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
yourwhiteshadow - Thursday, December 4, 2008 - link
absolutely brilliant. i've always read anandtech instead of tomshardware because of objective reviews. i was reading an intel review, and people were questioning the objectivity of anandtech. while some might could look at this as praising ATI/AMD, i would definitely say this was a very objective view of what happened. seriously, one of the BEST articles i've read since the 4850/4870 review.kevyeoh - Thursday, December 4, 2008 - link
I've been reading anandtech for years and there wasn't any article that makes me wanna read every single word of it. Usually i will read the forewords and then skip on to the Conclusion. But for this article, i really read every single words! period! Anandtech rocks!nitemareglitch - Thursday, December 4, 2008 - link
I was actually getting a little bored with the articles around here, until I read this one. Great job, I loved reading this story!!lchyi - Thursday, December 4, 2008 - link
This is by far the best (and most insightful) article I have read here to date Anand. It sounds like you put in a ton of thought to it and I have never flown through 7,500 words as quick as that read. Congrats to the ATI guys for their successful gamble on the RV770. The last three years must have been an extremely interesting experience for them and their engineers.joshjnm - Thursday, December 4, 2008 - link
Great article I will bandwagon with the rest of you and agree this is one of the best articles I've read in a while.josh6079 - Thursday, December 4, 2008 - link
I thoroughly enjoyed the article. Last time I was really involved with graphics cards was when the X1900's were in full swing and G80 was on everyone's mind. The history told in the article helped bring me up to pace as to what has transpired since I stopped gaming as much. I can remember how the Video card section used to be here on the forums with the trolls and constant flames. Two camps of people cheered on for one or the other competitors instead of realizing that they should be cheering for competition itself.Great job ATI, Nvidia - what's next?
Seikent - Thursday, December 4, 2008 - link
Very good article, most of these interesting background stories are written in books, but a lot of years latter.Something, that is not mentioned, is that it seems that AMD didn't affect ATI in any way (technically speaking). Many thought that the R600 failure had something to do with AMD.
BSMonitor - Thursday, December 4, 2008 - link
Awesome article.I am definately a performance/mainstream kinda guy in this market. Definately love the competition. I started my first build with a Geforce 4200Ti, moved up to the infamous 9700Pro, followed by X1900, and now 4850HD...
It is good to see that the ATI/AMD didn't damage ATI as a whole. Rock on guys! Love those cheap kick ass Crossfire cards! Go 4850HD x2.
dmer - Thursday, December 4, 2008 - link
as a long time reader of anand I never felt the need to register an account; however, after reading your article I felt compelled to create an account just to commend you on an excellent article.we need more articles that give us insight into business decisions like this. job well done mate!
johnkwright - Thursday, December 4, 2008 - link
Anand,I've been a long time reader of AnandTech but I especially liked this article. It was interesting to get a peek behind the curtain to see what challenges companies face when making these tough decisions. Hopefully more companies take a chance and share more of their stories with this site. Keep up the good work.
Regards,
John Wright