Select Country: India l Singapore       
 
Sitemap | Feedback | Press Release
 
  Home >Products and Solutions > Clusters > GpGpu    
 
 
NVIDIA Tesla based
Supercomputing Solutions

Get your own supercomputer. Experience cluster level computing performance-up to 250 times faster than standard PCs and workstations-right at your desk. The NVIDIA® Tesla Personal Supercomputer is based on the revolutionary NVIDIA® CUDA parallel computing architecture and powered by up to 960 parallel processing cores.

GPUs have evolved to the point where many real-world applications are easily implemented on them and run significantly faster than on multi-core systems. Future computing architectures will be hybrid systems with parallel-core GPUs working in tandem with multi-core CPUs.

Netweb offers solutions based on NVIDIA® Tesla C1060 and S1070. These solutions enable every computational researcher and technical professional to have a dedicated computing resource. It plugs into a standard office power socket and is quiet enough for use at your desk. You can scale your applications to multiple GPUs and harness the performance of thousands of processor cores to solve large-scale problems. Each Tesla C1060 GPU has 240 scalar processor cores and delivers 933 GFlops Single Precision and 78 GFlops Double Precision performance. Up to 4 C1060 can fit into a single system for a performance of almost 4TFLOPS. NVIDIA® Tesla S1070 in combination with Supermicro Twin1U enables a performance of approx 4TFLOPS in a 2U form factor. A cluster with as few as 250 of these systems would have a peak theoretical performance of a petaflop. It delivers incredible performance per watt and can upgrade the performance of your datacenters without requiring infrastructure changes for power or cooling.

Connecting Tesla S1070 to Host Servers Some suggested configurations
16 teraflops in single precision and 1.384 teraflops in Double
precision using about 11u of rack space
1 x Frontend
2 x Intel Xeon E5410
16 GB of RAM per system
4 x 146GB 15000RPM SAS HDD
Redundant Power supply
4 Twin1U systems (consisting of 8 dual-xeon servers)
2 x Intel Xeon E5410 per system
16 GB of RAM per system
1 x 250GB Serial-ATA HDD per system
4X DDR InfiniBand onboard
4 x Tesla S1070
1 x 24-port InfiniBand switch
1 x 24-port Gigabit Switch
32 teraflops in single precision and 2.768 teraflops in Double precision using about 19u of rack space
1 x Frontend
2 x Intel Xeon E5410
16 GB of RAM per system
4 x 146GB 15000RPM SAS HDD
Redundant Power supply
8 Twin1U systems (consisting of 8 dual-xeon servers)
2 x Intel Xeon E5410 per system
16 GB of RAM per system
1 x 250GB Serial-ATA HDD per system
4X DDR InfiniBand onboard
8 x Tesla S1070
1 x 24-port InfiniBand switch
1 x 24-port Gigabit Switch
64 teraflops in single precision and 5.536 teraflops in Double precision using about 35u of rack space
 
1 x Frontend
2 x Intel Xeon E5410
16 GB of RAM per system
4 x 146GB 15000RPM SAS HDD
Redundant Power supply
16 Twin1U systems (consisting of 8 dual-xeon servers)
2 x Intel Xeon E5410 per system
16 GB of RAM per system
1 x 250GB Serial-ATA HDD per system
4X DDR InfiniBand onboard
16 x Tesla S1070
1 x 24-port InfiniBand switch
1 x 24-port Gigabit Switch
 
 
Home About us Products
- Clusters
- Motherboards
- Chassis
- RAID Controllers 
- High Speed Interconnect
Solutions
Alliances
Contact Us

Sitemap
Feedback
Press Release
- Overview
- Order Status
- Case Studies
- Online Support
- Company Profile
- Locations
- Key Strengths
- Milestones
- Servers
- Workstations
- Blade
- Storage