Lines Matching defs:stride
229 void ff_loop_filter_v_4_8_lsx(uint8_t *dst, ptrdiff_t stride,
234 ptrdiff_t stride2 = stride << 1;
235 ptrdiff_t stride3 = stride2 + stride;
241 dst, -stride, p3, p2, p1, p0);
243 DUP2_ARG2(__lsx_vldx, dst, stride, dst, stride2, q1, q2);
257 __lsx_vstelm_d(p0_out, dst - stride, 0, 0);
259 __lsx_vstelm_d(q1_out, dst + stride, 0, 0);
262 void ff_loop_filter_v_44_16_lsx(uint8_t *dst, ptrdiff_t stride,
267 ptrdiff_t stride2 = stride << 1;
268 ptrdiff_t stride3 = stride2 + stride;
275 dst, -stride, p3, p2, p1, p0);
277 DUP2_ARG2(__lsx_vldx, dst, stride, dst, stride2, q1, q2);
297 __lsx_vst(p0, dst - stride, 0);
299 __lsx_vst(q1, dst + stride, 0);
302 void ff_loop_filter_v_8_8_lsx(uint8_t *dst, ptrdiff_t stride,
307 ptrdiff_t stride2 = stride << 1;
308 ptrdiff_t stride3 = stride2 + stride;
319 dst, -stride, p3, p2, p1, p0);
321 DUP2_ARG2(__lsx_vldx, dst, stride, dst, stride2, q1, q2);
339 __lsx_vstelm_d(p0_out, dst - stride, 0, 0);
341 __lsx_vstelm_d(q1_out, dst + stride, 0, 0);
367 __lsx_vstelm_d(p0_out, dst - stride, 0, 0);
369 __lsx_vstelm_d(q1_out, dst + stride, 0, 0);
374 void ff_loop_filter_v_88_16_lsx(uint8_t *dst, ptrdiff_t stride,
379 ptrdiff_t stride2 = stride << 1;
380 ptrdiff_t stride3 = stride2 + stride;
395 dst, -stride, p3, p2, p1, p0);
397 DUP2_ARG2(__lsx_vldx, dst, stride, dst, stride2, q1, q2);
422 __lsx_vst(p0_out, dst - stride, 0);
424 __lsx_vst(q1_out, dst + stride, 0);
458 __lsx_vstx(p0_out, dst, -stride);
460 __lsx_vstx(q1_out, dst, stride);
465 void ff_loop_filter_v_84_16_lsx(uint8_t *dst, ptrdiff_t stride,
470 ptrdiff_t stride2 = stride << 1;
471 ptrdiff_t stride3 = stride2 + stride;
483 dst, -stride, p3, p2, p1, p0);
485 DUP2_ARG2(__lsx_vldx, dst, stride, dst, stride2, q1, q2);
512 __lsx_vstx(p0_out, dst, -stride);
514 __lsx_vstx(q1_out, dst, stride);
540 __lsx_vstx(p0_out, dst, -stride);
542 __lsx_vstx(q1_out, dst, stride);
547 void ff_loop_filter_v_48_16_lsx(uint8_t *dst, ptrdiff_t stride,
552 ptrdiff_t stride2 = stride << 1;
553 ptrdiff_t stride3 = stride2 + stride;
565 dst, -stride, p3, p2, p1, p0);
567 DUP2_ARG2(__lsx_vldx, dst, stride, dst, stride2, q1, q2);
594 __lsx_vstx(p0_out, dst, -stride);
596 __lsx_vstx(q1_out, dst, stride);
622 __lsx_vstx(p0_out, dst, -stride);
624 __lsx_vstx(q1_out, dst, stride);
629 static int32_t vp9_hz_lpf_t4_and_t8_16w(uint8_t *dst, ptrdiff_t stride,
635 ptrdiff_t stride2 = stride << 1;
636 ptrdiff_t stride3 = stride2 + stride;
651 dst, -stride, p3, p2, p1, p0);
653 DUP2_ARG2(__lsx_vldx, dst, stride, dst, stride2, q1, q2);
670 __lsx_vstx(p0_out, dst, -stride);
672 __lsx_vstx(q1_out, dst, stride);
716 static void vp9_hz_lpf_t16_16w(uint8_t *dst, ptrdiff_t stride,
719 ptrdiff_t stride2 = stride << 1;
720 ptrdiff_t stride3 = stride2 + stride;
741 -stride2, dst_tmp, -stride, p7, p6, p5, p4);
743 DUP2_ARG2(__lsx_vldx, dst_tmp, stride, dst_tmp, stride2, p2, p1);
747 DUP2_ARG2(__lsx_vldx, dst, stride, dst, stride2, q1, q2);
751 DUP2_ARG2(__lsx_vldx, dst_tmp1, stride, dst_tmp1, stride2, q5, q6);
763 __lsx_vstx(p0, dst, -stride);
765 __lsx_vstx(q1, dst, stride);
823 dst += stride;
843 dst += stride;
863 dst += stride;
883 dst += stride;
904 dst += stride;
925 dst += stride;
946 dst += stride;
967 dst += stride;
986 dst += stride;
1005 dst += stride;
1023 dst += stride;
1041 dst += stride;
1059 dst += stride;
1080 void ff_loop_filter_v_16_16_lsx(uint8_t *dst, ptrdiff_t stride,
1088 early_exit = vp9_hz_lpf_t4_and_t8_16w(dst, stride, &filter48[0],
1092 vp9_hz_lpf_t16_16w(dst, stride, filter48);
1096 void ff_loop_filter_v_16_8_lsx(uint8_t *dst, ptrdiff_t stride,
1101 ptrdiff_t stride2 = stride << 1;
1102 ptrdiff_t stride3 = stride2 + stride;
1119 dst, -stride, p3, p2, p1, p0);
1121 DUP2_ARG2(__lsx_vldx, dst, stride, dst, stride2, q1, q2);
1139 __lsx_vstelm_d(p0_out, dst - stride, 0, 0);
1141 __lsx_vstelm_d(q1_out, dst + stride, 0, 0);
1169 dst_tmp - stride2, 0, dst_tmp - stride, 0, p7, p6, p5, p4);
1170 DUP4_ARG2(__lsx_vld, dst_tmp1, 0, dst_tmp1 + stride, 0,
1179 dst += stride;
1181 dst += stride;
1183 dst += stride;
1185 dst += stride;
1187 dst += stride;
1224 dst += stride;
1226 dst += stride;
1244 dst += stride;
1246 dst += stride;
1264 dst += stride;
1266 dst += stride;
1284 dst += stride;
1286 dst += stride;
1304 dst += stride;
1306 dst += stride;
1324 dst += stride;
1326 dst += stride;
1344 dst += stride;
1350 void ff_loop_filter_h_4_8_lsx(uint8_t *dst, ptrdiff_t stride,
1355 ptrdiff_t stride2 = stride << 1;
1356 ptrdiff_t stride3 = stride2 + stride;
1365 DUP2_ARG2(__lsx_vldx, dst_tmp1, stride, dst_tmp1, stride2, p2, p1);
1368 DUP2_ARG2(__lsx_vldx, dst_tmp2, stride, dst_tmp2, stride2, q1, q2);
1386 __lsx_vstelm_w(vec2, dst + stride, 0, 1);
1391 __lsx_vstelm_w(vec3, dst + stride, 0, 1);
1396 void ff_loop_filter_h_44_16_lsx(uint8_t *dst, ptrdiff_t stride,
1401 ptrdiff_t stride2 = stride << 1;
1402 ptrdiff_t stride3 = stride2 + stride;
1413 DUP2_ARG2(__lsx_vldx, dst_tmp, stride, dst_tmp, stride2, row1, row2);
1417 DUP2_ARG2(__lsx_vldx, dst_tmp, stride, dst_tmp, stride2, row5, row6);
1421 DUP2_ARG2(__lsx_vldx, dst_tmp, stride, dst_tmp, stride2, row9, row10);
1425 DUP2_ARG2(__lsx_vldx, dst_tmp, stride, dst_tmp, stride2, row13, row14);
1456 __lsx_vstelm_w(tmp2, dst + stride, 0, 1);
1461 __lsx_vstelm_w(tmp3, dst + stride, 0, 1);
1466 __lsx_vstelm_w(tmp4, dst + stride, 0, 1);
1471 __lsx_vstelm_w(tmp5, dst + stride, 0, 1);
1476 void ff_loop_filter_h_8_8_lsx(uint8_t *dst, ptrdiff_t stride,
1481 ptrdiff_t stride2 = stride << 1;
1482 ptrdiff_t stride3 = stride2 + stride;
1496 DUP2_ARG2(__lsx_vldx, dst_tmp, stride, dst_tmp, stride2, p2, p1);
1500 DUP2_ARG2(__lsx_vldx, dst_tmp, stride, dst_tmp, stride2, q1, q2);
1530 __lsx_vstelm_w(vec2, dst + stride, 0, 1);
1535 __lsx_vstelm_w(vec3, dst + stride, 0, 1);
1570 dst += stride;
1573 dst += stride;
1576 dst += stride;
1579 dst += stride;
1582 dst += stride;
1585 dst += stride;
1588 dst += stride;
1594 void ff_loop_filter_h_88_16_lsx(uint8_t *dst, ptrdiff_t stride,
1599 ptrdiff_t stride2 = stride << 1;
1600 ptrdiff_t stride3 = stride2 + stride;
1617 DUP2_ARG2(__lsx_vldx, dst_tmp, stride, dst_tmp, stride2, p1, p2);
1621 DUP2_ARG2(__lsx_vldx, dst_tmp, stride, dst_tmp, stride2, row5, row6);
1625 DUP2_ARG2(__lsx_vldx, dst_tmp, stride, dst_tmp, stride2, q2, q1);
1629 DUP2_ARG2(__lsx_vldx, dst_tmp, stride, dst_tmp, stride2, row13, row14);
1669 __lsx_vstelm_w(vec2, dst + stride, 0, 1);
1674 __lsx_vstelm_w(vec3, dst + stride, 0, 1);
1679 __lsx_vstelm_w(vec4, dst + stride, 0, 1);
1684 __lsx_vstelm_w(vec5, dst + stride, 0, 1);
1731 dst += stride;
1734 dst += stride;
1737 dst += stride;
1740 dst += stride;
1743 dst += stride;
1746 dst += stride;
1749 dst += stride;
1752 dst += stride;
1755 dst += stride;
1758 dst += stride;
1761 dst += stride;
1764 dst += stride;
1767 dst += stride;
1770 dst += stride;
1773 dst += stride;
1779 void ff_loop_filter_h_84_16_lsx(uint8_t *dst, ptrdiff_t stride,
1784 ptrdiff_t stride2 = stride << 1;
1785 ptrdiff_t stride3 = stride2 + stride;
1799 DUP2_ARG2(__lsx_vldx, dst_tmp, stride, dst_tmp, stride2, p1, p2);
1803 DUP2_ARG2(__lsx_vldx, dst_tmp, stride, dst_tmp, stride2, row5, row6);
1807 DUP2_ARG2(__lsx_vldx, dst_tmp, stride, dst_tmp, stride2, q2, q1);
1811 DUP2_ARG2(__lsx_vldx, dst_tmp, stride, dst_tmp, stride2, row13, row14);
1853 __lsx_vstelm_w(vec2, dst + stride, 0, 1);
1858 __lsx_vstelm_w(vec3, dst + stride, 0, 1);
1863 __lsx_vstelm_w(vec4, dst + stride, 0, 1);
1868 __lsx_vstelm_w(vec5, dst + stride, 0, 1);
1906 dst += stride;
1909 dst += stride;
1912 dst += stride;
1915 dst += stride;
1918 dst += stride;
1921 dst += stride;
1924 dst += stride;
1927 dst += stride;
1930 dst += stride;
1933 dst += stride;
1936 dst += stride;
1939 dst += stride;
1942 dst += stride;
1945 dst += stride;
1948 dst += stride;
1954 void ff_loop_filter_h_48_16_lsx(uint8_t *dst, ptrdiff_t stride,
1959 ptrdiff_t stride2 = stride << 1;
1960 ptrdiff_t stride3 = stride2 + stride;
1974 DUP2_ARG2(__lsx_vldx, dst_tmp, stride, dst_tmp, stride2, p1, p2);
1978 DUP2_ARG2(__lsx_vldx, dst_tmp, stride, dst_tmp, stride2, row5, row6);
1982 DUP2_ARG2(__lsx_vldx, dst_tmp, stride, dst_tmp, stride2, q2, q1);
1986 DUP2_ARG2(__lsx_vldx, dst_tmp, stride, dst_tmp, stride2, row13, row14);
2028 __lsx_vstelm_w(vec2, dst + stride, 0, 1);
2033 __lsx_vstelm_w(vec3, dst + stride, 0, 1);
2038 __lsx_vstelm_w(vec4, dst + stride, 0, 1);
2043 __lsx_vstelm_w(vec5, dst + stride, 0, 1);
2082 dst += stride;
2085 dst += stride;
2088 dst += stride;
2091 dst += stride;
2094 dst += stride;
2097 dst += stride;
2100 dst += stride;
2103 dst += stride;
2106 dst += stride;
2109 dst += stride;
2112 dst += stride;
2115 dst += stride;
2118 dst += stride;
2121 dst += stride;
2124 dst += stride;
2357 ptrdiff_t stride,
2400 dst_org += stride;
2403 dst_org += stride;
2406 dst_org += stride;
2409 dst_org += stride;
2412 dst_org += stride;
2415 dst_org += stride;
2418 dst_org += stride;
2612 void ff_loop_filter_h_16_8_lsx(uint8_t *dst, ptrdiff_t stride,
2621 vp9_transpose_16x8_to_8x16(dst - 8, stride, transposed_input);
2624 &filter48[0], dst, stride,
2628 early_exit = vp9_vt_lpf_t16_8w((transposed_input + 16 * 8), dst, stride,
2632 vp9_transpose_8x16_to_16x8(transposed_input, dst - 8, stride);
2638 uint8_t *dst_org, ptrdiff_t stride,
2643 ptrdiff_t stride2 = stride << 1;
2644 ptrdiff_t stride3 = stride2 + stride;
2687 __lsx_vstelm_w(vec2, dst_org + stride, 0, 1);
2692 __lsx_vstelm_w(vec3, dst_org + stride, 0, 1);
2697 __lsx_vstelm_w(vec4, dst_org + stride, 0, 1);
2702 __lsx_vstelm_w(vec5, dst_org + stride, 0, 1);
2750 ptrdiff_t stride,
2799 dst_org += stride;
2802 dst_org += stride;
2805 dst_org += stride;
2808 dst_org += stride;
2811 dst_org += stride;
2814 dst_org += stride;
2817 dst_org += stride;
2820 dst_org += stride;
2823 dst_org += stride;
2826 dst_org += stride;
2829 dst_org += stride;
2832 dst_org += stride;
2835 dst_org += stride;
2838 dst_org += stride;
2841 dst_org += stride;
3118 void ff_loop_filter_h_16_16_lsx(uint8_t *dst, ptrdiff_t stride,
3127 vp9_transpose_16x16((dst - 8), stride, &transposed_input[0], 16);
3130 &filter48[0], dst, stride,
3135 stride, &filter48[0]);
3138 vp9_transpose_16x16(transposed_input, 16, (dst - 8), stride);