NVIDIA talks smack, tries crow and doesn't like it

Multicore.info pointed me at an ejoyable rant at pcPRO on NVIDIA’s recent comments about Larrabee and ATI. The article starts out with Andy Keane, general manager of the company’s GPU computing group, banging on the hype Larrabee’s getting even though so much is “undefined.”

Ok, fair enough. Not a lot of details. Then he says this, which starts to sound like hysteria

Keane dismissed the idea that the Intel Parallel Studio, announced last week at IDF, might solve the problem. “Multi-processing is a hard problem in computer science. It’s been there for 30 years. It’s not answered by software tools.”

Uh, “not answered by software tools.” Flow of progress: problem exists, problem is identified, researchers make progress solving problem, solid progress institutionalized in tools for general use, researchers continue to work on problem. True enough that Parallel Studio isn’t anything like a panacea, but that statement betrays a lot of fear in its unreasonableness.

John Montrym, chief architect for the company’s GT200 core, raised further doubts about Larrabee’s real-world performance, brushing aside Intel’s announcements as marketing puff.

…”Every GPU we make, we always consider this type of design, we do a reasoned analysis, and we always conclude no. That’s why we haven’t built that type of machine.”

Ok, smart people differ. Then Montrym uses someone else’s mouth to attack Intel,

“As [blogger and CPU architect] Peter Glaskowsky said, the ‘large’ Larrabee in 2010 will have roughly the same performance as a 2006 GPU from Nvidia or ATI.”

Yuck. Feel the ickiness.

At least they have some grace about their position relative to ATI

“We underestimated ATI with respect to their product,” he admitted. “We’ve looked very closely at this, and we know there are certain things we can do better. There will be improvements to things from all angles: there are some easy fixes in the software domain that will soon be forthcoming. Believe me, it’s a very prime focus of ours.”

Well, kind of

“We’re forward-looking. And sometimes, when someone’s forward-looking, they get a little bit ahead of the game. And that’s kind of where we are.”

So their products are really better than ATI’s, but their customers are too “far behind” to realize that so they have to regroup.  So much for grace.

Resource Links: