Yesterday NVIDIA announced the GPU-based Tesla Personal Supercomputer which according to the release, “delivers the equivalent computing power of a cluster, at 1/100th of the price and in a form factor of a standard desktop workstation.”
So, this isn’t a product. It’s really a specification for the kinds of components that NVIDIA feels warrant the badge “Tesla Personal Supercomputer” and which is then built and sold by whomever. In fact, a lot of whomevers on launch day
As well as Dell, GPU-based Tesla Personal Supercomputers are available today from the following leading HPC OEMs, Systems Builders and Resellers: AMAX (US), Armari (UK), Asus (WW), Azken Muga (ES), Boxx (US), CAD2 (UK), CADnetwork (DE), Carri (FR), Colfax (US), Comptronic (DE), Concordia (IT), Connoisseur (IN), Dell (WW), Dospara (JP), E-Quattro (IT), JRTI (US), Lenovo (WW), Littlebit (CH), Meijin (RU), Microway (US), Sprinx (CZ), Sysgen (DE), Transtec (DE),Tycrid (US), Unitcom (JP), Ustar (UKR),Viglen (UK), Western Scientific (US) [sic]
Here NVIDIA is trying to use a brand as a conceptual handle for a personal scale resource that does high performance computing. A good thing. But, from what I understand, I could open up shop tomorrow and sell Tesla Personal Supercomputers just by building something that conforms to something close to the minimum spec, and this is not a good thing. With no controls on the brand, it is inevitable that it will creep away from the standard. You’ll always have to ask the question, “yeah, but who’s Tesla Personal Supercomputer is that?” and the value as a shorthand for the concept disappears.
[UPDATE: note that I’ve updated this post with some new information NVIDIA provided me. Check out the new information here.]