Skip to content

docs: correct T2S summary statistic #4

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
factnn merged 1 commit into from
Jul 21, 2026
Merged

docs: correct T2S summary statistic #4

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion BENCHMARK.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@ Run the same protocol with `python run.py --case <case> --track 1 --gpu 0`.

## Time to solution

Time includes optimizer updates, compilation, autotuning, and cold-start overhead. canpinn and FlashPDE are paired over seeds 42--46 and reported as mean ± standard deviation; `torch.compile` is a single-seed reference. Runs stop at the prescribed error threshold or 300,000 epochs.
Time includes optimizer updates, compilation, autotuning, and cold-start overhead. canpinn and FlashPDE are paired over seeds 42--46 and reported as the median together with the standard deviation across seeds; `torch.compile` is a single-seed reference. Runs stop at the prescribed error threshold or 300,000 epochs.

| Case | canpinn (s) | `torch.compile` (s) | FlashPDE (s) | Speedup | Final L2 error, canpinn / FlashPDE |
|---|---:|---:|---:|---:|---:|
Expand Down
Loading