Add workload sweeps, per-module comparisons, and GPU experiment runners - #10
Draft
brandonros wants to merge 2 commits into
Draft
brandonros wants to merge 2 commits into
brandonros wants to merge 2 commits into
Conversation
brandonros
added this pull request to stack #12
September 15, 2026 00:51
brandonros
force-pushed
the
stack/ptx-experiments
branch
from
September 15, 2026 01:13
18b60c8 to
9d830ff
Compare
brandonros
removed this pull request from stack #12
September 15, 2026 01:13
brandonros
added this pull request to stack #13
September 15, 2026 01:13
This was referenced Sep 15, 2026
This branch has not been deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds the broader workload matrix, per-module and size comparisons, representative GPU kernels, diagnostics, and numerical/timing runners.
Both mining runners prepare a temporary clone of the pinned commit. The supplied checkout, including local edits and its lockfile, is untouched. Temporary clones are removed after success or failure; source and patched manifest provenance are retained in the result directory. Only committed source at the pin is used.
Native stack: #3 → #7 → #8 → #9 → #10. Base: #9. Historical reports and generated PTX evidence have been dropped from the active stack by closing #11.
Validation: all 12 Python tests pass, including repeated preparation, failed-run retry for both entry points, preservation of local manifest/lockfile edits, and rejection of an incorrect revision. Offline locked Cargo metadata passes. Updated Linux CI is pending; NVIDIA execution was not rerun locally.