Chiebot-Mirror
/
FFmpeg
mirror of https://github.com/FFmpeg/FFmpeg.git
8
0
Fork 0
Code Issues Projects Releases Wiki Activity
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
35890 Commits
37 Branches
400 Tags
465 MiB
Tag: Branch: Tree: 9a16359c38
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from '9a16359c38'
${ noResults }
FFmpeg/libavcodec/x86/sbrdsp.asm

115 lines
3.2 KiB
Raw Normal View History Unescape

SBR DSP x86: implement SSE sbr_sum_square_sse The 32bits targets have been compiled with -mfpmath=sse for proper reference. sbr_sum_square C /32bits: 82c (unrolled)/102c C /64bits: 69c (unrolled)/82c SSE/32bits: 42c SSE/64bits: 31c Use of SSE4.1 dpps to perform the final sum is slower. Not unrolling to perform 8 operations in a loop yields 10 more cycles. Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
13 years ago
;******************************************************************************
;* AAC Spectral Band Replication decoding functions
;* Copyright (C) 2012 Christophe Gisquet <christophe.gisquet@gmail.com>
;*
;* This file is part of Libav.
;*
;* Libav 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.
;*
;* Libav 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 Libav; if not, write to the Free Software
;* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
;******************************************************************************
x86: yasm: Use complete source path for macro helper %includes This is more consistent with the way we handle C #includes and it simplifies the build system.
13 years ago
%include "libavutil/x86/x86util.asm"
SBR DSP x86: implement SSE sbr_sum_square_sse The 32bits targets have been compiled with -mfpmath=sse for proper reference. sbr_sum_square C /32bits: 82c (unrolled)/102c C /64bits: 69c (unrolled)/82c SSE/32bits: 42c SSE/64bits: 31c Use of SSE4.1 dpps to perform the final sum is slower. Not unrolling to perform 8 operations in a loop yields 10 more cycles. Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
13 years ago
;SECTION_RODATA
SECTION .text
INIT_XMM sse
cglobal sbr_sum_square, 2, 3, 6
mov r2, r1
xorps m0, m0
xorps m1, m1
sar r2, 3
jz .prepare
.loop:
movu m2, [r0 + 0]
movu m3, [r0 + 16]
movu m4, [r0 + 32]
movu m5, [r0 + 48]
mulps m2, m2
mulps m3, m3
mulps m4, m4
mulps m5, m5
addps m0, m2
addps m1, m3
addps m0, m4
addps m1, m5
add r0, 64
dec r2
jnz .loop
.prepare:
and r1, 7
sar r1, 1
jz .end
; len is a multiple of 2, thus there are at least 4 elements to process
.endloop:
movu m2, [r0]
add r0, 16
mulps m2, m2
dec r1
addps m0, m2
jnz .endloop
.end:
addps m0, m1
movhlps m2, m0
addps m0, m2
movss m1, m0
shufps m0, m0, 1
addss m0, m1
%if ARCH_X86_64 == 0
dsputil x86: use SSE float instruction instead of SSE2 integer equivalent All the more required since the users are pure SSE functions. Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
13 years ago
movss r0m, m0
SBR DSP x86: implement SSE sbr_sum_square_sse The 32bits targets have been compiled with -mfpmath=sse for proper reference. sbr_sum_square C /32bits: 82c (unrolled)/102c C /64bits: 69c (unrolled)/82c SSE/32bits: 42c SSE/64bits: 31c Use of SSE4.1 dpps to perform the final sum is slower. Not unrolling to perform 8 operations in a loop yields 10 more cycles. Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
13 years ago
fld dword r0m
%endif
RET
SBR DSP x86: implement SSE sbr_hf_g_filt Unrolling the main loop to process, instead of 4 elements: - 8: minor gain of 2 cycles (not worth the extra object size) - 2: loss of 8 cycles. Assigning STEP to a register is a loss. Output address (Y) is almost always unaligned. Timings: - C (32/64 bits): 117/109 cycles - SSE: 57 cycles Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
13 years ago
%define STEP 40*4*2
cglobal sbr_hf_g_filt, 5, 6, 5
lea r1, [r1 + 8*r4] ; offset by ixh elements into X_high
mov r5, r3
and r3, 0xFC
lea r2, [r2 + r3*4]
lea r0, [r0 + r3*8]
neg r3
aacsbr: handle m_max values smaller than 4. Prevents a signflip in the counter, and a subsequent crash because of overreads/overwrites. Found-by: Mateusz "j00ru" Jurczyk and Gynvael Coldwind CC: libav-stable@libav.org
13 years ago
jz .loop1
SBR DSP x86: implement SSE sbr_hf_g_filt Unrolling the main loop to process, instead of 4 elements: - 8: minor gain of 2 cycles (not worth the extra object size) - 2: loss of 8 cycles. Assigning STEP to a register is a loss. Output address (Y) is almost always unaligned. Timings: - C (32/64 bits): 117/109 cycles - SSE: 57 cycles Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
13 years ago
.loop4:
sbrdsp.asm: convert all instructions to float/SSE ones. Since the values are floats, using the float operations makes sense, improves performance on some CPUs and makes the code SSE compatible instead of needing SSE2. Based on suggestion by Jason. Signed-off-by: Reimar Döffinger <Reimar.Doeffinger@gmx.de> Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
13 years ago
movlps m0, [r2 + 4*r3 + 0]
movlps m1, [r2 + 4*r3 + 8]
movlps m2, [r1 + 0*STEP]
movlps m3, [r1 + 2*STEP]
SBR DSP x86: implement SSE sbr_hf_g_filt Unrolling the main loop to process, instead of 4 elements: - 8: minor gain of 2 cycles (not worth the extra object size) - 2: loss of 8 cycles. Assigning STEP to a register is a loss. Output address (Y) is almost always unaligned. Timings: - C (32/64 bits): 117/109 cycles - SSE: 57 cycles Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
13 years ago
movhps m2, [r1 + 1*STEP]
movhps m3, [r1 + 3*STEP]
sbrdsp.asm: convert all instructions to float/SSE ones. Since the values are floats, using the float operations makes sense, improves performance on some CPUs and makes the code SSE compatible instead of needing SSE2. Based on suggestion by Jason. Signed-off-by: Reimar Döffinger <Reimar.Doeffinger@gmx.de> Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
13 years ago
unpcklps m0, m0
unpcklps m1, m1
SBR DSP x86: implement SSE sbr_hf_g_filt Unrolling the main loop to process, instead of 4 elements: - 8: minor gain of 2 cycles (not worth the extra object size) - 2: loss of 8 cycles. Assigning STEP to a register is a loss. Output address (Y) is almost always unaligned. Timings: - C (32/64 bits): 117/109 cycles - SSE: 57 cycles Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
13 years ago
mulps m0, m2
mulps m1, m3
movu [r0 + 8*r3 + 0], m0
movu [r0 + 8*r3 + 16], m1
add r1, 4*STEP
add r3, 4
jnz .loop4
and r5, 3 ; number of single element loops
jz .end
.loop1: ; element 0 and 1 can be computed at the same time
movss m0, [r2]
sbrdsp.asm: convert all instructions to float/SSE ones. Since the values are floats, using the float operations makes sense, improves performance on some CPUs and makes the code SSE compatible instead of needing SSE2. Based on suggestion by Jason. Signed-off-by: Reimar Döffinger <Reimar.Doeffinger@gmx.de> Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
13 years ago
movlps m2, [r1]
unpcklps m0, m0
SBR DSP x86: implement SSE sbr_hf_g_filt Unrolling the main loop to process, instead of 4 elements: - 8: minor gain of 2 cycles (not worth the extra object size) - 2: loss of 8 cycles. Assigning STEP to a register is a loss. Output address (Y) is almost always unaligned. Timings: - C (32/64 bits): 117/109 cycles - SSE: 57 cycles Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
13 years ago
mulps m2, m0
SBR DSP: fix SSE code to not use SSE2 instructions. movq from SSE register _to_ memory is an SSE2 instruction. Use the SSE movlps function instead that does the same thing. Signed-off-by: Reimar Döffinger <Reimar.Doeffinger@gmx.de> Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
13 years ago
movlps [r0], m2
SBR DSP x86: implement SSE sbr_hf_g_filt Unrolling the main loop to process, instead of 4 elements: - 8: minor gain of 2 cycles (not worth the extra object size) - 2: loss of 8 cycles. Assigning STEP to a register is a loss. Output address (Y) is almost always unaligned. Timings: - C (32/64 bits): 117/109 cycles - SSE: 57 cycles Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
13 years ago
add r0, 8
add r2, 4
add r1, STEP
dec r5
jnz .loop1
.end:
RET