2
* Alpha optimized DSP utils
3
* Copyright (c) 2002 Falk Hueffner <falk@debian.org>
5
* This file is part of FFmpeg.
7
* FFmpeg is free software; you can redistribute it and/or
8
* modify it under the terms of the GNU Lesser General Public
9
* License as published by the Free Software Foundation; either
10
* version 2.1 of the License, or (at your option) any later version.
12
* FFmpeg is distributed in the hope that it will be useful,
13
* but WITHOUT ANY WARRANTY; without even the implied warranty of
14
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
15
* Lesser General Public License for more details.
17
* You should have received a copy of the GNU Lesser General Public
18
* License along with FFmpeg; if not, write to the Free Software
19
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
23
* These functions are scheduled for pca56. They should work
24
* reasonably on ev6, though.
29
/* Some nicer register names. */
34
/* Danger: these overlap with the argument list and the return value */
45
/************************************************************************
46
* void put_pixels_axp_asm(uint8_t *block, const uint8_t *pixels,
47
* int line_size, int h)
50
.globl put_pixels_axp_asm
51
.ent put_pixels_axp_asm
140
.end put_pixels_axp_asm
142
/************************************************************************
143
* void put_pixels_clamped_mvi_asm(const DCTELEM *block, uint8_t *pixels,
147
.globl put_pixels_clamped_mvi_asm
148
.ent put_pixels_clamped_mvi_asm
149
put_pixels_clamped_mvi_asm:
155
jsr AT, (AT), _mcount
159
lda t9, 8 # loop counter
160
zap t8, 0xaa, t8 # 00ff00ff00ff00ff
195
.end put_pixels_clamped_mvi_asm
197
/************************************************************************
198
* void add_pixels_clamped_mvi_asm(const DCTELEM *block, uint8_t *pixels,
202
.globl add_pixels_clamped_mvi_asm
203
.ent add_pixels_clamped_mvi_asm
204
add_pixels_clamped_mvi_asm:
210
jsr AT, (AT), _mcount
219
xor tg, t0, tg # 0x8000800080008000
220
zap t1, 0xaa, tf # 0x00ff00ff00ff00ff
223
1: ldl t1, 0(a1) # pix0 (try to hit cache line soon)
225
addq a1, a2, te # pixels += line_size
226
ldq t0, 0(a0) # shorts0
228
ldl t7, 0(te) # pix2 (try to hit cache line soon)
230
ldq t3, 8(a0) # shorts1
231
ldq t6, 16(a0) # shorts2
233
ldq t9, 24(a0) # shorts3
234
unpkbw t1, t1 # 0 0 (quarter/op no.)
241
addq t0, t1, t0 # 0 3
246
maxsw4 t0, zero, t0 # 0 5
250
minsw4 t0, tf, t0 # 0 6
251
addq t3, t4, t3 # 1 3
255
maxsw4 t3, zero, t3 # 1 5
256
addq t6, t7, t6 # 2 3
260
minsw4 t3, tf, t3 # 1 6
263
maxsw4 t6, zero, t6 # 2 5
264
addq t9, ta, t9 # 3 3
266
minsw4 t6, tf, t6 # 2 6
269
maxsw4 t9, zero, t9 # 3 5
270
lda a0, 32(a0) # block += 16;
273
minsw4 t9, tf, t9 # 3 6
279
addq te, a2, a1 # pixels += line_size
285
.end add_pixels_clamped_mvi_asm