Skip to content
Projects
Groups
Snippets
Help
Loading...
Sign in / Register
Toggle navigation
F
ffmpeg
Project
Project
Details
Activity
Cycle Analytics
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Charts
Issues
0
Issues
0
List
Board
Labels
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Charts
Packages
Packages
Wiki
Wiki
Snippets
Snippets
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Charts
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
submodule
ffmpeg
Commits
554d8190
Commit
554d8190
authored
Aug 23, 2014
by
Clément Bœsch
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
avutil/pixelutils: faster pixelutils_sad_16x16
501 to 439 decicycles. See
45c7f399
.
parent
f4dec0db
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
11 additions
and
5 deletions
+11
-5
pixelutils.asm
libavutil/x86/pixelutils.asm
+11
-5
No files found.
libavutil/x86/pixelutils.asm
View file @
554d8190
...
@@ -109,18 +109,24 @@ cglobal pixelutils_sad_16x16, 4,4,0, src1, stride1, src2, stride2
...
@@ -109,18 +109,24 @@ cglobal pixelutils_sad_16x16, 4,4,0, src1, stride1, src2, stride2
;-------------------------------------------------------------------------------
;-------------------------------------------------------------------------------
INIT_XMM
sse2
INIT_XMM
sse2
cglobal
pixelutils_sad_16x16
,
4
,
4
,
5
,
src1
,
stride1
,
src2
,
stride2
cglobal
pixelutils_sad_16x16
,
4
,
4
,
5
,
src1
,
stride1
,
src2
,
stride2
pxor
m4
,
m4
movu
m4
,
[src1q]
%rep
8
movu
m2
,
[src2q]
movu
m0
,
[src1q]
movu
m1
,
[
src1q
+
stride1q
]
movu
m1
,
[
src1q
+
stride1q
]
movu
m3
,
[
src2q
+
stride2q
]
psadbw
m4
,
m2
psadbw
m1
,
m3
paddw
m4
,
m1
%rep
7
lea
src1q
,
[
src1q
+
2
*
stride1q
]
lea
src2q
,
[
src2q
+
2
*
stride2q
]
movu
m0
,
[src1q]
movu
m2
,
[src2q]
movu
m2
,
[src2q]
movu
m1
,
[
src1q
+
stride1q
]
movu
m3
,
[
src2q
+
stride2q
]
movu
m3
,
[
src2q
+
stride2q
]
psadbw
m0
,
m2
psadbw
m0
,
m2
psadbw
m1
,
m3
psadbw
m1
,
m3
paddw
m4
,
m0
paddw
m4
,
m0
paddw
m4
,
m1
paddw
m4
,
m1
lea
src1q
,
[
src1q
+
2
*
stride1q
]
lea
src2q
,
[
src2q
+
2
*
stride2q
]
%endrep
%endrep
movhlps
m0
,
m4
movhlps
m0
,
m4
paddw
m4
,
m0
paddw
m4
,
m0
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment