NVIDIA Announces Tesla GPU For High End Computing

[dafloppyone]

This NVIDIA press release announces their new GPU called Tesla. NVIDIA claimes this product, designed for high end computing for university and research company tasks, will turn an ordinary research workstation into a super computer. The new family includes: -NVIDIA Tesla GPU Computing Processor, a dedicated computing board that scales to multiple Tesla GPUs inside a single PC or workstation. The Tesla GPU features 128 parallel processors, and delivers up to 518 gigaflops of parallel computation. The GPU Computing processor can be used in existing systems partnered with high-performance CPUs.
- NVIDIA Tesla Deskside Supercomputer, a scalable computing system that includes two NVIDIA Tesla GPUs and attaches to a PC or workstation through an industry-standard PCI-Express connection. With multiple deskside systems, a standard PC or workstation is transformed into a personal supercomputer, delivering up to 8 teraflops of compute power to the desktop.
- NVIDIA Tesla GPU Computing Server, a 1U server housing up to eight NVIDIA Tesla GPUs, containing more than 1000 parallel processors that add teraflops of parallel processing to clusters. The Tesla GPU Server is the first server system of its kind to bring GPU computing to the datacente

 

[Alex UK]

Wow. This thing run in SLi?

 

[Zefan]

I imagine these could be quite good at folding.

 

[Duff-Man]

What exactly will be the software interface?

Will it run C / fortran / pascal programs? Or will it require DX calls?

If it will run regular multi-threaded f90 programs then it could solve a LOT of problems in my field (CFD).

 

[Firegod]

So can you play games with it?

 

[queamin]

Yes pong

 

[Duke]

I imagine these could be quite good at folding.

I think the world would implode if you start folding with one of those

 

[NickK]

What exactly will be the software interface?

Will it run C / fortran / pascal programs? Or will it require DX calls?

If it will run regular multi-threaded f90 programs then it could solve a LOT of problems in my field (CFD).

The API is nVidia's CUDA framework. Basically superset of C.

 

[fornowagain]

The Tesla GPU features 128 parallel processors, and delivers up to 518 gigaflops of parallel computation.

http://www.nvidia.com/object/tesla_gpu_processor.html

Basically a G80 GTX core with twice the memory.

 

[Cyber-Mav]

powered by a tesla coil i bet.

 

[feriso]

powered by a tesla coil i bet.

Lol - bang goes your data as soon as you power up

 

[Chris Beard]

Lol - bang goes your data as soon as you power up

Nah you get that charging noise first - wirrrrrrrrrrRRRRRRRRRRRRRRRRRRRR... ZAP