Lines Matching refs:dst
67 uint8_t *dst, ptrdiff_t stride)
165 out0 = __lasx_xvld(dst, 0);
166 DUP2_ARG2(__lasx_xvldx, dst, stride, dst, stride_2x, out1, out2);
167 out3 = __lasx_xvldx(dst, stride_3x);
177 __lasx_xvstelm_d(tmp0, dst, 0, 0);
178 __lasx_xvstelm_d(tmp0, dst + stride, 0, 1);
179 __lasx_xvstelm_d(tmp1, dst + stride_2x, 0, 0);
180 __lasx_xvstelm_d(tmp1, dst + stride_3x, 0, 1);
182 __lasx_xvstelm_d(tmp0, dst, 8, 2);
183 __lasx_xvstelm_d(tmp0, dst + stride, 8, 3);
184 __lasx_xvstelm_d(tmp1, dst + stride_2x, 8, 2);
185 __lasx_xvstelm_d(tmp1, dst + stride_3x, 8, 3);
187 dst += stride_4x;
198 uint8_t *dst, ptrdiff_t stride)
296 __lasx_xvstelm_d(tmp0, dst, 0, 0);
297 __lasx_xvstelm_d(tmp0, dst + stride, 0, 1);
298 __lasx_xvstelm_d(tmp1, dst + stride_2x, 0, 0);
299 __lasx_xvstelm_d(tmp1, dst + stride_3x, 0, 1);
301 __lasx_xvstelm_d(tmp0, dst, 8, 2);
302 __lasx_xvstelm_d(tmp0, dst + stride, 8, 3);
303 __lasx_xvstelm_d(tmp1, dst + stride_2x, 8, 2);
304 __lasx_xvstelm_d(tmp1, dst + stride_3x, 8, 3);
306 dst += stride_4x;
315 /* put_pixels8_8_inline_asm: dst = src */
317 put_pixels8_8_inline_asm(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)
335 "st.d %[tmp0], %[dst], 0x0 \n\t"
336 "stx.d %[tmp1], %[dst], %[stride] \n\t"
337 "stx.d %[tmp2], %[dst], %[stride_2] \n\t"
338 "stx.d %[tmp3], %[dst], %[stride_3] \n\t"
339 "add.d %[dst], %[dst], %[stride_4] \n\t"
340 "st.d %[tmp4], %[dst], 0x0 \n\t"
341 "stx.d %[tmp5], %[dst], %[stride] \n\t"
342 "stx.d %[tmp6], %[dst], %[stride_2] \n\t"
343 "stx.d %[tmp7], %[dst], %[stride_3] \n\t"
350 [dst]"+&r"(dst), [src]"+&r"(src)
356 /* avg_pixels8_8_lsx : dst = avg(src, dst)
357 * put_pixels8_l2_8_lsx: dst = avg(src, half) , half stride is 8.
358 * avg_pixels8_l2_8_lsx: dst = avg(avg(src, half), dst) , half stride is 8.*/
360 avg_pixels8_8_lsx(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)
362 uint8_t *tmp = dst;
398 "vstelm.d $vr0, %[dst], 0, 0 \n\t"
399 "add.d %[dst], %[dst], %[stride] \n\t"
400 "vstelm.d $vr1, %[dst], 0, 0 \n\t"
401 "add.d %[dst], %[dst], %[stride] \n\t"
402 "vstelm.d $vr2, %[dst], 0, 0 \n\t"
403 "add.d %[dst], %[dst], %[stride] \n\t"
404 "vstelm.d $vr3, %[dst], 0, 0 \n\t"
405 "add.d %[dst], %[dst], %[stride] \n\t"
406 "vstelm.d $vr4, %[dst], 0, 0 \n\t"
407 "add.d %[dst], %[dst], %[stride] \n\t"
408 "vstelm.d $vr5, %[dst], 0, 0 \n\t"
409 "add.d %[dst], %[dst], %[stride] \n\t"
410 "vstelm.d $vr6, %[dst], 0, 0 \n\t"
411 "add.d %[dst], %[dst], %[stride] \n\t"
412 "vstelm.d $vr7, %[dst], 0, 0 \n\t"
413 : [dst]"+&r"(dst), [tmp]"+&r"(tmp), [src]"+&r"(src),
421 /* avg_pixels8_8_lsx : dst = avg(src, dst)
422 * put_pixels8_l2_8_lsx: dst = avg(src, half) , half stride is 8.
423 * avg_pixels8_l2_8_lsx: dst = avg(avg(src, half), dst) , half stride is 8.*/
425 put_pixels8_l2_8_lsx(uint8_t *dst, const uint8_t *src, const uint8_t *half,
462 "vstelm.d $vr0, %[dst], 0, 0 \n\t"
463 "add.d %[dst], %[dst], %[dstStride] \n\t"
464 "vstelm.d $vr1, %[dst], 0, 0 \n\t"
465 "add.d %[dst], %[dst], %[dstStride] \n\t"
466 "vstelm.d $vr2, %[dst], 0, 0 \n\t"
467 "add.d %[dst], %[dst], %[dstStride] \n\t"
468 "vstelm.d $vr3, %[dst], 0, 0 \n\t"
469 "add.d %[dst], %[dst], %[dstStride] \n\t"
470 "vstelm.d $vr4, %[dst], 0, 0 \n\t"
471 "add.d %[dst], %[dst], %[dstStride] \n\t"
472 "vstelm.d $vr5, %[dst], 0, 0 \n\t"
473 "add.d %[dst], %[dst], %[dstStride] \n\t"
474 "vstelm.d $vr6, %[dst], 0, 0 \n\t"
475 "add.d %[dst], %[dst], %[dstStride] \n\t"
476 "vstelm.d $vr7, %[dst], 0, 0 \n\t"
477 : [dst]"+&r"(dst), [half]"+&r"(half), [src]"+&r"(src),
485 /* avg_pixels8_8_lsx : dst = avg(src, dst)
486 * put_pixels8_l2_8_lsx: dst = avg(src, half) , half stride is 8.
487 * avg_pixels8_l2_8_lsx: dst = avg(avg(src, half), dst) , half stride is 8.*/
489 avg_pixels8_l2_8_lsx(uint8_t *dst, const uint8_t *src, const uint8_t *half,
492 uint8_t *tmp = dst;
549 "vstelm.d $vr0, %[dst], 0, 0 \n\t"
550 "add.d %[dst], %[dst], %[dstStride] \n\t"
551 "vstelm.d $vr1, %[dst], 0, 0 \n\t"
552 "add.d %[dst], %[dst], %[dstStride] \n\t"
553 "vstelm.d $vr2, %[dst], 0, 0 \n\t"
554 "add.d %[dst], %[dst], %[dstStride] \n\t"
555 "vstelm.d $vr3, %[dst], 0, 0 \n\t"
556 "add.d %[dst], %[dst], %[dstStride] \n\t"
557 "vstelm.d $vr4, %[dst], 0, 0 \n\t"
558 "add.d %[dst], %[dst], %[dstStride] \n\t"
559 "vstelm.d $vr5, %[dst], 0, 0 \n\t"
560 "add.d %[dst], %[dst], %[dstStride] \n\t"
561 "vstelm.d $vr6, %[dst], 0, 0 \n\t"
562 "add.d %[dst], %[dst], %[dstStride] \n\t"
563 "vstelm.d $vr7, %[dst], 0, 0 \n\t"
564 : [dst]"+&r"(dst), [tmp]"+&r"(tmp), [half]"+&r"(half),
572 /* put_pixels16_8_lsx: dst = src */
574 put_pixels16_8_lsx(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)
592 "vst $vr0, %[dst], 0 \n\t"
593 "vstx $vr1, %[dst], %[stride] \n\t"
594 "vstx $vr2, %[dst], %[stride_2] \n\t"
595 "vstx $vr3, %[dst], %[stride_3] \n\t"
596 "add.d %[dst], %[dst], %[stride_4] \n\t"
597 "vst $vr4, %[dst], 0 \n\t"
598 "vstx $vr5, %[dst], %[stride] \n\t"
599 "vstx $vr6, %[dst], %[stride_2] \n\t"
600 "vstx $vr7, %[dst], %[stride_3] \n\t"
601 "add.d %[dst], %[dst], %[stride_4] \n\t"
613 "vst $vr0, %[dst], 0 \n\t"
614 "vstx $vr1, %[dst], %[stride] \n\t"
615 "vstx $vr2, %[dst], %[stride_2] \n\t"
616 "vstx $vr3, %[dst], %[stride_3] \n\t"
617 "add.d %[dst], %[dst], %[stride_4] \n\t"
618 "vst $vr4, %[dst], 0 \n\t"
619 "vstx $vr5, %[dst], %[stride] \n\t"
620 "vstx $vr6, %[dst], %[stride_2] \n\t"
621 "vstx $vr7, %[dst], %[stride_3] \n\t"
622 : [dst]"+&r"(dst), [src]"+&r"(src),
630 /* avg_pixels16_8_lsx : dst = avg(src, dst)
631 * put_pixels16_l2_8_lsx: dst = avg(src, half) , half stride is 8.
632 * avg_pixels16_l2_8_lsx: dst = avg(avg(src, half), dst) , half stride is 8.*/
634 avg_pixels16_8_lsx(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)
636 uint8_t *tmp = dst;
674 "vst $vr0, %[dst], 0 \n\t"
675 "vstx $vr1, %[dst], %[stride] \n\t"
676 "vstx $vr2, %[dst], %[stride_2] \n\t"
677 "vstx $vr3, %[dst], %[stride_3] \n\t"
678 "add.d %[dst], %[dst], %[stride_4] \n\t"
679 "vst $vr4, %[dst], 0 \n\t"
680 "vstx $vr5, %[dst], %[stride] \n\t"
681 "vstx $vr6, %[dst], %[stride_2] \n\t"
682 "vstx $vr7, %[dst], %[stride_3] \n\t"
683 "add.d %[dst], %[dst], %[stride_4] \n\t"
715 "vst $vr0, %[dst], 0 \n\t"
716 "vstx $vr1, %[dst], %[stride] \n\t"
717 "vstx $vr2, %[dst], %[stride_2] \n\t"
718 "vstx $vr3, %[dst], %[stride_3] \n\t"
719 "add.d %[dst], %[dst], %[stride_4] \n\t"
720 "vst $vr4, %[dst], 0 \n\t"
721 "vstx $vr5, %[dst], %[stride] \n\t"
722 "vstx $vr6, %[dst], %[stride_2] \n\t"
723 "vstx $vr7, %[dst], %[stride_3] \n\t"
724 : [dst]"+&r"(dst), [tmp]"+&r"(tmp), [src]"+&r"(src),
732 /* avg_pixels16_8_lsx : dst = avg(src, dst)
733 * put_pixels16_l2_8_lsx: dst = avg(src, half) , half stride is 8.
734 * avg_pixels16_l2_8_lsx: dst = avg(avg(src, half), dst) , half stride is 8.*/
736 put_pixels16_l2_8_lsx(uint8_t *dst, const uint8_t *src, uint8_t *half,
778 "vst $vr0, %[dst], 0 \n\t"
779 "vstx $vr1, %[dst], %[dstStride] \n\t"
780 "vstx $vr2, %[dst], %[dstride_2] \n\t"
781 "vstx $vr3, %[dst], %[dstride_3] \n\t"
782 "add.d %[dst], %[dst], %[dstride_4] \n\t"
783 "vst $vr4, %[dst], 0 \n\t"
784 "vstx $vr5, %[dst], %[dstStride] \n\t"
785 "vstx $vr6, %[dst], %[dstride_2] \n\t"
786 "vstx $vr7, %[dst], %[dstride_3] \n\t"
787 "add.d %[dst], %[dst], %[dstride_4] \n\t"
818 "vst $vr0, %[dst], 0 \n\t"
819 "vstx $vr1, %[dst], %[dstStride] \n\t"
820 "vstx $vr2, %[dst], %[dstride_2] \n\t"
821 "vstx $vr3, %[dst], %[dstride_3] \n\t"
822 "add.d %[dst], %[dst], %[dstride_4] \n\t"
823 "vst $vr4, %[dst], 0 \n\t"
824 "vstx $vr5, %[dst], %[dstStride] \n\t"
825 "vstx $vr6, %[dst], %[dstride_2] \n\t"
826 "vstx $vr7, %[dst], %[dstride_3] \n\t"
827 : [dst]"+&r"(dst), [half]"+&r"(half), [src]"+&r"(src),
836 /* avg_pixels16_8_lsx : dst = avg(src, dst)
837 * put_pixels16_l2_8_lsx: dst = avg(src, half) , half stride is 8.
838 * avg_pixels16_l2_8_lsx: dst = avg(avg(src, half), dst) , half stride is 8.*/
840 avg_pixels16_l2_8_lsx(uint8_t *dst, const uint8_t *src, uint8_t *half,
843 uint8_t *tmp = dst;
903 "vst $vr0, %[dst], 0 \n\t"
904 "vstx $vr1, %[dst], %[dstStride] \n\t"
905 "vstx $vr2, %[dst], %[dstride_2] \n\t"
906 "vstx $vr3, %[dst], %[dstride_3] \n\t"
907 "add.d %[dst], %[dst], %[dstride_4] \n\t"
908 "vst $vr4, %[dst], 0 \n\t"
909 "vstx $vr5, %[dst], %[dstStride] \n\t"
910 "vstx $vr6, %[dst], %[dstride_2] \n\t"
911 "vstx $vr7, %[dst], %[dstride_3] \n\t"
912 "add.d %[dst], %[dst], %[dstride_4] \n\t"
962 "vst $vr0, %[dst], 0 \n\t"
963 "vstx $vr1, %[dst], %[dstStride] \n\t"
964 "vstx $vr2, %[dst], %[dstride_2] \n\t"
965 "vstx $vr3, %[dst], %[dstride_3] \n\t"
966 "add.d %[dst], %[dst], %[dstride_4] \n\t"
967 "vst $vr4, %[dst], 0 \n\t"
968 "vstx $vr5, %[dst], %[dstStride] \n\t"
969 "vstx $vr6, %[dst], %[dstride_2] \n\t"
970 "vstx $vr7, %[dst], %[dstride_3] \n\t"
971 : [dst]"+&r"(dst), [tmp]"+&r"(tmp), [half]"+&r"(half), [src]"+&r"(src),
1001 put_h264_qpel8_h_lowpass_lasx(uint8_t *dst, const uint8_t *src, int dstStride,
1020 __lasx_xvstelm_d(out0, dst, 0, 0);
1021 __lasx_xvstelm_d(out0, dst + dstStride, 0, 2);
1022 dst += dstStride_2x;
1023 __lasx_xvstelm_d(out1, dst, 0, 0);
1024 __lasx_xvstelm_d(out1, dst + dstStride, 0, 2);
1025 dst += dstStride_2x;
1026 __lasx_xvstelm_d(out2, dst, 0, 0);
1027 __lasx_xvstelm_d(out2, dst + dstStride, 0, 2);
1028 dst += dstStride_2x;
1029 __lasx_xvstelm_d(out3, dst, 0, 0);
1030 __lasx_xvstelm_d(out3, dst + dstStride, 0, 2);
1053 put_h264_qpel8_v_lowpass_lasx(uint8_t *dst, uint8_t *src, int dstStride,
1080 __lasx_xvstelm_d(tmp02, dst, 0, 0);
1081 __lasx_xvstelm_d(tmp02, dst + dstStride, 0, 2);
1082 dst += dstStride_2x;
1085 __lasx_xvstelm_d(tmp02, dst, 0, 0);
1086 __lasx_xvstelm_d(tmp02, dst + dstStride, 0, 2);
1087 dst += dstStride_2x;
1090 __lasx_xvstelm_d(tmp02, dst, 0, 0);
1091 __lasx_xvstelm_d(tmp02, dst + dstStride, 0, 2);
1092 dst += dstStride_2x;
1095 __lasx_xvstelm_d(tmp02, dst, 0, 0);
1096 __lasx_xvstelm_d(tmp02, dst + dstStride, 0, 2);
1100 avg_h264_qpel8_v_lowpass_lasx(uint8_t *dst, uint8_t *src, int dstStride,
1128 tmp06 = __lasx_xvld(dst, 0);
1129 DUP4_ARG2(__lasx_xvldx, dst, dstStride, dst, dstStride_2x,
1130 dst, dstStride_3x, dst, dstStride_4x,
1132 dst += dstStride_4x;
1133 DUP2_ARG2(__lasx_xvldx, dst, dstStride, dst, dstStride_2x,
1135 tmp01 = __lasx_xvldx(dst, dstStride_3x);
1136 dst -= dstStride_4x;
1146 __lasx_xvstelm_d(tmp06, dst, 0, 0);
1147 __lasx_xvstelm_d(tmp06, dst + dstStride, 0, 2);
1148 dst += dstStride_2x;
1152 __lasx_xvstelm_d(tmp07, dst, 0, 0);
1153 __lasx_xvstelm_d(tmp07, dst + dstStride, 0, 2);
1154 dst += dstStride_2x;
1158 __lasx_xvstelm_d(tmp08, dst, 0, 0);
1159 __lasx_xvstelm_d(tmp08, dst + dstStride, 0, 2);
1160 dst += dstStride_2x;
1164 __lasx_xvstelm_d(tmp09, dst, 0, 0);
1165 __lasx_xvstelm_d(tmp09, dst + dstStride, 0, 2);
1214 put_h264_qpel8_hv_lowpass_lasx(uint8_t *dst, const uint8_t *src,
1256 __lasx_xvstelm_d(tmp0, dst, 0, 0);
1257 dst += dstStride;
1258 __lasx_xvstelm_d(tmp0, dst, 0, 2);
1259 dst += dstStride;
1260 __lasx_xvstelm_d(tmp2, dst, 0, 0);
1261 dst += dstStride;
1262 __lasx_xvstelm_d(tmp2, dst, 0, 2);
1263 dst += dstStride;
1264 __lasx_xvstelm_d(tmp4, dst, 0, 0);
1265 dst += dstStride;
1266 __lasx_xvstelm_d(tmp4, dst, 0, 2);
1267 dst += dstStride;
1268 __lasx_xvstelm_d(tmp6, dst, 0, 0);
1269 dst += dstStride;
1270 __lasx_xvstelm_d(tmp6, dst, 0, 2);
1274 avg_h264_qpel8_h_lowpass_lasx(uint8_t *dst, const uint8_t *src, int dstStride,
1296 src00 = __lasx_xvld(dst, 0);
1297 DUP4_ARG2(__lasx_xvldx, dst, dstStride, dst, dstStride_2x, dst,
1298 dstStride_3x, dst, dstStride_4x, src01, src02, src03, src04);
1299 dst += dstStride_4x;
1300 DUP2_ARG2(__lasx_xvldx, dst, dstStride, dst, dstStride_2x, src05, dst00);
1301 dst01 = __lasx_xvldx(dst, dstStride_3x);
1302 dst -= dstStride_4x;
1311 __lasx_xvstelm_d(dst0, dst, 0, 0);
1312 __lasx_xvstelm_d(dst0, dst + dstStride, 0, 2);
1313 __lasx_xvstelm_d(dst1, dst + dstStride_2x, 0, 0);
1314 __lasx_xvstelm_d(dst1, dst + dstStride_3x, 0, 2);
1315 dst += dstStride_4x;
1316 __lasx_xvstelm_d(dst2, dst, 0, 0);
1317 __lasx_xvstelm_d(dst2, dst + dstStride, 0, 2);
1318 __lasx_xvstelm_d(dst3, dst + dstStride_2x, 0, 0);
1319 __lasx_xvstelm_d(dst3, dst + dstStride_3x, 0, 2);
1323 avg_h264_qpel8_hv_lowpass_lasx(uint8_t *dst, const uint8_t *src,
1369 src00 = __lasx_xvld(dst, 0);
1370 DUP4_ARG2(__lasx_xvldx, dst, dstStride, dst, dstStride_2x, dst,
1371 dstStride_3x, dst, dstStride_4x, src01, src02, src03, src04);
1372 dst += dstStride_4x;
1373 DUP2_ARG2(__lasx_xvldx, dst, dstStride, dst, dstStride_2x, src05, tmp8);
1374 tmp9 = __lasx_xvldx(dst, dstStride_3x);
1375 dst -= dstStride_4x;
1384 __lasx_xvstelm_d(tmp0, dst, 0, 0);
1385 dst += dstStride;
1386 __lasx_xvstelm_d(tmp0, dst, 0, 2);
1387 dst += dstStride;
1388 __lasx_xvstelm_d(tmp2, dst, 0, 0);
1389 dst += dstStride;
1390 __lasx_xvstelm_d(tmp2, dst, 0, 2);
1391 dst += dstStride;
1392 __lasx_xvstelm_d(tmp4, dst, 0, 0);
1393 dst += dstStride;
1394 __lasx_xvstelm_d(tmp4, dst, 0, 2);
1395 dst += dstStride;
1396 __lasx_xvstelm_d(tmp6, dst, 0, 0);
1397 dst += dstStride;
1398 __lasx_xvstelm_d(tmp6, dst, 0, 2);
1402 put_h264_qpel16_h_lowpass_lasx(uint8_t *dst, const uint8_t *src,
1405 put_h264_qpel8_h_lowpass_lasx(dst, src, dstStride, srcStride);
1406 put_h264_qpel8_h_lowpass_lasx(dst+8, src+8, dstStride, srcStride);
1408 dst += dstStride << 3;
1409 put_h264_qpel8_h_lowpass_lasx(dst, src, dstStride, srcStride);
1410 put_h264_qpel8_h_lowpass_lasx(dst+8, src+8, dstStride, srcStride);
1414 avg_h264_qpel16_h_lowpass_lasx(uint8_t *dst, const uint8_t *src,
1417 avg_h264_qpel8_h_lowpass_lasx(dst, src, dstStride, srcStride);
1418 avg_h264_qpel8_h_lowpass_lasx(dst+8, src+8, dstStride, srcStride);
1420 dst += dstStride << 3;
1421 avg_h264_qpel8_h_lowpass_lasx(dst, src, dstStride, srcStride);
1422 avg_h264_qpel8_h_lowpass_lasx(dst+8, src+8, dstStride, srcStride);
1425 static void put_h264_qpel16_v_lowpass_lasx(uint8_t *dst, const uint8_t *src,
1428 put_h264_qpel8_v_lowpass_lasx(dst, (uint8_t*)src, dstStride, srcStride);
1429 put_h264_qpel8_v_lowpass_lasx(dst+8, (uint8_t*)src+8, dstStride, srcStride);
1431 dst += 8*dstStride;
1432 put_h264_qpel8_v_lowpass_lasx(dst, (uint8_t*)src, dstStride, srcStride);
1433 put_h264_qpel8_v_lowpass_lasx(dst+8, (uint8_t*)src+8, dstStride, srcStride);
1436 static void avg_h264_qpel16_v_lowpass_lasx(uint8_t *dst, const uint8_t *src,
1439 avg_h264_qpel8_v_lowpass_lasx(dst, (uint8_t*)src, dstStride, srcStride);
1440 avg_h264_qpel8_v_lowpass_lasx(dst+8, (uint8_t*)src+8, dstStride, srcStride);
1442 dst += 8*dstStride;
1443 avg_h264_qpel8_v_lowpass_lasx(dst, (uint8_t*)src, dstStride, srcStride);
1444 avg_h264_qpel8_v_lowpass_lasx(dst+8, (uint8_t*)src+8, dstStride, srcStride);
1447 static void put_h264_qpel16_hv_lowpass_lasx(uint8_t *dst, const uint8_t *src,
1450 put_h264_qpel8_hv_lowpass_lasx(dst, src, dstStride, srcStride);
1451 put_h264_qpel8_hv_lowpass_lasx(dst + 8, src + 8, dstStride, srcStride);
1453 dst += dstStride << 3;
1454 put_h264_qpel8_hv_lowpass_lasx(dst, src, dstStride, srcStride);
1455 put_h264_qpel8_hv_lowpass_lasx(dst + 8, src + 8, dstStride, srcStride);
1458 static void avg_h264_qpel16_hv_lowpass_lasx(uint8_t *dst, const uint8_t *src,
1461 avg_h264_qpel8_hv_lowpass_lasx(dst, src, dstStride, srcStride);
1462 avg_h264_qpel8_hv_lowpass_lasx(dst + 8, src + 8, dstStride, srcStride);
1464 dst += dstStride << 3;
1465 avg_h264_qpel8_hv_lowpass_lasx(dst, src, dstStride, srcStride);
1466 avg_h264_qpel8_hv_lowpass_lasx(dst + 8, src + 8, dstStride, srcStride);
1469 void ff_put_h264_qpel8_mc00_lasx(uint8_t *dst, const uint8_t *src,
1474 put_pixels8_8_inline_asm(dst, src, stride);
1477 void ff_put_h264_qpel8_mc10_lasx(uint8_t *dst, const uint8_t *src,
1484 put_pixels8_l2_8_lsx(dst, src, half, stride, stride);
1487 void ff_put_h264_qpel8_mc20_lasx(uint8_t *dst, const uint8_t *src,
1490 put_h264_qpel8_h_lowpass_lasx(dst, src, stride, stride);
1493 void ff_put_h264_qpel8_mc30_lasx(uint8_t *dst, const uint8_t *src,
1499 put_pixels8_l2_8_lsx(dst, src+1, half, stride, stride);
1502 void ff_put_h264_qpel8_mc01_lasx(uint8_t *dst, const uint8_t *src,
1508 put_pixels8_l2_8_lsx(dst, src, half, stride, stride);
1511 void ff_put_h264_qpel8_mc11_lasx(uint8_t *dst, const uint8_t *src,
1519 put_pixels8_l2_8_lsx(dst, halfH, halfV, stride, 8);
1522 void ff_put_h264_qpel8_mc21_lasx(uint8_t *dst, const uint8_t *src,
1531 put_pixels8_l2_8_lsx(dst, halfH, halfHV, stride, 8);
1534 void ff_put_h264_qpel8_mc31_lasx(uint8_t *dst, const uint8_t *src,
1542 put_pixels8_l2_8_lsx(dst, halfH, halfV, stride, 8);
1545 void ff_put_h264_qpel8_mc02_lasx(uint8_t *dst, const uint8_t *src,
1548 put_h264_qpel8_v_lowpass_lasx(dst, (uint8_t*)src, stride, stride);
1551 void ff_put_h264_qpel8_mc12_lasx(uint8_t *dst, const uint8_t *src,
1560 put_pixels8_l2_8_lsx(dst, halfH, halfHV, stride, 8);
1563 void ff_put_h264_qpel8_mc22_lasx(uint8_t *dst, const uint8_t *src,
1566 put_h264_qpel8_hv_lowpass_lasx(dst, src, stride, stride);
1569 void ff_put_h264_qpel8_mc32_lasx(uint8_t *dst, const uint8_t *src,
1578 put_pixels8_l2_8_lsx(dst, halfH, halfHV, stride, 8);
1581 void ff_put_h264_qpel8_mc03_lasx(uint8_t *dst, const uint8_t *src,
1587 put_pixels8_l2_8_lsx(dst, src + stride, half, stride, stride);
1590 void ff_put_h264_qpel8_mc13_lasx(uint8_t *dst, const uint8_t *src,
1598 put_pixels8_l2_8_lsx(dst, halfH, halfV, stride, 8);
1601 void ff_put_h264_qpel8_mc23_lasx(uint8_t *dst, const uint8_t *src,
1610 put_pixels8_l2_8_lsx(dst, halfH, halfHV, stride, 8);
1613 void ff_put_h264_qpel8_mc33_lasx(uint8_t *dst, const uint8_t *src,
1621 put_pixels8_l2_8_lsx(dst, halfH, halfV, stride, 8);
1624 void ff_avg_h264_qpel8_mc00_lasx(uint8_t *dst, const uint8_t *src,
1629 avg_pixels8_8_lsx(dst, src, stride);
1632 void ff_avg_h264_qpel8_mc10_lasx(uint8_t *dst, const uint8_t *src,
1638 avg_pixels8_l2_8_lsx(dst, src, half, stride, stride);
1641 void ff_avg_h264_qpel8_mc20_lasx(uint8_t *dst, const uint8_t *src,
1644 avg_h264_qpel8_h_lowpass_lasx(dst, src, stride, stride);
1647 void ff_avg_h264_qpel8_mc30_lasx(uint8_t *dst, const uint8_t *src,
1653 avg_pixels8_l2_8_lsx(dst, src+1, half, stride, stride);
1656 void ff_avg_h264_qpel8_mc11_lasx(uint8_t *dst, const uint8_t *src,
1664 avg_pixels8_l2_8_lsx(dst, halfH, halfV, stride, 8);
1667 void ff_avg_h264_qpel8_mc21_lasx(uint8_t *dst, const uint8_t *src,
1676 avg_pixels8_l2_8_lsx(dst, halfH, halfHV, stride, 8);
1679 void ff_avg_h264_qpel8_mc31_lasx(uint8_t *dst, const uint8_t *src,
1687 avg_pixels8_l2_8_lsx(dst, halfH, halfV, stride, 8);
1690 void ff_avg_h264_qpel8_mc02_lasx(uint8_t *dst, const uint8_t *src,
1693 avg_h264_qpel8_v_lowpass_lasx(dst, (uint8_t*)src, stride, stride);
1696 void ff_avg_h264_qpel8_mc12_lasx(uint8_t *dst, const uint8_t *src,
1705 avg_pixels8_l2_8_lsx(dst, halfH, halfHV, stride, 8);
1708 void ff_avg_h264_qpel8_mc22_lasx(uint8_t *dst, const uint8_t *src,
1711 avg_h264_qpel8_hv_lowpass_lasx(dst, src, stride, stride);
1714 void ff_avg_h264_qpel8_mc32_lasx(uint8_t *dst, const uint8_t *src,
1723 avg_pixels8_l2_8_lsx(dst, halfH, halfHV, stride, 8);
1726 void ff_avg_h264_qpel8_mc13_lasx(uint8_t *dst, const uint8_t *src,
1734 avg_pixels8_l2_8_lsx(dst, halfH, halfV, stride, 8);
1737 void ff_avg_h264_qpel8_mc23_lasx(uint8_t *dst, const uint8_t *src,
1746 avg_pixels8_l2_8_lsx(dst, halfH, halfHV, stride, 8);
1749 void ff_avg_h264_qpel8_mc33_lasx(uint8_t *dst, const uint8_t *src,
1757 avg_pixels8_l2_8_lsx(dst, halfH, halfV, stride, 8);
1760 void ff_put_h264_qpel16_mc00_lasx(uint8_t *dst, const uint8_t *src,
1765 put_pixels16_8_lsx(dst, src, stride);
1768 void ff_put_h264_qpel16_mc10_lasx(uint8_t *dst, const uint8_t *src,
1774 put_pixels16_l2_8_lsx(dst, src, half, stride, stride);
1777 void ff_put_h264_qpel16_mc20_lasx(uint8_t *dst, const uint8_t *src,
1780 put_h264_qpel16_h_lowpass_lasx(dst, src, stride, stride);
1783 void ff_put_h264_qpel16_mc30_lasx(uint8_t *dst, const uint8_t *src,
1789 put_pixels16_l2_8_lsx(dst, src+1, half, stride, stride);
1792 void ff_put_h264_qpel16_mc01_lasx(uint8_t *dst, const uint8_t *src,
1798 put_pixels16_l2_8_lsx(dst, src, half, stride, stride);
1801 void ff_put_h264_qpel16_mc11_lasx(uint8_t *dst, const uint8_t *src,
1805 dst, stride);
1808 void ff_put_h264_qpel16_mc21_lasx(uint8_t *dst, const uint8_t *src,
1817 put_pixels16_l2_8_lsx(dst, halfH, halfHV, stride, 16);
1820 void ff_put_h264_qpel16_mc31_lasx(uint8_t *dst, const uint8_t *src,
1824 dst, stride);
1827 void ff_put_h264_qpel16_mc02_lasx(uint8_t *dst, const uint8_t *src,
1830 put_h264_qpel16_v_lowpass_lasx(dst, src, stride, stride);
1833 void ff_put_h264_qpel16_mc12_lasx(uint8_t *dst, const uint8_t *src,
1842 put_pixels16_l2_8_lsx(dst, halfH, halfHV, stride, 16);
1845 void ff_put_h264_qpel16_mc22_lasx(uint8_t *dst, const uint8_t *src,
1848 put_h264_qpel16_hv_lowpass_lasx(dst, src, stride, stride);
1851 void ff_put_h264_qpel16_mc32_lasx(uint8_t *dst, const uint8_t *src,
1860 put_pixels16_l2_8_lsx(dst, halfH, halfHV, stride, 16);
1863 void ff_put_h264_qpel16_mc03_lasx(uint8_t *dst, const uint8_t *src,
1869 put_pixels16_l2_8_lsx(dst, src+stride, half, stride, stride);
1872 void ff_put_h264_qpel16_mc13_lasx(uint8_t *dst, const uint8_t *src,
1876 dst, stride);
1879 void ff_put_h264_qpel16_mc23_lasx(uint8_t *dst, const uint8_t *src,
1888 put_pixels16_l2_8_lsx(dst, halfH, halfHV, stride, 16);
1891 void ff_put_h264_qpel16_mc33_lasx(uint8_t *dst, const uint8_t *src,
1895 (uint8_t*)src - (stride * 2) + 1, dst, stride);
1898 void ff_avg_h264_qpel16_mc00_lasx(uint8_t *dst, const uint8_t *src,
1903 avg_pixels16_8_lsx(dst, src, stride);
1906 void ff_avg_h264_qpel16_mc10_lasx(uint8_t *dst, const uint8_t *src,
1912 avg_pixels16_l2_8_lsx(dst, src, half, stride, stride);
1915 void ff_avg_h264_qpel16_mc20_lasx(uint8_t *dst, const uint8_t *src,
1918 avg_h264_qpel16_h_lowpass_lasx(dst, src, stride, stride);
1921 void ff_avg_h264_qpel16_mc30_lasx(uint8_t *dst, const uint8_t *src,
1927 avg_pixels16_l2_8_lsx(dst, src+1, half, stride, stride);
1930 void ff_avg_h264_qpel16_mc01_lasx(uint8_t *dst, const uint8_t *src,
1936 avg_pixels16_l2_8_lsx(dst, src, half, stride, stride);
1939 void ff_avg_h264_qpel16_mc11_lasx(uint8_t *dst, const uint8_t *src,
1944 dst, stride);
1947 void ff_avg_h264_qpel16_mc21_lasx(uint8_t *dst, const uint8_t *src,
1956 avg_pixels16_l2_8_lsx(dst, halfH, halfHV, stride, 16);
1959 void ff_avg_h264_qpel16_mc31_lasx(uint8_t *dst, const uint8_t *src,
1964 dst, stride);
1967 void ff_avg_h264_qpel16_mc02_lasx(uint8_t *dst, const uint8_t *src,
1970 avg_h264_qpel16_v_lowpass_lasx(dst, src, stride, stride);
1973 void ff_avg_h264_qpel16_mc12_lasx(uint8_t *dst, const uint8_t *src,
1982 avg_pixels16_l2_8_lsx(dst, halfH, halfHV, stride, 16);
1985 void ff_avg_h264_qpel16_mc22_lasx(uint8_t *dst, const uint8_t *src,
1988 avg_h264_qpel16_hv_lowpass_lasx(dst, src, stride, stride);
1991 void ff_avg_h264_qpel16_mc32_lasx(uint8_t *dst, const uint8_t *src,
2000 avg_pixels16_l2_8_lsx(dst, halfH, halfHV, stride, 16);
2003 void ff_avg_h264_qpel16_mc03_lasx(uint8_t *dst, const uint8_t *src,
2009 avg_pixels16_l2_8_lsx(dst, src + stride, half, stride, stride);
2012 void ff_avg_h264_qpel16_mc13_lasx(uint8_t *dst, const uint8_t *src,
2017 dst, stride);
2020 void ff_avg_h264_qpel16_mc23_lasx(uint8_t *dst, const uint8_t *src,
2029 avg_pixels16_l2_8_lsx(dst, halfH, halfHV, stride, 16);
2032 void ff_avg_h264_qpel16_mc33_lasx(uint8_t *dst, const uint8_t *src,
2037 dst, stride);