[GPU][AMD] Add support for address space reads #67
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
This commit enables the amd gpu process to read from different address spaces. We the following address spaces: * global - default address space * generic - flat address space * region - gds address space (not supported on MI300/MI350) * local - local (shared memory) address space * private_lane - thread local address space * private_wave - wave local address space These address spaces correspond to address spaces exposed for dwarf expressions. In order to read from the private_lane address space we need to keep the lane as part of the ThreadAMDGPU object. This is a straightforward modification to the existing code that creates the per-lane threads. Tests were added to exercise each of the exposed address spaces.
clayborg
requested changes
Nov 24, 2025
- Use enum class for address spaces - Get rid of global address space
clayborg
approved these changes
Nov 25, 2025
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Outdated suggestions cannot be applied.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.
This commit enables the amd gpu process to read from different address spaces. We the following address spaces:
These address spaces correspond to address spaces exposed for dwarf expressions.
In order to read from the private_lane address space we need to keep the lane as part of the ThreadAMDGPU object. This is a straightforward modification to the existing code that creates the per-lane threads.
Tests were added to exercise each of the exposed address spaces.