| NextIO vCORE™ Express | ||
|
||
The vCORE Express product family includes the vCORE Express 2090, vCORE Express 2075, vCORE Express Lite 2090 and vCORE Express Lite 2075. Each are powered by NVIDIA® Tesla™ M2090 and M2075 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 .
NextIO vCORE™ Express 2090 and 2075 are designed with four NVIDIA 20-Series Tesla GPU's in a standard 1U 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™ M2090, or M2075 GPU's. 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.
NextIO vCORE™ Express Lite is a two GPU solution designed for entry-level workgroup and small cluster GPU computing. Designed with two NVIDIA Tesla M2090 or M2075 GPUs in a standard 1U chassis, the NextIO vCORE™ Express Lite scales to solve the world's most important computing challenges – more quickly and accurately. vCORE Express Lite is an entry level solution for consolidated GPU computing systems suitable for workstation, workgroup and small cluster computing applications requiring a small number of jobs and 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 server 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.
Technical Specifications
| Form Factor | • 1U |
| # of Tesla GPUs |
vCORE Express M2090 • 4 M2090 vCORE Express M2075 • 4 M2075 vCORE Express Lite 2090 • 2 M2090 vCORE Express Lite 2075 • 2 M2075 |
| # CUDA Cores |
M2090 • 512 M2075 • 448 |
| GPU Memory Speed |
M2090 • 1.85 GHz M2075 • 1.565 GHz |
| GPU Memory Interface | • 384-bit |
| GPU Memory Bandwidth (ECC off) |
M2090 • 177 GB/sec M2075 • 150 GB/sec |
| Double Precision Floating Point Performance (Peak) |
M2090 • 665 Gigaflops M2070 • 515 Gigaflops |
| Single Precision Floating Point Performance (Peak) |
M2090 • 1331 Gigaflops M2070 • 1030 Gigaflops |
| GPU Memory* |
• 6GB GDDR5
*Note: With ECC on, a portion of the dedicated memory is used for ECC bits, so the available user memory is reduced by 12.5%. (e.g. 6 GB total memory yields 5.25 GB of user available memory.) |
| Power Consumption (Typical) | • 900W TDP |
| System Interface | • PCI Express x16 Gen2 |
| Software Development Tools |
• CUDA C/C++/Fortran, OpenCL, DirectCompute Toolkits • NVIDIA Parallel Nsight™ for Visual Studio |
NextIO vCORE™ Express Datasheet
Click here to download the vCORE Express datasheet
NextIO vCORE™ Express Lite Datasheet
Click here to download the vCORE Express Lite datasheet
NVIDIA Tesla™ M-class GPU Computing Modules Datasheet
Click here to download the Tesla M-class GPU Computing Modules datasheet
NVIDIA CUDA™ NVIDIA CUDA™ technology is the world’s only C language environment that enables programmers and developers to write software to solve complex computational problems in a fraction of the time by tapping into the many-core parallel processing power of GPUs. With millions of CUDA-capable GPUs already deployed, thousands of software programmers are already using the free CUDA software tools to accelerate applications—from video and audio encoding to oil and gas exploration, product design, medical imaging, and scientific research. Click here to learn more
NVIDIA CUDA Development Tools NVIDIA’s CUDA development tools provide three key components to help you get started: the latest CUDA driver, a complete CUDA Toolkit, and CUDA SDK code samples. Click here to download CUDA driver and toolkit