Fermi
NVIDIA® Fermi™ S2050 and S2070 Rackmount GPU Computing System
NVIDIA® Fermi™ S2050 rackmount GPU computing system is the first to bring a massively multi-threaded architecture to high performance computing (HPC) applications for scientists, analysts and other technical professionals.
The Fermi S2050 is a slim 1U form factor to fit into an enterprise server environment. In addition, it easily scales to solve the most complex, data-intensive HPC problems.
Featuring four 448-processor computing core GPUs, a C-language development environment for the GPU, a suite of developer tools, and the world's largest GPU ISV development community, the Tesla S870 allows professionals to develop applications faster and to deploy them across multiple generations of processors.
The Fermi S2050 is used in tandem with multi-core CPU systems to create a flexible computing solution that fits seamlessly into your existing IT infrastructure.
Product
Fermi S2050
Form Factor
Rackmount GPU System
Total Dedicated Memory
12 GB (3 GB GDDR5 per GPU) with ECC support **
Floating Point Precision
IEEE 754 single-precision floating point
Host Adapter Card
PCI Express x16 or x8 Gen2, Small Form Factor, Passive (10W)
Power
760W max., 100-240 VAC Autosensing
Acoustics
40 dB
Weight
~19 lb
Tesla
NVIDIA® Tesla™ S1060 GPU Computing System
NVIDIA® Tesla™ S1060 GPU computing system is the first to bring a massively multi-threaded architecture to high performance computing (HPC) applications for scientists, analysts and other technical professionals.
The Tesla S1060 is a slim 1U form factor to fit into an enterprise server environment. In addition, it easily scales to solve the most complex, data-intensive HPC problems.
Featuring four 240-processor computing core GPUs, a C-language development environment for the GPU, a suite of developer tools, and the world's largest GPU ISV development community, the Tesla S1060 allows professionals to develop applications faster and to deploy them across multiple generations of processors.
The Tesla S1060 is used in tandem with multi-core CPU systems to create a flexible computing solution that fits seamlessly into your existing IT infrastructure.
Product
Tesla S1060
Form Factor
Standard 19" 1U rack-mount chassis
# of GPUs
4
Total Dedicated Memory
16 GB (4 GB GDDR3 per GPU)
Floating Point Precision
IEEE 754 single-precision floating point
Power
800W max, 100-240 VAC Autosensing
Host Adapter Card
PCI Express x16 or x8, Small Form Factor, Passive (10W)
Software Tools
CUDA™ Toolkit
Each EclipseGP GPGPU powered system comes loaded with the latest version of nVIDIA's CUDA™ Toolkit for Linux. The CUDA™ Toolkit includes the following:
- nvcc C compiler
- CUDA FT and BLAS libraries for GPU
- Profiler
- gdb debugger for GPU (alpha availability in March 08)
- CUDA runtime driver
- CUDA programming manual
Benchmarks
In Development Stage
