1 month ahead of schedule means nothing as the usual forecast for 20nm GPUs was Q3. Take in mind that the article is talking about volume production, not mass production.
Anandtech had the Acer notebook with the 640m reviewed in march. Given its status as an OEM notebook part it would have been shipping to Acer months earlier.
I thought the article in the OP specifically referred to "mass production"...?
AMD always releases GPUs on new nodes way before Nvidia and there are no info at all about AMD on the new node.
Why would that change now?
I'd get excited about a new Nvidia GPU in a new node after AMD doing so.
It doesn't matter what you accept. If you think you can snip with your fingers and a GPU falls in your lap, you are dead wrong. Before the GTX 680 launch there were notebooks with GK107 out there, there are videos with them running BF3. It takes lots of time to integrate GPUs into notebook lineups, thus GPUs have to be finished months before.
And besides, the GK107 GPUs were purchased - by the OEMs, just not by you or me.
I thought the article in the OP specifically referred to "mass production"...?
Can someone please explain the difference between mass and volume production for me? As someone not at all involved in this business in any professional sense, the two terms seem to imply the same thing.
And GTX 680 cards bought by AIBs weeks or months before. And there are always been leaks with not ready products. Just take a moment to think about all those engineering chips from Intel running around months before the actual product. When do we point the pin? As for me the only reasonable date is the release date for consumers. It's the only thing you can't make up and comparable between ALL products. Not the announcement, not the engineering samples, not the initial shipments. What if the chip maker is careful and doesn't give engineering samples to leakers? What if the chip maker wants to give no info at all until the release date? Does it mean that a chip maker giving no info about a product doesn't have its product ready? Is it fair to say that Kepler was ready at the same time than Tahiti even being sold 3 months later?
Why are you talking about GK104 and not GK107? If you want to nitpick about a month or so, be my guest. But to ignore GK107 and claim, Nvidia was noticeably later with the transition to 28nm is nonsense.
Who is ignoring GK107? Its launch was at the same time as GK104. March 22 2012.
Lets do this again guys
28nm reached volume production, October 24th 2011
We got GK104, GK106 and GK107 in late March 2012. 5 months after 28nm volume production started.
20nm reached volume production, January 16th 2014
January > February > March > April > May > June
That is 5 months.
But according to TSMC, they expect 20nm production to ramp up 30% faster than 28nm.
Meaning we might see our first 20nm GPUs BEFORE June. April/May perhaps?
You are. For the x-th time - we're not talking about desktop, but mobile. How do you think Nvidia managed to get almost all Ivy Bridge design wins and increase its market share in that department by about 15%? By not delivering hundreds of thousands of GK107 GPUs?
Volume production is the next stage after prototyping and testing with the actual product being produced. In other words you already had the product right in the prototypes and now you can say you have it ready with actual products. That doesn't mean that your facilities are ready for it with the process implemented with time and then each product by itself.
That's why you say that you ramp up production after volume production.
Thank you for the explanation. So mass production comes after volume production? I can see how that would make sense I suppose. But then again, the article quoted in the OP says that TSMC has achieved mass production at 20nm...
I just picked up a GTX 780?
Why you do to me .
Not like all of a sudden the 780 won't be able to deliver high fps on Ultra just because Maxwell comes out lol
AMD always releases GPUs on new nodes way before Nvidia and there are no info at all about AMD on the new node.
Why would that change now?
I'd get excited about a new Nvidia GPU in a new node after AMD doing so.
What is the sources for 20nm gpu h2 actually?
The article actually says both things. And I assume the author doesnt know the difference.
Every other article points to xbitlabs. Anyone found the TSMC statement? I checked TSMCs site and found nothing.
We have two fabs, fab 12 and fab 14 that complete the core of the 20nm-SoC. As a matter of fact, we have started production. We are in the [high]-volume [20nm] production as we speak right now, said C. C. Wei, co-chief executive officer and co-president of TSMC, during a conference call with investors and financial analysts
I think you are confused. My source for this thread is X-bit. The actual source for the article is TSMC, which is at the very beginning of the article: