ffmpeg/libavcodec/aarch64/ac3dsp_neon.S
Martin Storsjö 359b6a7f8a aarch64/ac3dsp: simplify the end of ff_ac3_sum_square_butterfly_float_neon
Before:                           Cortex A53     A72     A78      M1
ac3_sum_square_bufferfly_float_neon:  1005.7   516.5   224.5   194.0
After:
ac3_sum_square_bufferfly_float_neon:   981.7   504.5   223.2   189.5

Signed-off-by: J. Dekker <jdek@itanimul.li>
2024-04-09 16:50:49 +02:00

112 lines
3.8 KiB
ArmAsm

/*
* Copyright (c) 2011 Mans Rullgard <mans@mansr.com>
* Copyright (c) 2024 Geoff Hill <geoff@geoffhill.org>
*
* This file is part of FFmpeg.
*
* FFmpeg is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 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 General Public License for more details.
*
* You should have received a copy of the GNU 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/aarch64/asm.S"
function ff_ac3_exponent_min_neon, export=1
cbz w1, 3f
1: ld1 {v0.16b}, [x0]
mov w3, w1
add x4, x0, #256
2: ld1 {v1.16b}, [x4]
umin v0.16b, v0.16b, v1.16b
add x4, x4, #256
subs w3, w3, #1
b.gt 2b
st1 {v0.16b}, [x0], #16
subs w2, w2, #16
b.gt 1b
3: ret
endfunc
function ff_ac3_extract_exponents_neon, export=1
movi v1.4s, #8
1: ld1 {v0.4s}, [x1], #16
abs v0.4s, v0.4s
clz v0.4s, v0.4s
sub v0.4s, v0.4s, v1.4s
xtn v0.4h, v0.4s
xtn v0.8b, v0.8h
st1 {v0.s}[0], [x0], #4
subs w2, w2, #4
b.gt 1b
ret
endfunc
function ff_float_to_fixed24_neon, export=1
1: ld1 {v0.4s, v1.4s}, [x1], #32
fcvtzs v0.4s, v0.4s, #24
ld1 {v2.4s, v3.4s}, [x1], #32
fcvtzs v1.4s, v1.4s, #24
fcvtzs v2.4s, v2.4s, #24
st1 {v0.4s, v1.4s}, [x0], #32
fcvtzs v3.4s, v3.4s, #24
st1 {v2.4s, v3.4s}, [x0], #32
subs w2, w2, #16
b.ne 1b
ret
endfunc
function ff_ac3_sum_square_butterfly_int32_neon, export=1
movi v0.2d, #0
movi v1.2d, #0
movi v2.2d, #0
movi v3.2d, #0
1: ld1 {v4.2s}, [x1], #8
ld1 {v5.2s}, [x2], #8
add v6.2s, v4.2s, v5.2s
sub v7.2s, v4.2s, v5.2s
smlal v0.2d, v4.2s, v4.2s
smlal v1.2d, v5.2s, v5.2s
smlal v2.2d, v6.2s, v6.2s
smlal v3.2d, v7.2s, v7.2s
subs w3, w3, #2
b.gt 1b
addp d0, v0.2d
addp d1, v1.2d
addp d2, v2.2d
addp d3, v3.2d
st1 {v0.1d-v3.1d}, [x0]
ret
endfunc
function ff_ac3_sum_square_butterfly_float_neon, export=1
movi v0.4s, #0
movi v1.4s, #0
movi v2.4s, #0
movi v3.4s, #0
1: ld1 {v30.4s}, [x1], #16
ld1 {v31.4s}, [x2], #16
fadd v16.4s, v30.4s, v31.4s
fsub v17.4s, v30.4s, v31.4s
fmla v0.4s, v30.4s, v30.4s
fmla v1.4s, v31.4s, v31.4s
fmla v2.4s, v16.4s, v16.4s
fmla v3.4s, v17.4s, v17.4s
subs w3, w3, #4
b.gt 1b
faddp v0.4s, v0.4s, v1.4s
faddp v2.4s, v2.4s, v3.4s
faddp v0.4s, v0.4s, v2.4s
st1 {v0.4s}, [x0]
ret
endfunc