Univa HPC Job Bank
HPC in the Cloud


Dedicated to covering high-end cloud computing
in science, industry and the datacenter

Language Flags

Emulex Introduces Portfolio of New I/O Connectivity Solutions


Company partners with Myricom to enter high performance networking market for low latency applications

LAS VEGAS, and COSTA MESA, Calif., May 8 — Emulex Corporation today announced the introduction of a family of new OneConnect Network Xceleration solutions for the High Performance Networking (HPN) market, its next generation LightPulse (LP)e16000R 16Gb Fibre Channel (16GFC) Host Bus Adapters (HBAs) based on the new Emulex Engine (XE)201R converged fabric controller, and its next generation OneConnect (OC)e11000R Universal Converged Network Adapters (UCNAs) based on the new XE4310R Ethernet controller, delivering a broad array of I/O connectivity solutions to address the needs of the changing data center.

Emulex is bringing its new family of OneConnect (OC)e12000 10Gb Ethernet (10GbE) Network Xceleration solutions to market in partnership with Myricom, an industry leader in delivering high performance, latency optimized Ethernet solutions for vertical market applications. This multi-generational marketing and development partnership leverages Myricom's deep expertise in HPN, specifically low latency, high packet-rate, vertical application optimizations, and Emulex's broad enterprise reach, high volume, enterprise-hardened hardware roadmap, and global go-to-market channels.

"By partnering with Myricom, Emulex is offering I/O connectivity solutions that broaden our reach in the Ethernet market and fast growing HPN vertical segments, such as High Frequency Trading (HFT), network security, and cloud-enabled video distribution," said Shaun Walsh, senior vice president of marketing, Emulex. "Ethernet-based High Performance Computing (HPC) is a rapidly growing market segment with a 63 percent compounded annual growth rate (CAGR) through 20161, and together, our partnership will provide our customers with a roadmap of solutions that leverage Emulex's market-proven I/O connectivity and Myricom's unique software IP."

Emulex OneConnect Network Xceleration solutions provide extreme performance for specific enterprise applications that rely on low latency, superior message rate or packet pacing through FastStack application acceleration software powered by Myricom. Using FastStack acceleration, customers get the benefit of high performance networking for their applications, within industry-standard 10GbE. Going forward, Myricom and Emulex will be jointly developing additional FastStack software solutions which will optimize Emulex's I/O connectivity solutions across additional vertical markets.

"Partnering with Emulex allows Myricom to bring its unique high performance networking software solutions for specific vertical market applications to a broader market," said Dr. Nan Boden, chief executive officer, Myricom. "Emulex's market strength and industry-leading Ethernet road map combined with Myricom's ultra-low latency performance, lossless packet capture/injection and traffic shaping technology enables the two companies to provide best-of-breed HPC networking."

Emulex is offering three OneConnect Network Xceleration solutions targeted at specific vertical applications which leverage kernel bypass operations that reduce latency and transaction times in conjunction with the OCe12000 adapters, including FastStack DBL (financial trading), FastStack Sniffer10G (cyber/network security) and FastStack VideoPump (video streaming and digital content delivery).

FastStack DBL
The Emulex OCe12000 combined with FastStack DBL software delivers industry-leading performance by accelerating UDP and TCP communication in HFT environments over industry-standard 10GbE network and IP protocols, and features:

  • Low Latency Performance: Delivers low latency, enabling faster transactional performance in HFT environments.
  • Broad Platform Support: Optimized for use on Linux and Windows operating system platforms which are broadly used in HFT environments.
  • Transparent Acceleration: Superior performance while accelerating existing Linux and Windows sockets applications without modifications.
  • Flexible Architecture: FastStack DBL can be combined with FastStack Sniffer10G to not only improve financial transaction performance, but also identify and address latencies which help optimize overall performance.


FastStack Sniffer10G

The Emulex OCe12000 combined with FastStack Sniffer10G software provides a powerful, cost-effective solution for network traffic capture, injection and analysis for performance-sensitive and mission-critical market segments, such as network surveillance, monitoring and analysis, deep packet inspection (DPI), test and measurement, and distributed denial-of-service (DDoS) defense appliances. FastStack Sniffer10G includes the following features:

  • 100 Percent Lossless Packet Capture: FastStack Sniffer10G provides 100 percent lossless packet capture and packet injection for all Ethernet packet sizes on a 10GbE data stream. This line-rate performance enables more thorough inspection and better detection of threats for cyber security environments and further refinement of market models and trading software algorithms for HFT environments.
  • Improved Multi-Core Utilization: FastStack Sniffer10G can distribute incoming packets over multiple CPU cores to not only improve CPU utilization, but also improve application performance through partitioning, duplication, and process sharing.
  • Increased Bandwidth: Port aggregation allows network traffic from two or more ports from the same or different OCe12000 adapters.
  • Cloud Multi-Tenancy Security SLAs: FastStack Sniffer10G helps cloud providers implement and track security policies in public cloud infrastructures to meet the demands of security service level agreements (SLAs) in multi-client environments.

FastStack VideoPump
The Emulex OCe12000 combined with FastStack VideoPump software, which will be available this summer, delivers more video streams per server and improves asset utilization for video streaming and IPTV, and features:

  • Predictable QoS: Designed for live streaming video, FastStack VideoPump traffic shaping technology provides predictable QoS with more effective data pacing and efficient bandwidth usage, improving the end-user experience.
  • Reduced Capital Expenditure (CAPEX): FastStack VideoPump supports more than 25,000 video streams per server, increasing server utilization and resulting in reduced costs and energy consumption.
  • Increased Scalability: FastStack VideoPump addresses the continuous growth of digital media content with line-rate streaming of multiple network adapters per server and more than 25,000 Over-the-Top (OTT) high-definition video streams (typically 3Mb per stream), by far the most scalable in the industry.

"As performance and latency become increasingly important, we expect that Ethernet products which can offer these characteristics will enjoy strong network adoption," said Seamus Crehan, founder and president, Crehan Research. "This partnership, which combines Emulex's current 10GbE port shipment leadership position with Myricom's HPC expertise, is well positioned to address this fast-growing market."

"Organizations looking for low latency solutions should consider the advantages of consolidating onto a common Ethernet platform because as data centers grow in size and complexity, achieving simplicity while driving down costs and overhead will become very important," said Bob Laliberte, senior analyst, Enterprise Strategy Group. "Emulex, in partnership with Myricom, is offering a compelling low latency Ethernet solution with excellent price-to-performance capabilities and the ability to deliver predictable, repeatable low latencies, while leveraging a common infrastructure to do it."

"The HPC market will be expanded by servers running data-intensive workloads, with spending for HPC servers expected to exceed $14 billion in 2016," said Steve Conway, vice president, HPC research, IDC. "With data-intensive workloads comes the need for the I/O to support them, and the new HPN solutions from Emulex aim to address this growing need for business and industry, government, and academia, and across vertical markets including financial services and digital content creation, among others."

The OCe12000 Network Xceleration and FastStack DBL or FastStack Sniffer10G software and hardware bundles are available now and range from $690 to $1,090 MSRP. Emulex will be demonstrating the key value propositions of all three OneConnect Network Xceleration and FastStack application acceleration software solutions, including low-latency, high-throughput, lossless pack capture and line-rate data streaming, at Interop this week in its booth #1117.

LPe16000R 16GFC HBA
Emulex's next generation LPe16000R 16GFC HBA is based on the new XE201R, a quad-port converged fabric controller that provides unique connectivity combinations of best-of-breed Fibre Channel and Ethernet connectivity on a single ASIC with up to four ports of 8Gb Fibre Channel (8GFC), Fibre Channel over Ethernet (FCoE), and 10GbE, two ports of 16GFC or one port of 40GbE. Key benefits of this new technology include the following:

  • Improved Signal Integrity and Reliability: The XE201R features new voltage controlled oscillator (VCO) technology for improved signal integrity and reliability.
  • Broad Configurability: Designed for new PCI Express (PCIe) 3.0 systems, the XE201R can be incorporated into industry-standard custom format mezzanine cards, special-purpose storage target controllers or daughter cards, providing Original Equipment Manufacturers (OEMs) with ultimate design flexibility.
  • vScale Virtualization Performance: The XE201R uses Emulex vScale, featuring an eight-core architecture, with full Fibre Channel and FCoE hardware offload. vScale enables optimum server efficiency and higher virtualization ratios with superior QoS.
  • vPath Virtual I/O Support: Emerging I/O virtualization standards, including Single Root I/O Virtualization (SR-IOV), Virtual Ethernet Port Aggregator (VEPA) and Virtual Ethernet Bridge (VEB), are supported by an internal Ethernet switch, which allows data to be forwarded between collocated virtual machines (VMs) while ensuring I/O traffic isolation.

OCe11000R UCNA
Emulex's next generation OCe11000R is based on the new XE4310R, a highly integrated, low-power, high performance 10GbE controller, ideal for accelerating network and storage application performance on servers and storage systems and for enterprise applications requiring 10Gb per second wire-speed performance, and advanced I/O virtualization. Key benefits of this new technology include:

  • Improved Signal Integrity and Reliability: The XE4310R also features new VCO technology for improved signal integrity and reliability.
  • Configurable Architecture: The XE4310R features an innovative purpose-built hardware architecture to carry network and storage traffic over two full-duplex 10GbE ports or four 1GbE ports, or a mix of two 10GbE and two 1GbE ports.
  • Multi-Protocol Offload Support: The XE4310R includes protocol offload support for TCP/IP, FCoE and iSCSI, minimizing CPU utilization and maximizing multi-core applications processing.

1According to Crehan Research, April 2012

About Emulex

Emulex, the leader in converged networking solutions, provides enterprise-class connectivity for servers, networks and storage devices within the data center. The company's product portfolio of Fibre Channel host bus adapters, network interface cards, converged network adapters, controllers, embedded bridges and switches, and connectivity management software are proven, tested and trusted by the world's largest and most demanding IT environments. Emulex solutions are used and offered by the industry's leading server and storage OEMs including, Cisco, Dell, EMC, Fujitsu, Hitachi, Hitachi Data Systems, HP, Huawei, IBM, NEC, NetApp and Oracle. Emulex is headquartered in Costa Mesa, Calif., and has offices and research facilities in North America, Asia and Europe. More information about Emulex (NYSE:ELX) is available at www.Emulex.com.

-----

Source: Emulex Corp.

Most Read Blogs

Aspen

Feature Articles

CometCloud: Using a Federated HPC-Cloud to Understand Fluid Flow in Microchannels

The ever-growing complexity of scientific and engineering problems continues to pose new computational challenges. Thus, we present a novel federation model that enables end-users with the ability to aggregate heterogeneous resource scale problems. The feasibility of this federation model has been proven, in the context of the UberCloud HPC Experiment, by gathering the most comprehensive information to date on the effects of pillars on microfluid channel flow.
Read more...

CERN, Google, and the Future of Global Science Initiatives

Large-scale, worldwide scientific initiatives rely on some cloud-based system to both coordinate efforts and manage computational efforts at peak times that cannot be contained within the combined in-house HPC resources. Last week at Google I/O, Brookhaven National Lab’s Sergey Panitkin discussed the role of the Google Compute Engine in providing computational support to ATLAS, a detector of high-energy particles at the Large Hadron Collider (LHC).
Read more...

Avoiding Scientific Computing Bottlenecks in the Cloud

Frank Ding, engineering analysis & technical computing manager at Simpson Strong-Tie, discussed the advantages of utilizing the cloud for occasional scientific computing, identified the obstacles to doing so, and proposed workarounds to some of those obstacles.
Read more...

Short Takes

NASA Builds 'Climate in a Box'

May 23, 2013 | he study of climate change is one of those scientific problems where it is almost essential to model the entire Earth to attain accurate results and make worthwhile predictions. In an attempt to make climate science more accessible to smaller research facilities, NASA introduced what they call ‘Climate in a Box,’ a system they note acts as a desktop supercomputer.
Read more...

Running Computational Fluid Dynamics in the Cloud

May 16, 2013 | When it comes to cloud, long distances mean unacceptably high latencies. Researchers from the University of Bonn in Germany examined those latency issues of doing CFD modeling in the cloud by utilizing a common CFD and its utilization in HPC instance types including both CPU and GPU cores of Amazon EC2.
Read more...

In Support of Cloud-based Rendering

May 10, 2013 | Australian visual effects company, Animal Logic, is considering a move to the public cloud.
Read more...

Internet2 Awards Program Seeks Innovative Applications

May 10, 2013 | Program provides cash awards up to $10,000 for the best open-source end-user applications deployed on 100G network.
Read more...

Sponsored Whitepapers

Best Practices in Big Data Storage

05/10/2013 | Cleversafe, Cray, DDN, NetApp, & Panasas | From Wall Street to Hollywood, drug discovery to homeland security, companies and organizations of all sizes and stripes are coming face to face with the challenges – and opportunities – afforded by Big Data. Before anyone can utilize these extraordinary data repositories, however, they must first harness and manage their data stores, and do so utilizing technologies that underscore affordability, security, and scalability.

Exploring the Potential of Heterogeneous Computing

04/02/2012 | AMD | Developers today are just beginning to explore the potential of heterogeneous computing, but the potential for this new paradigm is huge. This brief article reviews how the technology might impact a range of application development areas, including client experiences and cloud-based data management. As platforms like OpenCL continue to evolve, the benefits of heterogeneous computing will become even more accessible. Use this quick article to jump-start your own thinking on heterogeneous computing.

Sponsored Multimedias

Newsletters

Stay informed! Subscribe to HPC in the Cloud email Newsletters.

HPC in the Cloud Update
HPCwire Weekly Update
Digital Manufacturing Report
Datanami
HPCwire Conferences & Events
Job Bank
HPCwire Product Showcases



HPC Job Bank


Featured Events



  • June 16, 2013 - June 20, 2013
    ISC'13
    Leipzig,
    Germany

  • June 17, 2013 - June 18, 2013
    Forecast 2013
    San Francisco, CA
    United States




HPC in the Cloud Conferences & Events