Skip to content
体验新版
项目
组织
正在加载...
登录
切换导航
打开侧边栏
小白菜888
Ffmpeg
提交
a1d0b6a2
F
Ffmpeg
项目概览
小白菜888
/
Ffmpeg
通知
3
Star
0
Fork
0
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
0
列表
看板
标记
里程碑
合并请求
0
DevOps
流水线
流水线任务
计划
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
F
Ffmpeg
项目概览
项目概览
详情
发布
仓库
仓库
文件
提交
分支
标签
贡献者
分支图
比较
Issue
0
Issue
0
列表
看板
标记
里程碑
合并请求
0
合并请求
0
Pages
DevOps
DevOps
流水线
流水线任务
计划
分析
分析
仓库分析
DevOps
Wiki
0
Wiki
成员
成员
收起侧边栏
关闭侧边栏
动态
分支图
创建新Issue
流水线任务
提交
Issue看板
体验新版 GitCode,发现更多精彩内容 >>
提交
a1d0b6a2
编写于
10月 02, 2007
作者:
D
Diego Biurrun
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
cosmetics: Fix AltiVec spelling.
Originally committed as revision 10639 to
svn://svn.ffmpeg.org/ffmpeg/trunk
上级
6006a689
变更
5
显示空白变更内容
内联
并排
Showing
5 changed file
with
7 addition
and
7 deletion
+7
-7
doc/optimization.txt
doc/optimization.txt
+2
-2
libavcodec/ppc/dsputil_altivec.c
libavcodec/ppc/dsputil_altivec.c
+1
-1
libavcodec/ppc/dsputil_ppc.c
libavcodec/ppc/dsputil_ppc.c
+1
-1
libavcodec/ppc/mpegvideo_ppc.c
libavcodec/ppc/mpegvideo_ppc.c
+2
-2
libavcodec/ppc/snow_altivec.c
libavcodec/ppc/snow_altivec.c
+1
-1
未找到文件。
doc/optimization.txt
浏览文件 @
a1d0b6a2
...
@@ -168,10 +168,10 @@ http://download.intel.com/design/intelxscale/27347302.pdf
...
@@ -168,10 +168,10 @@ http://download.intel.com/design/intelxscale/27347302.pdf
PowerPC-specific:
PowerPC-specific:
PowerPC32/Alti
v
ec PIM:
PowerPC32/Alti
V
ec PIM:
www.freescale.com/files/32bit/doc/ref_manual/ALTIVECPEM.pdf
www.freescale.com/files/32bit/doc/ref_manual/ALTIVECPEM.pdf
PowerPC32/Alti
v
ec PEM:
PowerPC32/Alti
V
ec PEM:
www.freescale.com/files/32bit/doc/ref_manual/ALTIVECPIM.pdf
www.freescale.com/files/32bit/doc/ref_manual/ALTIVECPIM.pdf
CELL/SPU:
CELL/SPU:
...
...
libavcodec/ppc/dsputil_altivec.c
浏览文件 @
a1d0b6a2
...
@@ -216,7 +216,7 @@ int sad16_xy2_altivec(void *v, uint8_t *pix1, uint8_t *pix2, int line_size, int
...
@@ -216,7 +216,7 @@ int sad16_xy2_altivec(void *v, uint8_t *pix1, uint8_t *pix2, int line_size, int
pix3iv
=
vec_perm
(
tv
[
0
],
tv
[
1
],
vec_lvsl
(
0
,
&
pix3
[
1
]));
pix3iv
=
vec_perm
(
tv
[
0
],
tv
[
1
],
vec_lvsl
(
0
,
&
pix3
[
1
]));
/*
/*
Note that Alti
v
ec does have vec_avg, but this works on vector pairs
Note that Alti
V
ec does have vec_avg, but this works on vector pairs
and rounds up. We could do avg(avg(a,b),avg(c,d)), but the rounding
and rounds up. We could do avg(avg(a,b),avg(c,d)), but the rounding
would mean that, for example, avg(3,0,0,1) = 2, when it should be 1.
would mean that, for example, avg(3,0,0,1) = 2, when it should be 1.
Instead, we have to split the pixel vectors into vectors of shorts,
Instead, we have to split the pixel vectors into vectors of shorts,
...
...
libavcodec/ppc/dsputil_ppc.c
浏览文件 @
a1d0b6a2
...
@@ -257,7 +257,7 @@ static void prefetch_ppc(void *mem, int stride, int h)
...
@@ -257,7 +257,7 @@ static void prefetch_ppc(void *mem, int stride, int h)
void
dsputil_init_ppc
(
DSPContext
*
c
,
AVCodecContext
*
avctx
)
void
dsputil_init_ppc
(
DSPContext
*
c
,
AVCodecContext
*
avctx
)
{
{
// Common optimizations whether Alti
v
ec is available or not
// Common optimizations whether Alti
V
ec is available or not
c
->
prefetch
=
prefetch_ppc
;
c
->
prefetch
=
prefetch_ppc
;
switch
(
check_dcbzl_effect
())
{
switch
(
check_dcbzl_effect
())
{
case
32
:
case
32
:
...
...
libavcodec/ppc/mpegvideo_ppc.c
浏览文件 @
a1d0b6a2
...
@@ -51,14 +51,14 @@ void MPV_common_init_ppc(MpegEncContext *s)
...
@@ -51,14 +51,14 @@ void MPV_common_init_ppc(MpegEncContext *s)
(((
long
)(
s
->
q_inter_matrix
)
&
0x0f
)
!=
0
))
(((
long
)(
s
->
q_inter_matrix
)
&
0x0f
)
!=
0
))
{
{
av_log
(
s
->
avctx
,
AV_LOG_INFO
,
"Internal Error: q-matrix blocks must be 16-byte aligned "
av_log
(
s
->
avctx
,
AV_LOG_INFO
,
"Internal Error: q-matrix blocks must be 16-byte aligned "
"to use Alti
vec DCT. Reverting to non-altiv
ec version.
\n
"
);
"to use Alti
Vec DCT. Reverting to non-AltiV
ec version.
\n
"
);
return
;
return
;
}
}
if
(((
long
)(
s
->
intra_scantable
.
inverse
)
&
0x0f
)
!=
0
)
if
(((
long
)(
s
->
intra_scantable
.
inverse
)
&
0x0f
)
!=
0
)
{
{
av_log
(
s
->
avctx
,
AV_LOG_INFO
,
"Internal Error: scan table blocks must be 16-byte aligned "
av_log
(
s
->
avctx
,
AV_LOG_INFO
,
"Internal Error: scan table blocks must be 16-byte aligned "
"to use Alti
vec DCT. Reverting to non-altiv
ec version.
\n
"
);
"to use Alti
Vec DCT. Reverting to non-AltiV
ec version.
\n
"
);
return
;
return
;
}
}
...
...
libavcodec/ppc/snow_altivec.c
浏览文件 @
a1d0b6a2
/*
/*
* Alti
vec
optimized snow DSP utils
* Alti
Vec-
optimized snow DSP utils
* Copyright (c) 2006 Luca Barbato <lu_zero@gentoo.org>
* Copyright (c) 2006 Luca Barbato <lu_zero@gentoo.org>
*
*
* This file is part of FFmpeg.
* This file is part of FFmpeg.
...
...
编辑
预览
Markdown
is supported
0%
请重试
或
添加新附件
.
添加附件
取消
You are about to add
0
people
to the discussion. Proceed with caution.
先完成此消息的编辑!
取消
想要评论请
注册
或
登录