Developers of high-performance computing (HPC) applications are faced with an increasingly diverse number of computing platforms that feature multiple generations of CPUs, GPUs, FPGAs, and other accelerators.

Developing code that is performant and portable across a diverse set of platforms can be expensive and time-consuming to achieve the best result.

This workshop explains why performance, portability, and productivity are important for HPC development. Get hands-on practice to learn methods for achieving performance-portable SYCL* code that can run across different CPUs and GPUs available on the Intel® Tiber™ Developer Cloud.

The session covers these topics:

• Target different devices from SYCL code and use the environment variable
• Get device properties and optimize SYCL kernels based on the offload device
• Install the oneAPI tool to enable building for NVIDIA* and AMD* GPUs
• Build and run SYCL code to offload computation to GPUs from different vendors like Intel, NVIDIA, and AMD
• Introduce tools available for SYCL development like Intel® VTune™ Profiler and SYCLomatic