Q&A with NVIDIA

You've got Questions, We've got answers

As always happens with the launch of a new product, just as many new questions pop up from the press release and announcements as were answered by the announcement in the first place. Jen-Hsun Huang held a lengthy Q&A session after the press conference, and I was also able to talk to Dan Vivoli briefly after the Q&A was over. All of the answers are of course, paraphrased or otherwise interpreted (I'm a gaming guy, not a secretary who knows shorthand), and most of the answers came from Jen-Hsun Huang unless specifically noted.

Will there be any Linux support? What about a Mac version? NVIDIA already supports Linux, but there is no Macintosh product planned at this time. NVIDIA remains focused and dedicated to the PC platform.

When is the next part coming out? Will it be a new architecture or a clocked up GeForce 256? NVIDIA is on a 6 month product cycle, so the next big product will be announced at that time. None of the NVIDIA representatives would confirm or deny that the next product (NV15) would be a new architecture or just a clocked up GeForce 256

What about scaleability? Will it be possible to put two GeForce 256 chips on one board? Huang danced around this question, saying that there's plenty of power in the GeForce 256 to exploit already. According to Huang, the real boost will come from "unleashing" the power of the chip. We assume that means when software is specifically written or optimized for the chip

The board supports up to 128MB but what will a typical board have? Dan Vivoli informed me that most of the first run of GeForce 256 boards will mostly have 32MB, and that 32MB is all you're really going to need. Probably a couple of the OEMs will create some hardcore boards with 64MB or more, but that will drive up costs to an even greater degree, which brings us to the next question.

What price range are we talking about for the boards? This is another issue that NVIDIA danced around but understandably so - it's the OEMs who sell the boards and set the prices so NVIDIA is in no position to say how much the boards will cost. Huang did mention that graphics cards consistently increase in price with each generation, so based on that and the fact that TNT2 Ultras retail for $200-$230, and G400 Max's range from $200-$250, we'd say it's safe to assume that GeForce 256s will launch around the $300 mark or even a bit above.

How much power does GeForce 256 consume? What kind of cooling issues will there be? According to Jen-Hsun Huang, the GeForce "consumes more power than anything else before it," so it's going to probably be like the TNT2, which uses all the power that the AGP port can give. Recall that some issues arose with the TNT2 regarding certain motherboards not supplying enough power to the AGP port. It will be interesting to see if this mistake gets repeated or not by the motherboard manufacturers.

As for cooling, Huang joked that you're not going to want to touch the chip lest you sear your finger right onto the silicon! All GeForce 256 chips will require active cooling (heatsink and fan) because the 23 milllion transistors run quite hot! Huang even alluded to the possibility of liquid cooling for future products, a comment which left some of the crowd whispering "Kryotech."

What kind of RAM will the GeForce use? Huang mentioned NVIDIA's policy of using mass market RAM, so the GeForce will support regular SDRAM or DDR RAM. Using DDR would increase bandwidth but probably at the expense of cost - perhaps we might see some high end cards using DDR instead of SDRAM rather than bumping up clock speeds.