-
Notifications
You must be signed in to change notification settings - Fork 772
[SYCL][UR] Add stubs in L0 adapter #8402
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
Conversation
de490c6
to
f53f1d6
Compare
@jandres742, OpenCL CPU and ESIMD emulator results are impacted by infrastructure issues. I'll restart the pre-commit to get relevant results as soon as possible. No actions from your side are required. Sorry for inconvenience. |
f53f1d6
to
af0018d
Compare
needs to be merged after #8400 |
ad51928
to
136ec24
Compare
}; | ||
|
||
const int UrL0Debug = [] { | ||
const char *DebugMode = std::getenv("UR_L0_DEBUG"); |
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.
@smaslov-intel : what do you think of this format? So instead of ZE_DEBUG
, we would have UR_L0_DEBUG
, and generally speaking, we would have UR_<ADAPTER>_<KEY>
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.
Looks reasonable to me (but remember not to remove existing SYCL_PI_LEVEL_ZER0_* vars yet)
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.
@smaslov-intel , right, I'm not removing anything. For now, only adding UR variables
136ec24
to
9c46d02
Compare
9c46d02
to
b542eb3
Compare
@jandres742, I don't think closing and re-opening PR will help to pass |
I see similar failures in other PR and it looks like a regression introduced by @mmoadeli in intel/llvm-test-suite@d578db9. |
Thanks @bader . The errors were with OpenCL CPU, which these changes are not affecting, which is why I thought it was infra or something unrelated to the change. |
Even if so, it doesn't mean that closing/re-opening helps all infrastructure related issues. Please, apply this method only if you know what the problem was, know that it's fixed and re-running tests will give you different results. Otherwise, we just waist CI resources. |
I reverted the patch causing this test to fails. Please, update your branch and make sure 01511a3 is merged. It should fix |
Signed-off-by: Jaime Arteaga <jaime.a.arteaga.molina@intel.com>
b542eb3
to
e1af2f1
Compare
@smaslov-intel, @bmyates: ready for review. |
No description provided.