perf: single render pass with per-group scissor rect#200
Merged
Conversation
Replace flush-on-scissor-change (3 render passes per frame) with scissor timeline grouping (1 render pass, multiple SetScissorRect calls). SetScissorRect is dynamic render pass state — nearly free. - Add scissorSegment tracking in SDFAccelerator - Add ScissorGroup type for per-group draw dispatch - Add RenderFrameGrouped + encodeSubmit*Grouped in GPURenderSession - Add recordGroupDraws helper (DRY across readback/surface paths) - Remove flushOnScissorChange (caused 3x render pass overhead) Reduces GPU utilization from ~45% to ~5% on Intel Iris Xe during ScrollView scrolling (1000-item ListView).
Codecov Report✅ All modified and coverable lines are covered by tests. 📢 Thoughts on this report? Let us know! |
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
created multiple render passes per frame (one per scissor change), causing GPU
utilization to spike from ~3% to ~45% during ListView scrolling
flushOnScissorChangewithScissorGrouptimelinetracking — all draws accumulate within a single render pass, scissor rect changed
per group via
SetScissorRect()(WebGPU dynamic state, zero cost)Changes
internal/gpu/render_session.go—ScissorGrouptype,RenderFrameGrouped,encodeSubmitReadbackGrouped/encodeSubmitSurfaceGrouped,recordGroupDrawshelper for DRY 5-tier draw recording
internal/gpu/sdf_gpu.go—scissorSegmenttimeline tracking,buildScissorGroupsreplacesflushOnScissorChangeCHANGELOG.md— v0.36.2 entryTest plan
GOWORK=off go build ./...passesgolangci-lint run— 0 issues