Skip to content

JitKernel needs to be cleaned up #901

@chudur-budur

Description

@chudur-budur

Due to mutiple iterations, the the JitKernel class became messy. PR #896

  • There are at least two levels of caching for the same unspecialized kernel, i.e. self._cache and self._kernel_bundle_cache
  • For the specialized kernel, the caching is done in three individual levels. i.e. self._cache, self._kernel_bundle_cache and self._specialization_cache
  • These multiple levels of LRU caching is causing unnecessary overhead. Everything in that class needs to be made streamlined and clean. e.g. self._cache and self._kernel_bundle_cache can be consolidated.
  • Also due to these reasons, the cache-hit/miss counts (self._cache_hits) became ambiguous.
  • Either _check_range() and _check_ndrange() functions need to be moved inside Range, NdRange class or moved into the numba_dpex.core.kernel_interface.utils module.

Metadata

Metadata

Assignees

Labels

No labels
No labels

Type

No type

Projects

No projects

Milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions