1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
|
# Pure Data Packet mmx routine.
# Copyright (c) by Tom Schouten <tom@zwizwa.be>
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# This program 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 General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
#
.globl pixel_mul_s16
.type pixel_mul_s16,@function
# simple add
# void pixel_mul_s16(int *left, int *right, int nb_4pixel_vectors)
pixel_mul_s16:
pushl %ebp
movl %esp, %ebp
push %esi
push %edi
movl 8(%ebp), %edi # left array
movl 12(%ebp), %esi # right array
movl 16(%ebp), %ecx # pixel count
.align 16
.loop_mix:
# prefetch 128(%esi)
movq (%esi), %mm1 # load right 4 pixels from memory
movq (%edi), %mm0 # load 4 left pixels from memory
pmulhw %mm1, %mm0 # mul
psllw $1, %mm0 # fixed point shift correction
movq %mm0, (%edi)
addl $8, %esi
addl $8, %edi
decl %ecx
jnz .loop_mix # loop
emms
pop %edi
pop %esi
leave
ret
|
