Xilinx, Inc has introduced the Alveo U55C data centre accelerator card and a new standards-based, API-driven clustering solution for deploying FPGAs at a massive scale. The accelerator brings excellent performance-per-watt to high-performance computing (HPC) and database workloads and scales through the Xilinx HPC clustering solution.
Purpose-built for HPC and big data workloads, the new card is the company’s most powerful Alveo accelerator card ever, providing the highest compute density and HBM capacity in this accelerator portfolio. With the new Xilinx RoCE v2-based clustering solution, a wide spectrum of customers with large-scale compute workloads can now realise powerful FPGA-based HPC clustering utilising their existing data centre infrastructure and network.
“Scaling out Alveo compute capabilities to target HPC workloads is now easier, more efficient and more powerful than ever,” said Salil Raje, executive vice president and general manager, Data Center Group at Xilinx. “Architecturally, FPGA-based accelerators like Alveo cards provide the highest performance at the lowest cost for many compute-intensive workloads. By introducing a standards-based methodology that enables the creation of Alveo HPC clusters using a customer’s existing infrastructure and network, we’re delivering those key advantages at massive scale to any data centre. This is a major leap forward for even broader adoption of Alveo and adaptive computing throughout the data centre.”