nVidia unveils consumer supercomputer GPUs

nVidia has released their Tesla supercomputer GPUs aimed at the budget prosumer market.

The project slogan, "many core supercomputing connected to a workstation", explains the Tesla well.

The NVIDIA® Tesla™ D870 deskside GPU computing system helps solve high performance computing (HPC) challenges for scientists, analysts, and other technical professionals in a deskside supercomputer.

It features two Tesla C870 GPU computing processors in a quiet deskside system that is suitable for the office environment. With 256 streaming processor cores, the CUDA C-language development environment and developer tools, and a range of applications already ported, the Tesla D870 delivers a dedicated deskside system to solve problems that previously required a large shared computing cluster.

This deskside supercomputer with two GPUs with 256 processor cores can execute thousands of concurrent threads and easily express application parallelism to take advantage of the GPU’s many core architecture and deliver unprecedented application performance.

nVidia claimed that the performance of the Tesla GPU can rival industry-level supercomputers, for 1/200 the price. At under $10 000, this lean, mean, supercomputing GPU is intended for heavy-duty use such as in universities, astronomy labs, etc.

The Tesla D970 can be used with the systems shown here.



The Tesla D970 is a part of the Tesla product line.

Tesla D970 >>
Tesla Computing Solutions >>




The Tesla C870 GPU processor.


The Tesla C1060 GPU processor.



Get yourself a supercomputer from as low as $1549! Yes, that's very much cheaper than a Mac Pro, mind you! Even with Tesla processors!