Lines Matching refs:pitch
196 void ff_loop_filter_v_4_8_msa(uint8_t *src, ptrdiff_t pitch,
206 LD_UB8((src - 4 * pitch), pitch, p3, p2, p1, p0, q0, q1, q2, q3);
221 SD4(p1_d, p0_d, q0_d, q1_d, (src - 2 * pitch), pitch);
225 void ff_loop_filter_v_44_16_msa(uint8_t *src, ptrdiff_t pitch,
234 LD_UB8((src - 4 * pitch), pitch, p3, p2, p1, p0, q0, q1, q2, q3);
252 ST_UB4(p1, p0, q0, q1, (src - 2 * pitch), pitch);
255 void ff_loop_filter_v_8_8_msa(uint8_t *src, ptrdiff_t pitch,
270 LD_UB8((src - 4 * pitch), pitch, p3, p2, p1, p0, q0, q1, q2, q3);
290 SD4(p1_d, p0_d, q0_d, q1_d, (src - 2 * pitch), pitch);
319 src -= 3 * pitch;
321 SD4(p2_d, p1_d, p0_d, q0_d, src, pitch);
322 src += (4 * pitch);
324 src += pitch;
329 void ff_loop_filter_v_88_16_msa(uint8_t *src, ptrdiff_t pitch,
346 LD_UB8(src - (4 * pitch), pitch, p3, p2, p1, p0, q0, q1, q2, q3);
369 ST_UB4(p1_out, p0_out, q0_out, q1_out, (src - 2 * pitch), pitch);
399 src -= 3 * pitch;
401 ST_UB4(p2_out, p1_out, p0_out, q0_out, src, pitch);
402 src += (4 * pitch);
403 ST_UB2(q1_out, q2_out, src, pitch);
404 src += (2 * pitch);
408 void ff_loop_filter_v_84_16_msa(uint8_t *src, ptrdiff_t pitch,
422 LD_UB8(src - (4 * pitch), pitch, p3, p2, p1, p0, q0, q1, q2, q3);
447 ST_UB4(p1_out, p0_out, q0_out, q1_out, (src - 2 * pitch), pitch);
470 src -= 3 * pitch;
472 ST_UB4(p2_out, p1_out, p0_out, q0_out, src, pitch);
473 src += (4 * pitch);
474 ST_UB2(q1_out, q2_out, src, pitch);
475 src += (2 * pitch);
479 void ff_loop_filter_v_48_16_msa(uint8_t *src, ptrdiff_t pitch,
493 LD_UB8(src - (4 * pitch), pitch, p3, p2, p1, p0, q0, q1, q2, q3);
518 ST_UB4(p1_out, p0_out, q0_out, q1_out, (src - 2 * pitch), pitch);
542 src -= 3 * pitch;
544 ST_UB4(p2_out, p1_out, p0_out, q0_out, src, pitch);
545 src += (4 * pitch);
546 ST_UB2(q1_out, q2_out, src, pitch);
547 src += (2 * pitch);
551 static int32_t vp9_hz_lpf_t4_and_t8_16w(uint8_t *src, ptrdiff_t pitch,
569 LD_UB8(src - (4 * pitch), pitch, p3, p2, p1, p0, q0, q1, q2, q3);
584 ST_UB4(p1_out, p0_out, q0_out, q1_out, (src - 2 * pitch), pitch);
626 static void vp9_hz_lpf_t16_16w(uint8_t *src, ptrdiff_t pitch, uint8_t *filter48)
644 LD_UB8((src - 8 * pitch), pitch, p7, p6, p5, p4, p3, p2, p1, p0);
645 LD_UB8(src, pitch, q0, q1, q2, q3, q4, q5, q6, q7);
653 src -= 3 * pitch;
654 ST_UB4(p2, p1, p0, q0, src, pitch);
655 src += (4 * pitch);
656 ST_UB2(q1, q2, src, pitch);
658 src -= 7 * pitch;
701 src += pitch;
721 src += pitch;
741 src += pitch;
761 src += pitch;
782 src += pitch;
803 src += pitch;
824 src += pitch;
845 src += pitch;
864 src += pitch;
883 src += pitch;
901 src += pitch;
919 src += pitch;
937 src += pitch;
958 void ff_loop_filter_v_16_16_msa(uint8_t *src, ptrdiff_t pitch,
966 early_exit = vp9_hz_lpf_t4_and_t8_16w(src, pitch, &filter48[0],
970 vp9_hz_lpf_t16_16w(src, pitch, filter48);
974 void ff_loop_filter_v_16_8_msa(uint8_t *src, ptrdiff_t pitch,
993 LD_UB8((src - 4 * pitch), pitch, p3, p2, p1, p0, q0, q1, q2, q3);
1013 SD4(p1_d, p0_d, q0_d, q1_d, src - 2 * pitch, pitch);
1039 LD_UB4((src - 8 * pitch), pitch, p7, p6, p5, p4);
1040 LD_UB4(src + (4 * pitch), pitch, q4, q5, q6, q7);
1053 SD4(p2_d, p1_d, p0_d, q0_d, src - 3 * pitch, pitch);
1054 SD(q1_d, src + pitch);
1055 SD(q2_d, src + 2 * pitch);
1067 src -= 7 * pitch;
1084 src += pitch;
1086 src += pitch;
1102 src += pitch;
1104 src += pitch;
1120 src += pitch;
1122 src += pitch;
1138 src += pitch;
1140 src += pitch;
1156 src += pitch;
1158 src += pitch;
1174 src += pitch;
1176 src += pitch;
1192 src += pitch;
1198 void ff_loop_filter_h_4_8_msa(uint8_t *src, ptrdiff_t pitch,
1207 LD_UB8((src - 4), pitch, p3, p2, p1, p0, q0, q1, q2, q3);
1222 ST_W8(vec2, vec3, 0, 1, 2, 3, 0, 1, 2, 3, src, pitch);
1225 void ff_loop_filter_h_44_16_msa(uint8_t *src, ptrdiff_t pitch,
1237 LD_UB8(src - 4, pitch, row0, row1, row2, row3, row4, row5, row6, row7);
1238 LD_UB8(src - 4 + (8 * pitch), pitch,
1267 ST_W8(tmp2, tmp3, 0, 1, 2, 3, 0, 1, 2, 3, src, pitch);
1268 ST_W8(tmp4, tmp5, 0, 1, 2, 3, 0, 1, 2, 3, src + 8 * pitch, pitch);
1271 void ff_loop_filter_h_8_8_msa(uint8_t *src, ptrdiff_t pitch,
1286 LD_UB8(src - 4, pitch, p3, p2, p1, p0, q0, q1, q2, q3);
1313 ST_W8(vec2, vec3, 0, 1, 2, 3, 0, 1, 2, 3, src, pitch);
1341 ST_W4(vec2, 0, 1, 2, 3, src, pitch);
1342 ST_H4(vec4, 0, 1, 2, 3, src + 4, pitch);
1343 src += (4 * pitch);
1344 ST_W4(vec3, 0, 1, 2, 3, src, pitch);
1345 ST_H4(vec4, 4, 5, 6, 7, src + 4, pitch);
1349 void ff_loop_filter_h_88_16_msa(uint8_t *src, ptrdiff_t pitch,
1370 LD_UB8(temp_src, pitch, p0, p1, p2, p3, row4, row5, row6, row7);
1371 temp_src += (8 * pitch);
1372 LD_UB8(temp_src, pitch, q3, q2, q1, q0, row12, row13, row14, row15);
1408 ST_W8(vec2, vec3, 0, 1, 2, 3, 0, 1, 2, 3, src, pitch);
1409 ST_W8(vec4, vec5, 0, 1, 2, 3, 0, 1, 2, 3, src + 8 * pitch, pitch);
1448 ST_W4(vec3, 0, 1, 2, 3, src, pitch);
1449 ST_H4(vec2, 0, 1, 2, 3, src + 4, pitch);
1450 src += (4 * pitch);
1451 ST_W4(vec4, 0, 1, 2, 3, src, pitch);
1452 ST_H4(vec2, 4, 5, 6, 7, src + 4, pitch);
1453 src += (4 * pitch);
1454 ST_W4(vec6, 0, 1, 2, 3, src, pitch);
1455 ST_H4(vec5, 0, 1, 2, 3, src + 4, pitch);
1456 src += (4 * pitch);
1457 ST_W4(vec7, 0, 1, 2, 3, src, pitch);
1458 ST_H4(vec5, 4, 5, 6, 7, src + 4, pitch);
1462 void ff_loop_filter_h_84_16_msa(uint8_t *src, ptrdiff_t pitch,
1480 LD_UB8(temp_src, pitch, p0, p1, p2, p3, row4, row5, row6, row7);
1481 temp_src += (8 * pitch);
1482 LD_UB8(temp_src, pitch, q3, q2, q1, q0, row12, row13, row14, row15);
1520 ST_W8(vec2, vec3, 0, 1, 2, 3, 0, 1, 2, 3, src, pitch);
1521 ST_W8(vec4, vec5, 0, 1, 2, 3, 0, 1, 2, 3, src + 8 * pitch, pitch);
1551 ST_W4(vec3, 0, 1, 2, 3, src, pitch);
1552 ST_H4(vec2, 0, 1, 2, 3, src + 4, pitch);
1553 src += (4 * pitch);
1554 ST_W4(vec4, 0, 1, 2, 3, src, pitch);
1555 ST_H4(vec2, 4, 5, 6, 7, src + 4, pitch);
1556 src += (4 * pitch);
1557 ST_W4(vec6, 0, 1, 2, 3, src, pitch);
1558 ST_H4(vec5, 0, 1, 2, 3, src + 4, pitch);
1559 src += (4 * pitch);
1560 ST_W4(vec7, 0, 1, 2, 3, src, pitch);
1561 ST_H4(vec5, 4, 5, 6, 7, src + 4, pitch);
1565 void ff_loop_filter_h_48_16_msa(uint8_t *src, ptrdiff_t pitch,
1583 LD_UB8(temp_src, pitch, p0, p1, p2, p3, row4, row5, row6, row7);
1584 temp_src += (8 * pitch);
1585 LD_UB8(temp_src, pitch, q3, q2, q1, q0, row12, row13, row14, row15);
1623 ST_W8(vec2, vec3, 0, 1, 2, 3, 0, 1, 2, 3, src, pitch);
1624 ST_W8(vec4, vec5, 0, 1, 2, 3, 0, 1, 2, 3, src + 8 * pitch, pitch);
1656 ST_W4(vec3, 0, 1, 2, 3, src, pitch);
1657 ST_H4(vec2, 0, 1, 2, 3, src + 4, pitch);
1658 src += (4 * pitch);
1659 ST_W4(vec4, 0, 1, 2, 3, src, pitch);
1660 ST_H4(vec2, 4, 5, 6, 7, src + 4, pitch);
1661 src += (4 * pitch);
1662 ST_W4(vec6, 0, 1, 2, 3, src, pitch);
1663 ST_H4(vec5, 0, 1, 2, 3, src + 4, pitch);
1664 src += (4 * pitch);
1665 ST_W4(vec7, 0, 1, 2, 3, src, pitch);
1666 ST_H4(vec5, 4, 5, 6, 7, src + 4, pitch);
1842 static int32_t vp9_vt_lpf_t16_8w(uint8_t *src, uint8_t *src_org, ptrdiff_t pitch,
1874 ST_W4(vec3, 0, 1, 2, 3, src_org, pitch);
1875 ST_H4(vec2, 0, 1, 2, 3, (src_org + 4), pitch);
1876 src_org += (4 * pitch);
1877 ST_W4(vec4, 0, 1, 2, 3, src_org, pitch);
1878 ST_H4(vec2, 4, 5, 6, 7, (src_org + 4), pitch);
2066 void ff_loop_filter_h_16_8_msa(uint8_t *src, ptrdiff_t pitch,
2075 vp9_transpose_16x8_to_8x16(src - 8, pitch, transposed_input, 16);
2078 &filter48[0], src, pitch,
2082 early_exit = vp9_vt_lpf_t16_8w((transposed_input + 16 * 8), src, pitch,
2086 vp9_transpose_8x16_to_16x8(transposed_input, 16, src - 8, pitch);
2092 uint8_t *src_org, ptrdiff_t pitch,
2133 ST_W8(vec2, vec3, 0, 1, 2, 3, 0, 1, 2, 3, src_org, pitch);
2134 ST_W8(vec4, vec5, 0, 1, 2, 3, 0, 1, 2, 3, src_org + 8 * pitch, pitch);
2175 static int32_t vp9_vt_lpf_t16_16w(uint8_t *src, uint8_t *src_org, ptrdiff_t pitch,
2213 ST_W4(vec3, 0, 1, 2, 3, src_org, pitch);
2214 ST_H4(vec2, 0, 1, 2, 3, (src_org + 4), pitch);
2215 src_org += (4 * pitch);
2216 ST_W4(vec4, 0, 1, 2, 3, src_org, pitch);
2217 ST_H4(vec2, 4, 5, 6, 7, (src_org + 4), pitch);
2218 src_org += (4 * pitch);
2219 ST_W4(vec6, 0, 1, 2, 3, src_org, pitch);
2220 ST_H4(vec5, 0, 1, 2, 3, (src_org + 4), pitch);
2221 src_org += (4 * pitch);
2222 ST_W4(vec7, 0, 1, 2, 3, src_org, pitch);
2223 ST_H4(vec5, 4, 5, 6, 7, (src_org + 4), pitch);
2502 void ff_loop_filter_h_16_16_msa(uint8_t *src, ptrdiff_t pitch,
2511 vp9_transpose_16x16((src - 8), pitch, &transposed_input[0], 16);
2514 &filter48[0], src, pitch,
2518 early_exit = vp9_vt_lpf_t16_16w((transposed_input + 16 * 8), src, pitch,
2522 vp9_transpose_16x16(transposed_input, 16, (src - 8), pitch);