The RV770 Story: Documenting ATI's Road to Success
by Anand Lal Shimpi on December 2, 2008 12:00 AM EST- Posted in
- GPUs
Just One Small Problem: We Need a New Memory Technology
The R600 GPU had an incredibly wide 512-bit memory interface, the problem with such a large interface is that it artificially makes your die bigger as you’ve got to route those interface pads to the memory devices on the board. For RV770 to have the die size ATI wanted, it needed to have a 256-bit memory interface, but using (at the time) current memory technology that wouldn’t give the GPU enough memory bandwidth to hit the performance targets ATI wanted.
When the options were either make the chip too big or make the performance too low, ATI looked elsewhere: let’s use a new memory technology. Again, put yourself in ATI’s shoes, the time was 2005 and ATI had just decided to completely throw away the past few years of how-to-win-the-GPU-race and on top of that, even if the strategy were to succeed it would depend on a memory technology that hadn't even been prototyped yet.
The spec wasn’t finalized for GDDR5 at the time, there were no test devices, no interface design, nothing. Just an idea that at some point, there would be memory that could offer twice the bandwidth per pin of GDDR3, which would give ATI the bandwidth of a 512-bit bus, but with a physical 256-bit bus. It’s exactly what ATI needed, so it’s exactly what ATI decided to go with.
Unfortunately whether or not GDDR5 shipped by the summer of 2008 wasn’t all up to ATI, the memory manufacturers themselves had a lot of work to do. ATI committed a lot of resources both monetarily and engineering to working with its memory partners to make sure that not only was the spec ready, but that memory was ready, performing well and available by the summer of 2008. Note that the RV770 was going to be the only GPU that would use GDDR5, meaning that it was ATI and ATI alone driving the accelerated roadmap for this memory technology. It’s akin to you trying to single handedly bring 100Mbps internet to your city; it’ll happen eventually, but if you want it done on your time table you’re going to have to pickup a shovel and start burying a lot of your own cable.
ATI did much of the heavy lifting with the move to GDDR5, and it was risky because even if RV770 worked out perfectly but the memory wasn’t ready in time the GPU would get delayed. RV770 was married to GDDR5 memory, there was no other option, if in three years GDDR5 didn’t ship or had problems, then ATI would not only have no high end GPU, but it would have no performance GPU to sell into the market.
If GDDR5 did work out, then it meant that RV770 could succeed and that it would be another thing that NVIDIA didn’t have at launch. That is, of course, assuming that ATI’s smaller-die strategy would actually work...
Facebook
Twitter
RSS
116 Comments
View All Comments
n7 - Wednesday, December 3, 2008 - link
These kind of articles are why i love AT.Fantastic read, thanx!
glynor - Wednesday, December 3, 2008 - link
Thanks Anand. It is things just like this that have kept me coming back for years and year. Great work!jah128 - Wednesday, December 3, 2008 - link
Really good article, one of the best I've read here.doittoit - Wednesday, December 3, 2008 - link
Don't forget what rv770 did to GTX 280. Made it completely irrelevent. 2 x 4850 made it so no-one would ever bother with nvidia's "monster". Now they just have to get over the hump on driver support. Down with NVIDIA!!Element81 - Wednesday, December 3, 2008 - link
Best article I've read on your site in a long time. I crave all the performance benchmarks and reviews of new products but the back story behind the creation of the RV770 is amazing. I will be building myself a new rig very soon and I've been following hardware religiously in the last few months to help me make my decision. A new 4850 or 4870 will def end up in my new build.BernardP - Wednesday, December 3, 2008 - link
Thanks for this great article. Well-written and full of new information.truk007 - Wednesday, December 3, 2008 - link
This article is the best I've read on any tech site. Loved it! I hope Anandtech has more behind-the-scenes stories like this again, and I also hope that companies continue to give these types of interviews. It was a great journalistic piece that made the company all that much more human. Thanks!rwei - Wednesday, December 3, 2008 - link
I've been reading for 2-3 years and was too lazy to comment...but I found this article compelling enough to create an account just to say how much I liked it =)For a student studying both compsci and business/mgmt, the dual focus on engineering and business challenges was very interesting. Though there was a very obvious potential for a "rah-rah ATI!" bias given the nature of the interview, especially when discussing R600.
WeaselITB - Wednesday, December 3, 2008 - link
There must be echos in here, because I'm adding my words to the mix. In the roughly-10 years that I've been reading AnandTech (yes, I remember reading the Celeron "launch" article and the whole celery jokes that went with it), I must say that this is one of the best articles I've read here.It's articles like this that keep me coming back to AT all these years. Everyone and their dog can benchmark and put up pretty graphs (no offense, Derek), but it's the meaty articles like this one that give AT that leg-up over the competition.
Thanks, Anand, for an awesome ten years, and here's to ten more!
Goty - Wednesday, December 3, 2008 - link
On page 2, when discussing the Radeon 8500, you have to remember that the 8500's intended competition was the GeForce 3 series, against which it was fairly competitive (especially at the end of its life). ATI never really released a product to compete with the GeForce 4 cards.