Sign up for our newsletter and get the latest HPC news and analysis.
Send me information from insideHPC:


Video: Mellanox HDR InfiniBand Speeds HPC and Ai Applications with SHARP Technologies

Gilad Shainer (left) is VP of Marketing at Mellanox.

In this video, Gilad Shainer from Mellanox describes how the company’s newly available HDR 200 Gigabit/sec InfiniBand solutions can speed up HPC and Ai applications.

We are proud to see the first Mellanox HDR InfiniBand ConnectX-6 adapters and Quantum switches based supercomputer in the world,” said Gilad Shainer, vice president of marketing at Mellanox Technologies. “The smart In-Network Computing acceleration engines that InfiniBand enables will deliver the highest performance, efficiency and scalability for the University of Michigan users, for both HPC and AI applications.”

Over the past decade, no one has pushed the industry forward more than Mellanox. As the first to 40Gb/s, 56Gb/s and 100Gb/s bandwidth, Mellanox has both boosted data center and cloud performance and improved return on investment at a pace that far exceeds Moore’s Law and even exceeds its own roadmap. To that end, Mellanox has now announced that it is the first company to enable 200Gb/s data speeds with Mellanox Quantum switches, ConnectX-6 adapters, and LinkX cables combining for an end-to end 200G HDR InfiniBand solution in 2018. By doubling the previous data rate, only Mellanox can provide the necessary speed to meet the demands of the world’s most data-intensive applications.

With 40 ports of 200Gb/s HDR InfiniBand, Mellanox Quantum offers an amazing 16Tb/s of bidirectional throughput and 15.6 billion messages per second in only 90ns of port-to-port switch latency. Quantum provides industry-leading integration of 160 SerDes, which can operate at a flexible 2.5Gb/s to 50Gb/s per lane, making Quantum the world’s most scalable switch. Furthermore, Quantum is also the world’s smartest switch, improving performance by processing data as it traverses the network and eliminating the need to send data multiple times between endpoints. By including collective communication accelerators and Scalable Hierarchical Aggregation and Reduction Protocol (SHARP) 2.0 MPI aggregation and reduction technology, Quantum is able to meet the needs of even the most demanding applications, from high performance computing to machine learning.

See our complete coverage of SC18 in Dallas

Sign up for our insideHPC Newsletter

Leave a Comment

*

Resource Links: