Duncan Brawley comments

Results 33 comments of


                                            Duncan Brawley

[SYCL] Optimize NDRDescT by removing sycl::range, sycl::id and padding

> > > > > Can we remove the `throw` from these SYCL classes instead? > > > > > > > > > > > > Sorry, to clarify,...

[SYCL] Optimize NDRDescT by removing sycl::range, sycl::id and padding

> > > > > > Can we remove the `throw` from these SYCL classes instead? > > > > > > > > > > > > > >...

[SYCL] Optimize NDRDescT by removing sycl::range, sycl::id and padding

Thanks @aelovikov-intel. I have replied to your comment above. Just want to make sure you have the chance to read it before this PR gets merged. Otherwise I plan to...

bindless_images/read_sampled.cpp validation error on cuda/DG2

Hey Wenju. Want to let you know that I am working on this. As you have seen there are issues with different devices performing different rounding when concerning linear sampling....

[SYCL][Bindless] Create mapping of host and device handle

Corresponding UR PR: https://github.com/oneapi-src/unified-runtime/pull/1790

[SYCL][Bindless] Create mapping of host and device handle

Friendly ping @intel/unified-runtime-reviewers

[SYCL][Bindless] Create mapping of host and device handle

> > Friendly ping @intel/unified-runtime-reviewers > > The UR PR needs to be approved and merged before we'll approve this PR. No problem. I have a few other PRs up...

[SYCL][Bindless] Refactor existing bindless aspects for missing L0 bindless functionality

Corresponding UR PR: https://github.com/oneapi-src/unified-runtime/pull/1795

[SYCL][Bindless] Refactor existing bindless aspects for missing L0 bindless functionality

Friendly ping @intel/dpcpp-tools-reviewers @intel/unified-runtime-reviewers @intel/llvm-reviewers-runtime @againull

[SYCL][Bindless] Refactor existing bindless aspects for missing L0 bindless functionality

Friendly ping @intel/dpcpp-tools-reviewers