[TIR] LowerTVMBuiltin may use device_type from PrimFunc annotation #16727
Conversation
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
If an allocation occurs within a host function, it may not have a device/host split.
slyubomirsky
approved these changes
Mar 25, 2024
Contributor
slyubomirsky
left a comment
slyubomirsky
left a comment
There was a problem hiding this comment.
The change is simple and this seems like a good capability to have. Thank you for implementing it.
| def before(): | ||
| T.func_attr({"target": T.target("llvm")}) | ||
| T.attr("dummy", "device_id", 0) | ||
| T.attr("dummy", "device_type", 2) # kDLCuda |
Contributor
There was a problem hiding this comment.
Is this constant defined anywhere on the Python side? Perhaps it should be, to avoid such magic numbers (if we expect that to happen again).
Contributor
Author
There was a problem hiding this comment.
Good question, and looks like it is defined in the tvm.runtime.Device struct. I've updated the usage here, and throughout this unit test file.
Contributor
Author
|
Closing this PR, as changes were required for #16721, and were merged as part of that PR. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
If an allocation occurs within a host function, it may not have a device/host split, and may just be annotated with
"tir.is_host_func".