SiPearl has announced a collaboration with Intel to accelerate the deployment of exascale supercomputers in Europe. SiPearl, the company designing the microprocessor for the European Processor Initiative (EPI) and Intel will give European customers the opportunity to combine SiPearl’s CPU Rhea with Intel’s Ponte Vecchio GPU to create a high-performance heterogeneous HPC compute node. To enable this combination, SiPearl will port the open unified software stack, oneAPI for the Rhea processor architecture.
Jeff McVeigh, Intel vice president and general manager of the Super Compute Group states: ‘We are pleased that Ponte Vecchio, based on the Intel Xe HPC architecture, has been selected by SiPearl as their HPC accelerator to deliver Europe’s first exascale supercomputers, Intel is proud to support SiPearl in adopting oneAPI’s unified programming model to increase developer productivity and workload performance. We see great potential in our work with SiPearl as we execute on our IDM 2.0 strategy to bring leading-edge technologies to our European partners.’
This partnership will offer European customers the possibility to combine SiPearl’s high-performance and low-power CPU Rhea with Intel’s family of general-purpose GPU Ponte Vecchio making a high-performance compute node fostering European exascale deployment.
To enable this combination, SiPearl plans to port and optimise oneAPI for the Rhea processor. As an open, standards-based programming model oneAPI increases developer productivity and workload performance by providing a single programming solution across the heterogenous compute node. The paired solution will also underline the value of CXL standardisation in connecting compute elements, providing lower latency, coherent connectivity relative to PCIe connections.
Philippe Notton, SiPearl’s CEO and founder added: ‘We welcome this collaboration with Intel, whose GPU Ponte Vecchio, optimised for HPC workloads, is a great engineering innovation. A solution incorporating our European HPC CPU Rhea with the Intel Ponte Vecchio GPU under the unified programming model oneAPI allows us to rapidly develop heterogenous nodes to meet the needs of European exascale supercomputing.’
