| /external/libgav1/libgav1/src/dsp/x86/ |
| D | intrapred_cfl_sse4.cc | 76 StoreUnaligned16(dst, res); in CflIntraPredictor_SSE4_1()
81 StoreUnaligned16(dst + 16, res); in CflIntraPredictor_SSE4_1()
200 StoreUnaligned16(luma_ptr, samples0); in CflSubsampler444_8xH_SSE4_1()
213 StoreUnaligned16(luma_ptr, samples1); in CflSubsampler444_8xH_SSE4_1()
223 StoreUnaligned16(luma_ptr, samples1); in CflSubsampler444_8xH_SSE4_1()
227 StoreUnaligned16(luma_ptr, samples1); in CflSubsampler444_8xH_SSE4_1()
246 StoreUnaligned16(luma_ptr, _mm_sub_epi16(samples, averages)); in CflSubsampler444_8xH_SSE4_1()
328 StoreUnaligned16(luma_ptr, samples0); in CflSubsampler444_SSE4_1()
329 StoreUnaligned16(luma_ptr + 8, samples1); in CflSubsampler444_SSE4_1()
355 StoreUnaligned16(luma_ptr + 16, samples2); 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 | 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 | 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()
261 StoreUnaligned16(dst, xy_shifted); in DctDcOnly()
290 StoreUnaligned16(&dst[i], xy); in DctDcOnlyColumn()
1281 StoreUnaligned16(dst, _mm_packs_epi32(b, b1)); in Adst8DcOnly()
1587 StoreUnaligned16(&dst[i * 8], _mm_packs_epi32(b, b1)); in Adst16DcOnly()
1644 StoreUnaligned16(&dst[i * step], _mm_packs_epi32(b, b_hi)); in Identity4_SSE4_1()
1653 StoreUnaligned16(&dst[i * step], b); in Identity4_SSE4_1()
[all …]
|
| D | convolve_sse4.cc | 242 StoreUnaligned16(&dest16[x], v_sum); in FilterHorizontal()
470 StoreUnaligned16(dst16 + x + y * dst_stride, sum); in Filter2DVertical()
530 StoreUnaligned16(dst16, sum); in Filter2DVertical4xH()
830 StoreUnaligned16(dst16 + x + y * dst_stride, results); in FilterVertical()
887 StoreUnaligned16(dst16, results); in FilterVertical4xH()
934 StoreUnaligned16(dst16, results); in FilterVertical4xH()
993 StoreUnaligned16(dst16, results); in FilterVertical4xH()
1064 StoreUnaligned16(dst16, results); in FilterVertical4xH()
1451 StoreUnaligned16(&dest[x], v_dest_lo); in ConvolveCompoundCopy_SSE4()
1452 StoreUnaligned16(&dest[x + 8], v_dest_hi); in ConvolveCompoundCopy_SSE4()
[all …]
|
| D | loop_filter_sse4.cc | 1097 StoreUnaligned16(dst - 8 + 0 * stride, x0); in Vertical14()
1098 StoreUnaligned16(dst - 8 + 1 * stride, x1); in Vertical14()
1099 StoreUnaligned16(dst - 8 + 2 * stride, x2); in Vertical14()
1100 StoreUnaligned16(dst - 8 + 3 * stride, x3); in Vertical14()
1846 StoreUnaligned16(dst - 4 + 0 * stride, x0); in Vertical8()
1847 StoreUnaligned16(dst - 4 + 1 * stride, x1); in Vertical8()
1848 StoreUnaligned16(dst - 4 + 2 * stride, x2); in Vertical8()
1849 StoreUnaligned16(dst - 4 + 3 * stride, x3); in Vertical8()
2181 StoreUnaligned16(dst - 8 + 0 * stride, x0); in Vertical14()
2182 StoreUnaligned16(dst - 8 + 1 * stride, x1); in Vertical14()
[all …]
|
| D | obmc_sse4.cc | 177 StoreUnaligned16(pred, _mm_packus_epi16(result_lo, result_hi)); in OverlapBlendFromLeft_SSE4_1()
294 StoreUnaligned16(pred + x, _mm_packus_epi16(result_lo, result_hi)); in OverlapBlendFromTop_SSE4_1()
|
| D | average_blend_sse4.cc | 68 StoreUnaligned16(dest + x, _mm_packus_epi16(res0, res1)); in AverageBlendLargeRow()
|
| D | intrapred_sse4.cc | 241 StoreUnaligned16(dst, dc_dup); in DcStore16xH_SSE4_1()
244 StoreUnaligned16(dst, dc_dup); in DcStore16xH_SSE4_1()
255 StoreUnaligned16(dst, dc_dup); in DcStore32xH_SSE4_1()
256 StoreUnaligned16(dst + 16, dc_dup); in DcStore32xH_SSE4_1()
259 StoreUnaligned16(dst, dc_dup); in DcStore32xH_SSE4_1()
260 StoreUnaligned16(dst + 16, dc_dup); in DcStore32xH_SSE4_1()
271 StoreUnaligned16(dst, dc_dup); in DcStore64xH_SSE4_1()
272 StoreUnaligned16(dst + 16, dc_dup); in DcStore64xH_SSE4_1()
273 StoreUnaligned16(dst + 32, dc_dup); in DcStore64xH_SSE4_1()
274 StoreUnaligned16(dst + 48, dc_dup); in DcStore64xH_SSE4_1()
[all …]
|
| D | common_sse4.h | 207 inline void StoreUnaligned16(void* a, const __m128i v) { in StoreUnaligned16() function
|
| D | distance_weighted_blend_sse4.cc | 147 StoreUnaligned16(dst + x, _mm_packus_epi16(res_lo, res_hi)); in DistanceWeightedBlendLarge_SSE4_1()
|
| D | intrapred_smooth_sse4.cc | 131 StoreUnaligned16(dest, _mm_packus_epi16(pred1, pred2)); in WriteSmoothDirectionalSum16()
|
| /external/libgav1/libgav1/src/utils/ |
| D | entropy_decoder.cc | 337 inline void StoreUnaligned16(void* a, const __m128i v) { in StoreUnaligned16() function
377 StoreUnaligned16(cdf, cdf_vec); in UpdateCdf7To9()
408 StoreUnaligned16(cdf + 2, cdf_vec); in UpdateCdf11()
419 StoreUnaligned16(cdf + 2, cdf_vec); in UpdateCdf11()
440 StoreUnaligned16(cdf, cdf_vec0); in UpdateCdf13()
449 StoreUnaligned16(cdf + 4, cdf_vec1); in UpdateCdf13()
470 StoreUnaligned16(cdf, cdf_vec0); in UpdateCdf16()
480 StoreUnaligned16(cdf + 8, cdf_vec1); in UpdateCdf16()
|