The RV870 Story: AMD Showing up to the Fight
by Anand Lal Shimpi on February 14, 2010 12:00 AM EST- Posted in
- GPUs
Carrell Loses His Baby: Say Goodbye to Sideport
Sitting at dinner with Eric Demers and Carrell Killebrew is honestly one of the best experiences I’ve ever had working with ATI. Before he got huge and subsequently left, I used to have annual dinners with Pat Gelsinger at Intel. They were amazing. To get to sit at the same table as someone as talented and passionate as a Gelsinger, Demers or Killebrew is one of the most fortunate and cherished parts of my job.
Eric was telling me about how they trimmed down 870 from over 400mm2 down to 334mm2 and how wonderful the end product was. I stopped him and asked for more detail here. I wanted an example of a feature that they had to throw out but they really wanted to keep in. Manufacturers rarely tell you what they threw out, marketing likes to focus on what’s in the chip and make everything sound like a well calculated move. Thankfully, marketing wasn’t allowed to speak at my dinner.
Eric turned to Carrell and said: “i know one feature we could talk about.”
“Sideport”.
Carrell responded, “OH MY GOD, that’s totally not fair.” (note that Carrell does not sound like a teenage girl, imagine that phrase just spoken more engineer-y).
When ATI first talked about the Radeon HD 4870 X2 they told us about a feature called Sideport. It was a port off each RV770 GPU that could be used for GPU-to-GPU communication.
Sideport as it was intended to be used
The whole point of doing CrossFire in alternate frame rendering mode (AFR) is that the chips never have to talk. The minute you have to start synchronizing them, you kill performance. Sideport was supposed to alleviate that.
Unfortunately, due to power reasons, Sideport was never used on the 4870 X2. ATI’s reference design had it disabled and all vendors followed suit.
Sideport was Carrell Killebrew’s favorite feature, and he had to give it up.
In early 2008 ATI realized they had to cut this chip down from 20 - 22mm on a side to 18mm, everyone had to give up something. Carrell was the big advocate for making 870 smaller, he couldn’t be a hypocrite and not give anything up.
A bunch of my conversation with Carrell at this point had to go off the record. Sideport would have been useful in RV870, but it’s unfortunately not there. Although he did tell me not to be surprised if I saw Sideport again at some point. Carrell doesn’t give up easily.
Facebook
Twitter
RSS
132 Comments
View All Comments
devene - Sunday, February 14, 2010 - link
Just like many others, I've been a long time reader and I just couldn't carry on without leaving a comment:This has been an article, just like the RV770 one. It may not reveal many facts but is tremendously insightful and inspiring. Thank you for bringing this deeply hidden information out to the public and to the "fans". Please do everything in your power to continue this trend.
Once again, thank you Anand,
devene
medi01 - Sunday, February 14, 2010 - link
Germans say "lange Rede kurzer Sinn". So many pointless sentences that do not tell anything even remotely interesting.TGressus - Sunday, February 14, 2010 - link
Even the home team could not be sold on Eyefinity...William Gaatjes - Sunday, February 14, 2010 - link
Fantastic article."
First, it massively increased the confidence level of the engineering team. There’s this whole human nature aspect to everything in life, it comes with being human. Lose confidence and execution sucks, but if you are working towards a realistic set of goals then morale and confidence are both high. The side effect is that a passionate engineer will also work to try and beat those goals.
"
Finally, someone accepting and using human nature.
And see it works out...
The fun part is that a requested functionality that is desired but can not make it within the expected timeframe, can still be worked on and can be ready for the next "bulge" in the market. This way you relieve your engineers form stress, you have the time to sort errors and bugs out, you have time to solve unforseen consequences that always happen( people can get sick, a bug in software, machines breaking down) and you have a feature for the market department to market to the consumer for the next iteration of the product. This way you can use the free market to build an in the end perfect device. It is all about balance. If you have to invest to much energy in situation a, you will have less energy for situation b in a certain timeframe. We are bound by laws of nature meaning there is no "perpetuum mobile" in this universe. Nothing comes for free...
aegisofrime - Sunday, February 14, 2010 - link
Anand, you have taken an article that is really technical in nature, and turned it into something entertaining to read and yet informative for non-engineer types. My hats off to you. This is really the right balance of information and readability. If only all the Scientific Papers I have to read were written like this!dukeariochofchaos - Sunday, February 14, 2010 - link
i wonder if you will give fermi the same drama queen touch?i hope so.
Jamahl - Sunday, February 14, 2010 - link
I don't think anyone wants to read nvidia's marketing department tell us how awesome PhysX and CUDA is again tbh.TGressus - Sunday, February 14, 2010 - link
I suspect Fermi will be able to stand on it's technological innovation.RJohnson - Sunday, February 14, 2010 - link
...and it's exorbitant price/die size will exclude mere mortals from owning one.Spoelie - Sunday, February 14, 2010 - link
That depends entirely on the openness of NVIDIA on the subject, historically not one of their strong points.In fact ATi's take on NVIDIA's design process has been more informative than what has come out of NVIDIA itself.
But here's to hoping..