Performance Evolution of Different SYCL Implementations based on the Parallel Least Squares Support Vector Machine Library
Marcel Breyer, Alexander Van Craen, Dirk Pflüger · International Workshop on OpenCL · 2023
In machine learning and scientific computing, some of the biggest challenges are efficient and performant portable computing. With our Parallel Least Squares Support Vector Machine (PLSSVM) library, we have not only developed an unrivaled Support Vector Machine (SVM) implementation for huge dense data sets, but we have also created a representative benchmark for a frequently encountered task in scientific computing, a (implicit) matrix-vector multiplication. PLSSVM supports multiple backends—OpenMP, CUDA, HIP, OpenCL, and SYCL—to be able to target the most widely used hardware platforms in machine learning and scientific computing.