Fix device CTS tests #834
Fix device CTS tests #834
Conversation
|
There doesn't appear to be anything CUDA specific in this patch, even if that's what drove these changes I'm not sure its worth calling out in this PR. |
| @@ -144,6 +144,8 @@ params: | |||
| [out][optional] pointer to the number of devices. | |||
| pNumDevices will be updated with the total number of devices available. | |||
| returns: | |||
| - $X_RESULT_ERROR_INVALID_SIZE: | |||
| - "`NumEntries == 0 && phDevices != NULL`" | |||
There was a problem hiding this comment.
The description for NumEntries should be updated too since it says that it will return UR_RESULT_ERROR_INVALID_VALUE in this case
There was a problem hiding this comment.
Actually, I went with INVALID_SIZE because that's what the test was using. But on second thought, maybe INVALID_VALUE is better?
There was a problem hiding this comment.
It would align with the OpenCL error code. What do other entry points specify for this type of error case?
There was a problem hiding this comment.
There is only 2 other entries that are equivalent. urAdaptersGet and urPlatformsGet. Both are using INVALID_SIZE. I guess I will keep the change to INVALID_SIZE for consistency.
There was a problem hiding this comment.
Having the same fault on HIP so 👍 from me
fabiomestre
force-pushed
the
fabio/fix_cuda_device_cts
branch
from
07083c8
to
c9570db
Compare
fabiomestre
force-pushed
the
fabio/fix_cuda_device_cts
branch
from
c9570db
to
9a19e90
Compare
No description provided.