HPCwire: Solarflare Announces New 10GbE Offerings for Compute-Intensive Applications

King Abdullah University of Science and Technology

Since 1986 - Covering the Fastest Computers
in the World and the People Who Run Them

Translation Disclaimer

Subscribe | Sign In

Visit additional Tabor Communication Publications

Leading HPC
Solution Providers

January 31, 2012

Solarflare Announces New 10GbE Offerings for Compute-Intensive Applications

New ultra-low latency 10GbE dual-port server adapter delivers breakthrough application performance

IRVINE, Calif., Jan. 31 – Solarflare, the leader in application-intelligent 10 Gigabit Ethernet (10GbE) networking software and hardware, announced today the next-generation of its family of branded 10GbE products. Solarflare’s SFN6122F dual-port 10GbE server adapter delivers significantly lower latency and higher message rates compared to both prior Solarflare versions and competitive products, making it ideal for handling mission-critical, compute-intensive tasks in high performance, cloud computing and big data environments. The new server adapter features the industry’s first and only field-hardened, full-featured user-level TCP/UDP stack.

Leveraging Sandy Bridge I/O integration using PCIe 2.0, Solarflare’s SFN6122F delivers over a microsecond lower latency and a 100 percent increase in message rate over prior generations. The server adapter also features hypervisor bypass using SR-IOV to accelerate guest applications and alleviate network I/O bottlenecks. Demonstrating proven UDP/TCP acceleration at customer sites for over four years, Solarflare features a rich set of stateless offload for efficient acceleration of the most demanding network protocol tasks, including iSCSI and RSS. Further differentiating its family of 10GbE products from competing solutions, Solarflare also provides:

Network acceleration with full POSIX compatibility, requiring no application modifications
Support for common system calls (e.g. exec, fork), demonstrating mature and robust experience in multi-threading, large connection-counts and mixed file descriptors
Support for VLAN, teaming, failover and MLAG for redundant links and increased bandwidth, common features used in customer networks
Hybrid kernel / user space processing, maintaining consistent context between user level stack and kernel
Transparent control plane, requiring no manual intervention or new network configurations
Best performance in STAC M2 tests, delivering lowest latency at high message rates, plus sub-microsecond jitter

The SFN6122F features driver support for popular operating system environments, including Microsoft Windows, Red Hat RHEL, Novell SLES, Microsoft Windows, Solaris, Mac OS-X, Red Hat KVM, VMWare and Citrix XenServer. The server adapter consumes less than half the power of leading competitors’ NICs at 5 watts, and in addition meets Energy Star^® requirements. It also supports Solarflare’s open source network stack OpenOnload^® that accelerates application performance and is fully POSIX compatible. Solarflare delivers a comprehensive solution set that addresses critical bottlenecks, moving applications closer to the network for improved performance.

Solarflare’s SFN6122F is currently sampling and will be generally available in February. A companion product – the SFN6322F dual-port server adapter – combines the high-performance features of the SFN6122F server adapter with precision time synchronization and will be available in the third quarter of this year. For pricing information and more details, please contact sales@solarflare.com.

-----

Source: Solarflare

Share Options

Subscribe

Subscribe to HPCwire

Discussion

There are 0 discussion items posted.

Join the Discussion

Become a Registered User Today!

Registered Users Log in join the Discussion

RSS Feeds

Feeds by Topic

Feeds by Industry

Feeds by Content Type

Subscribe to All Content

All

May 23, 2012

May 22, 2012

May 21, 2012

May 18, 2012

May 17, 2012

May 16, 2012

May 15, 2012

May 14, 2012

May 11, 2012

Feature Articles

NVIDIA Works On CPU Co-Dependency Issues with Kepler GPU

NVIDIA is telling everyone that the GK110, its new Kepler GPU aimed at supercomputing, is all about improving performance per watt. But the other driving theme behind the new architecture is reducing the GPU's reliance on its CPU host. How well it accomplishes both these goals areas could determine the success of the new chip in high performance computing.
Read more...

OpenACC Starts to Gather Developer Mindshare

PGI, Cray, and CAPS enterprise are moving quickly to get their new OpenACC-supported compilers into the hands of GPGPU developers. At NVIDIA's GPU Technology Conference this week, there was plenty of discussion around the new HPC accelerator framework, and all three OpenACC compiler makers, as well as NVIDIA, were talking up the technology.
Read more...

NVIDIA Launches Kepler Into HPC

NVIDIA has introduced its first Kepler-generation GPU product for high performance computing, and revealed some of the inner working of the new architecture. The announcement took place at the kickoff of the company's GPU Technology Conference taking place this week in San Jose, California.
Read more...