WebAssembly improvements#43
Open
MilesCranmer wants to merge 2 commits into
Open
Conversation
MilesCranmer
commented
Dec 30, 2025
MilesCranmer
commented
Collaborator
- Allow threading to be turned on and off in the WebUI.
- Use minimal Plotly import.
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
Comment on lines
+41
to
+45
| return ( | ||
| s && | ||
| s.crossOriginIsolated === true && | ||
| s.sharedArrayBufferAvailable === true && | ||
| s.hasSharedMemory === true && |
There was a problem hiding this comment.
The new assertion hard-requires crossOriginIsolated and SharedArrayBuffer to be true, but the Playwright config still runs the plain chromium project without the thread flags (see web/ui/playwright.config.ts), where SharedArrayBuffer is unavailable and crossOriginIsolated is false. That project will now fail this test deterministically. Consider gating this expectation to the chromium-threads project or making the check conditional on the thread-capable runtime.
Useful? React with 👍 / 👎.
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
dynamic_expressions / eval
Details
| Benchmark suite | Current: 5f53078 | Previous: 9cd093a | Ratio |
|---|---|---|---|
evaluation/BuiltinF32/derivative |
16.456355 ms/iter (± 0.062832) |
16.419791 ms/iter (± 0.067833) |
1.00 |
evaluation/BuiltinF32/eval |
2.894064 ms/iter (± 0.015256) |
2.894556 ms/iter (± 0.013735) |
1.00 |
evaluation/BuiltinF64/derivative |
22.524298 ms/iter (± 0.117043) |
22.613046 ms/iter (± 0.116265) |
1.00 |
evaluation/BuiltinF64/eval |
3.823915 ms/iter (± 0.011008) |
3.826979 ms/iter (± 0.013402) |
1.00 |
evaluation/Float32/derivative |
11.532228 ms/iter (± 0.115183) |
11.530106 ms/iter (± 0.049528) |
1.00 |
evaluation/Float32/eval |
2.334183 ms/iter (± 0.048244) |
2.335922 ms/iter (± 0.019257) |
1.00 |
evaluation/Float64/derivative |
27.288104 ms/iter (± 0.103712) |
27.430499 ms/iter (± 0.043571) |
0.99 |
evaluation/Float64/eval |
5.249734 ms/iter (± 0.036829) |
5.250282 ms/iter (± 0.022245) |
1.00 |
utilities/Float32/clone |
7.227 us/iter (± 0.326) |
7.237 us/iter (± 0.019) |
1.00 |
utilities/Float32/combine_operators |
60.693 us/iter (± 3.431) |
60.459 us/iter (± 0.541) |
1.00 |
utilities/Float32/compress_constants |
6.575 us/iter (± 0.035) |
6.59 us/iter (± 0.047) |
1.00 |
utilities/Float32/count_depth_sizes/128 |
35.245 us/iter (± 4.725) |
36.037 us/iter (± 3.42) |
0.98 |
utilities/Float32/count_depth_sizes/20 |
3.486 us/iter (± 0.046) |
3.91 us/iter (± 0.195) |
0.89 |
utilities/Float32/count_depth_sizes/64 |
10.615 us/iter (± 0.492) |
10.617 us/iter (± 0.339) |
1.00 |
utilities/Float32/count_depth_sizes/8 |
1.621 us/iter (± 0.039) |
1.574 us/iter (± 0.055) |
1.03 |
utilities/Float32/counting |
3.568 us/iter (± 0.139) |
3.856 us/iter (± 0.014) |
0.93 |
utilities/Float32/simplify |
97.949 us/iter (± 0.715) |
98.467 us/iter (± 0.189) |
0.99 |
utilities/Float64/clone |
7.512 us/iter (± 0.069) |
7.695 us/iter (± 0.027) |
0.98 |
utilities/Float64/combine_operators |
61.651 us/iter (± 0.42) |
60.295 us/iter (± 0.083) |
1.02 |
utilities/Float64/compress_constants |
6.735 us/iter (± 0.024) |
6.736 us/iter (± 0.023) |
1.00 |
utilities/Float64/count_depth_sizes/128 |
34.987 us/iter (± 2.289) |
42.709 us/iter (± 1.613) |
0.82 |
utilities/Float64/count_depth_sizes/20 |
3.553 us/iter (± 0.173) |
3.888 us/iter (± 0.049) |
0.91 |
utilities/Float64/count_depth_sizes/64 |
11.077 us/iter (± 0.595) |
11.866 us/iter (± 0.069) |
0.93 |
utilities/Float64/count_depth_sizes/8 |
1.557 us/iter (± 0.034) |
1.641 us/iter (± 0.008) |
0.95 |
utilities/Float64/counting |
3.571 us/iter (± 0.152) |
3.855 us/iter (± 0.011) |
0.93 |
utilities/Float64/simplify |
100.462 us/iter (± 0.394) |
100.139 us/iter (± 1.224) |
1.00 |
This comment was automatically generated by workflow using github-action-benchmark.
Contributor
There was a problem hiding this comment.
symbolic_regression / optim
Details
| Benchmark suite | Current: 5f53078 | Previous: 9cd093a | Ratio |
|---|---|---|---|
rotate_tree_in_place/mixed_arity |
508.82 us/iter (± 2.695) |
505.901 us/iter (± 0.922) |
1.01 |
search/equation_search |
1.428615311 s/iter (± 0.087020596) |
1.391267402 s/iter (± 0.128592256) |
1.03 |
utils/best_of_sample |
379 ns/iter (± 1) |
380 ns/iter (± 4) |
1.00 |
utils/check_constraints_x10 |
6.677 us/iter (± 0.019) |
6.482 us/iter (± 0.024) |
1.03 |
utils/compute_complexity_x10/u16 |
0 ns/iter (± 0) |
0 ns/iter (± 0) |
1 |
utils/insert_random_op_x10 |
3.747 us/iter (± 5.157) |
3.478 us/iter (± 0.095) |
1.08 |
utils/next_generation_x100 |
165.481 us/iter (± 2.077) |
165.676 us/iter (± 2.197) |
1.00 |
utils/optimize_constants_x10 |
15.466348 ms/iter (± 0.544972) |
15.343225 ms/iter (± 0.543607) |
1.01 |
utils/randomly_rotate_tree_x10 |
1.515 us/iter (± 0.038) |
1.559 us/iter (± 0.017) |
0.97 |
This comment was automatically generated by workflow using github-action-benchmark.
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.