9c978f243a
benchmarked on sandybridge x86_64: 1358232 decicycles in flac_lpc_32_c 1244575 decicycles in flac_lpc_32_sse4, James Almer's patch 650045 decicycles in flac_lpc_32_sse4, this patch I haven't tested the edgecases such as odd block lengths odd block length tested-by: James Almer <jamrial@gmail.com> Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
72 lines
2.0 KiB
NASM
72 lines
2.0 KiB
NASM
;******************************************************************************
|
|
;* FLAC DSP SIMD optimizations
|
|
;*
|
|
;* Copyright (C) 2014 Loren Merritt
|
|
;*
|
|
;* 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
|
|
|
|
INIT_XMM sse4
|
|
cglobal flac_lpc_32, 5,6,5, decoded, coeffs, pred_order, qlevel, len, j
|
|
sub lend, pred_orderd
|
|
jle .ret
|
|
lea decodedq, [decodedq+pred_orderq*4-8]
|
|
lea coeffsq, [coeffsq+pred_orderq*4]
|
|
neg pred_orderq
|
|
movd m4, qlevelm
|
|
ALIGN 16
|
|
.loop_sample:
|
|
movd m0, [decodedq+pred_orderq*4+8]
|
|
add decodedq, 8
|
|
movd m1, [coeffsq+pred_orderq*4]
|
|
pxor m2, m2
|
|
pxor m3, m3
|
|
lea jq, [pred_orderq+1]
|
|
test jq, jq
|
|
jz .end_order
|
|
.loop_order:
|
|
pmuldq m0, m1
|
|
paddq m2, m0
|
|
movd m0, [decodedq+jq*4]
|
|
pmuldq m1, m0
|
|
paddq m3, m1
|
|
movd m1, [coeffsq+jq*4]
|
|
inc jq
|
|
jl .loop_order
|
|
.end_order:
|
|
pmuldq m0, m1
|
|
paddq m2, m0
|
|
psrlq m2, m4
|
|
movd m0, [decodedq]
|
|
paddd m0, m2
|
|
movd [decodedq], m0
|
|
sub lend, 2
|
|
jl .ret
|
|
pmuldq m1, m0
|
|
paddq m3, m1
|
|
psrlq m3, m4
|
|
movd m1, [decodedq+4]
|
|
paddd m1, m3
|
|
movd [decodedq+4], m1
|
|
jg .loop_sample
|
|
.ret:
|
|
REP_RET
|