Lines Matching refs:src
32 static void avc_chroma_hz_2x2_msa(uint8_t *src, uint8_t *dst, int32_t stride,
46 LD_SB2(src, stride, src0, src1);
63 static void avc_chroma_hz_2x4_msa(uint8_t *src, uint8_t *dst, int32_t stride,
76 LD_UB4(src, stride, src0, src1, src2, src3);
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,
115 LD_SB2(src, stride, src0, src1);
127 static void avc_chroma_hz_4x4_msa(uint8_t *src, uint8_t *dst, int32_t stride,
139 LD_UB4(src, stride, src0, src1, src2, src3);
150 static void avc_chroma_hz_4x8_msa(uint8_t *src, uint8_t *dst, int32_t stride,
162 LD_UB8(src, stride, src0, src1, src2, src3, src4, src5, src6, src7);
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,
198 LD_UB4(src, stride, src0, src1, src2, src3);
210 static void avc_chroma_hz_8x8_msa(uint8_t *src, uint8_t *dst, int32_t stride,
223 LD_UB8(src, stride, src0, src1, src2, src3, src4, src5, src6, src7);
243 static void avc_chroma_hz_nonmult_msa(uint8_t *src, uint8_t *dst,
258 LD_UB4(src, stride, src0, src1, src2, src3);
259 src += (4 * stride);
275 src0 = LD_UB(src);
276 src += 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,
317 LD_SB3(src, stride, src0, src1, src2);
337 static void avc_chroma_vt_2x4_msa(uint8_t *src, uint8_t *dst, int32_t stride,
348 LD_UB5(src, stride, src0, src1, src2, src3, src4);
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,
387 LD_UB3(src, stride, src0, src1, src2);
400 static void avc_chroma_vt_4x4_msa(uint8_t *src, uint8_t *dst, int32_t stride,
411 LD_UB5(src, stride, src0, src1, src2, src3, src4);
424 static void avc_chroma_vt_4x8_msa(uint8_t *src, uint8_t *dst, int32_t stride,
434 LD_UB5(src, stride, src0, src1, src2, src3, src4);
435 src += (5 * stride);
436 LD_UB4(src, stride, src5, src6, src7, src8);
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,
474 LD_UB5(src, stride, src0, src1, src2, src3, src4);
486 static void avc_chroma_vt_8x8_msa(uint8_t *src, uint8_t *dst, int32_t stride,
496 LD_UB5(src, stride, src0, src1, src2, src3, src4);
497 src += (5 * stride);
498 LD_UB4(src, stride, src5, src6, src7, src8);
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,
546 LD_UB3(src, stride, src0, src1, src2);
564 static void avc_chroma_hv_2x4_msa(uint8_t *src, uint8_t *dst, int32_t stride,
581 LD_UB5(src, stride, src0, src1, src2, src3, src4);
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,
627 LD_UB3(src, stride, src0, src1, src2);
640 static void avc_chroma_hv_4x4_msa(uint8_t *src, uint8_t *dst, int32_t stride,
657 LD_UB5(src, stride, src0, src1, src2, src3, src4);
673 static void avc_chroma_hv_4x8_msa(uint8_t *src, uint8_t *dst, int32_t stride,
689 LD_UB5(src, stride, src0, src1, src2, src3, src4);
690 src += (5 * stride);
691 LD_UB4(src, stride, src5, src6, src7, src8);
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,
746 src0 = LD_UB(src);
747 src += stride;
752 LD_UB4(src, stride, src1, src2, src3, src4);
753 src += (4 * stride);
773 static void avc_chroma_hv_8x8_msa(uint8_t *src, uint8_t *dst, int32_t stride,
792 LD_UB5(src, stride, src0, src1, src2, src3, src4);
793 src += (5 * stride);
794 LD_UB4(src, stride, src5, src6, src7, src8);
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,
859 LD_SB2(src, stride, src0, src1);
885 static void avc_chroma_hz_and_aver_dst_2x4_msa(uint8_t *src, uint8_t *dst,
900 LD_UB4(src, stride, src0, src1, src2, src3);
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,
951 LD_SB2(src, stride, src0, src1);
969 static void avc_chroma_hz_and_aver_dst_4x4_msa(uint8_t *src, uint8_t *dst,
984 LD_UB4(src, stride, src0, src1, src2, src3);
998 static void avc_chroma_hz_and_aver_dst_4x8_msa(uint8_t *src, uint8_t *dst,
1013 LD_UB8(src, stride, src0, src1, src2, src3, src4, src5, src6, src7);
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,
1057 LD_UB4(src, stride, src0, src1, src2, src3);
1073 static void avc_chroma_hz_and_aver_dst_8x8_msa(uint8_t *src, uint8_t *dst,
1089 LD_UB8(src, stride, src0, src1, src2, src3, src4, src5, src6, src7);
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,
1141 LD_SB3(src, stride, src0, src1, src2);
1165 static void avc_chroma_vt_and_aver_dst_2x4_msa(uint8_t *src, uint8_t *dst,
1179 LD_SB5(src, stride, src0, src1, src2, src3, src4);
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,
1231 LD_UB3(src, stride, src0, src1, src2);
1250 static void avc_chroma_vt_and_aver_dst_4x4_msa(uint8_t *src, uint8_t *dst,
1264 LD_UB5(src, stride, src0, src1, src2, src3, src4);
1280 static void avc_chroma_vt_and_aver_dst_4x8_msa(uint8_t *src, uint8_t *dst,
1293 LD_UB5(src, stride, src0, src1, src2, src3, src4);
1294 src += (5 * stride);
1295 LD_UB4(src, stride, src5, src6, src7, src8);
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,
1342 LD_UB5(src, stride, src0, src1, src2, src3, src4);
1358 static void avc_chroma_vt_and_aver_dst_8x8_msa(uint8_t *src, uint8_t *dst,
1371 LD_UB5(src, stride, src0, src1, src2, src3, src4);
1372 src += (5 * stride);
1373 LD_UB4(src, stride, src5, src6, src7, src8);
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,
1432 LD_UB3(src, stride, src0, src1, src2);
1454 static void avc_chroma_hv_and_aver_dst_2x4_msa(uint8_t *src, uint8_t *dst,
1475 LD_UB5(src, stride, src0, src1, src2, src3, src4);
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,
1536 LD_UB3(src, stride, src0, src1, src2);
1552 static void avc_chroma_hv_and_aver_dst_4x4_msa(uint8_t *src, uint8_t *dst,
1573 LD_UB5(src, stride, src0, src1, src2, src3, src4);
1591 static void avc_chroma_hv_and_aver_dst_4x8_msa(uint8_t *src, uint8_t *dst,
1612 LD_UB5(src, stride, src0, src1, src2, src3, src4);
1613 src += (5 * stride);
1614 LD_UB4(src, stride, src5, src6, src7, src8);
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,
1682 src0 = LD_UB(src);
1683 src += stride;
1686 LD_UB4(src, stride, src1, src2, src3, src4);
1687 src += (4 * stride);
1708 static void avc_chroma_hv_and_aver_dst_8x8_msa(uint8_t *src, uint8_t *dst,
1732 LD_UB5(src, stride, src0, src1, src2, src3, src4);
1733 src += (5 * stride);
1734 LD_UB4(src, stride, src5, src6, src7, src8);
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,
1800 LW4(src, stride, tp0, tp1, tp2, tp3);
1801 src += 4 * stride;
1802 LW4(src, stride, tp4, tp5, tp6, tp7);
1807 LW4(src, stride, tp0, tp1, tp2, tp3);
1810 LW2(src, stride, tp0, tp1);
1817 static void copy_width8_msa(uint8_t *src, uint8_t *dst, int32_t stride,
1823 LD4(src, stride, src0, src1, src2, src3);
1824 src += 4 * stride;
1825 LD4(src, stride, src4, src5, src6, src7);
1830 LD4(src, stride, src0, src1, src2, src3);
1835 static void avg_width4_msa(uint8_t *src, uint8_t *dst, int32_t stride,
1842 LW4(src, stride, tp0, tp1, tp2, tp3);
1843 src += 4 * stride;
1845 LW4(src, stride, tp0, tp1, tp2, tp3);
1854 LW4(src, stride, tp0, tp1, tp2, tp3);
1861 LW2(src, stride, tp0, tp1);
1870 static void avg_width8_msa(uint8_t *src, uint8_t *dst, int32_t stride,
1878 LD4(src, stride, tp0, tp1, tp2, tp3);
1879 src += 4 * stride;
1880 LD4(src, stride, tp4, tp5, tp6, tp7);
1895 LD4(src, stride, tp0, tp1, tp2, tp3);
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);
1955 src += 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;
2015 src += stride;