| ICC NovaServ™ SuperMicro Based 8 Tesla GPU SimCluster | ICC NovaServ™ Supermicro Based 16 Tesla GPU SimCluster | ICC NovaServ™ Supermicro Based 32 Tesla GPU SimCluster | |
|---|---|---|---|
| Performance | 10 TeraFlops | 20 TeraFlops | 42 TeraFlops |
| GPU | 8 Tesla M2090 GPUs with CUDA 4.0 | 16 Tesla M2090 GPUs with CUDA 4.0 | 32 Tesla M2090 GPUs with CUDA 4.0 |
| CPU | 8 Intel® Westmere X5650 2.66 GHz (6-core) | 16 Intel® Westmere X5650 2.66 GHz (6-core) | 32 Intel® Westmere X5650 2.66 GHz (6-core) |
| Nodes | 4 SuperMicro® SuperServer 6016GT-T GPU Nodes | 8 SuperMicro® SuperServer 6016GT-T GPU Nodes | 16 SuperMicro® SuperServer 6016GT-T GPU Nodes |
| Master Node | No separate master node | SuperMicro SuperServer 6016T-NTF | SuperMicro SuperServer 6016T-NTF |
| Memory | 96 GB | 192 GB | 384 GB |
| Network | Infiniband | Infiniband | Infiniband |
| Storage | 4 TB | 8 TB | 16 TB |
| Form-Factor | 14U Rack | 14U Rack | 42U Rack |
| Configure | 8 TESLA GPU SIMCLUSTER | 16 TESLA GPU SIMCLUSTER | 32 TESLA GPU SIMCLUSTER |
SuperMicro Based Tesla GPU SimClusters
Empower your Supercomputing with ICC's NovaServ™ Solutions
ICC NovaServ™ Tesla GPU SimCluster solutions integrate cutting-edge technology from our industry-leading partners. They are ready-to-deploy cluster solutions off the shelf, delivering the power of CPU-GPU parallel processing, the easiest way to purchase and utilize your GPU-based research cluster. The 1U 6016GT-T is a powerful stand-alone system. But the real power in high performance computing and GPU supercomputing comes from the ability to scale upward through computer clusters. By transforming the base 6016GT-T into such a configuration you gain an asset with incredible performance potential that draws upon the combined AND clustered power of CPU and GPU.
Our NovaServ™ line is optimized for performance and simplicity. With our preconfigured turnkey solutions, you are able to deploy your GPU SimCluster with no hassle or worry over the technology. Let us propel your supercomputing to new heights!
-
GPU SimClusters for HPC
Tesla GPU SimClusters make new things possible in high performance computing. For scientific, engineering, and other fields with high computational needs, NVIDIA®'s CUDA programming language for GPU performance is essential.
-
Molecular Dynamics
One of the top applications for GPU SimClusters is in molecular dynamics (MD). Tesla GPU SimClusters significantly accelerate simulation processes and have long supported MD codes such as AMBER and NAMD.
-
Financial Supercomputing
GPU solutions can have an enormous impact on an organization's computational finance capabilities. Tesla GPU with CUDA is the perfect answer to the complexity of options pricing, risk analysis, and algorithmic trading.
-
Bottom Line? Tesla GPU SimClusters Blow Away the Competition
Virtually across-the-board, tests show that GPU SimClusters have the edge over CPU-only systems. In one case, 4 Tesla GPU outperformed a cluster with 16 quad-core CPUs. In another test, a Tesla GPU pairing enalbed over 10x greater speed compared to a single quad-core CPU!
Why International Computer Concepts?
Cutting-edge technology
Famous for being first-to-market (like with 1U GPU servers), ICC delivers the latest computing solutions for an affordable price as soon as they become available.
Fast delivery
We expedite shipping so you can get on with the business of running your business.
Dedicated customer service
Have some questions? Call us ,or chat with us by clicking the "Live Chat" button at the top of the page, and we'll be happy to answer them.
Trusted industry partner
Official partners with Supermicro®, Intel®, AMD®, Microsoft®, NVIDIA® and many others. ISO 9001:2000 compliant.
NVIDIA, the NVIDIA logo, and Tesla, are trademarks and/or registered trademarks of NVIDIA Corporation in the United States and other countries.
