vivster said:
Neither Nvidia or AMD own their own fabs. They use manufacturers like TSMC, Globalfoundries or Samsung to produce the chips. Intel is the only one with its own fabs. |
What does that have to do with anything? The 20nm die shrink simply doesn't work, no matter who makes it.
http://www.pcper.com/reviews/Editorial/28-nm-GPUs-Extended-Through-2015-20-nm-Planar-Bust
The essential difficulty of the 20 nm planar node appears to be a lack of power scaling to match the increased transistor density. TSMC and others have successfully packed in more transistors into every square mm as compared to 28 nm, but the electrical characteristics did not scale proportionally well. Yes, there are improvements there per transistor, but when designers pack in all those transistors into a large design, TDP and voltage issues start to arise. As TDP increases, it takes more power to drive the processor, which then leads to more heat. The GPU guys probably looked at this and figured out that while they can achieve a higher transistor density and a wider design, they will have to downclock the entire GPU to hit reasonable TDP levels. When adding these concerns to yields and bins for the new process, the advantages of going to 20 nm would be slim to none at the end of the day.
The planned die shrink turned out to be a bust. Switching to finfet is not trivial and requires new designs for the entire tool chain. Sony might have contracts ensuring the price won't go up for production of the current 28nm planar apu, yet they simply can't make the originally planned slim version. The current ps4 design is a dead end.
I don't know if Sony could have made a 14nm slim version with exactly the same specs, however it would probably still cost roughly the same to make as the planned Neo and a lot harder to sell back at the starting price. Might as well test the waters with a ps4.5, easier to sell, and can be produced for less in the future.
