The RV870 Story: AMD Showing up to the Fight
by Anand Lal Shimpi on February 14, 2010 12:00 AM EST- Posted in
- GPUs
The Cost of Jumping to 40nm
This part of the story could almost stand on its own, but it directly impacts much of what happened with Cypress and the entire Evergreen stack that it’s worth talking about here.
By now you’ve most likely heard about issues with TSMC’s 40nm process. While the word is that the issues are finally over, poor yields and a slower than expected ramp lead to Cypress shortages last year and contributed to NVIDIA’s Fermi/GF100 delay. For the next couple of pages I want to talk about the move to 40nm and why it’s been so difficult.
The biggest issue with being a fabless semiconductor is that you have one more vendor to deal with when you’re trying to get out a new product. On top of dealing with memory companies, component manufacturers and folks who have IP you need, you also have to deal with a third party that’s going to actually make your chip. To make matters worse, every year or so, your foundry partner comes to you with a brand new process to use.
The pitch always goes the same way. This new process is usually a lot smaller, can run faster and uses less power. As with any company whose job it is to sell something, your foundry partner wants you to buy its latest and greatest as soon as possible. And as is usually the case in the PC industry, they want you to buy it before it's actually ready.
But have no fear. What normally happens is your foundry company will come to you with a list of design rules and hints. If you follow all of the guidelines, the foundry will guarantee that they can produce your chip and that it will work. In other words, do what we tell you to do, and your chip will yield.
Global Foundries' 2010 - 2011 Manufacturing Roadmap
The problem is that if you follow every last one of these design rules and hints your chip won’t be any faster than it was on the older manufacturing process. Your yield will be about the same but your cost will be higher since you’ll bloat your design taking into account these “hints”.
Generally between process nodes the size of the wafer doesn’t change. We were at 200mm wafers for a while and now modern fabs use 300mm wafers. The transistor size does shrink however, so in theory you could fit more die on a wafer with each process shrink.
The problem is with any new process, the cost per wafer goes up. It’s a new process, most likely more complex, and thus the wafer cost is higher. If the wafer costs are 50% higher, then you need to fit at least 50% more die on each wafer in order to break even with your costs on the old process. In reality you actually need to fit more than 50% die per wafer on the new process because yields usually suck at the start. But if you follow the foundry’s guidelines to guarantee yield, you won’t even be close to breaking even.
The end result is you get zero benefit from moving to the new process. That’s not an option for anyone looking to actually use Moore’s Law to their advantage. Definitely not for a GPU company.
The solution is to have some very smart people in your company that can take these design rules and hints the foundry provides, and figure out which ones can be ignored, and ways to work around the others. This is an area where ATI and NVIDIA differ greatly.
Facebook
Twitter
RSS
132 Comments
View All Comments
devene - Sunday, February 14, 2010 - link
Just like many others, I've been a long time reader and I just couldn't carry on without leaving a comment:This has been an article, just like the RV770 one. It may not reveal many facts but is tremendously insightful and inspiring. Thank you for bringing this deeply hidden information out to the public and to the "fans". Please do everything in your power to continue this trend.
Once again, thank you Anand,
devene
medi01 - Sunday, February 14, 2010 - link
Germans say "lange Rede kurzer Sinn". So many pointless sentences that do not tell anything even remotely interesting.TGressus - Sunday, February 14, 2010 - link
Even the home team could not be sold on Eyefinity...William Gaatjes - Sunday, February 14, 2010 - link
Fantastic article."
First, it massively increased the confidence level of the engineering team. There’s this whole human nature aspect to everything in life, it comes with being human. Lose confidence and execution sucks, but if you are working towards a realistic set of goals then morale and confidence are both high. The side effect is that a passionate engineer will also work to try and beat those goals.
"
Finally, someone accepting and using human nature.
And see it works out...
The fun part is that a requested functionality that is desired but can not make it within the expected timeframe, can still be worked on and can be ready for the next "bulge" in the market. This way you relieve your engineers form stress, you have the time to sort errors and bugs out, you have time to solve unforseen consequences that always happen( people can get sick, a bug in software, machines breaking down) and you have a feature for the market department to market to the consumer for the next iteration of the product. This way you can use the free market to build an in the end perfect device. It is all about balance. If you have to invest to much energy in situation a, you will have less energy for situation b in a certain timeframe. We are bound by laws of nature meaning there is no "perpetuum mobile" in this universe. Nothing comes for free...
aegisofrime - Sunday, February 14, 2010 - link
Anand, you have taken an article that is really technical in nature, and turned it into something entertaining to read and yet informative for non-engineer types. My hats off to you. This is really the right balance of information and readability. If only all the Scientific Papers I have to read were written like this!dukeariochofchaos - Sunday, February 14, 2010 - link
i wonder if you will give fermi the same drama queen touch?i hope so.
Jamahl - Sunday, February 14, 2010 - link
I don't think anyone wants to read nvidia's marketing department tell us how awesome PhysX and CUDA is again tbh.TGressus - Sunday, February 14, 2010 - link
I suspect Fermi will be able to stand on it's technological innovation.RJohnson - Sunday, February 14, 2010 - link
...and it's exorbitant price/die size will exclude mere mortals from owning one.Spoelie - Sunday, February 14, 2010 - link
That depends entirely on the openness of NVIDIA on the subject, historically not one of their strong points.In fact ATi's take on NVIDIA's design process has been more informative than what has come out of NVIDIA itself.
But here's to hoping..