;******************************************************************************
+;*
+;* Copyright (c) 2000-2001 Fabrice Bellard <fabrice@bellard.org>
+;* Copyright (c) Nick Kurshev <nickols_k@mail.ru>
+;* Copyright (c) 2002 Michael Niedermayer <michaelni@gmx.at>
+;* Copyright (c) 2002 Zdenek Kabelac <kabi@informatics.muni.cz>
+;* Copyright (c) 2013 Daniel Kang
+;*
;* MMX optimized hpel functions
;*
-;* This file is part of Libav.
+;* This file is part of FFmpeg.
;*
-;* Libav is free software; you can redistribute it and/or
+;* 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.
;*
-;* Libav is distributed in the hope that it will be useful,
+;* 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 Libav; if not, write to the Free Software
+;* License along with FFmpeg; if not, write to the Free Software
;* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
;******************************************************************************
SECTION_TEXT
-; put_pixels8_x2(uint8_t *block, const uint8_t *pixels, int line_size, int h)
+; put_pixels8_x2(uint8_t *block, const uint8_t *pixels, ptrdiff_t line_size, int h)
%macro PUT_PIXELS8_X2 0
cglobal put_pixels8_x2, 4,5
- movsxdifnidn r2, r2d
lea r4, [r2*2]
.loop:
mova m0, [r1]
PUT_PIXELS8_X2
-; put_pixels16_x2(uint8_t *block, const uint8_t *pixels, int line_size, int h)
+; put_pixels16_x2(uint8_t *block, const uint8_t *pixels, ptrdiff_t line_size, int h)
%macro PUT_PIXELS_16 0
cglobal put_pixels16_x2, 4,5
- movsxdifnidn r2, r2d
lea r4, [r2*2]
.loop:
mova m0, [r1]
PUT_PIXELS_16
-; put_no_rnd_pixels8_x2(uint8_t *block, const uint8_t *pixels, int line_size, int h)
+; put_no_rnd_pixels8_x2(uint8_t *block, const uint8_t *pixels, ptrdiff_t line_size, int h)
%macro PUT_NO_RND_PIXELS8_X2 0
cglobal put_no_rnd_pixels8_x2, 4,5
mova m6, [pb_1]
- movsxdifnidn r2, r2d
lea r4, [r2*2]
.loop:
mova m0, [r1]
PUT_NO_RND_PIXELS8_X2
-; put_no_rnd_pixels8_x2_exact(uint8_t *block, const uint8_t *pixels, int line_size, int h)
+; put_no_rnd_pixels8_x2_exact(uint8_t *block, const uint8_t *pixels, ptrdiff_t line_size, int h)
%macro PUT_NO_RND_PIXELS8_X2_EXACT 0
cglobal put_no_rnd_pixels8_x2_exact, 4,5
- movsxdifnidn r2, r2d
lea r4, [r2*3]
pcmpeqb m6, m6
.loop:
PUT_NO_RND_PIXELS8_X2_EXACT
-; put_pixels8_y2(uint8_t *block, const uint8_t *pixels, int line_size, int h)
+; put_pixels8_y2(uint8_t *block, const uint8_t *pixels, ptrdiff_t line_size, int h)
%macro PUT_PIXELS8_Y2 0
cglobal put_pixels8_y2, 4,5
- movsxdifnidn r2, r2d
lea r4, [r2*2]
mova m0, [r1]
sub r0, r2
PUT_PIXELS8_Y2
-; put_no_rnd_pixels8_y2(uint8_t *block, const uint8_t *pixels, int line_size, int h)
+; put_no_rnd_pixels8_y2(uint8_t *block, const uint8_t *pixels, ptrdiff_t line_size, int h)
%macro PUT_NO_RND_PIXELS8_Y2 0
cglobal put_no_rnd_pixels8_y2, 4,5
mova m6, [pb_1]
- movsxdifnidn r2, r2d
lea r4, [r2+r2]
mova m0, [r1]
sub r0, r2
PUT_NO_RND_PIXELS8_Y2
-; put_no_rnd_pixels8_y2_exact(uint8_t *block, const uint8_t *pixels, int line_size, int h)
+; put_no_rnd_pixels8_y2_exact(uint8_t *block, const uint8_t *pixels, ptrdiff_t line_size, int h)
%macro PUT_NO_RND_PIXELS8_Y2_EXACT 0
cglobal put_no_rnd_pixels8_y2_exact, 4,5
- movsxdifnidn r2, r2d
lea r4, [r2*3]
mova m0, [r1]
pcmpeqb m6, m6
PUT_NO_RND_PIXELS8_Y2_EXACT
-; avg_pixels8(uint8_t *block, const uint8_t *pixels, int line_size, int h)
+; avg_pixels8(uint8_t *block, const uint8_t *pixels, ptrdiff_t line_size, int h)
%macro AVG_PIXELS8 0
cglobal avg_pixels8, 4,5
- movsxdifnidn r2, r2d
lea r4, [r2*2]
.loop:
mova m0, [r0]
AVG_PIXELS8
-; avg_pixels8_x2(uint8_t *block, const uint8_t *pixels, int line_size, int h)
+; avg_pixels8_x2(uint8_t *block, const uint8_t *pixels, ptrdiff_t line_size, int h)
%macro AVG_PIXELS8_X2 0
cglobal avg_pixels8_x2, 4,5
- movsxdifnidn r2, r2d
lea r4, [r2*2]
.loop:
mova m0, [r1]
AVG_PIXELS8_X2
-; avg_pixels8_y2(uint8_t *block, const uint8_t *pixels, int line_size, int h)
+; avg_pixels8_y2(uint8_t *block, const uint8_t *pixels, ptrdiff_t line_size, int h)
%macro AVG_PIXELS8_Y2 0
cglobal avg_pixels8_y2, 4,5
- movsxdifnidn r2, r2d
lea r4, [r2*2]
mova m0, [r1]
sub r0, r2
AVG_PIXELS8_Y2
-; avg_pixels8_xy2(uint8_t *block, const uint8_t *pixels, int line_size, int h)
+; avg_pixels8_xy2(uint8_t *block, const uint8_t *pixels, ptrdiff_t line_size, int h)
%macro AVG_PIXELS8_XY2 0
cglobal avg_pixels8_xy2, 4,5
mova m6, [pb_1]
- movsxdifnidn r2, r2d
lea r4, [r2*2]
mova m0, [r1]
pavgb m0, [r1+1]
pavgb m2, [r0]
pavgb m1, [r0+r2]
mova [r0], m2
- mova [r0+r2], m2
+ mova [r0+r2], m1
add r0, r4
sub r3d, 4
jne .loop
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