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
    Preload reference area to an intermediate buffer in sub-pixel motion search · 20bd1446
    Yunqing Wang authored 
    In sub-pixel motion search, the search range is small(+/- 3 pixels).
Preload whole search area from reference buffer into a 32-byte
aligned buffer. Then in search, load reference data from this buffer
instead. This keeps data in cache, and reduces the crossing cache-
line penalty. For tulip clip, tests on Intel Core2 Quad machine(linux)
showed encoder speed improvement:
  3.4%   at --rt --cpu-used =-4
  2.8%   at --rt --cpu-used =-3
  2.3%   at --rt --cpu-used =-2
  2.2%   at --rt --cpu-used =-1

Test on Atom notebook showed only 1.1% speed improvement(speed=-4).
Test on Xeon machine also showed less improvement, since unaligned
data access latency is greatly reduced in newer cores.

Next, I will apply similar idea to other 2 sub-pixel search functions
for encoding speed > 4.

Make this change exclusively for x86 platforms.

Change-Id: Ia7bb9f56169eac0f01009fe2b2f2ab5b61d2eb2f
    20bd1446
sad_c.c 13.89 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 
#include "vpx_ports/config.h"
14 
#include "vpx/vpx_integer.h"
15
16 
unsigned int vp8_sad16x16_c(
17 
    const unsigned char *src_ptr,
18 
    int  src_stride,
19 
    const unsigned char *ref_ptr,
20 
    int  ref_stride,
21 
    int max_sad)
22 
{
23
24 
    int r, c;
25 
    unsigned int sad = 0;
26
27 
    for (r = 0; r < 16; r++)
28 
    {
29 
        for (c = 0; c < 16; c++)
30 
        {
31 
            sad += abs(src_ptr[c] - ref_ptr[c]);
32 
        }
33
34 
        src_ptr += src_stride;
35 
        ref_ptr += ref_stride;
36 
    }
37
38 
    return sad;
39 
}
40
41
42 
static __inline
43 
unsigned int sad_mx_n_c(
44 
    const unsigned char *src_ptr,
45 
    int  src_stride,
46 
    const unsigned char *ref_ptr,
47 
    int  ref_stride,
48 
    int m,
49 
    int n)
50 
{
51
52 
    int r, c;
53 
    unsigned int sad = 0;
54
55 
    for (r = 0; r < n; r++)
56 
    {
57 
        for (c = 0; c < m; c++)
58 
        {
59 
            sad += abs(src_ptr[c] - ref_ptr[c]);
60 
        }
61
62 
        src_ptr += src_stride;
63 
        ref_ptr += ref_stride;
64 
    }
65
66 
    return sad;
67 
}
68
69
70 
unsigned int vp8_sad8x8_c(
7172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140
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, 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);
141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210
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); 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); }
211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280
void vp8_sad8x16x3_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_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 ) {
281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350
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); 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); } /* Copy 2 macroblocks to a buffer */ void vp8_copy32xn_c( unsigned char *src_ptr, int src_stride, unsigned char *dst_ptr, int dst_stride, int height) {
351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403
int r; for (r = 0; r < height; r++) { #if !(CONFIG_FAST_UNALIGNED) dst_ptr[0] = src_ptr[0]; dst_ptr[1] = src_ptr[1]; dst_ptr[2] = src_ptr[2]; dst_ptr[3] = src_ptr[3]; dst_ptr[4] = src_ptr[4]; dst_ptr[5] = src_ptr[5]; dst_ptr[6] = src_ptr[6]; dst_ptr[7] = src_ptr[7]; dst_ptr[8] = src_ptr[8]; dst_ptr[9] = src_ptr[9]; dst_ptr[10] = src_ptr[10]; dst_ptr[11] = src_ptr[11]; dst_ptr[12] = src_ptr[12]; dst_ptr[13] = src_ptr[13]; dst_ptr[14] = src_ptr[14]; dst_ptr[15] = src_ptr[15]; dst_ptr[16] = src_ptr[16]; dst_ptr[17] = src_ptr[17]; dst_ptr[18] = src_ptr[18]; dst_ptr[19] = src_ptr[19]; dst_ptr[20] = src_ptr[20]; dst_ptr[21] = src_ptr[21]; dst_ptr[22] = src_ptr[22]; dst_ptr[23] = src_ptr[23]; dst_ptr[24] = src_ptr[24]; dst_ptr[25] = src_ptr[25]; dst_ptr[26] = src_ptr[26]; dst_ptr[27] = src_ptr[27]; dst_ptr[28] = src_ptr[28]; dst_ptr[29] = src_ptr[29]; dst_ptr[30] = src_ptr[30]; dst_ptr[31] = src_ptr[31]; #else ((uint32_t *)dst_ptr)[0] = ((uint32_t *)src_ptr)[0] ; ((uint32_t *)dst_ptr)[1] = ((uint32_t *)src_ptr)[1] ; ((uint32_t *)dst_ptr)[2] = ((uint32_t *)src_ptr)[2] ; ((uint32_t *)dst_ptr)[3] = ((uint32_t *)src_ptr)[3] ; ((uint32_t *)dst_ptr)[4] = ((uint32_t *)src_ptr)[4] ; ((uint32_t *)dst_ptr)[5] = ((uint32_t *)src_ptr)[5] ; ((uint32_t *)dst_ptr)[6] = ((uint32_t *)src_ptr)[6] ; ((uint32_t *)dst_ptr)[7] = ((uint32_t *)src_ptr)[7] ; #endif src_ptr += src_stride; dst_ptr += dst_stride; } }