|
| Home > Corporate Solutions > GPU Computing > High Performance Computing GPU Solutions |
| |
|
Complete Tesla Product Line: |
GPU Workstations |
| Tesla GPU |
SP Floating Point Performance (Peak) |
DP Floating Point Performance (Peak) |
CPU |
Model |
|
1,792
Cores |
4.12 Teraflops |
2,060 GFLOPS |
Dual Intel Xeon 5600 series processors |
PSC - 2n |
 |
1,344
Cores |
3.09 Teraflops |
1.545 Teraflops |
Single Intel Core i7 processor |
PSC - 1i |
|
896
Cores |
2.06 Teraflops |
1,030 GFLOPS |
Dual Intel Xeon 5600 series processors |
PSC - 5n |
|
960
Cores |
4 Teraflops |
312 GFLOPS |
Dual Intel Xeon 5600 series processors |
PSC - 2n |
|
480
Cores |
2 Teraflops |
156 GFLOPS |
Dual Intel Xeon 5600 series processors |
PSC - 5n |
|
|
 |
GPU Servers |
| Tesla GPU |
SP Floating Point Performance (Peak) |
DP Floating Point Performance (Peak) |
Hard Disk Drive Bays |
CPU |
Model |
|
3,584
Cores
|
8.24 Teraflops |
4.12 Teraflops |
1 x internal |
Dual Intel Xeon 5600 series processors |
Xn - 4101G |
|
1,920
Cores |
8 Teraflops |
624 GFLOPS |
1 x internal |
Dual Intel Xeon 5600 series processors |
Xn - 4101G |
|
896
Cores |
2.06 Teraflops |
1,030 GFLOPS |
6 x hot swap 2.5" SATA |
Dual Intel Xeon 5600 series processors |
Xn - 1114G |
|
896
Cores |
2.06 Teraflops |
1,030 GFLOPS |
3 x hot swap 3.5" SATA |
Dual Intel Xeon 5600 series processors |
Xn - 1113G |
|
480
Cores |
2 Teraflops |
156 GFLOPS |
6 x hot swap 2.5" SATA |
Dual Intel Xeon 5600 series processors |
Xn - 1114G |
|
480
Cores |
2 Teraflops |
156 GFLOPS |
3 x hot swap 3.5" SATA |
Dual Intel Xeon 5600 series processors |
Xn - 1113G |
|
480
Cores |
2 Teraflops |
156 GFLOPS |
3 x hot swap 3.5" SATA |
Dual Intel Xeon 5600 series processors |
Xn - 1113M |
|
960
Cores |
4 Teraflops |
312 GFLOPS |
|
|
Tesla S1070 |
|
1,792
Cores |
4.12 Teraflops |
2,060 GFLOPS |
|
|
Tesla S2050 |
|
|
With the world's first teraflop many-core processor, NVIDIA® Tesla™ high performance computing (HPC) solutions enable the necessary transition to energy efficient parallel computing power. With 448 cores per processor and a standard C compiler that simplifies application development, Tesla™ scales to solve the world's most important computing challenges-more quickly and accurately.
Tesla™ is a dedicated, high performance GPU computing solution, bring supercomputing power to any workstation or server and to standard, CPU-based server clusters.
- GPUs powered by the massively parallel CUDA architecture, transforming a GPU solution to perform like a small cluster at 1/20th the power consumption and 1/10th the cost.
- CUDA programming environment with broad support of programming languages and APIs, including C, C++, OpenCL, DirectCompute, or Fortran
- IEEE 754 single and double Precision floating point units, delivering up to 8X the double precision performance compared with previous generation of GPU products
• ECC Support, meeting a critical requirement for datacenters and supercomputing centers deploying GPUs on a large scale with uncompromised computing accuracy and reliability.
- NVIDIA® Parallel DataCache™, accelerating algorithms such as physics solvers, ray-tracing, and sparse matrix multiplication where data addresses are not known beforehand.
- NVIDIA® GigaThread™ Engine, maximizing the throughput by faster context switching, concurrent kernel execution, and improved thread block scheduling.
- Asynchronous Transfer, turbocharging system performance by executing data transfers, even when the computing cores are busy.
|
Applications
NVIDIA® Tesla™ computing solutions help to solve the world's most important computing challenges more quickly and accurately across many industries. |
|
1U Rackmount
