Nvidia Launches 'Tesla' GPU Family
Nvidia has launched a new class of products based on its newest GPU, with which the company hopes to make its debut in fields such as the geosciences, molecular biology, and medical diagnostics.
Nvidia will offer its new family of GPU computing products under the brand name 'Tesla' that promises to transform mere workstations into 'personal supercomputers', the company said.
The 'Tesla' family will encompass products ranging from PCs to large scale server clusters.
According to Jen-Hsun Huang, president and chief executive officer of Nvidia,
Out of the 'Tesla' family of products, the GPU computing processor is capable of scaling multiple 'Tesla' GPUs inside a single PC or workstation. The processor has 128 parallel processors, and delivers up to 518 gigaflops of parallel computation. It can be used in existing systems along with high-performance CPUs. :bounce:
Another 'Tesla' product, the Deskside Supercomputer, is a scalable computing system that includes two 'Tesla' GPUs, and attaches to a PC or workstation through an industry-standard PCI Express connection.
The third of the 'Tesla' family of products, the GPU Computing Server, is a server capable of housing up to 8 'Tesla' GPUs, containing more than 1,000 parallel processors that add teraflops of parallel processing to clusters.
The 'Tesla' family of GPU computing products is priced between $1,500 (Rs 61,139 approx) and $12,000 (Rs 489,119 approx), and will be available all over the world sometime in August. :wow:
In short, its key features are :
Key elements include:
* Industry's first massively multi-threaded architecture with a 128-processor computing core
* World's only C-language development environment for the GPU
* A suite of developer tools (C-compiler, debugger, performance profiler, optimized libraries)
* Largest ISV development community for GPU Computing applications
* Seamlessly able to fit into existing HPC environments
Also this GPU needs an external power supply as it stays out of the CPU cabinet. So if you will have to have space for two big boxes, one for CPU cabby and the other for GPU :lol:.
More details: NVIDIA Tesla - GPU Computing Solutions for HPC
Nvidia has launched a new class of products based on its newest GPU, with which the company hopes to make its debut in fields such as the geosciences, molecular biology, and medical diagnostics.
Nvidia will offer its new family of GPU computing products under the brand name 'Tesla' that promises to transform mere workstations into 'personal supercomputers', the company said.
The 'Tesla' family will encompass products ranging from PCs to large scale server clusters.
According to Jen-Hsun Huang, president and chief executive officer of Nvidia,
Out of the 'Tesla' family of products, the GPU computing processor is capable of scaling multiple 'Tesla' GPUs inside a single PC or workstation. The processor has 128 parallel processors, and delivers up to 518 gigaflops of parallel computation. It can be used in existing systems along with high-performance CPUs. :bounce:
Another 'Tesla' product, the Deskside Supercomputer, is a scalable computing system that includes two 'Tesla' GPUs, and attaches to a PC or workstation through an industry-standard PCI Express connection.
The third of the 'Tesla' family of products, the GPU Computing Server, is a server capable of housing up to 8 'Tesla' GPUs, containing more than 1,000 parallel processors that add teraflops of parallel processing to clusters.
The 'Tesla' family of GPU computing products is priced between $1,500 (Rs 61,139 approx) and $12,000 (Rs 489,119 approx), and will be available all over the world sometime in August. :wow:
In short, its key features are :
Key elements include:
* Industry's first massively multi-threaded architecture with a 128-processor computing core
* World's only C-language development environment for the GPU
* A suite of developer tools (C-compiler, debugger, performance profiler, optimized libraries)
* Largest ISV development community for GPU Computing applications
* Seamlessly able to fit into existing HPC environments
Also this GPU needs an external power supply as it stays out of the CPU cabinet. So if you will have to have space for two big boxes, one for CPU cabby and the other for GPU :lol:.
More details: NVIDIA Tesla - GPU Computing Solutions for HPC