Make HeuristicSummary a lazy cache #2973
Merged
Conversation
This file contains 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
|
!build |
naoyam
approved these changes
Sep 20, 2024
csrc/scheduler/compile_time_info.h
Outdated
| //! 2. When the compiled kernel is launched the first time, the | ||
| //! cache will be in `recording` phase and all the computed information | ||
| //! should be captured and written into the cache. | ||
| //! 2. When a kernel is created fior the first time, entries will be |
There was a problem hiding this comment.
typo:
Suggested change
| //! 2. When a kernel is created fior the first time, entries will be | |
| //! 2. When a kernel is created for the first time, entries will be |
|
!build |
|
!build |
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Outdated suggestions cannot be applied.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.
Currently, HeuristicSummary runs all the scheduler analyses to produce the cache it also validates all the information exists once doing so. I simply converted it to be lazy, populating on first hit and reusing if entries exist. This makes it easier to update and use correctly.
I tested it locally on a dynamic shape case and from profiling it seems to be caching as it's supposed to (latency remained consistent before and after).