The RV870 Story: AMD Showing up to the Fight
by Anand Lal Shimpi on February 14, 2010 12:00 AM EST- Posted in
- GPUs
What Made it All Ok: 4 GPUs in < 6 Months
Through a lot of hard work and sacrifice, even on Carrell’s part, ATI cut the RV870 from as much as 22mm on a side down to roughly 18mm x 18mm. The problem is that RV770 was around 16mm on a side. The RV870 was still too big.
Carrell wanted to cut it down even more, but two things changed his mind. First, in order to build 870 in the space of a 770 ATI would have to cut out much more from the chip than Carrell originally tought. One of the things that would have to go was some of the shader core.
In order to run the GDDR5 memory at the sort of data rates that ATI was targeting for the 5870 the analog PHYs on the chip had to grow considerably. At 16mm on a side ATI would either have to scale back memory bandwidth or eat into the shader core area. Either way we would’ve had a slower chip.
I asked Carrell if 16mm on a side would’ve made the RV870 $100 cheaper at launch, putting it on par with the RV770 launch prices. He said no. I didn’t find out why until much later, but I’ll save that story for another time.
Sacrificing performance to meet the 16mm x 16mm die size targets wasn’t going to happen, but what ultimately convinced Carrell to go with a larger die this time around was something that ATI didn’t get nearly enough praise for: the ability to launch 4 different 40nm DirectX 11 GPUs in less than 6 months.
Remember that Carrell’s beef with building the biggest GPU possible is that it takes too long for the majority of customers to get access to derivatives of that GPU. Look at how long it took G80 or GT200 to scale down. And who knows when we’ll see $150 Fermi/GF100 derivatives.
But ATI Engineering promised two things. First, that Cypress would have a successor called Juniper that would be ready around the same time. Secondly, two more GPUs would follow and the whole stack will be done and out in less than 6 months. ATI came close in 2008 with 3 GPUs in 3 months, but the fourth member of the 4000 series didn’t show up until April of 2009.
It wasn’t an impossible feat. ATI does have concurrent design teams and a lot of engineering resources in India/China. By working on Juniper in tandem with Cypress, assuming there were no show stopping bugs, ATI could exploit efficiencies in two teams effectively working on the same hardware (Juniper was just half a Cypress).
The idea of taking such a huge risk made Carrell uncomfortable. Running two GPU designs in parallel, for the same family of chips, is risky. If everything works out perfectly, you get two chips out at the same time. If it doesn’t, you’ve just tied up two design teams on one product generation. A slip here would give ATI its own Fermi.
What ultimately sold Carrell was the fact that engineering told him that they believed they could pull it off. Carrell believes in people. He believes if you expect the best out of those around you, then that’s what you’ll get. He couldn’t reconcile his beliefs with doubting the schedule engineering was feeding him. Carrell nervously signed off and the Evergreen stack was born.
Cypress and Juniper were delivered nearly at the same time. In fact, Juniper was ready a bit earlier and was sampled to developers months before ATI launched the 5000 series. Cedar and Redwood followed, not to mention a dual-Cypress board that became the Radeon HD 5970. And all of this was done and ready in less than 6 months (the chips themselves were all ready within 4 months).
When the smoke cleared ATI had new DirectX 11 parts at $600, $400, $300, $200, $150, $100 and $60. The Windows 7/DirectX 11 market bulge just got serviced.
Facebook
Twitter
RSS
132 Comments
View All Comments
Stas - Sunday, February 14, 2010 - link
Awesome. Thanks!Adul - Sunday, February 14, 2010 - link
Really helps pass the time at work today. :) Keep it up.Btw when can we expect to see the new site launch?
aapocketz - Sunday, February 14, 2010 - link
[quote]I was convinced that ATI had embraced a new, refocused approach to GPU design, only to learn that they nearly threw out all of the learnings with the RV870. [/quote]It sounds like they have had some successes trying different techniques, but without stability in their production process it is hard to repeat success. I understand that they require constant innovation to stay competitive, but throwing out whole processes seems chaotic to me. I would like them to refine and improve successful processes rather than toss everything every time a new business guru is in charge.
Also half of their effort was all about openness and collaboration. The opening up of the PRS document so that "everyone was involved in the process" seems to clash with the hyper-secret groups where "AMD has since incorporated much of Carrell’s brand of information compartmentalization into how it handled other upcoming features." This seems like a recipe for disaster to me. Which is it, broad openness, collaboration and consesus; or secret teams that have no idea what the other teams are doing?
SuperGee - Sunday, February 14, 2010 - link
The story told us that they didn't know it will become a succes because these desision where made before RV770 release. So doing the high risk choice again. Wasn't a nobrainer. But a risky choice. We know that it turn out good now.mckirkus - Sunday, February 14, 2010 - link
It's kind of funny that you're not yet running one of these companies yet Anand.One of the reasons I check this site on a daily basis is because you also seem to also get the business side of the equation. It's downright refreshing to see someone bridging that gap. You pretty much saved the Vertex from self destruction. I'd like to see what interesting things you could build us if you put your mind to it.
deputc26 - Sunday, February 14, 2010 - link
Articles like these are what differentiate AnandTech from all the other sites out there. AnandTech goes from being one of the best review sites out there to something special.Beyond excellent, thanks Anand.
rickyv - Sunday, February 14, 2010 - link
As a loyal follower of your website for the past 15 years, I also felt that I just had to register and compliment you on an excellent article.With the rapid advancement of technology, it is very easy just to get caught up in the PR and marketing hype or focus only on the numbers game. We often lose sight of the fact that it is teams of dedicated people who make this possible. You have always had the ability to bring out the "human" side to this. I have not seen this on any other site nor in printed form (that is not an unashamedly PR marketing exercise).
Thanks for staying true to your roots by giving honest opinions of the technology that you review. The latest releases are not necessarily always the greatest (as much as the marketing departments would like us to believe :-) )
krish123 - Sunday, February 14, 2010 - link
After i read the article, I found that "Engine is running well and firing on all the cylinders", It can create better products in the future, I can trust and buy ATI products, hope they deliver better products in the future for my upgrade."Kudos to Anand for the excellent article".
By the way graphics card is a product, not just hardware, it has to work in tandem with the software, its better ATI put some more effort on the driver/software side and fix all the issues.
Krish
smartalec - Sunday, February 14, 2010 - link
"When companies like AMD and NVIDIA do a product the engineers don't know all of the answers, and the knowledge they do have isn't binary - it's probability, it's weight, it's guesses. Sometimes they guess right, and sometimes they guess very wrong. The best they can do is to all weigh in with their individual experiences and together come up with the best group of guesses to implement."I'm afraid this is how all engineering works. Project managers think that engineers can predict the future. That we know exactly how much time it'll take, and how much risk a given feature will bring.
We don't. There's a lot of educated guesses. Sometimes we're pleasantly surprised that what we thought was a tough problem wasn't. Sometimes we're the bearer of bad news-- something we assumed would be trivial wasn't.
My most frustrating issues aren't technical at all. I ask for 2000 hours, and are given 1000. Or are given 2 engineers instead of 3, and told-- figure out a way to get it done anyway, without impacting schedule.
Great article Anand.
mckirkus - Sunday, February 14, 2010 - link
Any decent project manager (I do software) reviews the risks up front with the engineers before building the project plan / timeline.The fact that most project managers don't really understand the products they manage is the rule not the exception. The problem is that great engineers don't always make great PMs. Having a good tech lead helps.