The U.S. Department of Energy has awarded NVIDIA its fourth multi-million-dollar R&D contract to accelerate the development of next-generation heterogeneous supercomputers.
The Office of Science and the National Nuclear Security Administration (NNSA) awarded NVIDIA $8.5 million over two years to develop advanced interconnect architectures that enable “exascale” computing systems. These computers would perform a billion billion (a quintillion) floating point calculations per second. That’s roughly 100 times faster than many HPC systems today.
This research, which is part of the NNSA’s DesignForward program, will build on the network interface work initiated in our DOE FastForward project. NVIDIA will focus on developing network architectures that support throughput-optimized processors, massive and configurable bandwidth, a high degree of network resiliency, and sophisticated routing to improve sustained performance at scale.
One of the goals of our research will be to support very high message rates on the order of 500 million messages per second per compute node. This requires supporting very short messages, just 200Bytes/message at 100GB/s bandwidth. That would be a dramatic improvement from today’s software processing rates, which are in the range of a few million messages per second on a large system with latency-optimized processing cores.
As part of our work, we’ll collaborate with partners to define open standards for a software API and a NIC-to-router link protocol to facilitate interoperability with multiple network fabrics and with other processors. To that end, we’ll continue to work closely with other companies that design HPC systems, networks and processors to preserve an open interconnect ecosystem.
Exascale technology will play a vital role not only in scientific research, but in the U.S.’s overall economic competitiveness in the years to come. I’m proud to lead our research effort so that NVIDIA, along with its industry and academic partners, can advance the frontiers of science and technology.