vCORE Express: for GPU cluster and GPU supercomputing requirements

vCORE Express 2090

The World's fastest HPC GPU compute system

v-core express

The NextIO vCORE™ Express 2090 is an HPC GPU compute solution designed for large scale deployment of the most demanding HPC GPU supercomputing applications. vCORE Express 2090 is powered by the latest and most powerful NVIDIA® Tesla™ M2090 GPU's, and can accelerate scientific computations – including seismic processing, biochemistry simulations, weather and climate modeling, signal processing, computational finance, CAE, CFD, and data analysis – by up to 10X .

Based on the massively parallel CUDA GPU computing architecture, the vCORE Express 2090 features many must have HPC capabilities including:

  • 4 Tesla M2090 GPUs
  • 2.6 TFLOPS of DP calculations (665 GFLOPS/GPU)
  • 5.3 TFLOPS of SP calculations (1331 GFLOPS/GPU)
  • 2048 processing cores (512/GPU)
  • ECC Memory for uncompromised accuracy and reliability
  • GPUs have L1/L2 cache for improved bandwidth and data sharing

The NextIO vCORE™ Express line of GPU computing solutions deliver "must have" features for the technical and enterprise workgroup computing space. Compared to typical multi-core CPUs, vCORE Express delivers equivalent performance at 1/10th the cost and 1/20th the power consumption.

Designed with the NVIDIA 20-Series Tesla GPU's in a 1U GPU chassis, the NextIO vCORE™ Express scales to solve the world's most important computing challenges more quickly and accurately. vCORE Express is built upon the same design as the NVIDIA Tesla 1U products and incorporates the latest NVIDIA® Tesla™ M2070, or M2090 GPU's.

vCORE Express is a powerful solution for consolidated GPU computing systems suitable for all levels of HPC computing from workstation to workgroup to small flexible cluster computing to large scale fixed configuration.

The NextIO vCORE™ Express enables customers to run GPU's outside of their servers providing more dense server configurations, easier lifecycle management and a lower overall cost of ownership.

  • Dense Server Clusters: By removing GPU's from servers and extending connectivity from servers to GPU's over high speed PCI Express, smaller and more dense hybrid server GPU clusters can be realized in the data center. A 1U vCORE Express system provides each server with 4 Fermi-based GPU's.
  • Easier Lifecycle Management: GPU's and Servers each have different lifecycles, but when a GPU is located inside a server their lifecycles are merged. Whenever a server or GPU is upgraded, the server must be brought down, opened, and the GPU replaced. In most cases the server is also upgraded at the same time whether its at the end of its lifecycle or not. vCORE Express separates the GPU from the server and allows each to be managed separately while minimizing downtime.
  • Lower Total Cost of Ownership: Compared to multi-core CPU clusters, vCORE Express is at least 1/10th the cost – factoring in the number of servers and infrastructure for equivalent performance to GPU computing systems. When compared to servers with embedded GPU's, the savings associated with lifecycle management will often justify the price of a vCORE system.

For more information, download the vCORE Express 2090 data sheet or to purchase vCore Express, contact NextIO for a reseller partner in your area