Pushing the frontiers of science and technology requires extreme-scale computing. Mellanox specializes in delivering high-bandwidth, high-performance interconnects for HPC, Web 2.0, Cloud, storage and financial services markets, increasing data centre efficiency by providing high throughput and low latency. Mellanox IB adapters include advanced acceleration technology enabling higher cluster efficiency and large scalability to tens-of-thousands of nodes.
The ThunderX product family is designed for intensive scale-out workloads such as molecular dynamics, Big Data, and large-scale graph analytics, providing best-in-class ARMv8 performance with 48 custom cores, single and dual socket support, high memory bandwidth and capacity, and integrated hardware accelerators. Mellanox InfiniBand adapters provide very high bandwidth and ultra-low latency interconnect for ThunderX based servers utilized in high performance computing clusters.
"Mellanox and Cavium have similar goals: Delivering best-in-class, scalable products that accelerate HPC and Hyperscale workloads and drive greater return on investment", stated Gilad Shainer, Vice President, Marketing, Mellanox Technologies. "Cavium's powerful and scalable ARM SOCs are a great match for our highly-scalable, low-latency InfiniBand solutions, and we look forward to delivering optimal performance for our HPC, Cloud and Big Data customers."
"High performance compute clusters leveraging high performance scale out compute technologies based on ThunderX require a very high bandwidth and ultra-low latency cluster interconnects", stated Gopal Hegde, VP/GM, Data Center Processor Group, Cavium. "We optimized our ThunderX ARMv8 processors to deliver best-in-class performance for HPC and Hyperscale workloads, with 48 cores, high memory bandwidth, and onboard accelerators. This collaboration with Mellanox will enable an InfiniBand interconnect option to our customers for high performance and ultra-low latency interconnects for their HPC platforms based on ThunderX processors."