[Refactor] Optimize debug message for parallel inference #1096
+18
−3
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Outdated suggestions cannot be applied.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.
This pull request improves error handling and debugging in the layout inference logic, making it easier to diagnose issues when layout inference fails during parallel operations. The most important changes are:
Error reporting improvements:
Enhanced the error message in
get_unused_iters(inutils.cc) to include details about the operands when divisibility cannot be proven, aiding in debugging layout-related issues.Wrapped the layout inference logic in
ParallelOpNode::InferLayout(inparallel.cc) with a try-catch block to catch TVM runtime errors. The new error message provides context about the failed buffer, the underlying TVM error, the problematic loop AST, and a hint for resolving the issue, before logging a fatal error.Now:
will throw errs with it's for stmt:
Summary by CodeRabbit