Repository navigation
fix(streaming): reduce NV2A frame packing overhead - #365
Merged
Merged
Conversation
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## master #365 +/- ##
==========================================
+ Coverage 74.39% 74.44% +0.04%
==========================================
Files 72 72
Lines 8210 8224 +14
Branches 3514 3517 +3
==========================================
+ Hits 6108 6122 +14
Misses 1102 1102
Partials 1000 1000
Flags with carried forward coverage won't be shown. Click here to find out more.
Continue to review full report in Codecov by Harness.
|
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.



Description
At 720p, packing decoded YUV420 frames into the NV2A overlay's write-combined YUY2 buffers consumed most of the presentation budget and caused dropped frames at both 30 and 60 FPS.
Pack blocks of thirty-two pixels in cached storage and write them to the overlay with unaligned 16-byte SSE1 stores. Use scalar packing for tails and on other targets. SSE1 is supported by nxdk's Pentium III target.
Screenshot
Issues Fixed or Closed
Roadmap Issues
Testing
Fixed H.264 clips streamed through Sunshine in xemu with Vulkan showed these presentation rates. The 720p60 comparison ran twice with the order reversed and counts steady playback windows where the incoming rate was within 5% of the requested rate.
At 720p60, the median packing time was 8.1–9.8 ms with MMX and 5.6–7.5 ms with SSE1. The original scalar packer presented about 17 FPS at 720p30 and 19 FPS at 720p60 in earlier xemu measurements. A pre-SDL3 build sustained 720p30 with the same clip. The first affected commit and physical Xbox performance remain unverified.
uv run --locked lb-update-clang-formatandgit diff --checkpassed.ctest --test-dir cmake-build-release --output-on-failurepassed all 501 native tests, and the strict Dockle API documentation build passed.movupsstores in the compiled Pentium III code and checked the packaged ISO with 720p60 GPU and 720p30 software playback in xemu.Type of Change
Checklist
AI Usage
See our AI usage policy.