SIGGRAPH 2007: NVIDIA announce a 4 GPU Quadro Plex VCS

Wednesday 08th August 2007, 10:10:00 PM, written by Rys

NVIDIA launched a new Quadro Plex VCS 1000 yesterday at SIGGRAPH. The Model S4 is effectively just the Tesla S870 GPU Computing Server repurposed for Quadro-led apps.

NVIDIA attach 1.5GiB of VRAM to each of the four G80 GPUs in the Model S4, with all of the contained inside a 1U rack chassis with custom GPU cooling and power. Output from the system is via PCI Express Gen2, and NVIDIA target the product at users looking for offline accelerated rendering, or multi-user remote rendering, while still supporting the CUDA programming environment.

The S4 can be monitored remotely for power and heat, and NVIDIA hint that energy providers and scientific computing might be big customers, which is a somewhat mixed message given Tesla was aimed at those very same groups of users at the Tesla launch not long ago.

In its defence, the differences between the Quadro Plex VCS 1000 Model S4 and the Tesla S870 seem to be at the driver level at best, so the hardware similarities mean there might be some crossover depending on support and price.

NVIDIA are shipping the Model S4 in Q4 this year.

Discuss on the forums

Tagging

nvidia ± quadro, plex, vcs, 1000, model, s4, cuda, thanks, for, letting, us, know, in, advance

Related nvidia News

CUDA 4.0 and Parallel Nsight 2.0 released
NVIDIA Fermi GPU and Architecture Analysis
NVIDIA's Parallel Nsight finally released
NVIDIA GeForce GTX 460 - GF104 breaks cover
PhysX87, ancient tragedy in 5 acts by RWT
So long, Chris, and thanks for all the fish
NVIDIA GF100 graphics architecture details
NVIDIA Fermi: new GPU architecture, starting with GF100
NVIDIA release OpenCL GPU drivers for Linux and Windows
NVIDIA GeForce GTX 275 at $250 to fight HD 4890