As the world’s data-centric workloads become more diverse, so do architectures that process that data. Intel’s breadth of architectures span scalar (CPU), vector (GPU), matrix (AI) and spatial (FPGA). These architectures require efficient programming model cross industry and cross architecture. In this meet up we will discuss about the challenges and technical solutions unique to this space .
oneAPI ( https://www.oneapi.com/ ) is a unified programming model to optimize performance for a wide range of data-centric workloads across varied architectures such as in CPU, GPU, FPGA and other accelerators. It includes the programming language, Data Parallel C++ based on Industry standard SYCL ( https://sycl.tech/ ) that, together, deliver parallel programming productivity, and cross-architecture application performance while providing an alternative to single architecture programming approaches.