Ben Ashbaugh

Discussed in the December 17th teleconference. Some of this functionality appears to be implemented in Mesa: https://www.phoronix.com/news/OpenCL-C-Std-Lib-Mesa-25.0 https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32529 We should see what it would take to get this across the...

This has two approvals - can we merge this? I'd prefer not to merge my own PR. Thanks!

I took a look at the reproducer and it looks like the call to `malloc_device`: ```c++ T *dptr{sycl::malloc_device(NumElements, q)}; ``` is generating this OpenCL call to allocate the memory: ```...

Maybe we just need a check here to ensure that the pointer is properly aligned, in addition to the existing check that the pattern size is supported? https://github.com/oneapi-src/unified-runtime/blob/76898f0c5168841b715002748ae599a9d56f1bb1/source/adapters/opencl/usm.cpp#L272

Hi! The OpenCL SDK should work with MacOS and we have CI testing on MacOS in place. There are a few gremlins we might need to chase down, but at...

Yeah, this is confusing, but unfortunately it's been the case since OpenCL 1.0 so I'm not sure how much we can do to "fix" it at this point. Here's my...

Moving to mobica-backlog as per discussion in the February 18th teleconference.

We had another PR come in recently regarding `global_work_size` equal to `NULL`, so it would be great to get this added soon, if possible. https://github.com/KhronosGroup/OpenCL-CTS/pull/2287

Yep, seems fixed to me, closing!

Changing title. The code duplication described by (1) and (2) was fixed by #1401 but the missing test coverage for the floating-point types (3) still remains. See also https://github.com/KhronosGroup/OpenCL-Docs/issues/833.