Georgi Mirazchiyski

Results 27 comments of Georgi Mirazchiyski

> @GeorgeWeb Would you please help to have a look? Thanks. @jsji Yeah, no problem. If it is blocking the pulldown, the `XFAIL` commit is fine, because the test cannot...

> > > @GeorgeWeb Would you please help to have a look? Thanks. > > > > > > @jsji Yeah, no problem. If it is blocking the pulldown, the...

The macros are redefined here: https://github.com/intel/llvm/pull/12871/files#diff-354d01b108ecba542b9ccce083a74c9ea0714ad00fd08367ad5f8347045024dfR625 for our purposes (including OpenCL lang on AMD backend for libclc). They were previously removed but probably got reintroduced during upstream pulldown, hence this...

@intel/llvm-gatekeepers Think this is good to merge, thanks!

Hi @jinz2014 . Working on this, I'll ping you when a PR is up. Thank you!

> > Change the returned error code for exiting the kernel launch entry point in CUDA when exceeding the maximum available registers for execution on the SM. Previously we were...

@mmoadeli ping. That one may have flown under the radar - would it be possible to take a look, please?

> @GeorgeWeb I am just planning implementing the suggestion here: https://github.com/oneapi-src/unified-runtime/issues/1491#issuecomment-2083074881 > > which will I think make this implementation inconsistent because interop events will then have the possibility of...

@oneapi-src/unified-runtime-maintain just a ping to have a look as that's been stale for some time. Thanks!

> ``` > 2024-06-27T14:32:19.4840797Z Failed Tests (1): > 2024-06-27T14:32:19.4849324Z SYCL :: GroupAlgorithm/root_group.cpp > ``` @pbalcer Yeah aware, thanks! The root group barrier is currently not supported correctly for cooperative-group kernels...