SUNNYVALE, Calif., March 30, 2016 /PRNewswire/ -- Chelsio Communications, Inc., a leading provider of high performance Ethernet adapters for storage networking, virtualized enterprise data centers, cloud service installations, and cluster computing environments, today announced it will be showcasing its 40Gb Ethernet iWARP in a CUDA clustering demonstration at its booth (#528) at the NVIDIA GPU Technology Conference next week (April 4-7) at the San Jose Convention Center.
Chelsio will be demonstrating how its 40Gb Ethernet iWARP adapters can combine with NVIDIA GPU accelerators to deliver GPU-accelerated adapters from cloud data centers. The demo will show how GPU-accelerated simulation software, HOOMD (Highly Optimized Object Oriented Molecular Dynamics), and deep learning framework, Caffe, leverage 40GbE iWARP and NVIDIA GPUDirect RDMA.
In addition, Chelsio will be presenting two sessions, on April 6th and 7th, on High-Performance CUDA clustering using GPUDirect RDMA over 40GbE iWARP. These sessions will teach deployment strategies for using 40GbE iWARP in GPU applications that can scale to cloud performance requirements. The sessions will also share benchmark performance results for GPUDirect RDMA using 40GbE iWARP. For more information regarding these sessions, please visit: http://mygtc.gputechconf.com/quicklink/7dhW86U
"We are pleased to be able to show the dramatic performance advantages of using iWARP RDMA with the leading accelerated computing platform from NVIDIA," said Rajeev Sharma, senior product manager for Chelsio. "Our iWARP RDMA solution leverages existing Ethernet infrastructure and requires no new protocols, interoperability, or long maturity period as the no-risk path for Ethernet-based large-scale GPU clustering. We look forward to the continued increase in adoption of Ethernet for GPU-accelerated applications such as deep learning."
About Chelsio Communications
Chelsio is a recognized leader in high performance (10G/25G/40G/50G/100G) Ethernet adapters for networking and storage within virtualized enterprise data centers, public and private hyperscale clouds, and cluster computing environments. With a clear emphasis on performance and delivering the only robust offload solution, as opposed to simple speeds and feeds, Chelsio has set itself apart from the competition. The Chelsio Unified Wire fully offloads all protocol traffic, providing no-compromise performance with high packet processing capacity, sub-microsecond hardware latency and high bandwidth. Visit the company at www.chelsio.com, and follow the company on Twitter and Facebook.
To view the original version on PR Newswire, visit:http://www.prnewswire.com/news-releases/chelsio-to-demonstrate-high-performance-cuda-clustering-with-40gb-ethernet-and-nvidia-gpudirect-at-gpu-technology-conference-300243175.html
SOURCE Chelsio Communications, Inc.