SYCL/Intel GPU issue tracker

[BenWibking]

Describe the proposal

This issue is to track changes that need to be made to get Quokka to compile with the SYCL GPU backend:

• Can't use function references (used in ODEIntegrate.hpp for rhs function)

  /home/runner/work/quokka/quokka/src/ODEIntegrate.hpp:136:2: error: SYCL kernel cannot call through a function pointer
  136 |         rhs(t0, y0, ydot0, user_data);
      |         ^
  

• Can't use global variables on device (used everywhere in Microphysics...)

  In file included from /home/runner/work/quokka/quokka/src/EOS.hpp:20:
  /home/runner/work/quokka/quokka/extern/Microphysics/interfaces/eos.H:86:35: error: SYCL kernel cannot use a non-const global variable
   86 |   state.rho = amrex::min(EOSData::maxdens, amrex::max(EOSData::mindens, state.rho));
      |  
  

• Need to add fp-model=precise to compiler flags:

  export CMAKE_CXX_FLAGS="-ffp-model=precise" 
  

Additional context
SYCL 2020 specification lists many restrictions that CUDA and HIP do not have.
https://registry.khronos.org/SYCL/specs/sycl-2020/html/sycl-2020.html#sec:language.restrictions.kernels