Fix RuntimeError when running strided gemm on CUDA devices #1567
Merged
oleksandr-pavlyk merged 1 commit intomasterfrom Feb 28, 2024
Merged
Fix RuntimeError when running strided gemm on CUDA devices #1567oleksandr-pavlyk merged 1 commit intomasterfrom
oleksandr-pavlyk merged 1 commit intomasterfrom
Conversation
…is kernel
This resolves
```
RuntimeError: Exceeded the number of registers available on the hardware.
The number registers per work-group cannot exceed 65536 for this kernel on this device.
The kernel uses 108 registers per work-item for a total of 1024 work-items per work-group.
-54 (PI_ERROR_INVALID_WORK_GROUP_SIZE)
```
when running example:
```python
import dpctl.tensor as dpt
m1 = dpt.ones((1000, 1000), dtype="i4", device="cuda")
m2 = dpt.ones((1000, 1003), dtype="i4", device="cuda")
r = dpt.matmul(m1[:, :900], m2[:900, :])
```
|
Deleted rendered PR docs from intelpython.github.com/dpctl, latest should be updated shortly. 🤞 |
Collaborator
|
Array API standard conformance tests for dpctl=0.17.0dev0=py310h15de555_33 ran successfully. |
ndgrigorian
approved these changes
Feb 28, 2024
Collaborator
ndgrigorian
left a comment
There was a problem hiding this comment.
Tests all pass on Nvidia hardware now, LGTM!
Contributor
Author
|
Verified that performance on GPU Max has not deteriorated as the result of this change. Merging now. |
6 tasks
oleksandr-pavlyk
added a commit
that referenced
this pull request
Mar 27, 2024
Backport gh-1567 to 0.16.x maintenance branch
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Use kernel device-specific descriptor to determine maximal work-group size for this kernel.
This resolves
when running example: