Closed
Bug 1635616
Opened 5 years ago
Closed 5 years ago
Optimize SWGL x86 bilinear filtering code
Categories
(Core :: Graphics: WebRender, enhancement)
Tracking
()
RESOLVED
FIXED
mozilla78
| Tracking | Status | |
|---|---|---|
| firefox78 | --- | fixed |
People
(Reporter: lsalzman, Assigned: lsalzman)
References
(Blocks 1 open bug)
Details
Attachments
(1 file)
There's a lot of shuffling code in the inner loops that could be removed by more careful interleaving of pixels before doing the multiplications. Likewise, the setup code could more carefully pack coordinates together to reuse values. This gives us a total saving of around 12 SIMD intrinsic invocations, which is quite substantial. I also threw in some comments to make it a bit easier to follow...
|
Assignee | |
Comment 1•5 years ago
|
||
Pushed by lsalzman@mozilla.com:
https://hg.mozilla.org/integration/autoland/rev/81c36b4b79c6
shuffling optimizations for SWGL x86 bilinear filtering code. r=jimb
|
||
Comment 3•5 years ago
|
||
| bugherder | ||
Status: ASSIGNED → RESOLVED
Closed: 5 years ago
status-firefox78:
--- → fixed
Resolution: --- → FIXED
Target Milestone: --- → mozilla78
You need to log in
before you can comment on or make changes to this bug.
Description
•