The RV770 Story: Documenting ATI's Road to Success

This was the email that set it off:

Hi Anand,

You have an appointment with Carrell Killebrew at 3pm tomorrow at ATI Santa Clara - he's going to give you the background on what REALLY went on behind 770. He'll meet you in the lobby on the 5th floor.

Chris

The email was from Chris Hook, PR at AMD, I’d worked with him for years and at ATI before the acquisition. I’ve always given him a hard time for trying to spin me, for doing a great job of hosting parties but a terrible job of putting me face to face with the brightest engineers.

Chris Hook seems terribly uninterested in whatever is coming out of my mouth at this dinner years ago :)

Lately Chris has been on a quest to prove me wrong. He gets that I don’t care about the parties or the exotic destinations that AMD usually hosts its press events at, I just want the product and the engineers. Earlier this year Chris let one engineer out of the bag and we had a great conversation about AMD’s manufacturing and packaging technologies (yeah, I’m a boring date). He gained a bit of trust with that interaction, so when he sent me the email above my ears perked.

I made my way back to ATI Santa Clara for the 3PM meeting and as I exited the elevator I heard “Anand?” from behind me. I didn’t recognize any of the men there but that’s not too unusual, in my old age remembering all of the faces is getting difficult, after all I’ve been doing this for nearly 12 years now. Thankfully this wasn’t one of those cases of forgotten identities, the man who I’d soon find out was Carrell Killebrew simply recognized me from a picture. What picture? I have no idea, perhaps AMD keeps pictures of Derek, Gary and myself on walls to know who to be angry at.

We walked around 30 feet into a small room with a table and some chairs, there was a speakerphone in the middle of the table. In the room was myself, Carrell Killebrew, Eric Demers, Mike Schmit and Mark Leather.

Most of these people I’d never met before, although I had heard their names. AMD, and ATI before the acquisition, had historically done a terrible job of giving us access to their smartest people. At best we’d get people in technical marketing, but very rarely the lead architects or any Fellows (read: certified genius title). That day however, on my day off, I found myself in a room with AMD Fellow after Fellow, smart guy after smart guy...and not a single member of AMD PR to muzzle the engineers.

To appreciate Carrell you have to understand that most of the people we talk to about GPUs are there to market us, and do so in a very markety tone. These briefings normally start out with some slides on the lay of the land, talking about how gaming is important, then there’s some architecture talk, a bit about the cards, some performance data that we don’t pay attention to and then a couple of conclusion slides. For a company that builds products that let you blow off peoples’ heads and watch the whole thing in greater fidelity, the way they talk to us about product is pretty lame.

Carrell, was different. Carrell Killebrew was the engineering lead on RV770, the GPU behind the Radeon HD 4800 series, and he was exactly the type of person you’d expect to be lead engineer on a product used to play video games, ridiculously fun, video games.

Carrell started the conversation off by saying that everything he was about to tell me would be on record, and he was assuming that no one had any objections to that. This was going to be good.

He asked me what I’d like to talk about and he offered some choices. We could talk about future GPU trends and architectures, we could talk about GPU accelerated video transcoding or he, along with the rest of the group, could give me the back story on RV770.

Carrell’s final option piqued my interest, I hadn’t really thought about it. When RV770 launched in the summer we took for granted that it was a great part, it upset NVIDIA’s pricing structure and gave us value at $200 and $300. We went through the architecture of the Radeon HD 4800 series and looked at performance, but I spent only a page or so talking about AMD’s small-die strategy that ultimately resulted in the RV770 GPU. AMD had spent much of the past 8 years building bigger and bigger GPUs yet with the RV770 AMD reversed the trend, and I didn’t even catch it. I casually mentioned it, talked about how it was a different approach than the one NVIDIA took, but I didn’t dig deeper.

Normally when a manufacturer like AMD tells me they did something, I ask why. When Intel introduced me to Nehalem’s cache architecture, I asked why and later published my findings. And for the most part, with every aspect of the Radeon HD 4800’s architecture, we did the same. Derek Wilson and I spent several hours on the phone and in emails back and forth with AMD trying to wrap our heads around the RV770’s architecture so that we could do it justice in our reviews. But both of us all but ignored the biggest part of RV770: the decision that led to making GPU itself.

This is a tough article for me to write, there are no graphs, no charts, no architecture to analyze. I simply got to sit in that room and listen as these individuals, these engineers shared with me over the course of two hours the past three years of their lives. I want to do it justice, and I hope that I can, because what they conveyed to me in that room was the best meeting I’d ever had with AMD or ATI.