mirror of
https://git.videolan.org/git/ffmpeg.git
synced 2024-09-07 00:20:09 +02:00
x86: qpel: Move fullpel and l2 functions to a separate file
This way, they can be shared between mpeg4qpel and h264qpel without requiring either one to be compiled unconditionally. Signed-off-by: Martin Storsjö <martin@martin.st>
This commit is contained in:
parent
0f59845708
commit
610b18e2e3
@ -76,3 +76,4 @@ YASM-OBJS += x86/dsputil.o \
|
||||
x86/fmtconvert.o \
|
||||
x86/hpeldsp.o \
|
||||
x86/mpeg4qpel.o \
|
||||
x86/qpel.o \
|
||||
|
@ -648,195 +648,3 @@ BSWAP32_BUF
|
||||
|
||||
INIT_XMM ssse3
|
||||
BSWAP32_BUF
|
||||
|
||||
|
||||
; FIXME: All of the code below should be put back in h264_qpel_8bit.asm.
|
||||
; Unfortunately it is unconditionally used from dsputil_mmx.c since 71155d7 ..
|
||||
|
||||
%macro op_avgh 3
|
||||
movh %3, %2
|
||||
pavgb %1, %3
|
||||
movh %2, %1
|
||||
%endmacro
|
||||
|
||||
%macro op_avg 2
|
||||
pavgb %1, %2
|
||||
mova %2, %1
|
||||
%endmacro
|
||||
|
||||
%macro op_puth 2-3
|
||||
movh %2, %1
|
||||
%endmacro
|
||||
|
||||
%macro op_put 2
|
||||
mova %2, %1
|
||||
%endmacro
|
||||
|
||||
; void pixels4_l2_mmxext(uint8_t *dst, uint8_t *src1, uint8_t *src2, int dstStride, int src1Stride, int h)
|
||||
%macro PIXELS4_L2 1
|
||||
%define OP op_%1h
|
||||
cglobal %1_pixels4_l2, 6,6
|
||||
movsxdifnidn r3, r3d
|
||||
movsxdifnidn r4, r4d
|
||||
test r5d, 1
|
||||
je .loop
|
||||
movd m0, [r1]
|
||||
movd m1, [r2]
|
||||
add r1, r4
|
||||
add r2, 4
|
||||
pavgb m0, m1
|
||||
OP m0, [r0], m3
|
||||
add r0, r3
|
||||
dec r5d
|
||||
.loop:
|
||||
mova m0, [r1]
|
||||
mova m1, [r1+r4]
|
||||
lea r1, [r1+2*r4]
|
||||
pavgb m0, [r2]
|
||||
pavgb m1, [r2+4]
|
||||
OP m0, [r0], m3
|
||||
OP m1, [r0+r3], m3
|
||||
lea r0, [r0+2*r3]
|
||||
mova m0, [r1]
|
||||
mova m1, [r1+r4]
|
||||
lea r1, [r1+2*r4]
|
||||
pavgb m0, [r2+8]
|
||||
pavgb m1, [r2+12]
|
||||
OP m0, [r0], m3
|
||||
OP m1, [r0+r3], m3
|
||||
lea r0, [r0+2*r3]
|
||||
add r2, 16
|
||||
sub r5d, 4
|
||||
jne .loop
|
||||
REP_RET
|
||||
%endmacro
|
||||
|
||||
INIT_MMX mmxext
|
||||
PIXELS4_L2 put
|
||||
PIXELS4_L2 avg
|
||||
|
||||
; void pixels8_l2_mmxext(uint8_t *dst, uint8_t *src1, uint8_t *src2, int dstStride, int src1Stride, int h)
|
||||
%macro PIXELS8_L2 1
|
||||
%define OP op_%1
|
||||
cglobal %1_pixels8_l2, 6,6
|
||||
movsxdifnidn r3, r3d
|
||||
movsxdifnidn r4, r4d
|
||||
test r5d, 1
|
||||
je .loop
|
||||
mova m0, [r1]
|
||||
mova m1, [r2]
|
||||
add r1, r4
|
||||
add r2, 8
|
||||
pavgb m0, m1
|
||||
OP m0, [r0]
|
||||
add r0, r3
|
||||
dec r5d
|
||||
.loop:
|
||||
mova m0, [r1]
|
||||
mova m1, [r1+r4]
|
||||
lea r1, [r1+2*r4]
|
||||
pavgb m0, [r2]
|
||||
pavgb m1, [r2+8]
|
||||
OP m0, [r0]
|
||||
OP m1, [r0+r3]
|
||||
lea r0, [r0+2*r3]
|
||||
mova m0, [r1]
|
||||
mova m1, [r1+r4]
|
||||
lea r1, [r1+2*r4]
|
||||
pavgb m0, [r2+16]
|
||||
pavgb m1, [r2+24]
|
||||
OP m0, [r0]
|
||||
OP m1, [r0+r3]
|
||||
lea r0, [r0+2*r3]
|
||||
add r2, 32
|
||||
sub r5d, 4
|
||||
jne .loop
|
||||
REP_RET
|
||||
%endmacro
|
||||
|
||||
INIT_MMX mmxext
|
||||
PIXELS8_L2 put
|
||||
PIXELS8_L2 avg
|
||||
|
||||
; void pixels16_l2_mmxext(uint8_t *dst, uint8_t *src1, uint8_t *src2, int dstStride, int src1Stride, int h)
|
||||
%macro PIXELS16_L2 1
|
||||
%define OP op_%1
|
||||
cglobal %1_pixels16_l2, 6,6
|
||||
movsxdifnidn r3, r3d
|
||||
movsxdifnidn r4, r4d
|
||||
test r5d, 1
|
||||
je .loop
|
||||
mova m0, [r1]
|
||||
mova m1, [r1+8]
|
||||
pavgb m0, [r2]
|
||||
pavgb m1, [r2+8]
|
||||
add r1, r4
|
||||
add r2, 16
|
||||
OP m0, [r0]
|
||||
OP m1, [r0+8]
|
||||
add r0, r3
|
||||
dec r5d
|
||||
.loop:
|
||||
mova m0, [r1]
|
||||
mova m1, [r1+8]
|
||||
add r1, r4
|
||||
pavgb m0, [r2]
|
||||
pavgb m1, [r2+8]
|
||||
OP m0, [r0]
|
||||
OP m1, [r0+8]
|
||||
add r0, r3
|
||||
mova m0, [r1]
|
||||
mova m1, [r1+8]
|
||||
add r1, r4
|
||||
pavgb m0, [r2+16]
|
||||
pavgb m1, [r2+24]
|
||||
OP m0, [r0]
|
||||
OP m1, [r0+8]
|
||||
add r0, r3
|
||||
add r2, 32
|
||||
sub r5d, 2
|
||||
jne .loop
|
||||
REP_RET
|
||||
%endmacro
|
||||
|
||||
INIT_MMX mmxext
|
||||
PIXELS16_L2 put
|
||||
PIXELS16_L2 avg
|
||||
|
||||
INIT_MMX mmxext
|
||||
; void pixels(uint8_t *block, const uint8_t *pixels, int line_size, int h)
|
||||
%macro PIXELS48 2
|
||||
%if %2 == 4
|
||||
%define OP movh
|
||||
%else
|
||||
%define OP mova
|
||||
%endif
|
||||
cglobal %1_pixels%2, 4,5
|
||||
movsxdifnidn r2, r2d
|
||||
lea r4, [r2*3]
|
||||
.loop:
|
||||
OP m0, [r1]
|
||||
OP m1, [r1+r2]
|
||||
OP m2, [r1+r2*2]
|
||||
OP m3, [r1+r4]
|
||||
lea r1, [r1+r2*4]
|
||||
%ifidn %1, avg
|
||||
pavgb m0, [r0]
|
||||
pavgb m1, [r0+r2]
|
||||
pavgb m2, [r0+r2*2]
|
||||
pavgb m3, [r0+r4]
|
||||
%endif
|
||||
OP [r0], m0
|
||||
OP [r0+r2], m1
|
||||
OP [r0+r2*2], m2
|
||||
OP [r0+r4], m3
|
||||
sub r3d, 4
|
||||
lea r0, [r0+r2*4]
|
||||
jne .loop
|
||||
RET
|
||||
%endmacro
|
||||
|
||||
PIXELS48 put, 4
|
||||
PIXELS48 avg, 4
|
||||
PIXELS48 put, 8
|
||||
PIXELS48 avg, 8
|
||||
|
@ -452,44 +452,3 @@ INIT_MMX mmxext
|
||||
AVG_PIXELS8_XY2
|
||||
INIT_MMX 3dnow
|
||||
AVG_PIXELS8_XY2
|
||||
|
||||
INIT_XMM sse2
|
||||
; void put_pixels16_sse2(uint8_t *block, const uint8_t *pixels, ptrdiff_t line_size, int h)
|
||||
cglobal put_pixels16, 4,5,4
|
||||
lea r4, [r2*3]
|
||||
.loop:
|
||||
movu m0, [r1]
|
||||
movu m1, [r1+r2]
|
||||
movu m2, [r1+r2*2]
|
||||
movu m3, [r1+r4]
|
||||
lea r1, [r1+r2*4]
|
||||
mova [r0], m0
|
||||
mova [r0+r2], m1
|
||||
mova [r0+r2*2], m2
|
||||
mova [r0+r4], m3
|
||||
sub r3d, 4
|
||||
lea r0, [r0+r2*4]
|
||||
jnz .loop
|
||||
REP_RET
|
||||
|
||||
; void avg_pixels16_sse2(uint8_t *block, const uint8_t *pixels, ptrdiff_t line_size, int h)
|
||||
cglobal avg_pixels16, 4,5,4
|
||||
lea r4, [r2*3]
|
||||
.loop:
|
||||
movu m0, [r1]
|
||||
movu m1, [r1+r2]
|
||||
movu m2, [r1+r2*2]
|
||||
movu m3, [r1+r4]
|
||||
lea r1, [r1+r2*4]
|
||||
pavgb m0, [r0]
|
||||
pavgb m1, [r0+r2]
|
||||
pavgb m2, [r0+r2*2]
|
||||
pavgb m3, [r0+r4]
|
||||
mova [r0], m0
|
||||
mova [r0+r2], m1
|
||||
mova [r0+r2*2], m2
|
||||
mova [r0+r4], m3
|
||||
sub r3d, 4
|
||||
lea r0, [r0+r2*4]
|
||||
jnz .loop
|
||||
REP_RET
|
||||
|
256
libavcodec/x86/qpel.asm
Normal file
256
libavcodec/x86/qpel.asm
Normal file
@ -0,0 +1,256 @@
|
||||
;******************************************************************************
|
||||
;* MMX optimized DSP utils
|
||||
;* Copyright (c) 2008 Loren Merritt
|
||||
;* Copyright (c) 2003-2013 Michael Niedermayer
|
||||
;* Copyright (c) 2013 Daniel Kang
|
||||
;*
|
||||
;* 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
|
||||
;******************************************************************************
|
||||
|
||||
%include "libavutil/x86/x86util.asm"
|
||||
|
||||
SECTION .text
|
||||
|
||||
%macro op_avgh 3
|
||||
movh %3, %2
|
||||
pavgb %1, %3
|
||||
movh %2, %1
|
||||
%endmacro
|
||||
|
||||
%macro op_avg 2
|
||||
pavgb %1, %2
|
||||
mova %2, %1
|
||||
%endmacro
|
||||
|
||||
%macro op_puth 2-3
|
||||
movh %2, %1
|
||||
%endmacro
|
||||
|
||||
%macro op_put 2
|
||||
mova %2, %1
|
||||
%endmacro
|
||||
|
||||
; void pixels4_l2_mmxext(uint8_t *dst, uint8_t *src1, uint8_t *src2, int dstStride, int src1Stride, int h)
|
||||
%macro PIXELS4_L2 1
|
||||
%define OP op_%1h
|
||||
cglobal %1_pixels4_l2, 6,6
|
||||
movsxdifnidn r3, r3d
|
||||
movsxdifnidn r4, r4d
|
||||
test r5d, 1
|
||||
je .loop
|
||||
movd m0, [r1]
|
||||
movd m1, [r2]
|
||||
add r1, r4
|
||||
add r2, 4
|
||||
pavgb m0, m1
|
||||
OP m0, [r0], m3
|
||||
add r0, r3
|
||||
dec r5d
|
||||
.loop:
|
||||
mova m0, [r1]
|
||||
mova m1, [r1+r4]
|
||||
lea r1, [r1+2*r4]
|
||||
pavgb m0, [r2]
|
||||
pavgb m1, [r2+4]
|
||||
OP m0, [r0], m3
|
||||
OP m1, [r0+r3], m3
|
||||
lea r0, [r0+2*r3]
|
||||
mova m0, [r1]
|
||||
mova m1, [r1+r4]
|
||||
lea r1, [r1+2*r4]
|
||||
pavgb m0, [r2+8]
|
||||
pavgb m1, [r2+12]
|
||||
OP m0, [r0], m3
|
||||
OP m1, [r0+r3], m3
|
||||
lea r0, [r0+2*r3]
|
||||
add r2, 16
|
||||
sub r5d, 4
|
||||
jne .loop
|
||||
REP_RET
|
||||
%endmacro
|
||||
|
||||
INIT_MMX mmxext
|
||||
PIXELS4_L2 put
|
||||
PIXELS4_L2 avg
|
||||
|
||||
; void pixels8_l2_mmxext(uint8_t *dst, uint8_t *src1, uint8_t *src2, int dstStride, int src1Stride, int h)
|
||||
%macro PIXELS8_L2 1
|
||||
%define OP op_%1
|
||||
cglobal %1_pixels8_l2, 6,6
|
||||
movsxdifnidn r3, r3d
|
||||
movsxdifnidn r4, r4d
|
||||
test r5d, 1
|
||||
je .loop
|
||||
mova m0, [r1]
|
||||
mova m1, [r2]
|
||||
add r1, r4
|
||||
add r2, 8
|
||||
pavgb m0, m1
|
||||
OP m0, [r0]
|
||||
add r0, r3
|
||||
dec r5d
|
||||
.loop:
|
||||
mova m0, [r1]
|
||||
mova m1, [r1+r4]
|
||||
lea r1, [r1+2*r4]
|
||||
pavgb m0, [r2]
|
||||
pavgb m1, [r2+8]
|
||||
OP m0, [r0]
|
||||
OP m1, [r0+r3]
|
||||
lea r0, [r0+2*r3]
|
||||
mova m0, [r1]
|
||||
mova m1, [r1+r4]
|
||||
lea r1, [r1+2*r4]
|
||||
pavgb m0, [r2+16]
|
||||
pavgb m1, [r2+24]
|
||||
OP m0, [r0]
|
||||
OP m1, [r0+r3]
|
||||
lea r0, [r0+2*r3]
|
||||
add r2, 32
|
||||
sub r5d, 4
|
||||
jne .loop
|
||||
REP_RET
|
||||
%endmacro
|
||||
|
||||
INIT_MMX mmxext
|
||||
PIXELS8_L2 put
|
||||
PIXELS8_L2 avg
|
||||
|
||||
; void pixels16_l2_mmxext(uint8_t *dst, uint8_t *src1, uint8_t *src2, int dstStride, int src1Stride, int h)
|
||||
%macro PIXELS16_L2 1
|
||||
%define OP op_%1
|
||||
cglobal %1_pixels16_l2, 6,6
|
||||
movsxdifnidn r3, r3d
|
||||
movsxdifnidn r4, r4d
|
||||
test r5d, 1
|
||||
je .loop
|
||||
mova m0, [r1]
|
||||
mova m1, [r1+8]
|
||||
pavgb m0, [r2]
|
||||
pavgb m1, [r2+8]
|
||||
add r1, r4
|
||||
add r2, 16
|
||||
OP m0, [r0]
|
||||
OP m1, [r0+8]
|
||||
add r0, r3
|
||||
dec r5d
|
||||
.loop:
|
||||
mova m0, [r1]
|
||||
mova m1, [r1+8]
|
||||
add r1, r4
|
||||
pavgb m0, [r2]
|
||||
pavgb m1, [r2+8]
|
||||
OP m0, [r0]
|
||||
OP m1, [r0+8]
|
||||
add r0, r3
|
||||
mova m0, [r1]
|
||||
mova m1, [r1+8]
|
||||
add r1, r4
|
||||
pavgb m0, [r2+16]
|
||||
pavgb m1, [r2+24]
|
||||
OP m0, [r0]
|
||||
OP m1, [r0+8]
|
||||
add r0, r3
|
||||
add r2, 32
|
||||
sub r5d, 2
|
||||
jne .loop
|
||||
REP_RET
|
||||
%endmacro
|
||||
|
||||
INIT_MMX mmxext
|
||||
PIXELS16_L2 put
|
||||
PIXELS16_L2 avg
|
||||
|
||||
INIT_MMX mmxext
|
||||
; void pixels(uint8_t *block, const uint8_t *pixels, int line_size, int h)
|
||||
%macro PIXELS48 2
|
||||
%if %2 == 4
|
||||
%define OP movh
|
||||
%else
|
||||
%define OP mova
|
||||
%endif
|
||||
cglobal %1_pixels%2, 4,5
|
||||
movsxdifnidn r2, r2d
|
||||
lea r4, [r2*3]
|
||||
.loop:
|
||||
OP m0, [r1]
|
||||
OP m1, [r1+r2]
|
||||
OP m2, [r1+r2*2]
|
||||
OP m3, [r1+r4]
|
||||
lea r1, [r1+r2*4]
|
||||
%ifidn %1, avg
|
||||
pavgb m0, [r0]
|
||||
pavgb m1, [r0+r2]
|
||||
pavgb m2, [r0+r2*2]
|
||||
pavgb m3, [r0+r4]
|
||||
%endif
|
||||
OP [r0], m0
|
||||
OP [r0+r2], m1
|
||||
OP [r0+r2*2], m2
|
||||
OP [r0+r4], m3
|
||||
sub r3d, 4
|
||||
lea r0, [r0+r2*4]
|
||||
jne .loop
|
||||
RET
|
||||
%endmacro
|
||||
|
||||
PIXELS48 put, 4
|
||||
PIXELS48 avg, 4
|
||||
PIXELS48 put, 8
|
||||
PIXELS48 avg, 8
|
||||
|
||||
|
||||
INIT_XMM sse2
|
||||
; void put_pixels16_sse2(uint8_t *block, const uint8_t *pixels, ptrdiff_t line_size, int h)
|
||||
cglobal put_pixels16, 4,5,4
|
||||
lea r4, [r2*3]
|
||||
.loop:
|
||||
movu m0, [r1]
|
||||
movu m1, [r1+r2]
|
||||
movu m2, [r1+r2*2]
|
||||
movu m3, [r1+r4]
|
||||
lea r1, [r1+r2*4]
|
||||
mova [r0], m0
|
||||
mova [r0+r2], m1
|
||||
mova [r0+r2*2], m2
|
||||
mova [r0+r4], m3
|
||||
sub r3d, 4
|
||||
lea r0, [r0+r2*4]
|
||||
jnz .loop
|
||||
REP_RET
|
||||
|
||||
; void avg_pixels16_sse2(uint8_t *block, const uint8_t *pixels, ptrdiff_t line_size, int h)
|
||||
cglobal avg_pixels16, 4,5,4
|
||||
lea r4, [r2*3]
|
||||
.loop:
|
||||
movu m0, [r1]
|
||||
movu m1, [r1+r2]
|
||||
movu m2, [r1+r2*2]
|
||||
movu m3, [r1+r4]
|
||||
lea r1, [r1+r2*4]
|
||||
pavgb m0, [r0]
|
||||
pavgb m1, [r0+r2]
|
||||
pavgb m2, [r0+r2*2]
|
||||
pavgb m3, [r0+r4]
|
||||
mova [r0], m0
|
||||
mova [r0+r2], m1
|
||||
mova [r0+r2*2], m2
|
||||
mova [r0+r4], m3
|
||||
sub r3d, 4
|
||||
lea r0, [r0+r2*4]
|
||||
jnz .loop
|
||||
REP_RET
|
Loading…
Reference in New Issue
Block a user