Sync 1080p60: next research plan
18 September 2026 · Research plan · Synthesis of camera delivery and audio qualification roadmap
Recommended first experiment: execute 1080p60 native AVFoundation versus Chromium capture comparison to isolate camera extension transport from browser capture ceilings.
This document outlines proposed research following the delivery of bounded camera frame ownership. The measurements below come from earlier experiments. No new performance tests ran for this publication.
1. Objective and constraints
The objective remains sustained 1920×1080 at 60 unique delivered frames per second, without performance degradation over time, serving web and desktop builds. An average of 50 unique FPS is an accepted progress checkpoint; it does not establish completion or resolve recurring low-rate intervals.
Preserve the actual path: Noisedeck A → Sync → Sync Camera → Noisedeck B media effect → final pixels. Use testPattern() for reproducible identity checks. Check representative shader content before release. Defer 4K work.
- Work against current upstream versions. Preserve unrelated work.
- Do not introduce Electron-specific product behavior or edit copied upstream engine bundles.
- Keep raw measurements and generated reports outside Git. Publish reviewed reports in this archive.
- Complete short comparisons before a long soak. Commit only a retained, reviewed improvement.
2. Evidence that determines the next action
| Observation | Supported conclusion | Limit |
|---|---|---|
| Bounded camera queue in Noisedeck delivered +12.7 to +14.0 unique FPS on web; desktop signs differed (+9.0% vs -0.7%). | Retain bounded queue as measured progress while investigating underlying browser selection boundaries. | Short sequential comparisons. E1 |
| 4,802 public upload calls contained 1 native query each; unqueried native versions had lifetimes of 11–13 ms between queries. | Missed selection opportunities occur at the browser upload boundary. | Instrumented timing traces. E1 |
| Native sender profiling showed 11.7–12.4 ms GPU fence wait and 3.3 ms readback copying. | Eliminate duplicate export slot buffer via in-place WebGL2 row flip. | Requires single-variable sender comparison. E2 |
3. Measurement contract
All performance claims must adhere to the standard measurement contract: unique delivered FPS decoded from final rendered pixels, complete-second distributions (≥59 FPS complete, <50 FPS low-rate), marker-age percentiles, and paired baseline/candidate protocols including reverse-order confirmation.
4. Research order
- 1080p60 native AVFoundation versus Chromium comparison: Isolate extension transport from browser capture queue bottlenecks.
- Controlled sender stage separation: Attribute sender stamp-to-send latency and evaluate in-place row flipping.
- Combined 32-channel audio and 1080p60 video load qualification: Stress test daemon single-thread reactor event loop.
- Windows platform parity: Implement and qualify Windows Media Foundation virtual camera and WASAPI capture.
5. Short decision cycles
Each milestone executes with paired comparisons before long-duration endurance runs. Reversible changes with negative performance delta must be rejected promptly.
6. Long-session degradation and completion
Completion requires sustained 60 unique FPS without low-rate seconds over a continuous 30-minute soak window with flat process memory footprint.
7. Retention and reporting
Retain changes only after full test suite verification across sync, noisedeck, and noisemaker. Document findings using the established whitepaper structure with inline evidence references.
Evidence references
- E1. Sync 1080p60: bounded camera frame acquisition, 12 September 2026.
- E2. Sync 1080p60: controlled sender stage separation, 18 September 2026.