Intel® launch new GPU architecture at Supercomputing 2019
Supercomputing 2019 kicked off in Denver, Colorado yesterday and Intel's Senior Vice President, Chief Architect, and General Manager of Architecture, Graphics and Software unveiled their new GPU architecture called oneAPI. oneAPI is an Intel-led initiative that simplifies the programming of diverse architectures - CPUs, GPUs, FPGAs, AI accelerators - to meet customer workload needs.
The launch of oneAPI represents millions of Intel engineering hours in software development and marks a game-changing evolution from today's limiting, proprietary programming approaches to an open standards-based model for cross-architecture developer engagement and innovation. Intel's data-centric silicon portfolio and oneAPI initiative lays the foundation for the convergence of HPC and AI workloads.
Intel® needed to architect a software solution that would simplify the programming of the diverse architectures. There is a lot of data and a lot of need for compute as well as the need for different architectures to handle that type of compute. For example, some may need a CPU or some may need a GPU to deliver that. The purpose of oneAPI is to provide all types of options to customers in a unified way. The main difference of Intel® oneAPI products is the Data Parallel C++ Compiler. C++ is a strong programming language that can cross architecture and gives a very good performance. oneAPI looks at simplifying programming across a heterogeneous environment using Data Parallel C++ as it provides a good foundation for programming language.
Keep your eyes peeled for our announcement about testing oneAPI at our Boston Labs!