[Wave] Enable > 4GB bufferOps using resetOffset #84
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
With the IREE bump, we can now properly use resetOffset to enable > 4GB buffer ops. It works because Wave generates: memref.reinterpret_cast w/ workgroup offset + buffer_cast w/ resetOffset With resetOffset, amdgpu.raw_buffer_cast will make the base pointer as the memref's base_ptr + workgroup_offset from reinterpret_cast. This makes the offsets during the read much much smaller allowing us to do > 4GB buffer loads/writes. Signed-off-by: Stanley Winata <stanley.winata@amd.com>
raikonenfnu
changed the title
Hardcode84
approved these changes
Jul 23, 2025
badgerbroch
pushed a commit
to badgerbroch/wave
that referenced
this pull request
Jul 29, 2025
With the IREE bump, we can now properly use resetOffset to enable > 4GB buffer ops. It works because Wave generates: memref.reinterpret_cast w/ workgroup offset + buffer_cast w/ resetOffset With resetOffset, amdgpu.raw_buffer_cast will make the base pointer as the memref's base_ptr + workgroup_offset from reinterpret_cast. This makes the offsets during the read much much smaller allowing us to do > 4GB buffer loads/writes. We also enable the tests for batched GEMM mxpf4 that has > 4GB to use bufferOps. Signed-off-by: Stanley Winata <stanley.winata@amd.com>
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Outdated suggestions cannot be applied.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.
With the IREE bump, we can now properly use resetOffset to enable > 4GB buffer ops. It works because Wave generates:
memref.reinterpret_cast w/ workgroup offset + buffer_cast w/ resetOffset
With resetOffset, amdgpu.raw_buffer_cast will make the base pointer as the memref's base_ptr + workgroup_offset from reinterpret_cast. This makes the offsets during the read much much smaller allowing us to do > 4GB buffer loads/writes.
We also enable the tests for batched GEMM mxpf4 that has > 4GB to use bufferOps.