NVIDIA GF100 & Friends speculation
- Thread starter Arty
- Start date
End of March? Thats quite a bit later. If this is indeed a new spin, is there any word on whether we're talking about A1,2,3 or Bx? I've lost track on the number of spins here!
A3 went to the fab according to rumors in early December; it seems like they started mass production within February which makes sense. A hypothetical release in March makes sense for all the above and there doesn't seem to be any time for another metal spin (what for anyway?) let alone a full re spin which you'd rather expect somewhere in mid summer and not as early as March.
end of march is what i recal hearing from the december time period.
Basicly a full 6 months later than the 5870s
Unless ofcourse teh full respin tehy expect to fix what is preventing them from getting more than the handfull of working 512SP parts they currently have gotten A1-A3.
Mass production is obviously with A3 only at this point of time. Now they might of course go for a full respin but you won't see anything from it neither in March, April or May. The A3 metal spin fits into the March release timeframe and it looks like it took roughly 3 months from sending it to the fab until release. April or May would be time enough for another metal spin (something like A4; again what for?) but a re spin would take significantly longer than that.
As I said, to get more than the hand full of working 512SP parts they have gotten from all the A1-A3 runs to date. My understanding from someone who works in RTP for nvidia, A1-A3 has produced jack in terms of 512SP parts and they are planning a B1(a complete respin of all layers) run in April in hopes of improving the number of 512SP parts coming off the line. Launch products will be 448SP parts with 512SP parts being PE parts if shown at all. Given all teh Fermi parts seen todate have been confirmed as 448SP chips, this seems very plausable to me.
April is when they are sending it in, again, they are "NOT" happy wth the number of working 512SP parts they are getting currently and want to improve those numbers. B1 stepping is, from my understanding a test run to see if they fix what is causing the 512SP parts to fail and become 448SP parts. They dont want to go all summer without their top part out at all or as a PE part only til they get it coming off the line in numbers that they can sell.
If this rumor is true, then I would tend to think that the most likely scenario would be that they would do one of a couple of things:
1. Go ahead and launch with a top-end part somewhat overpriced to compensate for the low volume. The reasonable-priced part will be a 448SP part.
2. Launch with a 448SP part as their flagship product, holding onto good 512SP parts until they have enough volume down the line for a more full release.
My reasoning is basically that at the current time, they're already late, and they're losing potential sales for every further month that it takes to release the GF100. So they're likely to release whatever they can release in volume as soon as they can.
Obviously I do hope that this rumor turns out to be wrong and the 512SP parts are available in volume (which might be the case if, for instance, nVidia has been saving the good 512SP parts for a little while).
Sales of the 448-SP part will be hurt by the absence of a flagship. It will be a complete marketing and execution failure that will damage the product's image even if it is a good buy on its own merits. Given that Nvidia knows its marketing I doubt the second scenario is even on the table. Even if there is zero availability they will still launch it. Worked for the 5970 - showing up as out of stock at Newegg is still better than not showing up at all.
And how can they fix a process problem with a new design? It's a problem of tsmc. Over the time the yields will improve and there will be more 512 parts.
That would be completely dependent upon the performance achieved. Almost nobody out there would even know about this distinction.
Well, I am aware that it's been done before. What I'm not aware of is whether or not this genuinely helped.
The only problem in your example is that the 5970 has no competition. If we factor in late march for any fermi parts that means the 5970 is without a rival for 3-4 months. Fermi doesn't have that chance. It comes out with whatever avaliblity against the 5870 and 5970 and the 5970 will not be as rare then.
But I think more so than the lack of high end parts is what part is competitive and how much cooling it needs and power. That can really throw alot of people off.
Which is exactly why having it on the market and out of stock is better than not at all. At least then it can be compared to the also out of stock competition.
I'm not sure it will work when the competition has a part in stock that compares though or might even be faster.
What refresh? There's just 1 rumorsite which posted that there would be "fermi 2" during the fall, that's it
Similar threads
- Deleted member 2197
- Architecture and Products
