By combining 3 or 4 NVIDIA® Tesla™ C1060 Computing Processors into a single system, you can now enable your customers to experience cluster level computing performance – up to 250 times faster than standard PCs and workstations—right at their desk.
Why Do Computational Researchers, Graduate Students and Scientists Need a Tesla Personal Supercomputer?
1. It offers true cluster performance.
- Four Tesla GPU computing processors deliver nearly 4 Teraflops of performance and 16GB of dedicated compute memory in a desktop system - the computing equivalent of two racks of clustered Quad core servers.
- Powered by up to 960 parallel processing cores, the massively parallel GPU architecture can execute thousands of concurrent threads, and is up to 250 times faster than a multi-CPU core PC or workstation using traditional serial computing.
- Double and single IEEE 754 Floating Point Precision provides results that are consistent across platforms and meet industry standards.
2. It’s a dedicated supercomputing resource.
- With never-before-possible compute performance at the desktop, researchers can conduct complex computations at their desks, without the cost and difficulty associated with using a shared supercomputer.
- A Tesla Personal Supercomputer takes advantage of the revolutionary compute density of GPU computing, providing cluster performance with 15 times the power efficiency.
- It plugs into a standard power strip and operates quietly so your customers can take advantage of cluster level performance anytime they want, right from their desk.
3. It’s easy to use.
- The NVIDIA® CUDA® architecture and C programming environment is widely accepted, easy to learn and simplifies programming parallel applications.
Your Recipe to Build A Personal Supercomputer
- 3 or 4 Tesla C1060 Computing Processors with 4GB of dedicated memory per GPU
- 2.33 GHz+ Quad-core AMD Phenom or Opteron-- OR -- Quad-core Intel Core 2 or Xeon Processor
- Quadro NVS or NVIDIA motherboard graphics*
- 12GB+ system memory (at least 4GB per Tesla C1060)
- 1200-1350 Watt Power supply
- Microsoft® Windows® XP 64-bit and 32-bit (64-bit recommended)
- Linux® 64-bit and 32-bit (64-bit recommended)
- Red Hat Enterprise Linux 4 and 5
- SUSE 10.1, 10.2 and 10.3
*Current recommended motherboards include:
- Foxconn Destroyer 780a: On-board NVIDIA GPU + 4 Tesla C1060s
- MSI K9A2 Platinum 790FX: 3 Tesla C1060s + 1 Quadro FX
- Intel SkullTrail D5400XS : 3 Tesla C1060s + 1 Quadro FX3700
NVIDIA licenses the official NVIDIA Tesla Personal Supercomputer badge to those system builders who meet minimum system specs, successfully pass the system self-validation process, and meet branding requirements. System test documentation and instructions are available on the PartnerForce Portal.
Start building, testing and branding your Tesla Personal Supercomputers today!
NVIDIA Tesla solutions are available now at Synnex. Contact sales at Synnex at (800) 756-9888.
Learn more:
Visit the NVIDIA Tesla Supercomputer Web site
