NVIDIA GT200 Rumours & Speculation Thread
- Thread starter Arun
- Start date
- Status
Is there a G80 GX2?
You can only edit after a certain number of posts and days, see: http://forum.beyond3d.com/showthread.php?t=23045
As for GT2xx GX2; it's not that they can't, they just won't have to because they'll go monolithic every single generation from now on.
As for GT2xx GX2; it's not that they can't, they just won't have to because they'll go monolithic every single generation from now on.
There was a public statement by Jen-Hsun Huang to that effect, yes, but I also have heard some tidbits as to why that makes sense and what has changed since the last two GX2s. Anyhow, just search for Hans Mosesmann's first question on this page: http://seekingalpha.com/article/64536-nvidia-f4q08-qtr-end-1-27-08-earnings-call-transcript?page=-1
Exactly. They will definitely try to go monolithic every generation if they can. But if they have to do a GX2 to compete they certainly will. And the odds that they will have to are just going to increase as AMD pushes their own cost effective multi-GPU solutions.
My point is that the incremental cost to go monolithic for them has actually gone *down*. And Lukfi, I'm not aware of NV ever having said the GF7 Series was a mistake; management loved that series, it had awesome margins, awesome ASPs, awesome market share.
And sorry, but for this kind of thing, Jen-Hsun is honest the vast majority of the time; sometimes he's simply wrong or misinformed, but he has better things to do than to lie outright to investors. I've listened to more than enough NV CCs to know he's not the kind of guy who'll try to downright confuse everyone even if it's in his interests. He got a PR and marketing team to do that, though.
And sorry, but for this kind of thing, Jen-Hsun is honest the vast majority of the time; sometimes he's simply wrong or misinformed, but he has better things to do than to lie outright to investors. I've listened to more than enough NV CCs to know he's not the kind of guy who'll try to downright confuse everyone even if it's in his interests. He got a PR and marketing team to do that, though.
well in defense of lukifi they did learn from mistakes they made in the 7 series and implemented them in the 8 series (which produced an immensely powerful gpu) but i don't remember them saying that the series in total was a mistake i liked the 7 series sure it had flaws but it was a solid architecture overall
i wasn't saying he was lying i was agreeing with him about sandwiched cards but at the same time i was saying that nv's never going to rule out something that can regain the performance crown
i wasn't saying he was lying i was agreeing with him about sandwiched cards but at the same time i was saying that nv's never going to rule out something that can regain the performance crown
Reread Jen-Hsun's reply, he clearly hints at the 9800 GX2 there. And Lukfi, I am absolutely positive that NVIDIA always loved and still loves the GF7 series. In fact they initially expected a substantially slower transition than what actually happened (i.e. they expected OEMs to stick to GF7 for a variety of designs in the 2007 Back-to-School cycle, but nearly every design switched to G84/G86 or RV610/RV630)
Actually, aside from 3 architectures, NV has averaged an architectural transition every 13-16 months. Here's my timetable (source: wiki)
The transition from NV1 -> Riva 128 took 19 months, from September '95 to April '97. The next transition to the TNT generation took only a little over a year, from April '97 to June '98. The next transition to the Geforce generation took only slightly longer, from June '98 to October '99. The transition to the Geforce 3 generation taking the same length as the previous, but from October '99 to February '01. The transition to the FX generation took 2+ years and broke this trend, however. Following on from that the transition to NV40 was NV's quickest yet, taking only from March '03 to April '04. The latest architectural transition to G80 was the longest yet, taking from April '04 to November '06.
So, other than NV1, NV30 and NV50(G80), it is clear that NV tends to transition to a new architecture in 13-16 months on average, with the most recent GT200 only slightly outside this range @ ~18 months.
Tesla 2 most certainly does feature DP support, but I'm sure that's not the only new feature.
If they haven't fixed the setup bottleneck, then there would be almost no point in increasing functional unit count.
Basically, it is a reworked G8x/G9x. By the way, these rumours all lack one important piece of information about the chip that I'm sure will surprise you
I've noticed one consistent lack of spec across all these rumors, and that is TA/TF count. Shader-based texturing, anyone?
- Status
