Match vector norm exponent constants to the input dtype - #82
Open
devin-lai wants to merge 1 commit into
Open
Conversation
The general p-norm lowering passed Python scalars directly to broadcasting_pow, which could create exponent constants with a different element type from the operand. Integer ord values and float16 inputs therefore produced programs that failed verification. Normalize ord to a float and build both exponent constants in the operand element type. Add end-to-end coverage for integer ord spellings and float16 inputs.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The general p-norm lowering passed Python scalars directly to
broadcasting_pow. Integer orders and float16 inputs could therefore create exponent constants with a different element type from the operand, causing program verification to fail.This normalizes
ordto a float and builds both exponent constants in the operand element type. The regression coverage includes integer order spellings, negative orders, float16 inputs, and dynamic shapes.Tested with
pytest -q tests/ops/test_ops.py::test_linalg_vector_norm...