mirror of
https://github.com/xenia-project/FFmpeg.git
synced 2024-11-24 12:09:55 +00:00
d2ae5f77c6
Performance improvements: quant_bands: with: 681 decicycles in quant_bands, 8388453 runs, 155 skips without: 1190 decicycles in quant_bands, 8388386 runs, 222 skips Around 42% for the function Twoloop coder: abs_pow34: with/without: 7.82s/8.17s Around 4% for the entire encoder Both: with/without: 7.15s/8.17s Around 12% for the entire encoder Fast coder: abs_pow34: with/without: 3.40s/3.77s Around 10% for the entire encoder Both: with/without: 3.02s/3.77s Around 20% faster for the entire encoder Signed-off-by: Rostislav Pehlivanov <atomnuker@gmail.com> Tested-by: Michael Niedermayer <michael@niedermayer.cc> Reviewed-by: James Almer <jamrial@gmail.com>
87 lines
2.7 KiB
NASM
87 lines
2.7 KiB
NASM
;******************************************************************************
|
|
;* SIMD optimized AAC encoder DSP functions
|
|
;*
|
|
;* Copyright (C) 2016 Rostislav Pehlivanov <atomnuker@gmail.com>
|
|
;*
|
|
;* 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
|
|
|
|
float_abs_mask: times 4 dd 0x7fffffff
|
|
|
|
SECTION .text
|
|
|
|
;*******************************************************************
|
|
;void ff_abs_pow34(float *out, const float *in, const int size);
|
|
;*******************************************************************
|
|
INIT_XMM sse
|
|
cglobal abs_pow34, 3, 3, 3, out, in, size
|
|
mova m2, [float_abs_mask]
|
|
shl sizeq, 2
|
|
add inq, sizeq
|
|
add outq, sizeq
|
|
neg sizeq
|
|
.loop:
|
|
andps m0, m2, [inq+sizeq]
|
|
sqrtps m1, m0
|
|
mulps m0, m1
|
|
sqrtps m0, m0
|
|
mova [outq+sizeq], m0
|
|
add sizeq, mmsize
|
|
jl .loop
|
|
RET
|
|
|
|
;*******************************************************************
|
|
;void ff_aac_quantize_bands(int *out, const float *in, const float *scaled,
|
|
; int size, int is_signed, int maxval, const float Q34,
|
|
; const float rounding)
|
|
;*******************************************************************
|
|
INIT_XMM sse2
|
|
cglobal aac_quantize_bands, 5, 5, 6, out, in, scaled, size, is_signed, maxval, Q34, rounding
|
|
%if UNIX64 == 0
|
|
movss m0, Q34m
|
|
movss m1, roundingm
|
|
cvtsi2ss m3, dword maxvalm
|
|
%else
|
|
cvtsi2ss m3, maxvald
|
|
%endif
|
|
shufps m0, m0, 0
|
|
shufps m1, m1, 0
|
|
shufps m3, m3, 0
|
|
shl is_signedd, 31
|
|
movd m4, is_signedd
|
|
shufps m4, m4, 0
|
|
shl sized, 2
|
|
add inq, sizeq
|
|
add outq, sizeq
|
|
add scaledq, sizeq
|
|
neg sizeq
|
|
.loop:
|
|
mulps m2, m0, [scaledq+sizeq]
|
|
addps m2, m1
|
|
minps m2, m3
|
|
andps m5, m4, [inq+sizeq]
|
|
orps m2, m5
|
|
cvttps2dq m2, m2
|
|
mova [outq+sizeq], m2
|
|
add sizeq, mmsize
|
|
jl .loop
|
|
RET
|