November 11, 2009
New memory module, HyperCloud, enables 384GB of DRAM in a dual socket server
IRVINE, Calif., Nov. 11 -- Netlist, Inc., a designer and manufacturer of high-performance memory subsystems, today launches HyperCloud, the world's first 16GB, 2 virtual rank (vRank) memory module for servers. A double-data-rate three, registered dual in-line memory module (DDR3 RDIMM), HyperCloud maximizes server utilization to improve datacenter application performance. HyperCloud allows 384 Gigabytes (GB) of dynamic random access memory (DRAM) to be populated in a single dual socket server, reaching unprecedented levels of server performance.
HyperCloud utilizes Netlist's patented rank multiplication ASIC technology to fully populate three memory channels with 16GB vRank RDIMMs. Four physical ranks are hidden from the memory controller hub and presented as 2 vRanks. Dual socket servers can then be fully populated with 24 16GB 2 vRank RDIMMs reaching a total capacity of 384GB.
"In HPC datacenters, servers are typically under-utilized due to memory bandwidth and memory capacity bottlenecks. Netlist is addressing these limitations with its new high-performing DDR3 RDIMM solution, called HyperCloud," said Steve Conway, research vice president of technical computing at IDC. "HyperCloud is designed to improve server productivity and application performance, especially for memory-intensive applications and workloads."
With load reduction, servers populated with four DIMMs per channel can operate at the highest transfer-rate of 1333MT/s providing maximum memory bandwidth, increased server performance and low latency.
"HyperCloud marks an important step for Netlist as we look to fill the datacenter memory gap," said C.K. Hong, president and CEO of Netlist. "Growth in key technologies like virtualization and cloud computing has been stymied by the limitations of existing memory solutions. By breaking memory barriers, HyperCloud successfully supports these applications and others like high-performance computing. Maximizing memory is the easiest way to improve performance and lower operating expenses for datacenters."
HyperCloud will debut at the Supercomputing tradeshow, taking place in Portland, Ore., Nov. 17-19, 2009, in booth number 2398. Netlist plans to sample HyperCloud to major OEM customers in December with production slated for Q1 2010. HyperCloud will be available in 4GB, 8GB, and 16GB 2 vRank module options.
Netlist, Inc. (NASDAQ: NLST) designs and manufactures high-performance, logic-based memory subsystems for the server and high-performance computing and communications markets. The company's memory subsystems are developed for applications in which high-speed, high-capacity memory, functionality, small form factor, and heat dissipation are key requirements. These applications include tower-servers, rack-mounted servers, blade servers, high-performance computing clusters, engineering workstations, and telecommunication equipment. Netlist was founded in 2000 and is headquartered in Irvine, Calif., with manufacturing facilities in Suzhou, People's Republic of China.
Source: Netlist, Inc.
10/30/2013 | Cray, DDN, Mellanox, NetApp, ScaleMP, Supermicro, Xyratex | Creating data is easy… the challenge is getting it to the right place to make use of it. This paper discusses fresh solutions that can directly increase I/O efficiency, and the applications of these solutions to current, and new technology infrastructures.
10/01/2013 | IBM | A new trend is developing in the HPC space that is also affecting enterprise computing productivity with the arrival of “ultra-dense” hyper-scale servers.
Ken Claffey, SVP and General Manager at Xyratex, presents ClusterStor at the Vendor Showdown at ISC13 in Leipzig, Germany.
Join HPCwire Editor Nicole Hemsoth and Dr. David Bader from Georgia Tech as they take center stage on opening night at Atlanta's first Big Data Kick Off Week, filmed in front of a live audience. Nicole and David look at the evolution of HPC, today's big data challenges, discuss real world solutions, and reveal their predictions. Exactly what does the future holds for HPC?