Intel® CPUs & GPUs on Structured Mesh Stencil Workloads

oneAPI and SYCL* are quickly evolving to become key tools for programming a wide breadth of massively parallel architectures. This talk presents performance results from some of Intel’s latest parallel architectures including CPUs and GPUs on a set of industrially representative and academic structured mesh stencil applications. Review benchmarks and comparisons of different formulations of parallel operations on different platforms with both low-order, bandwidth-bound kernels and high-order, more computationally expensive kernels. Get a demonstration of scalability that combines a message passing interface (MPI) and SYCL.


István Reguly is an associate professor at Pazmany Peter Catholic University, leading the High Performance Computing Lab. His research focuses on delivering performant, portable, and productive programming environments to scientists.