1;******************************************************************************
2;* SIMD-optimized SVQ1 encoder functions
3;* Copyright (c) 2007 Loren Merritt
4;*
5;* This file is part of FFmpeg.
6;*
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.
11;*
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.
16;*
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
20;******************************************************************************
21
22%include "libavutil/x86/x86util.asm"
23
24SECTION_TEXT
25
26%macro SSD_INT8_VS_INT16 0
27cglobal ssd_int8_vs_int16, 3, 3, 3, pix1, pix2, size
28    pxor m0, m0
29.loop
30    sub       sizeq, 8
31    movq      m1, [pix1q + sizeq]
32    movu      m2, [pix2q + sizeq*2]
33%if mmsize == 8
34    movq      m3, [pix2q + sizeq*2 + mmsize]
35    punpckhbw m4, m1
36    punpcklbw m1, m1
37    psraw     m4, 8
38    psraw     m1, 8
39    psubw     m3, m4
40    psubw     m2, m1
41    pmaddwd   m3, m3
42    pmaddwd   m2, m2
43    paddd     m0, m3
44    paddd     m0, m2
45%else
46    punpcklbw m1, m1
47    psraw     m1, 8
48    psubw     m2, m1
49    pmaddwd   m2, m2
50    paddd     m0, m2
51%endif
52    jg .loop
53    HADDD     m0, m1
54    movd     eax, m0
55    RET
56%endmacro
57
58INIT_MMX mmx
59SSD_INT8_VS_INT16
60INIT_XMM sse2
61SSD_INT8_VS_INT16
62