How to Port Your Code From CUDA to SYCL, Targeting Nvidia GPUs and More
Codeplay’s contributions are helping developers target Nvidia GPUs, using SYCL and oneAPI, and researchers using the pre-exascale supercomputer Perlmutter are developing software using SYCL and oneAPI.
By using SYCL and oneAPI developers can widen their targets, with Nvidia GPUs, Intel GPUs, and AMD GPUs supported by the DPC++ compiler project.
This session will help you to understand how you can port your CUDA code to SYCL and continue to target Nvidia GPUs and retain a good level of performance. Using nbody simulation project code written in CUDA we will show how the code is automatically translated to SYCL and then compiled using the DPC++ compiler. Furthermore we will present some performance tips and tricks to ensure you can get the best performance from your SYCL code on Nvidia GPUs.