Microway (R) Technology you can count on.  
               508-746-7341  
HPC Newsletter
Clusters
Designers and Manufacturers of HTPC Solutions Since 1982
Workstations
Servers
Storage
White Papers
Custom Chassis
Software
Tech Overview
Alpha
Partners

 


Microway® to Showcase NVIDIA® Tesla™ GPU-Based Products and 32 Core AMD® Opteron Servers at HPCC in Newport, RI March 25-26, 2008


Contact Bruce Schulman, Director of Business Development bschulman@microway.com

Kingston, MA - March 6, 2008 -

At HPCC Newport, Microway will exhibit a WhisperStation, featuring NVIDIA Tesla GPUs and the Tesla S870 GPU computing Server. These new offerings have gained wide acceptance in industries where OpenMP applications employing hundreds of parallel threads are used to speed up floating point operations. These include tomography, oil and gas, simulation of complex molecular systems and other numeric or computationally intensive applications. Microway will also exhibit their Navion™ 8 processor, 32 core Opteron server. This server can be used stand alone for demanding HPC applications, or as the master node of an HPC computational cluster.

The Tesla C870 processor employs a massively multi-threaded architecture with 128 independent IEEE 754 single precision floating point cores. Coupled with NVIDIA CUDA™ - a suite of developer tools including a C-compiler, debugger, performance profiler and optimized libraries- one or two Tesla C870 cards transform a standard workstation into a personal supercomputer. The product delivers 518 gigaflops of peak floating point performance, 1.5 GB local memory and up to 76.8 GB/sec. memory bandwidth per GPU.

The Tesla S870 server incorporates four Tesla GPUs in a 1U platform which can be incorporated into any HPC cluster. Multiple GPUs can be controlled by a single system via the GPU computing driver, delivering incredible throughput on computing applications. The power of the GPU to solve large-scale problems can be multiplied by splitting the problem across multiple GPUs. System monitoring, thermal control and fault notification in the server product provide the necessary features for efficient integration of GPU computing servers into the data center.

Benchmarks have shown an incredible increase in GFLOPS by offloading computations to the GPU. VMD, a molecular modeling application from UIUC, has obtained an amazing 291 GFLOPS performing a computation of the coulombic interactions. By comparison, a typical dual Opteron or Xeon system will only get 1-2 GFLOPS.

"As multi-core and parallel processing architectures become ubiquitous in high performance computing, computer scientists around the world are beginning to fundamentally advance the pace of their research," said Andy Keane, general manager of the GPU Computing business at NVIDIA. "The massively multi-threaded core of the GPU positions it at the very heart of this revolution and with the support of companies like Microway, we look forward to making the promise of the "personal supercomputer" a reality."

"Historically, math coprocessors have been utilized in the HPC space to provide higher throughput for floating point calculations," commented Stephen Fried, Microway"s CTO. "Now, a new era of coprocessing has begun, leveraging COTS parts to dramatically improve performance while still being very affordable. In fact, utilization of GPU computing improves your price/performance ratio significantly. Power savings can also be realized through reduction in the number of systems needed to effectively compute your applications. It"s win-win!"

About the Navion-QQ™ Server
This powerful SMP computational platform is designed for four or eight Quad-Core AMD Opteron™ processors, up to 128 GB memory and eight drives in Microway"s 4U RuggedRack™. With redundant power and excellent cooling, the Navion-QQ server is an exceptionally quiet 4/8 way AMD Opteron-based configuration. It is ideal for compute-intensive applications including DSP, CFD and FEA, as well as high-performance database and enterprise-class applications. Navion-Q, a dual processor version designed for clusters, features two Quad-Core AMD Opteron processors packed into a robustly cooled 1U rack chassis. A standard cabinet can contain up to 336 cores. All Navion configurations have been "quietized" by employing noise reducing technologies and are available running many flavors of Linux or Microsoft Windows® 2003 Enterprise operating systems.

Microway"s integrated advanced manageability features have been refined over years of development and hundreds of real-world cluster deployments. Microway"s NodeWatch™ and MCMS™ hardware/software management solution for remote cluster monitoring and control are included as standard features on the Navion-QQ and Navion-Q. Well known for expertise in cooling, Microway"s achieved operating temperatures are consistently lower than industry guidelines. Both the 1U CoolFlow™ chassis and 4U RuggedRack feature proprietary Across-the-Board™ enhanced cooling. The RuggedRack includes front access hard disks and Hot-Swap power supplies. This allows the most common system failures to be serviced without powering off the server, or even removing the unit from a cabinet.

Microway"s Navion-QQ, Navion-Q and WhisperStation are also available as multi-function SMP storage servers. Navion-QQ supports HPC/Enterprise applications while providing up to 48 Terabytes of Storage in one single machine! One 19" Microway CoolRak™ cabinet can provide 384 Terabytes of Storage along with 128 cores of compute power sharing 512 GBs of memory. These machines are all fault tolerant, highly available with redundant power.

About Quad-Core Opterons
Technical innovations of the new Quad-Core AMD Opteron processors are of special importance to data center design and TCO considerations. AMD"s native Quad-Core AMD Opteron processors are packed with core and cache enhancements designed to improve performance of server and workstation applications. They also feature power efficient features such as AMD CoolCore™ technology, designed to turn off portions of the processor logic and memory controller when not in use, helping to reduce processor energy consumption and heat generation. Dual Dynamic Power Management offers separate power planes for the cores and integrated memory controller for optimum performance and reduced power consumption, and Independent Dynamic Core Technology, designed to allow each core"s utilization to be separately controlled for better power management for a reduction in power consumption. Enhanced AMD PowerNow!™ technology can help lower the total operational cost of datacenters by reducing processor power consumption during non-peak workloads, thereby reducing heat generation and decreasing strain on facility cooling systems to protect investments in today"s demanding data processing environments.

"The AMD Opteron processor is designed to meet the demands of the HPC market. Critical features of the processor, like its integrated memory controller and HyperTransport technology, provide it with a clear advantage over the front side bus-based architecture that has dominated the x86 space for many years. AMD"s latest innovation, a native quad-core design with 4 cores on a single die, enables programs that are not memory-bound to take full advantage of the additional processing power," commented Stephen Fried, President and CTO, Microway, Inc. "Programs that can dramatically improve in speed include floating point intensive computations, like FFTs, which have high data re-use rates; SMP applications that make frequent calls, including transaction-based business applications; and programs that depend on byte code interpreters like JAVA to carry the work load. Quad-Core AMD Opteron processors will change the face of high performance computing."

"Microway"s outstanding cooling technology combined with the energy-efficient capabilities of AMD Opteron processors continues to deliver world-class performance to both data center and high-performance computing customers, without compromising power consumption," said Patrick Patla, Director of Product Management, Server/Workstation Division, AMD (NYSE: AMD). "Quad-Core AMD Opteron processors provide performance-on-demand capabilities for optimum performance-per-watt and outstanding power savings, helping to maximize utilization."


About Microway, Inc.
Incorporated in 1982, Microway is a leader in the high performance computing market, designing state-of-the-art, high-end Linux clusters, servers, and data storage solutions. Users worldwide, pushing the limits of technology, who choose Microway include universities, life sciences, financial, military, Fortune 500s and research agencies. Microway partners with leading commercial software providers to include products such as SUSE and Red Hat Enterprise Linux, PathScale and PGI Compilers on its AMD Opteron-based clusters and storage servers. Microway is an AMD Platinum Partner, Intel Premier Channel Partner, Mellanox partner, Nvidia PartnerForce Premier Member and Novell Gold Partner. Classified as a small business, woman owned and operated, Microway"s GSA Contract Number is GS-35F-0431N.

Microway, InfiniScope, FasTree, MCMS, MPI Link-Checker, Navion, NodeWatch, Quadputer, ServaStor, TriCom and WhisperStation are trademarks or registered trademarks of Microway, Inc.

AMD, the AMD Arrow logo, AMD Opteron, and combinations thereof, are trademarks or registered trademarks of Advanced Micro Devices, Inc. Intel is a registered trademark of Intel Corporation (NASDAQ: INTC).  Mellanox is a registered trademark of Mellanox Technologies, LTD (NASDAQ: MLNX).  NVIDIA is a registered trademark and Tesla and CUDA are trademarks of NVIDIA Corporation (NASDAQ: NVDA).  Other names are for informational purposes only and may be trademarks of their respective companies.

 

 

  Our mission is to provide customers with leading edge technologies for high performance computing solutions (HPC). We establish and maintain industry recognized products and expertise for beowolf cluster interconnect, clustre management and HPC storage solutions.