The Call

My love/hate relationship with AMD PR continued last year. But lately, it’s been far less hate. Let’s rewind back to the Summer of 2009. I’d been waiting for AMD to call for weeks.

We all knew that the RV870 was going to launch sometime before the end of the year, and we’re normally briefed on new GPUs around a month or so before we get hardware. The rumors said that the launch had been pushed back, but just like clockwork I got a call in June or July of last year. It was my old friend, Chris Hook of AMD PR.

This time he wanted me to come to a press event on a carrier off the coast of California. Sigh.

It’s not that I have anything against carriers. It’s just that all I cared about at that time was the long awaited successor to the RV770. The RV770 was the GPU that unequivocally restored my faith in ATI graphics, an impact shared by others last June. But that’s not how the game is played I’m afraid. AMD promises its management and its partners that they can fill a room (or carrier) up with important press. We get promised access to engineers, useful information and free drinks.


The USS Hornet. GPUs are in there.

I’m not easily swayed by free drinks, but Chris Hook knows me well enough by now to know what I’d appreciate even more.

The Dinner - September 2009

I had to leave dinner earlier than I wanted to. ASUS’ Chairman Jonney Shih was in town and only had one opportunity to meet me before I left Oakland. Whenever either of us happens to be in the same town, we always make our best effort to meet - and I wasn’t going to let him down. In the same vein that Steve Jobs is successful because he is a product guy at heart, running a company best known for its products. Jonney Shih is an engineer at heart, and he runs a company who has always been known for their excellence in engineering. This wasn’t just another meeting with an executive, this was a meeting with someone who has a passion for the same things I do. His focus isn’t on making money, it’s on engineering. It’s a rare treat.

My ride was waiting outside. I closed the lid on my laptop, making sure to save the 13 pages of notes I just took while at dinner. And I shook this man’s hand:

Before I left he asked me to do one thing. He said “Try not to make the story about me. There are tons of hardworking engineers that really made this chip happen”. Like Jonney, Carrell Killebrew has his own combination of traits that make him completely unique in this industry. All of the greats are like that. They’ve all got their own history that brought them to the companies that they work for today, and they have their own sets of personality traits that when combined make them so unique. For Carrell Killebrew it's a mixture of intelligence, pragmatism, passion and humility that's very rare to see. He's also a genuinely good guy. One of his tenets is that you should always expect the best from others. If you expect any less than the best, that’s all you’ll ever get from them. It’s a positive take on people, one that surprisingly enough only burned Carrell once. Perhaps he’s more fortunate than most.

Mr. Killebrew didn’t make the RV870, but he was beyond instrumental in making sure it was a success. What follows is a small portion of the story of the RV870, the GPU behind the Radeon HD 5800 series. I call it a small portion of the story because despite this article using more than eight thousand words to tell it, the actual story took place over years and in the minds and work of hundreds of engineers. This GPU, like all others (even Fermi) is the lifework of some of the best engineers in the industry. They are the heroes of our industry, and I hope I can do their story justice.

As is usually the case with these GPU backstories, to understand why things unfolded the way they did we have to look back a few years. Introducing a brand new GPU can take 2 - 4 years from start to finish. Thus to understand the origins of the Radeon HD 5800 series (RV870) we have to look back to 2005.

Sidebar on Naming

AMD PR really doesn’t like it when I use the name RV870. With this last generation of GPUs, AMD wanted to move away from its traditional naming. According to AMD, there is no GPU called the RV870, despite the fact that Carrell Killebrew, Eric Demers and numerous others referred to it as such over the past couple of years. As with most drastic changes, it usually takes a while for these things to sink in. I’ve also heard reference to an RV870 jar - think of it as a swear jar but for each time someone calls Cypress an RV870.

Why the change? Well, giving each member of a GPU family a name helps confuse the competition. It’s easy to know that RV870 is the successor to the RV770. It’s harder to tell exactly what a Cypress is.

AMD PR would rather me refer to RV870 and the subject of today’s story as Cypress. The chart below shows AMD’s full listing of codenames for the 40nm DX11 GPU lineup:

GPU Codename
ATI Radeon HD 5900 Series Hemlock
ATI Radeon HD 5800 Series Cypress
ATI Radeon HD 5700 Series Juniper
ATI Radeon HD 5600/5500 Series Redwood
ATI Radeon HD 5400 Series Cedar

 

Given that we still haven’t purged the RVxxx naming from our vocabulary, I’m going to stick with RV870 for this story. But for those of you who have embraced the new nomenclature - RV870 = Cypress and at points I will use the two names interchangeably. The entire chip stack is called Evergreen. The replacement stack is called the Northern Islands.

The Best Way to Lose a Fight - How R5xx Changed ATI
POST A COMMENT

132 Comments

View All Comments

  • ImmortalZ - Monday, February 15, 2010 - link

    Long time reader and lurker here.

    This article is one of the best I've read here - hell, it's one of the best I've ever read on any tech site. Reading about and getting perspective on what makes companies like ATI tick is great. Thank you and please, more!
    Reply
  • tygrus - Sunday, February 14, 2010 - link

    Sequences of numbers in a logical way are easier to remember than names. The RV500, RV600 .. makes order obvious. Using multiple names within a generation of chips are confusing and not memorable. They do not convey sequence or relative complexity.

    Can you ask if AMD are analysing current games/GPGPU and future games/GPGPU to identify possible areas for improvement or skip less useful proposed design changes. Like the Intel >2% gain for <1% cost.
    Reply
  • Yakk - Sunday, February 14, 2010 - link

    Excellent article! As I've read in a few other comments, this article (and one similar I'd read prior) made me register for the first time, even if I've been reading this site for many years.

    I could see why "Behind the scenes" articles can make certain companies nervous and others not, mostly based on their own "corporate culture" I'd think.

    It was a very good read, and I'm sure every engineer who worked on any given generation on GPU's could have many stories to tell about tech challenges and baffling (at the time) corporate decisions. And also a manager's side of the work in navigating corporate red tape, working with people, while delivering something worthwhile as an end product is also a huge. Having a good manager (people) with a good subject knowledge (tech) is rare, then for Corp. Execs. to know they have one is MUCH rarer still...

    If anyone at AMD/ATI read these comments, PLEASE look at the hardware division and try to implement changes to the software division to match their successes...

    (btw been using nv cards almost exclusively since the TNT days, and just got a 5870 for the first time this month. ATI Hardware I'd give an "A+", Software... hmm, I'd give it a "C". Funny thing is nv is almost the exact opposite right now)
    Reply
  • Perisphetic - Sunday, February 14, 2010 - link

    Someone nominate this man for the Pulitzer Prize!

    As many have stated before, this is a fantastic article. It goes beyond extraordinary, exceptional and excellent. This has become my new benchmark for high quality computer industry related writing.
    Thank you sir.
    Reply
  • ritsu - Monday, February 15, 2010 - link

    It's not exactly The Soul of a New Machine. But, fine article. It's nice to have a site willing to do this sort of work.
    Reply
  • shaggart5446 - Sunday, February 14, 2010 - link

    very appreciative for this article im from ja but reading this make me file like ill go back to school thanks anand ur the best big up yeah man Reply
  • 529th - Sunday, February 14, 2010 - link

    The little knowledge I have about the business of making a graphics card, that it was Eyefinity that stunted the stability-growth of the 5xxx drivers by the allocation of resources of the software engineers to make Eyefinity work. Reply
  • chizow - Sunday, February 14, 2010 - link

    I usually don't care much for these fluff/PR pieces but this one was pretty entertaining, probably because there was less coverage of what the PR/Marketing guys had to say and more emphasis on the designers and engineers. Carrell sounds like a very interesting guy and a real asset to AMD, they need more innovators like him leading their company and less media exposure from PR talking heads like Chris Hook. Almost tuned out when I saw that intro pic, thankfully the article shifted focus quickly.

    As for the article itself, among the many interesting points made in there, a few that caught my eye:

    1) It sounds like some of the sacrifices made with RV870's die size help explain why it fell short of doubling RV770/790 in terms of performance scaling. Seems as if memory controllers might've also been cut as edge real estate was lost, and happen to be the most glaring case where RV870 specs weren't doubled with regard to RV770.

    2) The whole cloak and dagger bit with EyeFinity was very amusing and certainly helps give these soulless tech giants some humanity and color.

    3) Also with EyeFinity, I'd probably say Nvidia's solution will ultimately be better, as long as AMD continues to struggle with CrossFire EyeFinity support. It actually seems as if Nvidia is applying the same framebuffer splitting technology via PCIe/SLI link with their recently announced Optimus technology to Nvidia Surround, both of course lending technology from their Quadro line of cards.

    4) The discussion about fabs/yields was also very interesting and helps shed some light on some of the differences between the strategies used by both companies in the past to present. AMD has always leveraged new process technologies in the past as soon as possible, Nvidia in the past has more closely followed Intel's Tick/Tock cadence of building high-end on mature processes and teething smaller chips on new processes. That clearly changed this time around on 40nm so it'll be interesting to see what AMD does going forward. I was surprised there wasn't any discussion about why AMD hasn't looked into GlobalFoundries as their GPU foundry.

    Reply
  • SuperGee - Sunday, February 14, 2010 - link

    nV eyeFinity counter solution is a fast software reaction wich is barly the same thing. You need SLI because one GPU can do only 2 active ports. That the main diference. So you depend on a more high-end platform. A SLI mobo PSU capable of feeding two Gcards. While ATI give yo 3 or 6 ou t of one GPU.
    nV can deliver something native in there next design. Equal and the possibility to be better at it. But we are still waiting for there DX11 parts. I wonder if they could slap a solution in the refresh or can do only wenn they introduce the new archtecture "GF200".

    Reply
  • chizow - Monday, February 15, 2010 - link

    Actually EyeFinity's current CF problems are most likely a software problem which is why Nvidia's solution is already superior from a flexibility and scalability standpoint. They've clearly worked out the kinks of running multiple GPUs to a single frame buffer and then redistributing portions of that framebuffer to different GPU outputs.

    AMD's solution seems to have problems because output on each individual GPU is only downstream atm, so while one GPU can send frame data to a primary GPU for CF, it seems secondary GPUs have problems receiving frame data to output portions of the frame.

    Why I say Nvidia's solution is better overall is simply because the necessity of SLI will automatically decrease the chance of a poor gaming experience when gaming at triple resolutions, which is clearly a problem with some newer games and single-GPU EyeFinity. Also, if AMD was able to use multiple card display outputs, it would solve the problem of requiring a $100 active DP dongle for the 3rd output if a user doesn't have a DP capable monitor.
    Reply

Log in

Don't have an account? Sign up now