mirror of
https://github.com/FFmpeg/FFmpeg.git
synced 2026-08-10 17:14:41 +00:00
23d3116af9
If the subpel part of the horizontal component of the motion vector is 1/4 or 3/4, the MPEG-4 qpel motion compensation first computes the mc for the corresponding motion vector with 1/2 horizontal subpel part and then averages this with the left (for 1/4) or the right (for 3/4) source pixel. These two stages are currently performed in two different functions, involving a stack buffer as intermediate. This means that horizontal prediction for every function with a 1/4 or 3/4 horizontal subpel mv is more expensive code-size wise (and also performance-wise) as it involves two calls. Given that the horizontal lowpass functions are not that long, adding combinations of h_lowpass+l2 actually reduces binary size: An increase of 1136B in the asm files is more than offset by size reductions in the wrappers: 1968B here when not using stack protection, 2256B when using stack protection. Of course it also improves performance. Old benchmarks: avg_qpel_pixels_tab[0][1]_ssse3: 106.9 ( 8.69x) avg_qpel_pixels_tab[0][3]_ssse3: 105.5 ( 8.84x) avg_qpel_pixels_tab[0][5]_ssse3: 226.9 ( 8.57x) avg_qpel_pixels_tab[0][7]_ssse3: 231.1 ( 8.38x) avg_qpel_pixels_tab[0][9]_ssse3: 217.8 ( 9.04x) avg_qpel_pixels_tab[0][11]_ssse3: 214.9 ( 9.32x) avg_qpel_pixels_tab[0][13]_ssse3: 227.1 ( 8.48x) avg_qpel_pixels_tab[0][15]_ssse3: 236.1 ( 8.02x) New benchmarks: avg_qpel_pixels_tab[0][1]_ssse3: 96.7 ( 9.65x) avg_qpel_pixels_tab[0][3]_ssse3: 96.6 ( 9.73x) avg_qpel_pixels_tab[0][5]_ssse3: 225.8 ( 8.61x) avg_qpel_pixels_tab[0][7]_ssse3: 228.4 ( 8.51x) avg_qpel_pixels_tab[0][9]_ssse3: 217.1 ( 9.05x) avg_qpel_pixels_tab[0][11]_ssse3: 217.8 ( 9.32x) avg_qpel_pixels_tab[0][13]_ssse3: 227.2 ( 8.54x) avg_qpel_pixels_tab[0][15]_ssse3: 220.5 ( 8.72x) Note: The l2 functions are also used for vertical lowpass functions, yet given that they are much bigger, duplicating them would lead to massive code size increase. Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>
73 lines
2.1 KiB
NASM
73 lines
2.1 KiB
NASM
;******************************************************************************
|
|
;* SIMD-optimized quarterpel functions
|
|
;* Copyright (c) 2008 Loren Merritt
|
|
;* Copyright (c) 2003-2013 Michael Niedermayer
|
|
;* Copyright (c) 2013 Daniel Kang
|
|
;*
|
|
;* 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 .text
|
|
|
|
%macro op_avg 2
|
|
pavgb %1, %2
|
|
mova %2, %1
|
|
%endmacro
|
|
|
|
%macro op_put 2
|
|
mova %2, %1
|
|
%endmacro
|
|
|
|
%macro PIXELS_L2 2 ; avg vs put, size
|
|
%define OP op_%1
|
|
; void ff_avg/put_pixels8x8_l2_mmxext(uint8_t *dst, const uint8_t *src1, const uint8_t *src2,
|
|
; ptrdiff_t dstStride, ptrdiff_t src1Stride)
|
|
cglobal %1_pixels%2x%2_l2, 5,6,2
|
|
mov r5d, %2
|
|
.loop:
|
|
movu m0, [r1]
|
|
movu m1, [r1+r4]
|
|
lea r1, [r1+2*r4]
|
|
pavgb m0, [r2]
|
|
pavgb m1, [r2+mmsize]
|
|
OP m0, [r0]
|
|
OP m1, [r0+r3]
|
|
lea r0, [r0+2*r3]
|
|
movu m0, [r1]
|
|
movu m1, [r1+r4]
|
|
lea r1, [r1+2*r4]
|
|
pavgb m0, [r2+2*mmsize]
|
|
pavgb m1, [r2+3*mmsize]
|
|
OP m0, [r0]
|
|
OP m1, [r0+r3]
|
|
lea r0, [r0+2*r3]
|
|
add r2, 4*mmsize
|
|
sub r5d, 4
|
|
jne .loop
|
|
RET
|
|
%endmacro
|
|
|
|
INIT_MMX mmxext
|
|
PIXELS_L2 put, 8
|
|
PIXELS_L2 avg, 8
|
|
|
|
INIT_XMM sse2
|
|
PIXELS_L2 put, 16
|
|
PIXELS_L2 avg, 16
|