-
Notifications
You must be signed in to change notification settings - Fork 194
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Fix vulkan subtest for diffCtx and platform/device info #2046
base: main
Are you sure you want to change the base?
Conversation
* Test fails for implementations that do not advertise external memory/semaphore extensions, skip such a case. * Add changes to correctly query the handle types list and skip if not supported. * Add checks to enforce memory import support and semaphore import/export support when cl_khr_external_memory and cl_khr_external_semaphore are available respectively.
Fixes the issue where the subtest incorrectly tries to acquire/release memory using a command queue associated with a context different from the one under which the external memory was imported.
Instead of iterating over all available platform, just get the platform belonging to the supplied device handle.
293438a
to
843ba0d
Compare
a8bc7b1
to
f151be9
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks, latest version LGTM.
I'm still unable to choose the platform and device to run on for these tests using the usual mechanisms (e.g. CL_PLATFORM_INDEX
), so some additional work is still needed, but this is a definite step in the right direction.
Discussed in the September 3rd memory subgroup. Waiting a bit longer for a review from Qualcomm. |
Fixes: