summaryrefslogtreecommitdiffstats
path: root/media/base/yuv_row_linux.cc
Commit message (Collapse)AuthorAgeFilesLines
* Optimized version of bilinear video scaler. It is about 2 times faster than ↵sergeyu@chromium.org2010-04-091-699/+0
| | | | | | | | | | | Skia that is currently used for video scaling. BUG=19113 TEST=none Review URL: http://codereview.chromium.org/1556021 git-svn-id: svn://svn.chromium.org/chrome/trunk/src@44119 0039d316-1c4b-4281-b951-d872f2087c98
* -fPIC buildable version of yuv for 64 bit linux.fbarchard@chromium.org2009-10-161-97/+106
| | | | | | | | | BUG=25070 TEST=add -fPIC to gcc. Old code failed to build. New code builds with 64 bit. Review URL: http://codereview.chromium.org/269106 git-svn-id: svn://svn.chromium.org/chrome/trunk/src@29329 0039d316-1c4b-4281-b951-d872f2087c98
* MMX2 improvements on Linux 64 bit.fbarchard@chromium.org2009-10-151-47/+51
| | | | | | | | | | | MMX2 to avoid EMMS LEA to remove 2 instructions from Scale loop shuffle to remove one instruction sub at top of loop avoids one branch Review URL: http://codereview.chromium.org/269088 git-svn-id: svn://svn.chromium.org/chrome/trunk/src@29107 0039d316-1c4b-4281-b951-d872f2087c98
* Reverting 29019.finnur@chromium.org2009-10-141-38/+40
| | | | | | | | | Reverting due to test_shell_tests Linux 64 release failures TBR: fbarchard Review URL: http://codereview.chromium.org/275021 git-svn-id: svn://svn.chromium.org/chrome/trunk/src@29031 0039d316-1c4b-4281-b951-d872f2087c98
* Use lea to remove 2 instructions from the inner loop of YUV Scale.fbarchard@chromium.org2009-10-141-40/+38
| | | | | | | | | | | Use MMX2 to remove emms. unittest has code to time yuv scale and convert 100 times so it takes about 1 second... useful for catching performance issues. But the code is disabled. BUG=23263 TEST=media_unittest should pass and run much faster: 28% faster than 32 bit version. Review URL: http://codereview.chromium.org/273047 git-svn-id: svn://svn.chromium.org/chrome/trunk/src@29019 0039d316-1c4b-4281-b951-d872f2087c98
* 64 bit linux yuvfbarchard@chromium.org2009-10-131-39/+119
| | | | | | | | BUG=23263 TEST=media_unittest should pass and run much faster: faster than 32 bit even. Review URL: http://codereview.chromium.org/268029 git-svn-id: svn://svn.chromium.org/chrome/trunk/src@28802 0039d316-1c4b-4281-b951-d872f2087c98
* Off by one in YUV scale caused an extra read (mostly harmless)fbarchard@chromium.org2009-09-221-7/+1
| | | | | | | | | BUG=22594 TEST=none Review URL: http://codereview.chromium.org/212043 git-svn-id: svn://svn.chromium.org/chrome/trunk/src@26797 0039d316-1c4b-4281-b951-d872f2087c98
* Reverting 26070 from media tests failuremhm@chromium.org2009-09-121-12/+12
| | | | | | | | | | | | | | | | | | 6 failed media_unittests - CreateFrame - Clamp - YV12 - YV16 - YV12 - YV16 TBR=fbarchard BUG=none TEST=none Review URL: http://codereview.chromium.org/202068 git-svn-id: svn://svn.chromium.org/chrome/trunk/src@26074 0039d316-1c4b-4281-b951-d872f2087c98
* Mac Assembler and Linux cleanupfbarchard@chromium.org2009-09-121-12/+12
| | | | | | | | | BUG=20749 TEST=play mac video... it should be time times faster rendering and visibly smoother Review URL: http://codereview.chromium.org/180066 git-svn-id: svn://svn.chromium.org/chrome/trunk/src@26070 0039d316-1c4b-4281-b951-d872f2087c98
* mmx for linux yuv convert function.fbarchard@chromium.org2009-09-011-10/+421
| | | | | | | | | BUG=18449,20718 TEST=play a video on linux without scaling and it should go 4 times faster than with scaling. Review URL: http://codereview.chromium.org/174442 git-svn-id: svn://svn.chromium.org/chrome/trunk/src@25001 0039d316-1c4b-4281-b951-d872f2087c98
* A quick fix for YUV overflow on Mac concern.fbarchard@chromium.org2009-08-181-8/+17
| | | | | | | | | BUG=18672 TEST=run videos in debug mode and watch for DCHECK. Review URL: http://codereview.chromium.org/170019 git-svn-id: svn://svn.chromium.org/chrome/trunk/src@23599 0039d316-1c4b-4281-b951-d872f2087c98
* YUV with clipping.fbarchard@chromium.org2009-05-181-75/+13
| | | | | | | | | | | | All functions do 2 pixels at a time. 90 and 270 rotations implemented. YV16 refactored. YV12 code accepts a YuvType that allows the same code to support YV16 as well. Special case for half size removed. Special case for doubling added. 3.62 ms versus 8.62 for general purpose code. Review URL: http://codereview.chromium.org/113407 git-svn-id: svn://svn.chromium.org/chrome/trunk/src@16334 0039d316-1c4b-4281-b951-d872f2087c98
* YUV scaling and conversion refactored into low levels per platform that do a ↵fbarchard@chromium.org2009-05-131-0/+254
row and high levels that step thru the image. Low level is implemented in MMX assembly. Mac and Linux use reference code for this version. Review URL: http://codereview.chromium.org/113247 git-svn-id: svn://svn.chromium.org/chrome/trunk/src@16011 0039d316-1c4b-4281-b951-d872f2087c98
generated by cgit v1.1 at 2025-04-02 20:41:41 +0000