Repository navigation
Phase 6: differential fuzzing, regression corpus, verification docs - #6
Merged
Merged
Conversation
Add a differential fuzzer that compiles random programs for gpu -O0/-O1/-O2 and tpu -O0/-O1, runs every result on the real simulator/RTL, and requires bit-exact agreement with the numpy oracle of the source program, untouched R5-R7, estimate bounds containing the measurement and the TPU cost model equal to the measured cycles. Failures are shrunk by Hypothesis into tests/regressions/_last_failure.tiny. Add a 13-program corner-case corpus (K=1, one output column, 1x1, rank-1 values, outputs that are inputs or constants, duplicate subexpressions, partial tiles, zero constant tiles, K=20, 900 threads) replayed on every backend, plus a nightly workflow that runs 5000 fresh programs and uploads the shrunk failing program. Two independent 5000-program runs were green. Document every verification layer in docs/VERIFICATION.md.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Stacked on feat/phase-5-gpu-opts. Merge the stack in order, starting from the bottom PR.
Commits in this PR: