mirror of
https://mirror.skon.top/https://github.com/FFmpeg/FFmpeg
synced 2026-04-20 21:00:41 +08:00
2d1358a84d
For bit depths <= 14, the result is saturated to 15 bits.
For bit depths > 14, the result is saturated to 19 bits.
x86_64:
chrRangeFromJpeg8_1920_c: 2126.5 2127.4 (1.00x)
chrRangeFromJpeg16_1920_c: 2331.4 2325.2 (1.00x)
chrRangeToJpeg8_1920_c: 3163.0 3166.9 (1.00x)
chrRangeToJpeg16_1920_c: 3163.7 2152.4 (1.47x)
lumRangeFromJpeg8_1920_c: 1262.2 1263.0 (1.00x)
lumRangeFromJpeg16_1920_c: 1079.5 1080.5 (1.00x)
lumRangeToJpeg8_1920_c: 1860.5 1886.8 (0.99x)
lumRangeToJpeg16_1920_c: 1910.2 1077.0 (1.77x)
aarch64 A55:
chrRangeFromJpeg8_1920_c: 28836.2 28835.2 (1.00x)
chrRangeFromJpeg16_1920_c: 28840.1 28839.8 (1.00x)
chrRangeToJpeg8_1920_c: 44196.2 23074.7 (1.92x)
chrRangeToJpeg16_1920_c: 36527.3 17318.9 (2.11x)
lumRangeFromJpeg8_1920_c: 15388.5 15389.7 (1.00x)
lumRangeFromJpeg16_1920_c: 15389.3 15388.2 (1.00x)
lumRangeToJpeg8_1920_c: 23069.7 19227.8 (1.20x)
lumRangeToJpeg16_1920_c: 19227.8 15387.0 (1.25x)
aarch64 A76:
chrRangeFromJpeg8_1920_c: 6334.7 6324.4 (1.00x)
chrRangeFromJpeg16_1920_c: 6336.0 6339.9 (1.00x)
chrRangeToJpeg8_1920_c: 11474.5 9656.0 (1.19x)
chrRangeToJpeg16_1920_c: 9640.5 6340.4 (1.52x)
lumRangeFromJpeg8_1920_c: 4453.2 4422.0 (1.01x)
lumRangeFromJpeg16_1920_c: 4414.2 4420.9 (1.00x)
lumRangeToJpeg8_1920_c: 6645.0 5949.1 (1.12x)
lumRangeToJpeg16_1920_c: 6005.2 4446.8 (1.35x)
NOTE: all simd optimizations for range_convert have been disabled
except for x86, which already had the same behaviour.
they will be re-enabled when they are fixed for each architecture.
134 lines
4.3 KiB
NASM
134 lines
4.3 KiB
NASM
;******************************************************************************
|
|
;* Copyright (c) 2024 Ramiro Polla
|
|
;*
|
|
;* 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
|
|
|
|
chr_to_mult: times 4 dw 4663, 0
|
|
chr_to_offset: times 4 dd -9289992
|
|
%define chr_to_shift 12
|
|
|
|
chr_from_mult: times 4 dw 1799, 0
|
|
chr_from_offset: times 4 dd 4081085
|
|
%define chr_from_shift 11
|
|
|
|
lum_to_mult: times 4 dw 19077, 0
|
|
lum_to_offset: times 4 dd -39057361
|
|
%define lum_to_shift 14
|
|
|
|
lum_from_mult: times 4 dw 14071, 0
|
|
lum_from_offset: times 4 dd 33561947
|
|
%define lum_from_shift 14
|
|
|
|
SECTION .text
|
|
|
|
;-----------------------------------------------------------------------------
|
|
; lumConvertRange
|
|
;
|
|
; void ff_lumRangeToJpeg_<opt>(int16_t *dst, int width);
|
|
; void ff_lumRangeFromJpeg_<opt>(int16_t *dst, int width);
|
|
;
|
|
;-----------------------------------------------------------------------------
|
|
|
|
%macro LUMCONVERTRANGE 4
|
|
cglobal %1, 2, 2, 5, dst, width
|
|
shl widthd, 1
|
|
VBROADCASTI128 m2, [%2]
|
|
VBROADCASTI128 m3, [%3]
|
|
pxor m4, m4
|
|
add dstq, widthq
|
|
neg widthq
|
|
.loop:
|
|
movu m0, [dstq+widthq]
|
|
punpckhwd m1, m0, m4
|
|
punpcklwd m0, m4
|
|
pmaddwd m0, m2
|
|
pmaddwd m1, m2
|
|
paddd m0, m3
|
|
paddd m1, m3
|
|
psrad m0, %4
|
|
psrad m1, %4
|
|
packssdw m0, m1
|
|
movu [dstq+widthq], m0
|
|
add widthq, mmsize
|
|
jl .loop
|
|
RET
|
|
%endmacro
|
|
|
|
;-----------------------------------------------------------------------------
|
|
; chrConvertRange
|
|
;
|
|
; void ff_chrRangeToJpeg_<opt>(int16_t *dstU, int16_t *dstV, int width);
|
|
; void ff_chrRangeFromJpeg_<opt>(int16_t *dstU, int16_t *dstV, int width);
|
|
;
|
|
;-----------------------------------------------------------------------------
|
|
|
|
%macro CHRCONVERTRANGE 4
|
|
cglobal %1, 3, 3, 7, dstU, dstV, width
|
|
shl widthd, 1
|
|
VBROADCASTI128 m4, [%2]
|
|
VBROADCASTI128 m5, [%3]
|
|
pxor m6, m6
|
|
add dstUq, widthq
|
|
add dstVq, widthq
|
|
neg widthq
|
|
.loop:
|
|
movu m0, [dstUq+widthq]
|
|
movu m2, [dstVq+widthq]
|
|
punpckhwd m1, m0, m6
|
|
punpckhwd m3, m2, m6
|
|
punpcklwd m0, m6
|
|
punpcklwd m2, m6
|
|
pmaddwd m0, m4
|
|
pmaddwd m1, m4
|
|
pmaddwd m2, m4
|
|
pmaddwd m3, m4
|
|
paddd m0, m5
|
|
paddd m1, m5
|
|
paddd m2, m5
|
|
paddd m3, m5
|
|
psrad m0, %4
|
|
psrad m1, %4
|
|
psrad m2, %4
|
|
psrad m3, %4
|
|
packssdw m0, m1
|
|
packssdw m2, m3
|
|
movu [dstUq+widthq], m0
|
|
movu [dstVq+widthq], m2
|
|
add widthq, mmsize
|
|
jl .loop
|
|
RET
|
|
%endmacro
|
|
|
|
INIT_XMM sse2
|
|
LUMCONVERTRANGE lumRangeToJpeg, lum_to_mult, lum_to_offset, lum_to_shift
|
|
CHRCONVERTRANGE chrRangeToJpeg, chr_to_mult, chr_to_offset, chr_to_shift
|
|
LUMCONVERTRANGE lumRangeFromJpeg, lum_from_mult, lum_from_offset, lum_from_shift
|
|
CHRCONVERTRANGE chrRangeFromJpeg, chr_from_mult, chr_from_offset, chr_from_shift
|
|
|
|
%if HAVE_AVX2_EXTERNAL
|
|
INIT_YMM avx2
|
|
LUMCONVERTRANGE lumRangeToJpeg, lum_to_mult, lum_to_offset, lum_to_shift
|
|
CHRCONVERTRANGE chrRangeToJpeg, chr_to_mult, chr_to_offset, chr_to_shift
|
|
LUMCONVERTRANGE lumRangeFromJpeg, lum_from_mult, lum_from_offset, lum_from_shift
|
|
CHRCONVERTRANGE chrRangeFromJpeg, chr_from_mult, chr_from_offset, chr_from_shift
|
|
%endif
|