus_epi16(result, result)); in OverlapBlendFromLeft8xH_SSE4_1() 250 StoreLo8(pred, _mm_packus_epi16(result, result)); in OverlapBlendFromTop8xH_SSE4_1() 380 StoreLo8(pred, packed_result); in OverlapBlendFromLeft4xH_SSE4_1() 517 StoreLo8(pred, packed_result); in OverlapBlendFromTop4xH_SSE4_1()
|
D | weight_mask_sse4.cc | 66 StoreLo8(mask, inverted_mask_value); in WeightMask16_SSE4() 73 StoreLo8(mask, mask_value); in WeightMask16_SSE4() 517 StoreLo8(mask, inverted_mask_value); in WeightMask16_10bpp_SSE4() 524 StoreLo8(mask, mask_value); in WeightMask16_10bpp_SSE4()
|
D | common_sse4.h | 122 using sse4::StoreLo8;
|
D | convolve_avx2.cc | 325 StoreLo8(&dest8[0], _mm256_castsi256_si128(result)); in FilterHorizontal() 326 StoreLo8(&dest8[pred_stride], _mm256_extracti128_si256(result, 1)); in FilterHorizontal() 354 StoreLo8(&dest16[0], _mm256_castsi256_si128(result)); in FilterHorizontal() 355 StoreLo8(&dest16[pred_stride], _mm256_extracti128_si256(result, 1)); in FilterHorizontal() 378 StoreLo8(&dest16[0], _mm256_castsi256_si128(result)); in FilterHorizontal() 1035 StoreLo8(dst8, this_dst); in FilterVertical8xH() 1036 StoreLo8(dst8 + dst_stride, next_dst); in FilterVertical8xH() 1102 StoreLo8(dst8, _mm_packus_epi16(results, results)); in FilterVertical8xH()
|
D | average_blend_sse4.cc | 53 StoreLo8(dest, _mm_packus_epi16(res, res)); in AverageBlend8Row() 181 StoreLo8(dst, result); in AverageBlendRow()
|
D | warp_sse4.cc | 133 StoreLo8(static_cast<uint8_t*>(dst_row), _mm_packus_epi16(sum, sum)); in WriteVerticalFilter() 164 StoreLo8(static_cast<uint8_t*>(dst_row), _mm_packus_epi16(sum, sum)); in WriteVerticalFilter()
|
D | mask_blend_sse4.cc | 269 StoreLo8(dst + x, _mm_packus_epi16(result, result)); in MaskBlend_SSE4() 395 StoreLo8(prediction_1 + x, res); in InterIntraMaskBlend8bpp_SSE4() 542 StoreLo8(dst, result); in WriteMaskBlendLine10bpp4x2_SSE4_1() 748 StoreLo8(dst, res); in InterIntraWriteMaskBlendLine10bpp4x2_SSE4_1()
|
D | film_grain_sse4.cc | 57 StoreLo8(dest, _mm_packus_epi16(data, data)); in StoreUnsigned() 352 StoreLo8(merged_buffer, _mm_packus_epi16(merged, merged)); in BlendChromaValsNoCfl8bpp()
|
D | intra_edge_sse4.cc | 152 StoreLo8(dest, _mm_packus_epi16(sum, sum)); in ComputeKernel3Store8()
|
D | common_sse4.inc | 139 inline void StoreLo8(void* a, const __m128i v) {
|
D | intrapred_sse4.cc | 224 StoreLo8(dst, dc_dup); in DcStore8xH_SSE4_1() 227 StoreLo8(dst, dc_dup); in DcStore8xH_SSE4_1() 1813 StoreLo8(dst, dc_dup); in DcStore4xH_SSE4_1() 1816 StoreLo8(dst, dc_dup); in DcStore4xH_SSE4_1()
|
D | cdef_avx2.cc | 740 StoreLo8(dst, result); in CdefFilter_AVX2()
|
D | cdef_sse4.cc | 686 StoreLo8(dst, result); in CdefFilter_SSE4_1()
|
D | intrapred_smooth_sse4.cc | 88 StoreLo8(dest, _mm_packus_epi16(pred, pred)); in WriteSmoothDirectionalSum8() 401 StoreLo8(dst, sum0); in WriteSmoothPred8xH() 529 StoreLo8(dst + x, _mm_packus_epi16(pred, pred)); in SmoothWxH()
|
D | convolve_sse4.inc | 249 StoreLo8(dst8_x, _mm_packus_epi16(sum, sum));
|
D | loop_restoration_10bit_sse4.cc | 1078 StoreLo8(temp, idx); in LookupIntermediate()
|
/external/libgav1/libgav1/src/utils/ |
D | entropy_decoder.cc | 346 inline void StoreLo8(void* a, const __m128i v) { in StoreLo8() function 375 StoreLo8(cdf, cdf_vec); in UpdateCdf5() 466 StoreLo8(cdf, cdf_vec0); in UpdateCdf13() 865 StoreLo8(cdf, cdf_vec); in ReadSymbol3Or4() 952 StoreLo8(cdf, cdf_vec); in ReadSymbol3Or4()
|