1;****************************************************************************** 2;* MMX/SSE2-optimized functions for the VP6 decoder 3;* Copyright (C) 2009 Sebastien Lucas <sebastien.lucas@gmail.com> 4;* Copyright (C) 2009 Zuxy Meng <zuxy.meng@gmail.com> 5;* 6;* This file is part of FFmpeg. 7;* 8;* FFmpeg is free software; you can redistribute it and/or 9;* modify it under the terms of the GNU Lesser General Public 10;* License as published by the Free Software Foundation; either 11;* version 2.1 of the License, or (at your option) any later version. 12;* 13;* FFmpeg is distributed in the hope that it will be useful, 14;* but WITHOUT ANY WARRANTY; without even the implied warranty of 15;* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU 16;* Lesser General Public License for more details. 17;* 18;* You should have received a copy of the GNU Lesser General Public 19;* License along with FFmpeg; if not, write to the Free Software 20;* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA 21;****************************************************************************** 22 23%include "libavutil/x86/x86util.asm" 24 25cextern pw_64 26 27SECTION .text 28 29%macro DIAG4 6 30%if mmsize == 8 31 movq m0, [%1+%2] 32 movq m1, [%1+%3] 33 movq m3, m0 34 movq m4, m1 35 punpcklbw m0, m7 36 punpcklbw m1, m7 37 punpckhbw m3, m7 38 punpckhbw m4, m7 39 pmullw m0, [rsp+8*11] ; src[x-8 ] * biweight [0] 40 pmullw m1, [rsp+8*12] ; src[x ] * biweight [1] 41 pmullw m3, [rsp+8*11] ; src[x-8 ] * biweight [0] 42 pmullw m4, [rsp+8*12] ; src[x ] * biweight [1] 43 paddw m0, m1 44 paddw m3, m4 45 movq m1, [%1+%4] 46 movq m2, [%1+%5] 47 movq m4, m1 48 movq m5, m2 49 punpcklbw m1, m7 50 punpcklbw m2, m7 51 punpckhbw m4, m7 52 punpckhbw m5, m7 53 pmullw m1, [rsp+8*13] ; src[x+8 ] * biweight [2] 54 pmullw m2, [rsp+8*14] ; src[x+16] * biweight [3] 55 pmullw m4, [rsp+8*13] ; src[x+8 ] * biweight [2] 56 pmullw m5, [rsp+8*14] ; src[x+16] * biweight [3] 57 paddw m1, m2 58 paddw m4, m5 59 paddsw m0, m1 60 paddsw m3, m4 61 paddsw m0, m6 ; Add 64 62 paddsw m3, m6 ; Add 64 63 psraw m0, 7 64 psraw m3, 7 65 packuswb m0, m3 66 movq [%6], m0 67%else ; mmsize == 16 68 movq m0, [%1+%2] 69 movq m1, [%1+%3] 70 punpcklbw m0, m7 71 punpcklbw m1, m7 72 pmullw m0, m4 ; src[x-8 ] * biweight [0] 73 pmullw m1, m5 ; src[x ] * biweight [1] 74 paddw m0, m1 75 movq m1, [%1+%4] 76 movq m2, [%1+%5] 77 punpcklbw m1, m7 78 punpcklbw m2, m7 79 pmullw m1, m6 ; src[x+8 ] * biweight [2] 80 pmullw m2, m3 ; src[x+16] * biweight [3] 81 paddw m1, m2 82 paddsw m0, m1 83 paddsw m0, [pw_64] ; Add 64 84 psraw m0, 7 85 packuswb m0, m0 86 movq [%6], m0 87%endif ; mmsize == 8/16 88%endmacro 89 90%macro SPLAT4REGS 0 91%if mmsize == 8 92 movq m5, m3 93 punpcklwd m3, m3 94 movq m4, m3 95 punpckldq m3, m3 96 punpckhdq m4, m4 97 punpckhwd m5, m5 98 movq m2, m5 99 punpckhdq m2, m2 100 punpckldq m5, m5 101 movq [rsp+8*11], m3 102 movq [rsp+8*12], m4 103 movq [rsp+8*13], m5 104 movq [rsp+8*14], m2 105%else ; mmsize == 16 106 pshuflw m4, m3, 0x0 107 pshuflw m5, m3, 0x55 108 pshuflw m6, m3, 0xAA 109 pshuflw m3, m3, 0xFF 110 punpcklqdq m4, m4 111 punpcklqdq m5, m5 112 punpcklqdq m6, m6 113 punpcklqdq m3, m3 114%endif ; mmsize == 8/16 115%endmacro 116 117; void ff_vp6_filter_diag4_<opt>(uint8_t *dst, uint8_t *src, ptrdiff_t stride, 118; const int16_t h_weight[4], const int16_t v_weights[4]) 119INIT_XMM sse2 120cglobal vp6_filter_diag4, 5, 7, 8 121 mov r5, rsp ; backup stack pointer 122 and rsp, ~(mmsize-1) ; align stack 123 sub rsp, 8*11 124 125 sub r1, r2 126 127 pxor m7, m7 128 movq m3, [r3] 129 SPLAT4REGS 130 131 mov r3, rsp 132 mov r6, 11 133.nextrow: 134 DIAG4 r1, -1, 0, 1, 2, r3 135 add r3, 8 136 add r1, r2 137 dec r6 138 jnz .nextrow 139 140 movq m3, [r4] 141 SPLAT4REGS 142 143 lea r3, [rsp+8] 144 mov r6, 8 145.nextcol: 146 DIAG4 r3, -8, 0, 8, 16, r0 147 add r3, 8 148 add r0, r2 149 dec r6 150 jnz .nextcol 151 152 mov rsp, r5 ; restore stack pointer 153 RET 154