[PATCH] D99190: WIP: [SYCL] Add design document for SYCL mode

Thu Apr 1 07:14:58 PDT 2021

bader added inline comments.

================
Comment at: clang/docs/SYCLSupport.md:123
+traverse all symbols accessible from kernel functions and add them to the
+"device part" of the code marking them with the new SYCL device attribute.
+
----------------
Naghasan wrote:
> ABataev wrote:
> > bader wrote:
> > > Naghasan wrote:
> > > > OpenMP offload uses a similar approach isn't it? Might be worth to describe how the 2 relates to each other and where they diverge. 
> > > Do you mean the approach OpenMP compiler uses to outline single-source code parts to offload?
> > > To be honest, I'm not sure... @ABataev, is there any description how OpenMP compiler outlines device code?
> > > https://clang.llvm.org/docs/OpenMPSupport.html doesn't provide much details unfortunately.
> > I don't think we have anything like this. Moreover, currently, there are 2 different models, one with outlining by the frontend and another one with the outlining by the LLVM.
> I mentioned that as I know there is some support for CUDA and the clang driver openmp offload works with multiple frontend passes.
> If the model(s) is too different then there is no point going further here. 
> 
> > Moreover, currently, there are 2 different models, one with outlining by the frontend and another one with the outlining by the LLVM.
> 
> I do recall some brief conversations about that. Are they meant to work in pair or one aims to replace the other ?
What do say if add a TODO here (or in a separate TODO document) to study more about differences between SYCL/OpenMP-offload/CUDA implementation designs?
It seems to be useful to understanding if we want to re-use other programming model experience with implementing common tasks like device code outlining.

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D99190/new/

https://reviews.llvm.org/D99190