Custom configurations
Many custom configurations are available, including drive configurations, expansion cards, etc.
If you don't see the configuration you're looking for, use your Custom System form so we can configure your perfect machine.
Warranty and support
All systems come with our standard 9x5 one year cross-ship return to depot warranty. Upgraded warranty options including multiple years, 24x7, and on-site service are available. Read more information about our warranties.
Lifetime technical support is included with every Advanced Clustering system. This includes support via, email, or our toll-free support telephone line.
|
|
GPU Clusters
Overview
Advanced Clustering's GPU clusters consist of our innovative Pinnacle Compute Blade products and the 1U NVIDIA Tesla S2050 or S2070 Computing Systems. This flexible and modular design allows for mixing and matching of GPU and CPU configurations while at the same time preserving precious rack and datacenter space.
The most common configuration is a pair of Pinnacle Compute blade servers connected to one NVIDIA Tesla Computing System, which provides 2x Tesla Fermi-based GPUs per server system. This configuration offers a maximum of 2x dual-processor servers (4x CPUs) connected to 4x GPUs. Each server system can be customized with either AMD or Intel processors, multiple RAM configurations, and gigabit ethernet with options for 10-gigabit ethernet or InfiniBand.
Features and Benefits of Tesla Computing Systems
 GPUs Powered by the Fermi-Generation of the CUDA Architecture
Delivers cluster performance at 1/10th the cost and 1/20th the power of CPU-only systems based on the latest quad-core CPUs.
448 CUDA Cores per GPU (4x GPU in 1U)
Delivers up to 515 Gigaflops of double-precision peak performance in each GPU, enabling 2 Teraflops of double-precision performance in 1U of space. Single precision peak performance is more than a Teraflop per GPU.
ECC Memory
Meets a critical requirement for mission-critical applications with uncompromised computing accuracy and reliability. Offers protection of data in memory to enhance data integrity and reliability for applications. Register files, L1/L2 caches, shared memory, and DRAM all are Ecc protected.
Up to 6GB of GDDR5 Memory per GPU
Maximizes performance and reduces data transfers by keeping larger data sets in local memory that is attached directly to the GPU. Tesla S2050 includes 3GB/GPU.
CUDA Programming Environment
Choose C, C++, OpenCL, DirectCompute, or Fortran to express application parallelism and take advantage of the “Fermi” GPU’s innovative architecture.
More information:
Contact Us
Whatever your GPU computing needs are, you can be sure that Advanced Clustering has the experience and technical know-how to help. Our expert staff can assist you with your GPU computing questions and design a solution that's right for you. Give us a call at 866-802-8222 or Contact us for more information. |
|
Products 