[PATCH] D60455: [SYCL] Add support for SYCL device attributes
Alexey Bader via Phabricator via cfe-commits
cfe-commits at lists.llvm.org
Tue Apr 16 08:38:14 PDT 2019
bader added a comment.
In D60455#1468386 <https://reviews.llvm.org/D60455#1468386>, @Fznamznon wrote:
> > Ok, my question is whether you are planning to duplicate the same logic as for OpenCL kernel which doesn't really seem like an ideal design choice. Is this the only difference then we can simply add an extra check for SYCL compilation mode in this template handling case. The overall interaction between OpenCL and SYCL implementation is still a very big unknown to me so it's not very easy to judge about the implementations details...
> Of course, if nothing prevents us to re-use OpenCL kernel attribute for SYCL I assume it would be good idea.
> But I'm thinking about the situation with https://reviews.llvm.org/D60454 . If we re-use OpenCL kernel attributes - we affected by OpenCL-related changes and OpenCL-related changes shouldn't violate SYCL semantics. Will it be usable for SYCL/OpenCL clang developers? @bader , what do you think about it?
I also think it's worth trying. We should be able to cover "SYCL semantics" with LIT test to avoid regressions by OpenCL related changes. E.g. add a test case checking that -fsycl-is-device option disables restriction on applying `__kernel` to template functions.
I want to confirm that everyone is okay to enable `__kernel` keyword for SYCL extension and cover SYCL use cases with additional regression tests. IIRC, on yesterday call, @keryell, said that having SYCL specific attributes useful for separation of concerns.
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
More information about the cfe-commits