Skip to content

Historical coagulation benchmark evidence

This is the 2026-07-10 machine-bounded decision record preserved from revision 7b064295037c3c9a137f5dd13c03f4a40da3f11b. Its timings are historical observations, not measurements of the v0.3.0 tree. The mutable local artifact path may now contain a different run; inspect its metadata before comparison. It is not resident/capture evidence.

The repository does not retain generated files under .artifacts/benchmarks/. Optional benchmark runs may recreate that ignored output directory. The documentation viewer uses the declared snapshot in docs/data/gpu_benchmark_results.json; its recorded provenance is unchanged and does not imply that it contains the July capture described below.

  • Command evidence: run pytest particula/gpu/tests/benchmark_test.py --benchmark -v -s. This remains opt-in benchmark evidence for local CUDA-capable environments, not part of the standard Warp CPU release-validation command set. The historical source-of-record artifact at .artifacts/benchmarks/gpu_benchmark_results.json preserves the exact executed local command in benchmark_metadata.command; the 2026-07-10 UTC capture came from a local coverage-wrapped invocation of that same benchmark target, but the plain user-facing reproduction command remains the one above.
  • Hardware/context: the same artifact records warp_version=1.15.0, device.alias=cuda:0, device.name=NVIDIA GeForce RTX 5060, and device.total_memory_bytes=8082096128 (about 8.08 GiB), with started_at=2026-07-10T01:59:34.215800+00:00 and updated_at=2026-07-10T02:00:43.918911+00:00.
  • Artifact output: .artifacts/benchmarks/gpu_benchmark_results.json
  • Mixed-scale fixture note: the coagulation benchmark path uses a dedicated deterministic mixed NPF/droplet fixture aligned with the shipped coagulation rejection sampling baseline, while condensation benchmarks keep the generic helper.

The recorded decision accepts the one-thread-per-box coagulation design with caveats: it is the current documented baseline for many independent boxes, especially when CUDA can deliver box-level parallel throughput, and for low-level direct-kernel workflows, but large single-box use remains bounded by the caution band below and does not imply a broader long-term scaling decision.

  • Single-box caution band: treat the recorded 1x10k to 1x50k range as the current caution band for large single-box workloads on the shipped one-thread-per-box kernel. The measured GPU time per step rises from 0.6809s at 1x10k to 1.3689s at 1x20k and 3.3984s at 1x50k, so this path is no longer a strong recommendation for large single-box work in that band. Smaller 1x500 to 1x5k cases (0.0361s, 0.1366s, 0.3411s) remain a modest-throughput regime, not a decisive GPU win.
  • Multi-box effective region: independent-box parallelism remains effective in the recorded many-box cases, where equivalent or larger total-particle workloads stay near the smaller timings seen at lower box counts: 10x500 0.0359s, 10x1k 0.0699s, 50x1k 0.0714s, 10x5k 0.3437s, 50x5k 0.3528s, 100x1k 0.0766s, and 10x10k 0.6938s. Record this as the region where the current GPU path still benefits from many independent boxes keeping threads busy.
  • Machine-bounded caveat: this is measured evidence from the 2026-07-10 capture on the recorded Warp/device context above, not a universal cutoff for every GPU or every future kernel variant. Treat it as the current decision record for the shipped one-thread-per-box design, not as a final acceptance decision on the long-term scaling strategy.

The legacy viewer reads a locally recorded artifact. Resident benchmark qualification requires its separate schema and reviewed evidence.

Explore this topic: Performance and memory evidence