June 01, 2010
NextIO vCORETM C200 delivers a modular, manageable GPU solution for pooling and scaling GPU resources among servers and workstations
AUSTIN, Texas, June 1 -- NextIO, the premier provider of next-generation I/O consolidated solutions, today announced the release of the vCORE C200 GPU Consolidation Appliance, the first product that brings enterprise-class features to a GPU compute platform. NextIO's vCORE C200 represents the next-generation of GPU compute solutions by delivering serviceability, manageability and flexibility to today's GPU farms through increased server uptime and reduced GPU over-provisioning. vCORE C200 was launched this week at the 2010 International Supercomputing Conference (ISC) in Hamburg Germany, May 30 – June 3 at booth #700.
Due to their high core densities and low cost, Tesla GPU solutions are one of the fastest-growing technologies in the High Performance Computing industry. NVIDIA Tesla GPUs are typically installed in servers and workstations as a single unit or in pairs, and can deliver server performance equal to supercomputers for a fraction of the price. However, managing and scaling GPUs has been challenging because each GPU is dedicated to a specific server. NextIO's vCORE C200 solves this issue by allowing NVIDIA Tesla GPUs to be added "on-demand" to servers as required. By pooling, sharing and dynamically reconfiguring up to eight Tesla GPUs per server, vCORE addresses the need for managing GPUs in a dynamic high performance computing (HPC) environment. Its modular architecture also allows GPUs to be hot-swapped or updated without disrupting jobs already running on the system.
"One of the main hurdles for the rapid adoption of GPUs arises from the management complexity of the new heterogeneous computing environment," said Jie Wu, Research Director, Technical Computing, IDC. "The ability to pool, share and dynamically reconfigure GPUs across multiple servers will allow HPC users to not only achieve performance gain for their applications, but also improve the resources utilization, resulting in improved GPU value as well as significantly lower total cost of ownership (TCO) for their organizations."
NextIO's vCORE product family exclusively offers NVIDIA's record-setting GPUs for both compute-intensive and data visualization needs. With the ability to hold eight double-wide GPUs in 4U of space, the vCORE C200 delivers over eight TeraFLOPS of GPU computing power that can be provisioned and managed through a simple-to-use interface. The fully serviceable and redundant design, together with NextIO's patented vConnectTM switching technology, allows vCORE to dynamically map Tesla GPUs to servers as needed, increasing the GPU utilization in HPC clusters. The hot-plug capability and serviceable chassis provides quick repair of GPUs and eliminates the need for "forklift" upgrades to migrate to the newest GPU. In addition, GPUs can be driven by industry-standard resource schedulers to deliver GPU compute power when needed, which makes vCORE C200 ideal for medium-to-large clusters.
"Tesla 20-series GPUs are designed to meet the specific needs of the HPC applications, and we are seeing many cluster deployments as a result," said Andy Keane, general manager of the Tesla business at NVIDIA. "The ability to scale a large number of GPUs per node is critical, and vCORE C200 allows users to manage and dynamically reconfigure these resources across multiple servers."
Ideally suited for customers with high job counts, high GPU counts or a combination of both, vCORE C200 increases business value with more effective jobs per time period and reduces GPU management overhead for many industries, including:
"Customers have expressed the need for a smooth, non-disruptive way to allocate, provision, and service their GPUs," said Mike Heumann, vice president of worldwide marketing at NextIO. "We developed the vCORE C200 to help customers manage their GPU resources, reduce their operational costs and avoid over-provisioning their infrastructure. vCORE C200 allows customers to manage and upgrade their GPUs without experiencing disruptions."
The family of NextIO vCORE C200 products includes NVIDIA Tesla 20-series GPUs bundled in a variety of configurations and can be ordered now for delivery in July. NextIO also offers the vSTOR Application Acceleration Appliance that provides the highest flash performance for applications requiring high-speed storage transactions (IOPS) or high bandwidth at the lowest cost.
NextIO, Inc. is the leader in next-generation network consolidation solutions for today's dynamic datacenter in a variety of industries including enterprise, oil and gas, high performance computing, digital media and financial services. With its innovative vConnect platforms, NextIO offers the unique ability to virtualize I/O technology on any server, operating system, hypervisor and storage architecture. Leveraging PCI Express, NextIO offers true I/O consolidation for any end-point technology. vConnect delivers unprecedented rack-level scalability, with I/O and server resources that can be scaled independently for 50-70 percent savings in capital, power, and cooling. NextIO's any-to-any I/O connectivity boosts performance and reliability while streamlining IT deployment, simplifying administration and reducing costs. For more information, visit www.nextio.com.
Source: NextIO, 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?