At SuperComputing ’22 we demonstrated demonstrating key aspects of the developer workflow using Intel® oneAPI tools to program for the Intel® Data Center GPU Max Series, formerly codenamed Ponte Vecchio (PVC), all using cross vendor, cross architecture standards based techniques. We would like to share several use cases with you in the form of a live code tutorial + demo, representing the latest and most interesting aspects of oneAPI programming
1. oneAPI based GPU porting of a A) Thermal Solver and B) a Seismic Modeler both using our Intel DPC++/C++ Compiler to create vendor agnostic SYCL code
2. Intel® Fortran offload to GPUs using A) auto offload through native language features and compilation techniques and B) using OpenMP on GRILLIX/PARALLAX, a plasma turbulence/transport simulator
Intel oneAPI tools and SYCL from the Khronos Group provide a standards-based programming model that enables code portability across computing architectures (including CPUs, GPUs and FPGAs) and across vendors. This standards-based approach increases developer productivity, avoiding the vendor lock-in inherent with proprietary languages.