Reported in version: HG 1.2
Reported for operating system, platform: All, All
Comments on the original bug report:
On 2020-10-24 15:00:43 +0000, Cameron Cawley wrote:
Created attachment 4484
video: Backport the fast paths for 24/32-bit blitting
This backports the optimized blitting code to SDL 1.2. This provides noticeable performance improvements in CSE2, however I haven't done extensive amounts of testing for all of the new paths.
On 2020-10-24 15:25:02 +0000, Ozkan Sezer wrote:
(In reply to Cameron Cawley from comment # 0)
however I haven't done
extensive amounts of testing for all of the new paths.
If you can do some more testing, I'd wait, say, a week or
something.
On 2020-10-25 15:50:43 +0000, Sylvain wrote:
Hey, if you look at the bug 4503
There is a testcase, an image, and a script to compare.
the testcase load a multi-color image, convert to all format and print some CRC for each step.
if you run it before the patch to have a reference and after: the compare script will tell if it breaks anything and the speed improvements.
Need to use IMG_Load (instead of loadBMP) for a .png file, so that the image has an alpha channel for testing.
Is there blending in SDL-1.2 ?
Currently it has lots of pixel_format:
It takes all SDL2 pixel formats and copies them as SDL1 pixel formats.
Not sure if that are all relevant. ( BPP1 and BPP4 commented out )
It needs to be tested with the SDL-1.2 + patch
On 2020-11-13 10:04:59 +0000, Sylvain wrote:
Created attachment 4516
compare script
The compare script hasn't changed much. I just updated to python3
(if needed:
The image must be relevant. big enough to mesure the image processing time.
Multi color + alpha so that we have all corner cases.
various size odd/even, pitch padding.
I've just tested the patch, and all pixel format ARGB2101010 are failing. not sure if this is supported, but at there are not "unsupported()" neither ?
Otherwise, there are improvements as expected:
like BGRX8888 -> RGB24 with goes from 15 ms to 3 ms.
and many others.
On 2020-11-13 16:42:33 +0000, Sylvain wrote:
Created attachment 4517
test-case for SDL-1.2
Update the test-case to remove ARGB2101010 and use IMG_Load from SDL_image
On 2020-11-13 16:43:22 +0000, Sylvain wrote:
Created attachment 4518
compare script
Update the script to print the "faster/slower" indication
On 2020-11-13 16:46:23 +0000, Sylvain wrote:
Created attachment 4519
results file
This my result file if you want to look at.
It shows where there are blit improvements.
(NB: there are a few irrelevant suspicious/slower conversion because blits at two fast in those cases.)
On 2020-11-14 08:05:52 +0000, Sylvain wrote:
Created attachment 4521
test-case for SDL-1.2
Update the test-case to re-add the SDL_GetPerformanceCounter + some padding/memcheck.
On 2020-11-14 08:08:24 +0000, Sylvain wrote:
Created attachment 4522
results file
This the results file which show the the speed improvements on 50 conversions.
using the image "IMG_2476_ColorKey_very_small.png" from bug 4503
This bug report was migrated from our old Bugzilla tracker.
These attachments are available in the static archive:
test-case for SDL-1.2 (fast_bench.c, text/x-csrc, 2020-11-13 10:00:22 +0000, 32108 bytes)compare script (compare_blitlog.py, text/x-python, 2020-11-13 10:04:59 +0000, 5787 bytes)test-case for SDL-1.2 (fast_bench.c, text/x-csrc, 2020-11-13 16:42:33 +0000, 32104 bytes)results file (diff.txt, text/plain, 2020-11-13 16:46:23 +0000, 5486 bytes)Reported in version: HG 1.2 Reported for operating system, platform: All, All
Comments on the original bug report:
On 2020-10-24 15:00:43 +0000, Cameron Cawley wrote:
On 2020-10-24 15:25:02 +0000, Ozkan Sezer wrote:
On 2020-10-25 15:50:43 +0000, Sylvain wrote:
On 2020-11-12 04:21:52 +0000, Ozkan Sezer wrote:
On 2020-11-13 10:00:22 +0000, Sylvain wrote:
On 2020-11-13 10:04:59 +0000, Sylvain wrote:
On 2020-11-13 10:32:57 +0000, Sylvain wrote:
On 2020-11-13 16:42:33 +0000, Sylvain wrote:
On 2020-11-13 16:43:22 +0000, Sylvain wrote:
On 2020-11-13 16:46:23 +0000, Sylvain wrote:
On 2020-11-14 08:05:52 +0000, Sylvain wrote:
On 2020-11-14 08:08:24 +0000, Sylvain wrote:
On 2020-11-14 08:13:06 +0000, Sylvain wrote:
On 2020-11-14 08:25:12 +0000, Ozkan Sezer wrote:
On 2020-11-14 08:26:44 +0000, Ozkan Sezer wrote:
On 2020-11-14 22:47:43 +0000, Cameron Cawley wrote: