Lines Matching refs:dst
32 static void avc_chroma_hz_2x2_msa(uint8_t *src, uint8_t *dst, int32_t stride,
58 SH(out0, dst);
59 dst += stride;
60 SH(out1, dst);
63 static void avc_chroma_hz_2x4_msa(uint8_t *src, uint8_t *dst, int32_t stride,
88 ST_H4(res, 0, 1, 2, 3, dst, stride);
91 static void avc_chroma_hz_2w_msa(uint8_t *src, uint8_t *dst, int32_t stride,
96 avc_chroma_hz_2x2_msa(src, dst, stride, coeff0, coeff1);
98 avc_chroma_hz_2x4_msa(src, dst, stride, coeff0, coeff1);
102 static void avc_chroma_hz_4x2_msa(uint8_t *src, uint8_t *dst, int32_t stride,
124 ST_W2(res, 0, 1, dst, stride);
127 static void avc_chroma_hz_4x4_msa(uint8_t *src, uint8_t *dst, int32_t stride,
147 ST_W4(out, 0, 1, 2, 3, dst, stride);
150 static void avc_chroma_hz_4x8_msa(uint8_t *src, uint8_t *dst, int32_t stride,
171 ST_W8(out0, out1, 0, 1, 2, 3, 0, 1, 2, 3, dst, stride);
174 static void avc_chroma_hz_4w_msa(uint8_t *src, uint8_t *dst, int32_t stride,
179 avc_chroma_hz_4x2_msa(src, dst, stride, coeff0, coeff1);
181 avc_chroma_hz_4x4_msa(src, dst, stride, coeff0, coeff1);
183 avc_chroma_hz_4x8_msa(src, dst, stride, coeff0, coeff1);
187 static void avc_chroma_hz_8x4_msa(uint8_t *src, uint8_t *dst, int32_t stride,
207 ST_D4(out0, out1, 0, 1, 0, 1, dst, stride);
210 static void avc_chroma_hz_8x8_msa(uint8_t *src, uint8_t *dst, int32_t stride,
240 ST_D8(out0, out1, out2, out3, 0, 1, 0, 1, 0, 1, 0, 1, dst, stride);
243 static void avc_chroma_hz_nonmult_msa(uint8_t *src, uint8_t *dst,
269 ST_D4(out0, out1, 0, 1, 0, 1, dst, stride);
270 dst += (4 * stride);
286 ST_D1(res0, 0, dst);
287 dst += stride;
292 static void avc_chroma_hz_8w_msa(uint8_t *src, uint8_t *dst, int32_t stride,
297 avc_chroma_hz_8x4_msa(src, dst, stride, coeff0, coeff1);
299 avc_chroma_hz_8x8_msa(src, dst, stride, coeff0, coeff1);
301 avc_chroma_hz_nonmult_msa(src, dst, stride, coeff0, coeff1, height);
305 static void avc_chroma_vt_2x2_msa(uint8_t *src, uint8_t *dst, int32_t stride,
332 SH(out0, dst);
333 dst += stride;
334 SH(out1, dst);
337 static void avc_chroma_vt_2x4_msa(uint8_t *src, uint8_t *dst, int32_t stride,
362 ST_H4(res, 0, 1, 2, 3, dst, stride);
365 static void avc_chroma_vt_2w_msa(uint8_t *src, uint8_t *dst, int32_t stride,
370 avc_chroma_vt_2x2_msa(src, dst, stride, coeff0, coeff1);
372 avc_chroma_vt_2x4_msa(src, dst, stride, coeff0, coeff1);
376 static void avc_chroma_vt_4x2_msa(uint8_t *src, uint8_t *dst, int32_t stride,
397 ST_W2(res, 0, 1, dst, stride);
400 static void avc_chroma_vt_4x4_msa(uint8_t *src, uint8_t *dst, int32_t stride,
421 ST_W4(out, 0, 1, 2, 3, dst, stride);
424 static void avc_chroma_vt_4x8_msa(uint8_t *src, uint8_t *dst, int32_t stride,
449 ST_W8(out0, out1, 0, 1, 2, 3, 0, 1, 2, 3, dst, stride);
452 static void avc_chroma_vt_4w_msa(uint8_t *src, uint8_t *dst, int32_t stride,
457 avc_chroma_vt_4x2_msa(src, dst, stride, coeff0, coeff1);
459 avc_chroma_vt_4x4_msa(src, dst, stride, coeff0, coeff1);
461 avc_chroma_vt_4x8_msa(src, dst, stride, coeff0, coeff1);
465 static void avc_chroma_vt_8x4_msa(uint8_t *src, uint8_t *dst, int32_t stride,
483 ST_D4(out0, out1, 0, 1, 0, 1, dst, stride);
486 static void avc_chroma_vt_8x8_msa(uint8_t *src, uint8_t *dst, int32_t stride,
515 ST_D8(out0, out1, out2, out3, 0, 1, 0, 1, 0, 1, 0, 1, dst, stride);
518 static void avc_chroma_vt_8w_msa(uint8_t *src, uint8_t *dst, int32_t stride,
523 avc_chroma_vt_8x4_msa(src, dst, stride, coeff0, coeff1);
525 avc_chroma_vt_8x8_msa(src, dst, stride, coeff0, coeff1);
529 static void avc_chroma_hv_2x2_msa(uint8_t *src, uint8_t *dst, int32_t stride,
559 SH(out0, dst);
560 dst += stride;
561 SH(out1, dst);
564 static void avc_chroma_hv_2x4_msa(uint8_t *src, uint8_t *dst, int32_t stride,
595 ST_H4(res, 0, 1, 2, 3, dst, stride);
598 static void avc_chroma_hv_2w_msa(uint8_t *src, uint8_t *dst, int32_t stride,
604 avc_chroma_hv_2x2_msa(src, dst, stride, coef_hor0, coef_hor1, coef_ver0,
607 avc_chroma_hv_2x4_msa(src, dst, stride, coef_hor0, coef_hor1, coef_ver0,
612 static void avc_chroma_hv_4x2_msa(uint8_t *src, uint8_t *dst, int32_t stride,
637 ST_W2(res, 0, 1, dst, stride);
640 static void avc_chroma_hv_4x4_msa(uint8_t *src, uint8_t *dst, int32_t stride,
669 ST_W2(res0, 0, 1, dst, stride);
670 ST_W2(res1, 0, 1, dst + 2 * stride, stride);
673 static void avc_chroma_hv_4x8_msa(uint8_t *src, uint8_t *dst, int32_t stride,
710 ST_W8(res0, res1, 0, 1, 2, 3, 0, 1, 2, 3, dst, stride);
713 static void avc_chroma_hv_4w_msa(uint8_t *src, uint8_t *dst, int32_t stride,
719 avc_chroma_hv_4x2_msa(src, dst, stride, coef_hor0, coef_hor1, coef_ver0,
722 avc_chroma_hv_4x4_msa(src, dst, stride, coef_hor0, coef_hor1, coef_ver0,
725 avc_chroma_hv_4x8_msa(src, dst, stride, coef_hor0, coef_hor1, coef_ver0,
730 static void avc_chroma_hv_8x4_msa(uint8_t *src, uint8_t *dst, int32_t stride,
770 ST_D4(out0, out1, 0, 1, 0, 1, dst, stride);
773 static void avc_chroma_hv_8x8_msa(uint8_t *src, uint8_t *dst, int32_t stride,
826 ST_D8(out0, out1, out2, out3, 0, 1, 0, 1, 0, 1, 0, 1, dst, stride);
829 static void avc_chroma_hv_8w_msa(uint8_t *src, uint8_t *dst, int32_t stride,
835 avc_chroma_hv_8x4_msa(src, dst, stride, coef_hor0, coef_hor1, coef_ver0,
838 avc_chroma_hv_8x8_msa(src, dst, stride, coef_hor0, coef_hor1, coef_ver0,
843 static void avc_chroma_hz_and_aver_dst_2x2_msa(uint8_t *src, uint8_t *dst,
861 out0 = LH(dst);
862 out1 = LH(dst + stride);
880 SH(out0, dst);
881 dst += stride;
882 SH(out1, dst);
885 static void avc_chroma_hz_and_aver_dst_2x4_msa(uint8_t *src, uint8_t *dst,
901 tp0 = LH(dst);
902 tp1 = LH(dst + stride);
903 tp2 = LH(dst + 2 * stride);
904 tp3 = LH(dst + 3 * stride);
922 ST_H4(dst0, 0, 1, 2, 3, dst, stride);
925 static void avc_chroma_hz_and_aver_dst_2w_msa(uint8_t *src, uint8_t *dst,
930 avc_chroma_hz_and_aver_dst_2x2_msa(src, dst, stride, coeff0, coeff1);
932 avc_chroma_hz_and_aver_dst_2x4_msa(src, dst, stride, coeff0, coeff1);
936 static void avc_chroma_hz_and_aver_dst_4x2_msa(uint8_t *src, uint8_t *dst,
953 LW2(dst, stride, load0, load1);
966 ST_W2(dst_data, 0, 1, dst, stride);
969 static void avc_chroma_hz_and_aver_dst_4x4_msa(uint8_t *src, uint8_t *dst,
985 LW4(dst, stride, tp0, tp1, tp2, tp3);
995 ST_W4(out, 0, 1, 2, 3, dst, stride);
998 static void avc_chroma_hz_and_aver_dst_4x8_msa(uint8_t *src, uint8_t *dst,
1014 LW4(dst, stride, tp0, tp1, tp2, tp3);
1016 LW4(dst + 4 * stride, stride, tp0, tp1, tp2, tp3);
1027 ST_W8(out0, out1, 0, 1, 2, 3, 0, 1, 2, 3, dst, stride);
1030 static void avc_chroma_hz_and_aver_dst_4w_msa(uint8_t *src, uint8_t *dst,
1035 avc_chroma_hz_and_aver_dst_4x2_msa(src, dst, stride, coeff0, coeff1);
1037 avc_chroma_hz_and_aver_dst_4x4_msa(src, dst, stride, coeff0, coeff1);
1039 avc_chroma_hz_and_aver_dst_4x8_msa(src, dst, stride, coeff0, coeff1);
1043 static void avc_chroma_hz_and_aver_dst_8x4_msa(uint8_t *src, uint8_t *dst,
1058 LD4(dst, stride, tp0, tp1, tp2, tp3);
1070 ST_D4(dst0, dst1, 0, 1, 0, 1, dst, stride);
1073 static void avc_chroma_hz_and_aver_dst_8x8_msa(uint8_t *src, uint8_t *dst,
1090 LD4(dst, stride, tp0, tp1, tp2, tp3);
1093 LD4(dst + 4 * stride, stride, tp0, tp1, tp2, tp3);
1114 ST_D8(out0, out1, out2, out3, 0, 1, 0, 1, 0, 1, 0, 1, dst, stride);
1117 static void avc_chroma_hz_and_aver_dst_8w_msa(uint8_t *src, uint8_t *dst,
1122 avc_chroma_hz_and_aver_dst_8x4_msa(src, dst, stride, coeff0, coeff1);
1124 avc_chroma_hz_and_aver_dst_8x8_msa(src, dst, stride, coeff0, coeff1);
1128 static void avc_chroma_vt_and_aver_dst_2x2_msa(uint8_t *src, uint8_t *dst,
1142 out0 = LH(dst);
1143 out1 = LH(dst + stride);
1160 SH(out0, dst);
1161 dst += stride;
1162 SH(out1, dst);
1165 static void avc_chroma_vt_and_aver_dst_2x4_msa(uint8_t *src, uint8_t *dst,
1181 tp0 = LH(dst);
1182 tp1 = LH(dst + stride);
1183 tp2 = LH(dst + 2 * stride);
1184 tp3 = LH(dst + 3 * stride);
1204 ST_H4(res, 0, 1, 2, 3, dst, stride);
1207 static void avc_chroma_vt_and_aver_dst_2w_msa(uint8_t *src, uint8_t *dst,
1212 avc_chroma_vt_and_aver_dst_2x2_msa(src, dst, stride, coeff0, coeff1);
1214 avc_chroma_vt_and_aver_dst_2x4_msa(src, dst, stride, coeff0, coeff1);
1218 static void avc_chroma_vt_and_aver_dst_4x2_msa(uint8_t *src, uint8_t *dst,
1233 LW2(dst, stride, load0, load1);
1247 ST_W2(res, 0, 1, dst, stride);
1250 static void avc_chroma_vt_and_aver_dst_4x4_msa(uint8_t *src, uint8_t *dst,
1265 LW4(dst, stride, tp0, tp1, tp2, tp3);
1277 ST_W4(out, 0, 1, 2, 3, dst, stride);
1280 static void avc_chroma_vt_and_aver_dst_4x8_msa(uint8_t *src, uint8_t *dst,
1296 LW4(dst, stride, tp0, tp1, tp2, tp3);
1298 LW4(dst + 4 * stride, stride, tp0, tp1, tp2, tp3);
1313 ST_W8(out0, out1, 0, 1, 2, 3, 0, 1, 2, 3, dst, stride);
1316 static void avc_chroma_vt_and_aver_dst_4w_msa(uint8_t *src, uint8_t *dst,
1321 avc_chroma_vt_and_aver_dst_4x2_msa(src, dst, stride, coeff0, coeff1);
1323 avc_chroma_vt_and_aver_dst_4x4_msa(src, dst, stride, coeff0, coeff1);
1325 avc_chroma_vt_and_aver_dst_4x8_msa(src, dst, stride, coeff0, coeff1);
1329 static void avc_chroma_vt_and_aver_dst_8x4_msa(uint8_t *src, uint8_t *dst,
1343 LD4(dst, stride, tp0, tp1, tp2, tp3);
1355 ST_D4(out0, out1, 0, 1, 0, 1, dst, stride);
1358 static void avc_chroma_vt_and_aver_dst_8x8_msa(uint8_t *src, uint8_t *dst,
1374 LD4(dst, stride, tp0, tp1, tp2, tp3);
1377 LD4(dst + 4 * stride, stride, tp0, tp1, tp2, tp3);
1398 ST_D8(out0, out1, out2, out3, 0, 1, 0, 1, 0, 1, 0, 1, dst, stride);
1401 static void avc_chroma_vt_and_aver_dst_8w_msa(uint8_t *src, uint8_t *dst,
1406 avc_chroma_vt_and_aver_dst_8x4_msa(src, dst, stride, coeff0, coeff1);
1408 avc_chroma_vt_and_aver_dst_8x8_msa(src, dst, stride, coeff0, coeff1);
1412 static void avc_chroma_hv_and_aver_dst_2x2_msa(uint8_t *src, uint8_t *dst,
1433 out0 = LH(dst);
1434 out1 = LH(dst + stride);
1449 SH(out0, dst);
1450 dst += stride;
1451 SH(out1, dst);
1454 static void avc_chroma_hv_and_aver_dst_2x4_msa(uint8_t *src, uint8_t *dst,
1476 tp0 = LH(dst);
1477 tp1 = LH(dst + stride);
1478 tp2 = LH(dst + 2 * stride);
1479 tp3 = LH(dst + 3 * stride);
1496 ST_H4(dst0, 0, 1, 2, 3, dst, stride);
1499 static void avc_chroma_hv_and_aver_dst_2w_msa(uint8_t *src, uint8_t *dst,
1508 avc_chroma_hv_and_aver_dst_2x2_msa(src, dst, stride, coef_hor0,
1511 avc_chroma_hv_and_aver_dst_2x4_msa(src, dst, stride, coef_hor0,
1516 static void avc_chroma_hv_and_aver_dst_4x2_msa(uint8_t *src, uint8_t *dst,
1537 LW2(dst, stride, tp0, tp1);
1549 ST_W2(dst0, 0, 1, dst, stride);
1552 static void avc_chroma_hv_and_aver_dst_4x4_msa(uint8_t *src, uint8_t *dst,
1574 LW4(dst, stride, tp0, tp1, tp2, tp3);
1588 ST_W4(out, 0, 1, 2, 3, dst, stride);
1591 static void avc_chroma_hv_and_aver_dst_4x8_msa(uint8_t *src, uint8_t *dst,
1615 LW4(dst, stride, tp0, tp1, tp2, tp3);
1617 LW4(dst + 4 * stride, stride, tp0, tp1, tp2, tp3);
1637 ST_W8(res0, res1, 0, 1, 2, 3, 0, 1, 2, 3, dst, stride);
1640 static void avc_chroma_hv_and_aver_dst_4w_msa(uint8_t *src, uint8_t *dst,
1649 avc_chroma_hv_and_aver_dst_4x2_msa(src, dst, stride, coef_hor0,
1652 avc_chroma_hv_and_aver_dst_4x4_msa(src, dst, stride, coef_hor0,
1655 avc_chroma_hv_and_aver_dst_4x8_msa(src, dst, stride, coef_hor0,
1660 static void avc_chroma_hv_and_aver_dst_8x4_msa(uint8_t *src, uint8_t *dst,
1688 LD4(dst, stride, tp0, tp1, tp2, tp3);
1705 ST_D4(out0, out1, 0, 1, 0, 1, dst, stride);
1708 static void avc_chroma_hv_and_aver_dst_8x8_msa(uint8_t *src, uint8_t *dst,
1752 LD4(dst, stride, tp0, tp1, tp2, tp3);
1755 LD4(dst + 4 * stride, stride, tp0, tp1, tp2, tp3);
1774 ST_D8(out0, out1, out2, out3, 0, 1, 0, 1, 0, 1, 0, 1, dst, stride);
1777 static void avc_chroma_hv_and_aver_dst_8w_msa(uint8_t *src, uint8_t *dst,
1786 avc_chroma_hv_and_aver_dst_8x4_msa(src, dst, stride, coef_hor0,
1789 avc_chroma_hv_and_aver_dst_8x8_msa(src, dst, stride, coef_hor0,
1794 static void copy_width4_msa(uint8_t *src, uint8_t *dst, int32_t stride,
1803 SW4(tp0, tp1, tp2, tp3, dst, stride);
1804 dst += 4 * stride;
1805 SW4(tp4, tp5, tp6, tp7, dst, stride);
1808 SW4(tp0, tp1, tp2, tp3, dst, stride);
1811 SW(tp0, dst);
1812 dst += stride;
1813 SW(tp1, dst);
1817 static void copy_width8_msa(uint8_t *src, uint8_t *dst, int32_t stride,
1826 SD4(src0, src1, src2, src3, dst, stride);
1827 dst += 4 * stride;
1828 SD4(src4, src5, src6, src7, dst, stride);
1831 SD4(src0, src1, src2, src3, dst, stride);
1835 static void avg_width4_msa(uint8_t *src, uint8_t *dst, int32_t stride,
1847 LW4(dst, stride, tp0, tp1, tp2, tp3);
1849 LW4(dst + 4 * stride, stride, tp0, tp1, tp2, tp3);
1852 ST_W8(dst0, dst1, 0, 1, 2, 3, 0, 1, 2, 3, dst, stride);
1856 LW4(dst, stride, tp0, tp1, tp2, tp3);
1859 ST_W4(dst0, 0, 1, 2, 3, dst, stride);
1863 LW2(dst, stride, tp0, tp1);
1866 ST_W2(dst0, 0, 1, dst, stride);
1870 static void avg_width8_msa(uint8_t *src, uint8_t *dst, int32_t stride,
1885 LD4(dst, stride, tp0, tp1, tp2, tp3);
1886 LD4(dst + 4 * stride, stride, tp4, tp5, tp6, tp7);
1893 ST_D8(dst0, dst1, dst2, dst3, 0, 1, 0, 1, 0, 1, 0, 1, dst, stride);
1898 LD4(dst, stride, tp0, tp1, tp2, tp3);
1902 ST_D4(dst0, dst1, 0, 1, 0, 1, dst, stride);
1906 void ff_put_h264_chroma_mc8_msa(uint8_t *dst, uint8_t *src,
1912 avc_chroma_hv_8w_msa(src, dst, stride, x, (8 - x), y, (8 - y), height);
1914 avc_chroma_hz_8w_msa(src, dst, stride, x, (8 - x), height);
1916 avc_chroma_vt_8w_msa(src, dst, stride, y, (8 - y), height);
1918 copy_width8_msa(src, dst, stride, height);
1922 void ff_put_h264_chroma_mc4_msa(uint8_t *dst, uint8_t *src,
1928 avc_chroma_hv_4w_msa(src, dst, stride, x, (8 - x), y, (8 - y), height);
1930 avc_chroma_hz_4w_msa(src, dst, stride, x, (8 - x), height);
1932 avc_chroma_vt_4w_msa(src, dst, stride, y, (8 - y), height);
1934 copy_width4_msa(src, dst, stride, height);
1938 void ff_put_h264_chroma_mc2_msa(uint8_t *dst, uint8_t *src,
1946 avc_chroma_hv_2w_msa(src, dst, stride, x, (8 - x), y, (8 - y), height);
1948 avc_chroma_hz_2w_msa(src, dst, stride, x, (8 - x), height);
1950 avc_chroma_vt_2w_msa(src, dst, stride, y, (8 - y), height);
1953 *((uint16_t *) dst) = *((uint16_t *) src);
1956 dst += stride;
1961 void ff_avg_h264_chroma_mc8_msa(uint8_t *dst, uint8_t *src,
1968 avc_chroma_hv_and_aver_dst_8w_msa(src, dst, stride, x, (8 - x), y,
1971 avc_chroma_hz_and_aver_dst_8w_msa(src, dst, stride, x, (8 - x), height);
1973 avc_chroma_vt_and_aver_dst_8w_msa(src, dst, stride, y, (8 - y), height);
1975 avg_width8_msa(src, dst, stride, height);
1979 void ff_avg_h264_chroma_mc4_msa(uint8_t *dst, uint8_t *src,
1985 avc_chroma_hv_and_aver_dst_4w_msa(src, dst, stride, x, (8 - x), y,
1988 avc_chroma_hz_and_aver_dst_4w_msa(src, dst, stride, x, (8 - x), height);
1990 avc_chroma_vt_and_aver_dst_4w_msa(src, dst, stride, y, (8 - y), height);
1992 avg_width4_msa(src, dst, stride, height);
1996 void ff_avg_h264_chroma_mc2_msa(uint8_t *dst, uint8_t *src,
2004 avc_chroma_hv_and_aver_dst_2w_msa(src, dst, stride, x, (8 - x), y,
2007 avc_chroma_hz_and_aver_dst_2w_msa(src, dst, stride, x, (8 - x), height);
2009 avc_chroma_vt_and_aver_dst_2w_msa(src, dst, stride, y, (8 - y), height);
2012 dst[0] = (dst[0] + src[0] + 1) >> 1;
2013 dst[1] = (dst[1] + src[1] + 1) >> 1;
2016 dst += stride;