Skip to content
GitLab
Select Git revision
  • v1.14.0-linphone default
  • v1.12.0-linphone
  • v1.9.0-linphone
  • v1.7.0-linphone
  • feature/update_to_v1.9.0-linphone
  • feature/uwp_nuget
  • m68-3440
  • m66-3359
  • sandbox/luoyi@google.com/convolve
  • mandarinduck
  • sandbox/wangch@google.com/vp9
  • v1.6.1_linphone
  • linphone-android
  • longtailedduck
  • m56-2924
  • nextgenv2
  • m54-2840
  • sandbox/yaowu@google.com/mergeaom
  • khakicampbell
  • m52-2743
  • v1.9.0
  • v1.9.0-rc1
  • v1.8.2
  • v1.8.1
  • v1.8.0
  • v1.7.0
  • v1.6.1
  • v1.6.0
  • v1.5.0
  • v1.4.0
  • v1.3.0
  • v1.2.0
  • v1.1.0
  • v1.0.0
  • v0.9.7-p1
  • v0.9.7
  • v0.9.6
  • v0.9.5
  • v0.9.2
  • v0.9.1
Find file BlameHistoryPermalink
  • Yunqing Wang's avatar
    Full search SAD function optimization in SSE4.1 · 71ecb5d7
    Yunqing Wang authored 
    Use mpsadbw, and calculate 8 sad at once. Function list:
vp8_sad16x16x8_sse4
vp8_sad16x8x8_sse4
vp8_sad8x16x8_sse4
vp8_sad8x8x8_sse4
vp8_sad4x4x8_sse4

(test clip: tulip)
For best quality mode, this gave encoder a 5% performance boost.
For good quality mode with speed=1, this gave encoder a 3%
performance boost.

Change-Id: I083b5a39d39144f88dcbccbef95da6498e490134
    71ecb5d7
sad_c.c 11.94 KiB
1 
/*
2 
 *  Copyright (c) 2010 The WebM project authors. All Rights Reserved.
3 
 *
4 
 *  Use of this source code is governed by a BSD-style license
5 
 *  that can be found in the LICENSE file in the root of the source
6 
 *  tree. An additional intellectual property rights grant can be found
7 
 *  in the file PATENTS.  All contributing project authors may
8 
 *  be found in the AUTHORS file in the root of the source tree.
9 
 */
10
11
12 
#include <stdlib.h>
13
14 
unsigned int vp8_sad16x16_c(
15 
    const unsigned char *src_ptr,
16 
    int  src_stride,
17 
    const unsigned char *ref_ptr,
18 
    int  ref_stride,
19 
    int max_sad)
20 
{
21
22 
    int r, c;
23 
    unsigned int sad = 0;
24
25 
    for (r = 0; r < 16; r++)
26 
    {
27 
        for (c = 0; c < 16; c++)
28 
        {
29 
            sad += abs(src_ptr[c] - ref_ptr[c]);
30 
        }
31
32 
        src_ptr += src_stride;
33 
        ref_ptr += ref_stride;
34 
    }
35
36 
    return sad;
37 
}
38
39
40 
static __inline
41 
unsigned int sad_mx_n_c(
42 
    const unsigned char *src_ptr,
43 
    int  src_stride,
44 
    const unsigned char *ref_ptr,
45 
    int  ref_stride,
46 
    int m,
47 
    int n)
48 
{
49
50 
    int r, c;
51 
    unsigned int sad = 0;
52
53 
    for (r = 0; r < n; r++)
54 
    {
55 
        for (c = 0; c < m; c++)
56 
        {
57 
            sad += abs(src_ptr[c] - ref_ptr[c]);
58 
        }
59
60 
        src_ptr += src_stride;
61 
        ref_ptr += ref_stride;
62 
    }
63
64 
    return sad;
65 
}
66
67
68 
unsigned int vp8_sad8x8_c(
69 
    const unsigned char *src_ptr,
70 
    int  src_stride,
7172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140
const unsigned char *ref_ptr, int ref_stride, int max_sad) { return sad_mx_n_c(src_ptr, src_stride, ref_ptr, ref_stride, 8, 8); } unsigned int vp8_sad16x8_c( const unsigned char *src_ptr, int src_stride, const unsigned char *ref_ptr, int ref_stride, int max_sad) { return sad_mx_n_c(src_ptr, src_stride, ref_ptr, ref_stride, 16, 8); } unsigned int vp8_sad8x16_c( const unsigned char *src_ptr, int src_stride, const unsigned char *ref_ptr, int ref_stride, int max_sad) { return sad_mx_n_c(src_ptr, src_stride, ref_ptr, ref_stride, 8, 16); } unsigned int vp8_sad4x4_c( const unsigned char *src_ptr, int src_stride, const unsigned char *ref_ptr, int ref_stride, int max_sad) { return sad_mx_n_c(src_ptr, src_stride, ref_ptr, ref_stride, 4, 4); } void vp8_sad16x16x3_c( const unsigned char *src_ptr, int src_stride, const unsigned char *ref_ptr, int ref_stride, unsigned int *sad_array ) { sad_array[0] = vp8_sad16x16_c(src_ptr, src_stride, ref_ptr , ref_stride, 0x7fffffff); sad_array[1] = vp8_sad16x16_c(src_ptr, src_stride, ref_ptr + 1, ref_stride, 0x7fffffff); sad_array[2] = vp8_sad16x16_c(src_ptr, src_stride, ref_ptr + 2, ref_stride, 0x7fffffff); } void vp8_sad16x16x8_c( const unsigned char *src_ptr, int src_stride, const unsigned char *ref_ptr, int ref_stride, unsigned short *sad_array ) { sad_array[0] = (unsigned short)vp8_sad16x16_c(src_ptr, src_stride, ref_ptr , ref_stride, 0x7fffffff); sad_array[1] = (unsigned short)vp8_sad16x16_c(src_ptr, src_stride, ref_ptr + 1, ref_stride, 0x7fffffff); sad_array[2] = (unsigned short)vp8_sad16x16_c(src_ptr, src_stride, ref_ptr + 2, ref_stride, 0x7fffffff); sad_array[3] = (unsigned short)vp8_sad16x16_c(src_ptr, src_stride, ref_ptr + 3 , ref_stride, 0x7fffffff);
141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210
sad_array[4] = (unsigned short)vp8_sad16x16_c(src_ptr, src_stride, ref_ptr + 4, ref_stride, 0x7fffffff); sad_array[5] = (unsigned short)vp8_sad16x16_c(src_ptr, src_stride, ref_ptr + 5, ref_stride, 0x7fffffff); sad_array[6] = (unsigned short)vp8_sad16x16_c(src_ptr, src_stride, ref_ptr + 6 , ref_stride, 0x7fffffff); sad_array[7] = (unsigned short)vp8_sad16x16_c(src_ptr, src_stride, ref_ptr + 7, ref_stride, 0x7fffffff); } void vp8_sad16x8x3_c( const unsigned char *src_ptr, int src_stride, const unsigned char *ref_ptr, int ref_stride, unsigned int *sad_array ) { sad_array[0] = vp8_sad16x8_c(src_ptr, src_stride, ref_ptr , ref_stride, 0x7fffffff); sad_array[1] = vp8_sad16x8_c(src_ptr, src_stride, ref_ptr + 1, ref_stride, 0x7fffffff); sad_array[2] = vp8_sad16x8_c(src_ptr, src_stride, ref_ptr + 2, ref_stride, 0x7fffffff); } void vp8_sad16x8x8_c( const unsigned char *src_ptr, int src_stride, const unsigned char *ref_ptr, int ref_stride, unsigned short *sad_array ) { sad_array[0] = (unsigned short)vp8_sad16x8_c(src_ptr, src_stride, ref_ptr , ref_stride, 0x7fffffff); sad_array[1] = (unsigned short)vp8_sad16x8_c(src_ptr, src_stride, ref_ptr + 1, ref_stride, 0x7fffffff); sad_array[2] = (unsigned short)vp8_sad16x8_c(src_ptr, src_stride, ref_ptr + 2, ref_stride, 0x7fffffff); sad_array[3] = (unsigned short)vp8_sad16x8_c(src_ptr, src_stride, ref_ptr + 3 , ref_stride, 0x7fffffff); sad_array[4] = (unsigned short)vp8_sad16x8_c(src_ptr, src_stride, ref_ptr + 4, ref_stride, 0x7fffffff); sad_array[5] = (unsigned short)vp8_sad16x8_c(src_ptr, src_stride, ref_ptr + 5, ref_stride, 0x7fffffff); sad_array[6] = (unsigned short)vp8_sad16x8_c(src_ptr, src_stride, ref_ptr + 6 , ref_stride, 0x7fffffff); sad_array[7] = (unsigned short)vp8_sad16x8_c(src_ptr, src_stride, ref_ptr + 7, ref_stride, 0x7fffffff); } void vp8_sad8x8x3_c( const unsigned char *src_ptr, int src_stride, const unsigned char *ref_ptr, int ref_stride, unsigned int *sad_array ) { sad_array[0] = vp8_sad8x8_c(src_ptr, src_stride, ref_ptr , ref_stride, 0x7fffffff); sad_array[1] = vp8_sad8x8_c(src_ptr, src_stride, ref_ptr + 1, ref_stride, 0x7fffffff); sad_array[2] = vp8_sad8x8_c(src_ptr, src_stride, ref_ptr + 2, ref_stride, 0x7fffffff); } void vp8_sad8x8x8_c( const unsigned char *src_ptr, int src_stride, const unsigned char *ref_ptr, int ref_stride, unsigned short *sad_array ) { sad_array[0] = (unsigned short)vp8_sad8x8_c(src_ptr, src_stride, ref_ptr , ref_stride, 0x7fffffff); sad_array[1] = (unsigned short)vp8_sad8x8_c(src_ptr, src_stride, ref_ptr + 1, ref_stride, 0x7fffffff); sad_array[2] = (unsigned short)vp8_sad8x8_c(src_ptr, src_stride, ref_ptr + 2, ref_stride, 0x7fffffff); sad_array[3] = (unsigned short)vp8_sad8x8_c(src_ptr, src_stride, ref_ptr + 3 , ref_stride, 0x7fffffff); sad_array[4] = (unsigned short)vp8_sad8x8_c(src_ptr, src_stride, ref_ptr + 4, ref_stride, 0x7fffffff); sad_array[5] = (unsigned short)vp8_sad8x8_c(src_ptr, src_stride, ref_ptr + 5, ref_stride, 0x7fffffff); sad_array[6] = (unsigned short)vp8_sad8x8_c(src_ptr, src_stride, ref_ptr + 6 , ref_stride, 0x7fffffff); sad_array[7] = (unsigned short)vp8_sad8x8_c(src_ptr, src_stride, ref_ptr + 7, ref_stride, 0x7fffffff); } void vp8_sad8x16x3_c( const unsigned char *src_ptr,
211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280
int src_stride, const unsigned char *ref_ptr, int ref_stride, unsigned int *sad_array ) { sad_array[0] = vp8_sad8x16_c(src_ptr, src_stride, ref_ptr , ref_stride, 0x7fffffff); sad_array[1] = vp8_sad8x16_c(src_ptr, src_stride, ref_ptr + 1, ref_stride, 0x7fffffff); sad_array[2] = vp8_sad8x16_c(src_ptr, src_stride, ref_ptr + 2, ref_stride, 0x7fffffff); } void vp8_sad8x16x8_c( const unsigned char *src_ptr, int src_stride, const unsigned char *ref_ptr, int ref_stride, unsigned short *sad_array ) { sad_array[0] = (unsigned short)vp8_sad8x16_c(src_ptr, src_stride, ref_ptr , ref_stride, 0x7fffffff); sad_array[1] = (unsigned short)vp8_sad8x16_c(src_ptr, src_stride, ref_ptr + 1, ref_stride, 0x7fffffff); sad_array[2] = (unsigned short)vp8_sad8x16_c(src_ptr, src_stride, ref_ptr + 2, ref_stride, 0x7fffffff); sad_array[3] = (unsigned short)vp8_sad8x16_c(src_ptr, src_stride, ref_ptr + 3 , ref_stride, 0x7fffffff); sad_array[4] = (unsigned short)vp8_sad8x16_c(src_ptr, src_stride, ref_ptr + 4, ref_stride, 0x7fffffff); sad_array[5] = (unsigned short)vp8_sad8x16_c(src_ptr, src_stride, ref_ptr + 5, ref_stride, 0x7fffffff); sad_array[6] = (unsigned short)vp8_sad8x16_c(src_ptr, src_stride, ref_ptr + 6 , ref_stride, 0x7fffffff); sad_array[7] = (unsigned short)vp8_sad8x16_c(src_ptr, src_stride, ref_ptr + 7, ref_stride, 0x7fffffff); } void vp8_sad4x4x3_c( const unsigned char *src_ptr, int src_stride, const unsigned char *ref_ptr, int ref_stride, unsigned int *sad_array ) { sad_array[0] = vp8_sad4x4_c(src_ptr, src_stride, ref_ptr , ref_stride, 0x7fffffff); sad_array[1] = vp8_sad4x4_c(src_ptr, src_stride, ref_ptr + 1, ref_stride, 0x7fffffff); sad_array[2] = vp8_sad4x4_c(src_ptr, src_stride, ref_ptr + 2, ref_stride, 0x7fffffff); } void vp8_sad4x4x8_c( const unsigned char *src_ptr, int src_stride, const unsigned char *ref_ptr, int ref_stride, unsigned short *sad_array ) { sad_array[0] = (unsigned short)vp8_sad4x4_c(src_ptr, src_stride, ref_ptr , ref_stride, 0x7fffffff); sad_array[1] = (unsigned short)vp8_sad4x4_c(src_ptr, src_stride, ref_ptr + 1, ref_stride, 0x7fffffff); sad_array[2] = (unsigned short)vp8_sad4x4_c(src_ptr, src_stride, ref_ptr + 2, ref_stride, 0x7fffffff); sad_array[3] = (unsigned short)vp8_sad4x4_c(src_ptr, src_stride, ref_ptr + 3 , ref_stride, 0x7fffffff); sad_array[4] = (unsigned short)vp8_sad4x4_c(src_ptr, src_stride, ref_ptr + 4, ref_stride, 0x7fffffff); sad_array[5] = (unsigned short)vp8_sad4x4_c(src_ptr, src_stride, ref_ptr + 5, ref_stride, 0x7fffffff); sad_array[6] = (unsigned short)vp8_sad4x4_c(src_ptr, src_stride, ref_ptr + 6 , ref_stride, 0x7fffffff); sad_array[7] = (unsigned short)vp8_sad4x4_c(src_ptr, src_stride, ref_ptr + 7, ref_stride, 0x7fffffff); } void vp8_sad16x16x4d_c( const unsigned char *src_ptr, int src_stride, unsigned char *ref_ptr[], int ref_stride, unsigned int *sad_array ) { sad_array[0] = vp8_sad16x16_c(src_ptr, src_stride, ref_ptr[0], ref_stride, 0x7fffffff); sad_array[1] = vp8_sad16x16_c(src_ptr, src_stride, ref_ptr[1], ref_stride, 0x7fffffff);
281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340
sad_array[2] = vp8_sad16x16_c(src_ptr, src_stride, ref_ptr[2], ref_stride, 0x7fffffff); sad_array[3] = vp8_sad16x16_c(src_ptr, src_stride, ref_ptr[3], ref_stride, 0x7fffffff); } void vp8_sad16x8x4d_c( const unsigned char *src_ptr, int src_stride, unsigned char *ref_ptr[], int ref_stride, unsigned int *sad_array ) { sad_array[0] = vp8_sad16x8_c(src_ptr, src_stride, ref_ptr[0], ref_stride, 0x7fffffff); sad_array[1] = vp8_sad16x8_c(src_ptr, src_stride, ref_ptr[1], ref_stride, 0x7fffffff); sad_array[2] = vp8_sad16x8_c(src_ptr, src_stride, ref_ptr[2], ref_stride, 0x7fffffff); sad_array[3] = vp8_sad16x8_c(src_ptr, src_stride, ref_ptr[3], ref_stride, 0x7fffffff); } void vp8_sad8x8x4d_c( const unsigned char *src_ptr, int src_stride, unsigned char *ref_ptr[], int ref_stride, unsigned int *sad_array ) { sad_array[0] = vp8_sad8x8_c(src_ptr, src_stride, ref_ptr[0], ref_stride, 0x7fffffff); sad_array[1] = vp8_sad8x8_c(src_ptr, src_stride, ref_ptr[1], ref_stride, 0x7fffffff); sad_array[2] = vp8_sad8x8_c(src_ptr, src_stride, ref_ptr[2], ref_stride, 0x7fffffff); sad_array[3] = vp8_sad8x8_c(src_ptr, src_stride, ref_ptr[3], ref_stride, 0x7fffffff); } void vp8_sad8x16x4d_c( const unsigned char *src_ptr, int src_stride, unsigned char *ref_ptr[], int ref_stride, unsigned int *sad_array ) { sad_array[0] = vp8_sad8x16_c(src_ptr, src_stride, ref_ptr[0], ref_stride, 0x7fffffff); sad_array[1] = vp8_sad8x16_c(src_ptr, src_stride, ref_ptr[1], ref_stride, 0x7fffffff); sad_array[2] = vp8_sad8x16_c(src_ptr, src_stride, ref_ptr[2], ref_stride, 0x7fffffff); sad_array[3] = vp8_sad8x16_c(src_ptr, src_stride, ref_ptr[3], ref_stride, 0x7fffffff); } void vp8_sad4x4x4d_c( const unsigned char *src_ptr, int src_stride, unsigned char *ref_ptr[], int ref_stride, unsigned int *sad_array ) { sad_array[0] = vp8_sad4x4_c(src_ptr, src_stride, ref_ptr[0], ref_stride, 0x7fffffff); sad_array[1] = vp8_sad4x4_c(src_ptr, src_stride, ref_ptr[1], ref_stride, 0x7fffffff); sad_array[2] = vp8_sad4x4_c(src_ptr, src_stride, ref_ptr[2], ref_stride, 0x7fffffff); sad_array[3] = vp8_sad4x4_c(src_ptr, src_stride, ref_ptr[3], ref_stride, 0x7fffffff); }