diff options
Diffstat (limited to 'libavcodec/x86/pixblockdsp.asm')
-rw-r--r-- | libavcodec/x86/pixblockdsp.asm | 59 |
1 files changed, 40 insertions, 19 deletions
diff --git a/libavcodec/x86/pixblockdsp.asm b/libavcodec/x86/pixblockdsp.asm index 8712442..440fe29 100644 --- a/libavcodec/x86/pixblockdsp.asm +++ b/libavcodec/x86/pixblockdsp.asm @@ -4,20 +4,20 @@ ;* Copyright (c) 2000, 2001 Fabrice Bellard ;* Copyright (c) 2002-2004 Michael Niedermayer <michaelni@gmx.at> ;* -;* This file is part of Libav. +;* This file is part of FFmpeg. ;* -;* Libav is free software; you can redistribute it and/or +;* 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. ;* -;* Libav is distributed in the hope that it will be useful, +;* 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 Libav; if not, write to the Free Software +;* License along with FFmpeg; if not, write to the Free Software ;* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA ;***************************************************************************** @@ -50,7 +50,7 @@ cglobal get_pixels, 3,4 REP_RET INIT_XMM sse2 -cglobal get_pixels, 3, 4 +cglobal get_pixels, 3, 4, 5 lea r3, [r2*3] pxor m4, m4 movh m0, [r1] @@ -80,28 +80,49 @@ cglobal get_pixels, 3, 4 mova [r0+0x70], m3 RET -INIT_MMX mmx ; void ff_diff_pixels_mmx(int16_t *block, const uint8_t *s1, const uint8_t *s2, ; ptrdiff_t stride); -cglobal diff_pixels, 4,5 - pxor m7, m7 +%macro DIFF_PIXELS 0 +cglobal diff_pixels, 4,5,5 + pxor m4, m4 add r0, 128 mov r4, -128 .loop: - mova m0, [r1] - mova m2, [r2] - mova m1, m0 - mova m3, m2 - punpcklbw m0, m7 - punpckhbw m1, m7 - punpcklbw m2, m7 - punpckhbw m3, m7 + movq m0, [r1] + movq m2, [r2] +%if mmsize == 8 + movq m1, m0 + movq m3, m2 + punpcklbw m0, m4 + punpckhbw m1, m4 + punpcklbw m2, m4 + punpckhbw m3, m4 +%else + movq m1, [r1+r3] + movq m3, [r2+r3] + punpcklbw m0, m4 + punpcklbw m1, m4 + punpcklbw m2, m4 + punpcklbw m3, m4 +%endif psubw m0, m2 psubw m1, m3 mova [r0+r4+0], m0 - mova [r0+r4+8], m1 + mova [r0+r4+mmsize], m1 +%if mmsize == 8 add r1, r3 add r2, r3 - add r4, 16 +%else + lea r1, [r1+r3*2] + lea r2, [r2+r3*2] +%endif + add r4, 2 * mmsize jne .loop - REP_RET + RET +%endmacro + +INIT_MMX mmx +DIFF_PIXELS + +INIT_XMM sse2 +DIFF_PIXELS |