Repository navigation
profiling(PyAutoArray#577): lever 3 real-scatter A100 sma witness - #319
Merged
Merged
Conversation
…ch legs (PyAutoArray#577) Runs the #308 sma dense breakdown twice on one node: PyAutoArray origin/main (control) and the lever-3 branch, from a private branch-libs copy (the shared mirror is not touched). Outputs carry a _real_scatter suffix so the #308 JSON stays. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…yAutoArray#577) RAL job 356364, one A100 node, control (PyAutoArray main 1bf641e4) vs branch (f9d3bc67): step 3 852.7 -> 0.51 ms, total 856.2 -> 4.04 ms, full single jit 854.6 -> 3.39 ms, log L bit-identical (-3153.942384509246). CPU sma and the transform_mapping_matrix micro-timing show no regression (ABBA under load). Notes: "Lever 3: real scatter (2026-09-26)". READMEs regenerate unchanged (the suffixed JSONs are outside the dashboard regex). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
A100 witness for PyAutoArray#577, lever 3 of #308. RAL job 356364 ran the sma MGE breakdown leg on the dense library path twice on the same node: once with main's PyAutoArray as a control, once with this branch. Step 3 went from 851.5 ms to 0.51 ms, the full pipeline from 868.5 ms to 3.39 ms, with log L identical. The alma chunked arm was deliberately not re-run: it uses the cell's own
_transform_script_chunkedand never callstransform_mapping_matrix, so a re-run would measure unchanged code (explained in the note).Scripts Changed
hpc/batch_gpu/submit_breakdown_interferometer_mge_a100_sma_fp64_real_scatter: new submit that runs control and branch legs, each asserting its PyAutoArray__file__.results/breakdown/interferometer/sma/mge_hpc_a100_fp64_real_scatter{,_main_control}.{json,png}: results, withsource_revisions.results/notes/interferometer_mge_breakdown_2026_09.md: new "Lever 3: real scatter (2026-09-26)" subsection.Upstream PR
PyAutoLabs/PyAutoArray#578
Test Plan
build_readme.py --check,ruff check,ruff format --check,check_submits.py --checkpytest scripts/misc/test/: 912 passed, 5 skippedmanifest drift: hub organism blurb (organs present) — 7 mismatch(es) vs PyAutoMind/repos.yaml;manifest drift: organism-map blocks (generated) — 1 mismatch(es) vs PyAutoMind/repos.yaml;manifest drift: workspace checkouts (manifest ↔ disk) — 1 mismatch(es) vs PyAutoMind/repos.yaml;release validation stale: source moved since rehearsal (PyAutoFit, PyAutoArray, PyAutoGalaxy, PyAutoLens).🤖 Generated with Claude Code