Changes between Version 1 and Version 2 of Ticket #926, comment 1
- Timestamp:
- 07/28/15 07:55:18 (6 years ago)
Legend:
- Unmodified
- Added
- Removed
- Modified
-
Ticket #926, comment 1
v1 v2 3 3 Then after updating the wiki performance page above, it seems that the regression is not new: it happened between 0.14.x and 0.15.x (halved). 4 4 5 The other problem is our calls to {{{memoryview_to_bytes}}} , which is a nice utility function, but too coarse: in some cases we can handle the data without converting it to bytes, and we should. r10087 + r10089 fix that for the opencl csc, backport in r10088 + r10090.5 The other problem is our calls to {{{memoryview_to_bytes}}} (new related ticket: #927), which is a nice utility function, but too coarse: in some cases we can handle the data without converting it to bytes, and we should. r10087 + r10089 fix that for the opencl csc, backport in r10088 + r10090. 6 6 7 7 @smo: re-assigning to you so you can take a look at the performance data which might interest you, in particular just how fast swscale has become - but opencl isn't bad either...