Hu Chunming / FFNvDecoder

h264_idct.asm 30.5 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 
;*****************************************************************************
;* MMX/SSE2-optimized H.264 iDCT
;*****************************************************************************
;* Copyright (C) 2004-2005 Michael Niedermayer, Loren Merritt
;* Copyright (C) 2003-2008 x264 project
;*
;* Authors: Laurent Aimar <fenrir@via.ecp.fr>
;*          Loren Merritt <lorenm@u.washington.edu>
;*          Holger Lubitz <hal@duncan.ol.sub.de>
;*          Min Chen <chenm001.163.com>
;*
;* This file is part of FFmpeg.
;*
;* FFmpeg is free software; you can redistribute it and/or
;* modify it under the terms of the GNU Lesser General Public
;* License as published by the Free Software Foundation; either
;* version 2.1 of the License, or (at your option) any later version.
;*
;* FFmpeg is distributed in the hope that it will be useful,
;* but WITHOUT ANY WARRANTY; without even the implied warranty of
;* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
;* Lesser General Public License for more details.
;*
;* You should have received a copy of the GNU Lesser General Public
;* License along with FFmpeg; if not, write to the Free Software
;* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
;*****************************************************************************

%include "libavutil/x86/x86util.asm"

SECTION_RODATA

scan8_mem: db  4+ 1*8, 5+ 1*8, 4+ 2*8, 5+ 2*8
           db  6+ 1*8, 7+ 1*8, 6+ 2*8, 7+ 2*8
           db  4+ 3*8, 5+ 3*8, 4+ 4*8, 5+ 4*8
           db  6+ 3*8, 7+ 3*8, 6+ 4*8, 7+ 4*8
           db  4+ 6*8, 5+ 6*8, 4+ 7*8, 5+ 7*8
           db  6+ 6*8, 7+ 6*8, 6+ 7*8, 7+ 7*8
           db  4+ 8*8, 5+ 8*8, 4+ 9*8, 5+ 9*8
           db  6+ 8*8, 7+ 8*8, 6+ 9*8, 7+ 9*8
           db  4+11*8, 5+11*8, 4+12*8, 5+12*8
           db  6+11*8, 7+11*8, 6+12*8, 7+12*8
           db  4+13*8, 5+13*8, 4+14*8, 5+14*8
           db  6+13*8, 7+13*8, 6+14*8, 7+14*8
%ifdef PIC
%define npicregs 1
%define scan8 picregq
%else
%define npicregs 0
%define scan8 scan8_mem
%endif

cextern pw_32
cextern pw_1

SECTION .text

; %1=uint8_t *dst, %2=int16_t *block, %3=int stride
%macro IDCT4_ADD 3
    ; Load dct coeffs
    movq         m0, [%2]
    movq         m1, [%2+8]
    movq         m2, [%2+16]
    movq         m3, [%2+24]

    IDCT4_1D      w, 0, 1, 2, 3, 4, 5
    mova         m6, [pw_32]
    %if mmsize == 8
        TRANSPOSE4x4W 0, 1, 2, 3, 4
    %else
        punpcklwd m0, m1
        punpcklwd m2, m3
        SBUTTERFLY dq, 0, 2, 4
        MOVHL m1, m0
        MOVHL m3, m2
    %endif
    paddw        m0, m6
    IDCT4_1D      w, 0, 1, 2, 3, 4, 5
    pxor         m7, m7
    movq    [%2+ 0], m7
    movq    [%2+ 8], m7
    movq    [%2+16], m7
    movq    [%2+24], m7

    STORE_DIFFx2 m0, m1, m4, m5, m7, 6, %1, %3
    lea          %1, [%1+%3*2]
    STORE_DIFFx2 m2, m3, m4, m5, m7, 6, %1, %3
%endmacro

INIT_MMX mmx
; void ff_h264_idct_add_8_mmx(uint8_t *dst, int16_t *block, int stride)
cglobal h264_idct_add_8, 3, 3, 0
    movsxdifnidn r2, r2d
    IDCT4_ADD    r0, r1, r2
    RET

%macro IDCT8_1D 2
    psraw        m0, m1, 1
    SWAP 0, 1
    psraw        m4, m5, 1
    paddw        m4, m5
    paddw        m1, m0
    paddw        m4, m7
    paddw        m1, m5
    psubw        m4, m0
    paddw        m1, m3

    psubw        m0, m3
    psubw        m5, m3
    psraw        m3, 1
    paddw        m0, m7
    psubw        m5, m7
    psraw        m7, 1
    psubw        m0, m3
    psubw        m5, m7

    psraw        m7, m1, 2
    SWAP 7,1
    psraw        m3, m4, 2
    paddw        m3, m0
    psraw        m0, 2
    paddw        m1, m5
    psraw        m5, 2
    psubw        m0, m4
    psubw        m7, m5

    psraw        m5, m6, 1
    SWAP 5,6
    psraw        m4, m2, 1
    paddw        m6, m2
    psubw        m4, m5

    mova         m2, %1
    mova         m5, %2
    SUMSUB_BA    w, 5, 2
    SUMSUB_BA    w, 6, 5
    SUMSUB_BA    w, 4, 2
    SUMSUB_BA    w, 7, 6
    SUMSUB_BA    w, 0, 4
    SUMSUB_BA    w, 3, 2
    SUMSUB_BA    w, 1, 5
    SWAP         7, 6, 4, 5, 2, 3, 1, 0 ; 70315246 -> 01234567
%endmacro

%macro IDCT8_1D_FULL 1
    mova         m7, [%1+112]
    mova         m6, [%1+ 96]
    mova         m5, [%1+ 80]
    mova         m3, [%1+ 48]
    mova         m2, [%1+ 32]
    mova         m1, [%1+ 16]
    IDCT8_1D   [%1], [%1+ 64]
%endmacro

; %1=int16_t *block, %2=int16_t *dstblock
%macro IDCT8_ADD_MMX_START 2
    IDCT8_1D_FULL %1
    mova       [%1], m7
    TRANSPOSE4x4W 0, 1, 2, 3, 7
    mova         m7, [%1]
    mova    [%2   ], m0
    mova    [%2+16], m1
    mova    [%2+32], m2
    mova    [%2+48], m3
    TRANSPOSE4x4W 4, 5, 6, 7, 3
    mova    [%2+ 8], m4
    mova    [%2+24], m5
    mova    [%2+40], m6
    mova    [%2+56], m7
%endmacro

; %1=uint8_t *dst, %2=int16_t *block, %3=int stride
%macro IDCT8_ADD_MMX_END 3-4
    IDCT8_1D_FULL %2
    mova    [%2   ], m5
    mova    [%2+16], m6
    mova    [%2+32], m7

    pxor         m7, m7
%if %0 == 4
    movq   [%4+  0], m7
    movq   [%4+  8], m7
    movq   [%4+ 16], m7
    movq   [%4+ 24], m7
    movq   [%4+ 32], m7
    movq   [%4+ 40], m7
    movq   [%4+ 48], m7
    movq   [%4+ 56], m7
    movq   [%4+ 64], m7
    movq   [%4+ 72], m7
    movq   [%4+ 80], m7
    movq   [%4+ 88], m7
    movq   [%4+ 96], m7
    movq   [%4+104], m7
    movq   [%4+112], m7
    movq   [%4+120], m7
%endif
    STORE_DIFFx2 m0, m1, m5, m6, m7, 6, %1, %3
    lea          %1, [%1+%3*2]
    STORE_DIFFx2 m2, m3, m5, m6, m7, 6, %1, %3
    mova         m0, [%2   ]
    mova         m1, [%2+16]
    mova         m2, [%2+32]
    lea          %1, [%1+%3*2]
    STORE_DIFFx2 m4, m0, m5, m6, m7, 6, %1, %3
    lea          %1, [%1+%3*2]
    STORE_DIFFx2 m1, m2, m5, m6, m7, 6, %1, %3
%endmacro

INIT_MMX mmx
; void ff_h264_idct8_add_8_mmx(uint8_t *dst, int16_t *block, int stride)
cglobal h264_idct8_add_8, 3, 4, 0
    movsxdifnidn r2, r2d
    %assign pad 128+4-(stack_offset&7)
    SUB         rsp, pad

    add   word [r1], 32
    IDCT8_ADD_MMX_START r1  , rsp
    IDCT8_ADD_MMX_START r1+8, rsp+64
    lea          r3, [r0+4]
    IDCT8_ADD_MMX_END   r0  , rsp,   r2, r1
    IDCT8_ADD_MMX_END   r3  , rsp+8, r2

    ADD         rsp, pad
    RET

; %1=uint8_t *dst, %2=int16_t *block, %3=int stride
%macro IDCT8_ADD_SSE 4
    IDCT8_1D_FULL %2
%if ARCH_X86_64
    TRANSPOSE8x8W 0, 1, 2, 3, 4, 5, 6, 7, 8
%else
    TRANSPOSE8x8W 0, 1, 2, 3, 4, 5, 6, 7, [%2], [%2+16]
%endif
    paddw        m0, [pw_32]

%if ARCH_X86_64 == 0
    mova    [%2   ], m0
    mova    [%2+16], m4
    IDCT8_1D   [%2], [%2+ 16]
    mova    [%2   ], m6
    mova    [%2+16], m7
%else
    SWAP          0, 8
    SWAP          4, 9
    IDCT8_1D     m8, m9
    SWAP          6, 8
    SWAP          7, 9
%endif

    pxor         m7, m7
    lea          %4, [%3*3]
    STORE_DIFF   m0, m6, m7, [%1     ]
    STORE_DIFF   m1, m6, m7, [%1+%3  ]
    STORE_DIFF   m2, m6, m7, [%1+%3*2]
    STORE_DIFF   m3, m6, m7, [%1+%4  ]
%if ARCH_X86_64 == 0
    mova         m0, [%2   ]
    mova         m1, [%2+16]
%else
    SWAP          0, 8
    SWAP          1, 9
%endif
    mova   [%2+  0], m7
    mova   [%2+ 16], m7
    mova   [%2+ 32], m7
    mova   [%2+ 48], m7
    mova   [%2+ 64], m7
    mova   [%2+ 80], m7
    mova   [%2+ 96], m7
    mova   [%2+112], m7
    lea          %1, [%1+%3*4]
    STORE_DIFF   m4, m6, m7, [%1     ]
    STORE_DIFF   m5, m6, m7, [%1+%3  ]
    STORE_DIFF   m0, m6, m7, [%1+%3*2]
    STORE_DIFF   m1, m6, m7, [%1+%4  ]
%endmacro

INIT_XMM sse2
; void ff_h264_idct8_add_8_sse2(uint8_t *dst, int16_t *block, int stride)
cglobal h264_idct8_add_8, 3, 4, 10
    movsxdifnidn  r2, r2d
    IDCT8_ADD_SSE r0, r1, r2, r3
    RET

%macro DC_ADD_MMXEXT_INIT 2
    add          %1, 32
    sar          %1, 6
    movd         m0, %1d
    lea          %1, [%2*3]
    pshufw       m0, m0, 0
    pxor         m1, m1
    psubw        m1, m0
    packuswb     m0, m0
    packuswb     m1, m1
%endmacro

%macro DC_ADD_MMXEXT_OP 4
    %1           m2, [%2     ]
    %1           m3, [%2+%3  ]
    %1           m4, [%2+%3*2]
    %1           m5, [%2+%4  ]
    paddusb      m2, m0
    paddusb      m3, m0
    paddusb      m4, m0
    paddusb      m5, m0
    psubusb      m2, m1
    psubusb      m3, m1
    psubusb      m4, m1
    psubusb      m5, m1
    %1    [%2     ], m2
    %1    [%2+%3  ], m3
    %1    [%2+%3*2], m4
    %1    [%2+%4  ], m5
%endmacro

INIT_MMX mmxext
; void ff_h264_idct_dc_add_8_mmxext(uint8_t *dst, int16_t *block, int stride)
%if ARCH_X86_64
cglobal h264_idct_dc_add_8, 3, 4, 0
    movsxd       r2, r2d
    movsx        r3, word [r1]
    mov  dword [r1], 0
    DC_ADD_MMXEXT_INIT r3, r2
    DC_ADD_MMXEXT_OP movh, r0, r2, r3
    RET

; void ff_h264_idct8_dc_add_8_mmxext(uint8_t *dst, int16_t *block, int stride)
cglobal h264_idct8_dc_add_8, 3, 4, 0
    movsxd       r2, r2d
    movsx        r3, word [r1]
    mov  dword [r1], 0
    DC_ADD_MMXEXT_INIT r3, r2
    DC_ADD_MMXEXT_OP mova, r0, r2, r3
    lea          r0, [r0+r2*4]
    DC_ADD_MMXEXT_OP mova, r0, r2, r3
    RET
%else
; void ff_h264_idct_dc_add_8_mmxext(uint8_t *dst, int16_t *block, int stride)
cglobal h264_idct_dc_add_8, 2, 3, 0
    movsx        r2, word [r1]
    mov  dword [r1], 0
    mov          r1, r2m
    DC_ADD_MMXEXT_INIT r2, r1
    DC_ADD_MMXEXT_OP movh, r0, r1, r2
    RET

; void ff_h264_idct8_dc_add_8_mmxext(uint8_t *dst, int16_t *block, int stride)
cglobal h264_idct8_dc_add_8, 2, 3, 0
    movsx        r2, word [r1]
    mov  dword [r1], 0
    mov          r1, r2m
    DC_ADD_MMXEXT_INIT r2, r1
    DC_ADD_MMXEXT_OP mova, r0, r1, r2
    lea          r0, [r0+r1*4]
    DC_ADD_MMXEXT_OP mova, r0, r1, r2
    RET
%endif

INIT_MMX mmx
; void ff_h264_idct_add16_8_mmx(uint8_t *dst, const int *block_offset,
;                               int16_t *block, int stride,
;                               const uint8_t nnzc[6 * 8])
cglobal h264_idct_add16_8, 5, 7 + npicregs, 0, dst, block_offset, block, stride, nnzc, cntr, coeff, picreg
    movsxdifnidn r3, r3d
    xor          r5, r5
%ifdef PIC
    lea     picregq, [scan8_mem]
%endif
.nextblock:
    movzx        r6, byte [scan8+r5]
    movzx        r6, byte [r4+r6]
    test         r6, r6
    jz .skipblock
    mov         r6d, dword [r1+r5*4]
    lea          r6, [r0+r6]
    IDCT4_ADD    r6, r2, r3
.skipblock:
    inc          r5
    add          r2, 32
    cmp          r5, 16
    jl .nextblock
    REP_RET

; void ff_h264_idct8_add4_8_mmx(uint8_t *dst, const int *block_offset,
;                               int16_t *block, int stride,
;                               const uint8_t nnzc[6 * 8])
cglobal h264_idct8_add4_8, 5, 7 + npicregs, 0, dst, block_offset, block, stride, nnzc, cntr, coeff, picreg
    movsxdifnidn r3, r3d
    %assign pad 128+4-(stack_offset&7)
    SUB         rsp, pad

    xor          r5, r5
%ifdef PIC
    lea     picregq, [scan8_mem]
%endif
.nextblock:
    movzx        r6, byte [scan8+r5]
    movzx        r6, byte [r4+r6]
    test         r6, r6
    jz .skipblock
    mov         r6d, dword [r1+r5*4]
    add          r6, r0
    add   word [r2], 32
    IDCT8_ADD_MMX_START r2  , rsp
    IDCT8_ADD_MMX_START r2+8, rsp+64
    IDCT8_ADD_MMX_END   r6  , rsp,   r3, r2
    mov         r6d, dword [r1+r5*4]
    lea          r6, [r0+r6+4]
    IDCT8_ADD_MMX_END   r6  , rsp+8, r3
.skipblock:
    add          r5, 4
    add          r2, 128
    cmp          r5, 16
    jl .nextblock
    ADD         rsp, pad
    RET

INIT_MMX mmxext
; void ff_h264_idct_add16_8_mmxext(uint8_t *dst, const int *block_offset,
;                                  int16_t *block, int stride,
;                                  const uint8_t nnzc[6 * 8])
cglobal h264_idct_add16_8, 5, 8 + npicregs, 0, dst1, block_offset, block, stride, nnzc, cntr, coeff, dst2, picreg
    movsxdifnidn r3, r3d
    xor          r5, r5
%ifdef PIC
    lea     picregq, [scan8_mem]
%endif
.nextblock:
    movzx        r6, byte [scan8+r5]
    movzx        r6, byte [r4+r6]
    test         r6, r6
    jz .skipblock
    cmp          r6, 1
    jnz .no_dc
    movsx        r6, word [r2]
    test         r6, r6
    jz .no_dc
    mov   word [r2], 0
    DC_ADD_MMXEXT_INIT r6, r3
%if ARCH_X86_64 == 0
%define dst2q r1
%define dst2d r1d
%endif
    mov       dst2d, dword [r1+r5*4]
    lea       dst2q, [r0+dst2q]
    DC_ADD_MMXEXT_OP movh, dst2q, r3, r6
%if ARCH_X86_64 == 0
    mov          r1, r1m
%endif
    inc          r5
    add          r2, 32
    cmp          r5, 16
    jl .nextblock
    REP_RET
.no_dc:
    mov         r6d, dword [r1+r5*4]
    add          r6, r0
    IDCT4_ADD    r6, r2, r3
.skipblock:
    inc          r5
    add          r2, 32
    cmp          r5, 16
    jl .nextblock
    REP_RET

INIT_MMX mmx
; void ff_h264_idct_add16intra_8_mmx(uint8_t *dst, const int *block_offset,
;                                    int16_t *block, int stride,
;                                    const uint8_t nnzc[6 * 8])
cglobal h264_idct_add16intra_8, 5, 7 + npicregs, 0, dst, block_offset, block, stride, nnzc, cntr, coeff, picreg
    movsxdifnidn r3, r3d
    xor          r5, r5
%ifdef PIC
    lea     picregq, [scan8_mem]
%endif
.nextblock:
    movzx        r6, byte [scan8+r5]
    movzx        r6, byte [r4+r6]
    or          r6w, word [r2]
    test         r6, r6
    jz .skipblock
    mov         r6d, dword [r1+r5*4]
    add          r6, r0
    IDCT4_ADD    r6, r2, r3
.skipblock:
    inc          r5
    add          r2, 32
    cmp          r5, 16
    jl .nextblock
    REP_RET

INIT_MMX mmxext
; void ff_h264_idct_add16intra_8_mmxext(uint8_t *dst, const int *block_offset,
;                                       int16_t *block, int stride,
;                                       const uint8_t nnzc[6 * 8])
cglobal h264_idct_add16intra_8, 5, 8 + npicregs, 0, dst1, block_offset, block, stride, nnzc, cntr, coeff, dst2, picreg
    movsxdifnidn r3, r3d
    xor          r5, r5
%ifdef PIC
    lea     picregq, [scan8_mem]
%endif
.nextblock:
    movzx        r6, byte [scan8+r5]
    movzx        r6, byte [r4+r6]
    test         r6, r6
    jz .try_dc
    mov         r6d, dword [r1+r5*4]
    lea          r6, [r0+r6]
    IDCT4_ADD    r6, r2, r3
    inc          r5
    add          r2, 32
    cmp          r5, 16
    jl .nextblock
    REP_RET
.try_dc:
    movsx        r6, word [r2]
    test         r6, r6
    jz .skipblock
    mov   word [r2], 0
    DC_ADD_MMXEXT_INIT r6, r3
%if ARCH_X86_64 == 0
%define dst2q r1
%define dst2d r1d
%endif
    mov       dst2d, dword [r1+r5*4]
    add       dst2q, r0
    DC_ADD_MMXEXT_OP movh, dst2q, r3, r6
%if ARCH_X86_64 == 0
    mov          r1, r1m
%endif
.skipblock:
    inc          r5
    add          r2, 32
    cmp          r5, 16
    jl .nextblock
    REP_RET

; void ff_h264_idct8_add4_8_mmxext(uint8_t *dst, const int *block_offset,
;                                  int16_t *block, int stride,
;                                  const uint8_t nnzc[6 * 8])
cglobal h264_idct8_add4_8, 5, 8 + npicregs, 0, dst1, block_offset, block, stride, nnzc, cntr, coeff, dst2, picreg
    movsxdifnidn r3, r3d
    %assign pad 128+4-(stack_offset&7)
    SUB         rsp, pad

    xor          r5, r5
%ifdef PIC
    lea     picregq, [scan8_mem]
%endif
.nextblock:
    movzx        r6, byte [scan8+r5]
    movzx        r6, byte [r4+r6]
    test         r6, r6
    jz .skipblock
    cmp          r6, 1
    jnz .no_dc
    movsx        r6, word [r2]
    test         r6, r6
    jz .no_dc
    mov   word [r2], 0
    DC_ADD_MMXEXT_INIT r6, r3
%if ARCH_X86_64 == 0
%define dst2q r1
%define dst2d r1d
%endif
    mov       dst2d, dword [r1+r5*4]
    lea       dst2q, [r0+dst2q]
    DC_ADD_MMXEXT_OP mova, dst2q, r3, r6
    lea       dst2q, [dst2q+r3*4]
    DC_ADD_MMXEXT_OP mova, dst2q, r3, r6
%if ARCH_X86_64 == 0
    mov          r1, r1m
%endif
    add          r5, 4
    add          r2, 128
    cmp          r5, 16
    jl .nextblock

    ADD         rsp, pad
    RET
.no_dc:
    mov         r6d, dword [r1+r5*4]
    add          r6, r0
    add   word [r2], 32
    IDCT8_ADD_MMX_START r2  , rsp
    IDCT8_ADD_MMX_START r2+8, rsp+64
    IDCT8_ADD_MMX_END   r6  , rsp,   r3, r2
    mov         r6d, dword [r1+r5*4]
    lea          r6, [r0+r6+4]
    IDCT8_ADD_MMX_END   r6  , rsp+8, r3
.skipblock:
    add          r5, 4
    add          r2, 128
    cmp          r5, 16
    jl .nextblock

    ADD         rsp, pad
    RET

INIT_XMM sse2
; void ff_h264_idct8_add4_8_sse2(uint8_t *dst, const int *block_offset,
;                                int16_t *block, int stride,
;                                const uint8_t nnzc[6 * 8])
cglobal h264_idct8_add4_8, 5, 8 + npicregs, 10, dst1, block_offset, block, stride, nnzc, cntr, coeff, dst2, picreg
    movsxdifnidn r3, r3d
    xor          r5, r5
%ifdef PIC
    lea     picregq, [scan8_mem]
%endif
.nextblock:
    movzx        r6, byte [scan8+r5]
    movzx        r6, byte [r4+r6]
    test         r6, r6
    jz .skipblock
    cmp          r6, 1
    jnz .no_dc
    movsx        r6, word [r2]
    test         r6, r6
    jz .no_dc
INIT_MMX cpuname
    mov   word [r2], 0
    DC_ADD_MMXEXT_INIT r6, r3
%if ARCH_X86_64 == 0
%define dst2q r1
%define dst2d r1d
%endif
    mov       dst2d, dword [r1+r5*4]
    add       dst2q, r0
    DC_ADD_MMXEXT_OP mova, dst2q, r3, r6
    lea       dst2q, [dst2q+r3*4]
    DC_ADD_MMXEXT_OP mova, dst2q, r3, r6
%if ARCH_X86_64 == 0
    mov          r1, r1m
%endif
    add          r5, 4
    add          r2, 128
    cmp          r5, 16
    jl .nextblock
    REP_RET
.no_dc:
INIT_XMM cpuname
    mov       dst2d, dword [r1+r5*4]
    add       dst2q, r0
    IDCT8_ADD_SSE dst2q, r2, r3, r6
%if ARCH_X86_64 == 0
    mov          r1, r1m
%endif
.skipblock:
    add          r5, 4
    add          r2, 128
    cmp          r5, 16
    jl .nextblock
    REP_RET

INIT_MMX mmx
h264_idct_add8_mmx_plane:
    movsxdifnidn r3, r3d
.nextblock:
    movzx        r6, byte [scan8+r5]
    movzx        r6, byte [r4+r6]
    or          r6w, word [r2]
    test         r6, r6
    jz .skipblock
%if ARCH_X86_64
    mov         r0d, dword [r1+r5*4]
    add          r0, [dst2q]
%else
    mov          r0, r1m ; XXX r1m here is actually r0m of the calling func
    mov          r0, [r0]
    add          r0, dword [r1+r5*4]
%endif
    IDCT4_ADD    r0, r2, r3
.skipblock:
    inc          r5
    add          r2, 32
    test         r5, 3
    jnz .nextblock
    rep ret

; void ff_h264_idct_add8_8_mmx(uint8_t **dest, const int *block_offset,
;                              int16_t *block, int stride,
;                              const uint8_t nnzc[6 * 8])
cglobal h264_idct_add8_8, 5, 8 + npicregs, 0, dst1, block_offset, block, stride, nnzc, cntr, coeff, dst2, picreg
    movsxdifnidn r3, r3d
    mov          r5, 16
    add          r2, 512
%ifdef PIC
    lea     picregq, [scan8_mem]
%endif
%if ARCH_X86_64
    mov       dst2q, r0
%endif
    call         h264_idct_add8_mmx_plane
    mov          r5, 32
    add          r2, 384
%if ARCH_X86_64
    add       dst2q, gprsize
%else
    add        r0mp, gprsize
%endif
    call         h264_idct_add8_mmx_plane
    RET ; TODO: check rep ret after a function call

cglobal h264_idct_add8_422_8, 5, 8 + npicregs, 0, dst1, block_offset, block, stride, nnzc, cntr, coeff, dst2, picreg
; dst1, block_offset, block, stride, nnzc, cntr, coeff, dst2, picreg
    movsxdifnidn r3, r3d
%ifdef PIC
    lea     picregq, [scan8_mem]
%endif
%if ARCH_X86_64
    mov       dst2q, r0
%endif

    mov          r5, 16  ; i
    add          r2, 512 ; i * 16 * sizeof(dctcoef) ; #define dctcoef int16_t

    call         h264_idct_add8_mmx_plane
    add r5, 4
    call         h264_idct_add8_mmx_plane

%if ARCH_X86_64
    add       dst2q, gprsize ; dest[1]
%else
    add        r0mp, gprsize
%endif

    add r5, 4   ; set to 32
    add r2, 256 ; set to i * 16 * sizeof(dctcoef)

    call         h264_idct_add8_mmx_plane
    add r5, 4
    call         h264_idct_add8_mmx_plane

    RET ; TODO: check rep ret after a function call

h264_idct_add8_mmxext_plane:
    movsxdifnidn r3, r3d
.nextblock:
    movzx        r6, byte [scan8+r5]
    movzx        r6, byte [r4+r6]
    test         r6, r6
    jz .try_dc
%if ARCH_X86_64
    mov         r0d, dword [r1+r5*4]
    add          r0, [dst2q]
%else
    mov          r0, r1m ; XXX r1m here is actually r0m of the calling func
    mov          r0, [r0]
    add          r0, dword [r1+r5*4]
%endif
    IDCT4_ADD    r0, r2, r3
    inc          r5
    add          r2, 32
    test         r5, 3
    jnz .nextblock
    rep ret
.try_dc:
    movsx        r6, word [r2]
    test         r6, r6
    jz .skipblock
    mov   word [r2], 0
    DC_ADD_MMXEXT_INIT r6, r3
%if ARCH_X86_64
    mov         r0d, dword [r1+r5*4]
    add          r0, [dst2q]
%else
    mov          r0, r1m ; XXX r1m here is actually r0m of the calling func
    mov          r0, [r0]
    add          r0, dword [r1+r5*4]
%endif
    DC_ADD_MMXEXT_OP movh, r0, r3, r6
.skipblock:
    inc          r5
    add          r2, 32
    test         r5, 3
    jnz .nextblock
    rep ret

INIT_MMX mmxext
; void ff_h264_idct_add8_8_mmxext(uint8_t **dest, const int *block_offset,
;                                 int16_t *block, int stride,
;                                 const uint8_t nnzc[6 * 8])
cglobal h264_idct_add8_8, 5, 8 + npicregs, 0, dst1, block_offset, block, stride, nnzc, cntr, coeff, dst2, picreg
    movsxdifnidn r3, r3d
    mov          r5, 16
    add          r2, 512
%if ARCH_X86_64
    mov       dst2q, r0
%endif
%ifdef PIC
    lea     picregq, [scan8_mem]
%endif
    call h264_idct_add8_mmxext_plane
    mov          r5, 32
    add          r2, 384
%if ARCH_X86_64
    add       dst2q, gprsize
%else
    add        r0mp, gprsize
%endif
    call h264_idct_add8_mmxext_plane
    RET ; TODO: check rep ret after a function call

; r0 = uint8_t *dst, r2 = int16_t *block, r3 = int stride, r6=clobbered
h264_idct_dc_add8_mmxext:
    movsxdifnidn r3, r3d
    movd         m0, [r2   ]          ;  0 0 X D
    mov word [r2+ 0], 0
    punpcklwd    m0, [r2+32]          ;  x X d D
    mov word [r2+32], 0
    paddsw       m0, [pw_32]
    psraw        m0, 6
    punpcklwd    m0, m0               ;  d d D D
    pxor         m1, m1               ;  0 0 0 0
    psubw        m1, m0               ; -d-d-D-D
    packuswb     m0, m1               ; -d-d-D-D d d D D
    pshufw       m1, m0, 0xFA         ; -d-d-d-d-D-D-D-D
    punpcklwd    m0, m0               ;  d d d d D D D D
    lea          r6, [r3*3]
    DC_ADD_MMXEXT_OP movq, r0, r3, r6
    ret

ALIGN 16
INIT_XMM sse2
; r0 = uint8_t *dst (clobbered), r2 = int16_t *block, r3 = int stride
h264_add8x4_idct_sse2:
    movsxdifnidn r3, r3d
    movq   m0, [r2+ 0]
    movq   m1, [r2+ 8]
    movq   m2, [r2+16]
    movq   m3, [r2+24]
    movhps m0, [r2+32]
    movhps m1, [r2+40]
    movhps m2, [r2+48]
    movhps m3, [r2+56]
    IDCT4_1D w,0,1,2,3,4,5
    TRANSPOSE2x4x4W 0,1,2,3,4
    paddw m0, [pw_32]
    IDCT4_1D w,0,1,2,3,4,5
    pxor  m7, m7
    mova [r2+ 0], m7
    mova [r2+16], m7
    mova [r2+32], m7
    mova [r2+48], m7
    STORE_DIFFx2 m0, m1, m4, m5, m7, 6, r0, r3
    lea   r0, [r0+r3*2]
    STORE_DIFFx2 m2, m3, m4, m5, m7, 6, r0, r3
    ret

%macro add16_sse2_cycle 2
    movzx       r0, word [r4+%2]
    test        r0, r0
    jz .cycle%1end
    mov        r0d, dword [r1+%1*8]
%if ARCH_X86_64
    add         r0, r5
%else
    add         r0, r0m
%endif
    call        h264_add8x4_idct_sse2
.cycle%1end:
%if %1 < 7
    add         r2, 64
%endif
%endmacro

; void ff_h264_idct_add16_8_sse2(uint8_t *dst, const int *block_offset,
;                                int16_t *block, int stride,
;                                const uint8_t nnzc[6 * 8])
cglobal h264_idct_add16_8, 5, 5 + ARCH_X86_64, 8
    movsxdifnidn r3, r3d
%if ARCH_X86_64
    mov         r5, r0
%endif
    ; unrolling of the loop leads to an average performance gain of
    ; 20-25%
    add16_sse2_cycle 0, 0xc
    add16_sse2_cycle 1, 0x14
    add16_sse2_cycle 2, 0xe
    add16_sse2_cycle 3, 0x16
    add16_sse2_cycle 4, 0x1c
    add16_sse2_cycle 5, 0x24
    add16_sse2_cycle 6, 0x1e
    add16_sse2_cycle 7, 0x26
REP_RET

%macro add16intra_sse2_cycle 2
    movzx       r0, word [r4+%2]
    test        r0, r0
    jz .try%1dc
    mov        r0d, dword [r1+%1*8]
%if ARCH_X86_64
    add         r0, r7
%else
    add         r0, r0m
%endif
    call        h264_add8x4_idct_sse2
    jmp .cycle%1end
.try%1dc:
    movsx       r0, word [r2   ]
    or         r0w, word [r2+32]
    jz .cycle%1end
    mov        r0d, dword [r1+%1*8]
%if ARCH_X86_64
    add         r0, r7
%else
    add         r0, r0m
%endif
    call        h264_idct_dc_add8_mmxext
.cycle%1end:
%if %1 < 7
    add         r2, 64
%endif
%endmacro

; void ff_h264_idct_add16intra_8_sse2(uint8_t *dst, const int *block_offset,
;                                     int16_t *block, int stride,
;                                     const uint8_t nnzc[6 * 8])
cglobal h264_idct_add16intra_8, 5, 7 + ARCH_X86_64, 8
    movsxdifnidn r3, r3d
%if ARCH_X86_64
    mov         r7, r0
%endif
    add16intra_sse2_cycle 0, 0xc
    add16intra_sse2_cycle 1, 0x14
    add16intra_sse2_cycle 2, 0xe
    add16intra_sse2_cycle 3, 0x16
    add16intra_sse2_cycle 4, 0x1c
    add16intra_sse2_cycle 5, 0x24
    add16intra_sse2_cycle 6, 0x1e
    add16intra_sse2_cycle 7, 0x26
REP_RET

%macro add8_sse2_cycle 2
    movzx       r0, word [r4+%2]
    test        r0, r0
    jz .try%1dc
%if ARCH_X86_64
    mov        r0d, dword [r1+(%1&1)*8+64*(1+(%1>>1))]
    add         r0, [r7]
%else
    mov         r0, r0m
    mov         r0, [r0]
    add         r0, dword [r1+(%1&1)*8+64*(1+(%1>>1))]
%endif
    call        h264_add8x4_idct_sse2
    jmp .cycle%1end
.try%1dc:
    movsx       r0, word [r2   ]
    or         r0w, word [r2+32]
    jz .cycle%1end
%if ARCH_X86_64
    mov        r0d, dword [r1+(%1&1)*8+64*(1+(%1>>1))]
    add         r0, [r7]
%else
    mov         r0, r0m
    mov         r0, [r0]
    add         r0, dword [r1+(%1&1)*8+64*(1+(%1>>1))]
%endif
    call        h264_idct_dc_add8_mmxext
.cycle%1end:
%if %1 == 1
    add         r2, 384+64
%elif %1 < 3
    add         r2, 64
%endif
%endmacro

; void ff_h264_idct_add8_8_sse2(uint8_t **dest, const int *block_offset,
;                               int16_t *block, int stride,
;                               const uint8_t nnzc[6 * 8])
cglobal h264_idct_add8_8, 5, 7 + ARCH_X86_64, 8
    movsxdifnidn r3, r3d
    add          r2, 512
%if ARCH_X86_64
    mov          r7, r0
%endif
    add8_sse2_cycle 0, 0x34
    add8_sse2_cycle 1, 0x3c
%if ARCH_X86_64
    add          r7, gprsize
%else
    add        r0mp, gprsize
%endif
    add8_sse2_cycle 2, 0x5c
    add8_sse2_cycle 3, 0x64
REP_RET

;void ff_h264_luma_dc_dequant_idct_mmx(int16_t *output, int16_t *input, int qmul)

%macro WALSH4_1D 5
    SUMSUB_BADC w, %4, %3, %2, %1, %5
    SUMSUB_BADC w, %4, %2, %3, %1, %5
    SWAP %1, %4, %3
%endmacro

%macro DEQUANT 1-3
%if cpuflag(sse2)
    movd      xmm4, t3d
    movq      xmm5, [pw_1]
    pshufd    xmm4, xmm4, 0
    movq2dq   xmm0, m0
    movq2dq   xmm1, m1
    movq2dq   xmm2, m2
    movq2dq   xmm3, m3
    punpcklwd xmm0, xmm5
    punpcklwd xmm1, xmm5
    punpcklwd xmm2, xmm5
    punpcklwd xmm3, xmm5
    pmaddwd   xmm0, xmm4
    pmaddwd   xmm1, xmm4
    pmaddwd   xmm2, xmm4
    pmaddwd   xmm3, xmm4
    psrad     xmm0, %1
    psrad     xmm1, %1
    psrad     xmm2, %1
    psrad     xmm3, %1
    packssdw  xmm0, xmm1
    packssdw  xmm2, xmm3
%else
    mova        m7, [pw_1]
    mova        m4, %1
    punpcklwd   %1, m7
    punpckhwd   m4, m7
    mova        m5, %2
    punpcklwd   %2, m7
    punpckhwd   m5, m7
    movd        m7, t3d
    punpckldq   m7, m7
    pmaddwd     %1, m7
    pmaddwd     %2, m7
    pmaddwd     m4, m7
    pmaddwd     m5, m7
    psrad       %1, %3
    psrad       %2, %3
    psrad       m4, %3
    psrad       m5, %3
    packssdw    %1, m4
    packssdw    %2, m5
%endif
%endmacro

%macro STORE_WORDS 5-9
%if cpuflag(sse)
    movd  t0d, %1
    psrldq  %1, 4
    movd  t1d, %1
    psrldq  %1, 4
    mov [t2+%2*32], t0w
    mov [t2+%4*32], t1w
    shr   t0d, 16
    shr   t1d, 16
    mov [t2+%3*32], t0w
    mov [t2+%5*32], t1w
    movd  t0d, %1
    psrldq  %1, 4
    movd  t1d, %1
    mov [t2+%6*32], t0w
    mov [t2+%8*32], t1w
    shr   t0d, 16
    shr   t1d, 16
    mov [t2+%7*32], t0w
    mov [t2+%9*32], t1w
%else
    movd  t0d, %1
    psrlq  %1, 32
    movd  t1d, %1
    mov [t2+%2*32], t0w
    mov [t2+%4*32], t1w
    shr   t0d, 16
    shr   t1d, 16
    mov [t2+%3*32], t0w
    mov [t2+%5*32], t1w
%endif
%endmacro

%macro DEQUANT_STORE 1
%if cpuflag(sse2)
    DEQUANT     %1
    STORE_WORDS xmm0,  0,  1,  4,  5,  2,  3,  6,  7
    STORE_WORDS xmm2,  8,  9, 12, 13, 10, 11, 14, 15
%else
    DEQUANT     m0, m1, %1
    STORE_WORDS m0,  0,  1,  4,  5
    STORE_WORDS m1,  2,  3,  6,  7

    DEQUANT     m2, m3, %1
    STORE_WORDS m2,  8,  9, 12, 13
    STORE_WORDS m3, 10, 11, 14, 15
%endif
%endmacro

%macro IDCT_DC_DEQUANT 1
cglobal h264_luma_dc_dequant_idct, 3, 4, %1
    ; manually spill XMM registers for Win64 because
    ; the code here is initialized with INIT_MMX
    WIN64_SPILL_XMM %1
    movq        m3, [r1+24]
    movq        m2, [r1+16]
    movq        m1, [r1+ 8]
    movq        m0, [r1+ 0]
    WALSH4_1D    0,1,2,3,4
    TRANSPOSE4x4W 0,1,2,3,4
    WALSH4_1D    0,1,2,3,4

; shift, tmp, output, qmul
%if WIN64
    DECLARE_REG_TMP 0,3,1,2
    ; we can't avoid this, because r0 is the shift register (ecx) on win64
    xchg        r0, t2
%elif ARCH_X86_64
    DECLARE_REG_TMP 3,1,0,2
%else
    DECLARE_REG_TMP 1,3,0,2
%endif

    cmp        t3d, 32767
    jg .big_qmul
    add        t3d, 128 << 16
    DEQUANT_STORE 8
    RET
.big_qmul:
    bsr        t0d, t3d
    add        t3d, 128 << 16
    mov        t1d, 7
    cmp        t0d, t1d
    cmovg      t0d, t1d
    inc        t1d
    shr        t3d, t0b
    sub        t1d, t0d
%if cpuflag(sse2)
    movd      xmm6, t1d
    DEQUANT_STORE xmm6
%else
    movd        m6, t1d
    DEQUANT_STORE m6
%endif
    RET
%endmacro

INIT_MMX mmx
IDCT_DC_DEQUANT 0
INIT_MMX sse2
IDCT_DC_DEQUANT 7

%ifdef __NASM_VER__
%if __NASM_MAJOR__ >= 2 && __NASM_MINOR__ >= 4
%unmacro STORE_DIFFx2 8 ; remove macro from x86util.asm but yasm doesn't have this yet
%endif
%endif
%macro STORE_DIFFx2 8 ; add1, add2, reg1, reg2, zero, shift, source, stride
    movd       %3, [%7]
    movd       %4, [%7+%8]
    psraw      %1, %6
    psraw      %2, %6
    punpcklbw  %3, %5
    punpcklbw  %4, %5
    paddw      %3, %1
    paddw      %4, %2
    packuswb   %3, %5
    packuswb   %4, %5
    movd     [%7], %3
    movd  [%7+%8], %4
%endmacro

%macro DC_ADD_INIT 1
    add      %1d, 32
    sar      %1d, 6
    movd     m0, %1d
    pshuflw  m0, m0, 0
    lea      %1, [3*stride_q]
    pxor     m1, m1
    psubw    m1, m0
    packuswb m0, m0
    packuswb m1, m1
%endmacro

%macro IDCT_XMM 1

INIT_XMM %1

cglobal h264_idct_add_8, 3, 3, 8, dst_, block_, stride_
    movsxdifnidn stride_q, stride_d
    IDCT4_ADD    dst_q, block_q, stride_q
RET

cglobal h264_idct_dc_add_8, 3, 4, 6, dst_, block_, stride_
    movsxdifnidn stride_q, stride_d
    movsx             r3d, word [block_q]
    mov   dword [block_q], 0
    DC_ADD_INIT r3
    DC_ADD_MMXEXT_OP movd, dst_q, stride_q, r3
RET

%endmacro

IDCT_XMM sse2
IDCT_XMM avx