Looking Back: ATI's Catalyst Drivers Exposed
by Ryan Smith on December 11, 2005 3:22 PM EST- Posted in
- GPUs
Looking Back: ATI’s Catalyst Drivers Exposed
It’s no secret in the hardware world that good software is often just as important as good hardware. The best processor, the best TV tuner, and even the best sound card can only be as good as the software and drivers backing it up. Even a small change in one critical piece of code can result in a massive difference that represents a significant change in performance and sales of a piece of hardware.
Above all, however, this concept is embodied in the realm of video cards, where over the years, we have been spoiled by promises of “A performance improvement between 17 and 24% is noticed in Jedi Knight II” and “up to 25% performance improvement in popular consumer and professional applications”. These days, it’s not just common to see GPU makers find ways to squeeze out more performance out of their parts - it’s expected. Finishing the design of and launching a GPU is just the first steps of a much longer process of maximizing performance out of a part, a process that can quite literally take years.
With the flexible nature of software, however, it has caused a significant shift in the marketing strategies of GPU makers, where the war is not over at launch time, but continues throughout the entire product cycle and in to the next one as new optimizations and bug fixes are worked in to their drivers, keeping the performance landscape in constant motion. Just because a side did not win the battle at launch doesn’t mean that they can’t still take it later, and just because a side won now doesn’t mean that they’ll keep their win.
We have seen on more than one occasion that our benchmarks have been turned upside down and inside out, with cases such as ATI’s Catalyst 5.11 drivers suddenly giving ATI a decisive win in OpenGL games, when they were being soundly defeated just a driver version before. However, we have also seen this pressure to win drive all sides to various levels of dishonesty, hoping to capture the lead with driver optimizations that make a product look faster on a benchmark table, but literally look worse on a monitor. Quake3, 3DMark 2003, and similar incidents have shown that there is a fine line between optimizing and cheating, and that as a cost for the flexibility of software, we may sometimes see that line crossed.
That said, when the optimizations, the tweaks, the bug fixes, and the cheats are all said and done, just how much faster has all of this work made a product? Are these driver improvements really all that substantial all the time, or is much of this over-exuberance and distraction over only minor issues? Do we have any way of predicting what future drivers for new products will do?
Today, we set out to answer these questions by taking a look back at a piece of hardware whose time has come and is nearly gone: ATI’s R300 GPU and the Radeon 9700 Pro.
It’s no secret in the hardware world that good software is often just as important as good hardware. The best processor, the best TV tuner, and even the best sound card can only be as good as the software and drivers backing it up. Even a small change in one critical piece of code can result in a massive difference that represents a significant change in performance and sales of a piece of hardware.
Above all, however, this concept is embodied in the realm of video cards, where over the years, we have been spoiled by promises of “A performance improvement between 17 and 24% is noticed in Jedi Knight II” and “up to 25% performance improvement in popular consumer and professional applications”. These days, it’s not just common to see GPU makers find ways to squeeze out more performance out of their parts - it’s expected. Finishing the design of and launching a GPU is just the first steps of a much longer process of maximizing performance out of a part, a process that can quite literally take years.
With the flexible nature of software, however, it has caused a significant shift in the marketing strategies of GPU makers, where the war is not over at launch time, but continues throughout the entire product cycle and in to the next one as new optimizations and bug fixes are worked in to their drivers, keeping the performance landscape in constant motion. Just because a side did not win the battle at launch doesn’t mean that they can’t still take it later, and just because a side won now doesn’t mean that they’ll keep their win.
We have seen on more than one occasion that our benchmarks have been turned upside down and inside out, with cases such as ATI’s Catalyst 5.11 drivers suddenly giving ATI a decisive win in OpenGL games, when they were being soundly defeated just a driver version before. However, we have also seen this pressure to win drive all sides to various levels of dishonesty, hoping to capture the lead with driver optimizations that make a product look faster on a benchmark table, but literally look worse on a monitor. Quake3, 3DMark 2003, and similar incidents have shown that there is a fine line between optimizing and cheating, and that as a cost for the flexibility of software, we may sometimes see that line crossed.
That said, when the optimizations, the tweaks, the bug fixes, and the cheats are all said and done, just how much faster has all of this work made a product? Are these driver improvements really all that substantial all the time, or is much of this over-exuberance and distraction over only minor issues? Do we have any way of predicting what future drivers for new products will do?
Today, we set out to answer these questions by taking a look back at a piece of hardware whose time has come and is nearly gone: ATI’s R300 GPU and the Radeon 9700 Pro.
Facebook
Twitter
RSS
58 Comments
View All Comments
ksherman - Friday, December 16, 2005 - link
Any chance for a nVidia comparison? Ive ehear that some older drivers were better...semiconductorslave - Tuesday, December 13, 2005 - link
Great, I'll tell the person that bought my videocard three cards ago! Maybe next we could see an article about how adding 3 extra 16k memory cards to the Atari 800 improves games.HWAddict77 - Tuesday, December 13, 2005 - link
[lecture]Guess what? There is real value in the fact that the people writing these articles actually interact with us to find out what we think. In publishing, web-based or otherwise, that's rare and valuable, and it puts us in a pretty cool position if you ask me. So I think being a smartass is particularly lame. It's not like there are only 20 people reading the articles. Hell, it's not like there are only 1000 people reading them.
[/lecture]
My .02: I would also like to see a similar article with an Nvidia card.
semiconductorslave - Wednesday, December 14, 2005 - link
So your saying we can't use sarcasim to voice our opinions? I totally appreciate this site and all of the reviews, and hope the editors can handle a little bit of facetiousness every now and then. It is my attempt at humor and way of saying that I think this article, being more of a research piece into the history of driver support on an older card, is more academic and not very pragmatic. I'm not saying the author made the following assumtion, but it would be a logical fallacy for a person to assume the future will happen like the past. ATI could have better driver releases in the future, put more resources into it, hire more talented programers, also the hardware is always changing, like dual core CPUs and ring bus memory architectures on graphics cards. So I personaly don't think how the drivers perform on the old 9700pro make much difference to anyone but a person running the old 9700pro. This in turn will limit what games they can run since the newer games take a bit more power, especially with AA enabled, AS filtering, and HDR, so now--once again in my opinion--the article is most helpful to the person running old games on an old card.Still I read it.
jeffrey - Monday, December 12, 2005 - link
Ryan Smith,Thank you for publishing this article! The whole idea of the article itself is what makes me so happy. It was not another "product release -> generate review" type article. This article stepped-out of that mold and required thinking of an idea and then testing to find the result. Kudos!
What made the article an A+ was that the results were not there. To clarify, I should say expected results. ATI has been promising increase after increase, but after several generations, there just was not a whole lot there.
ATI has impressed with monthly driver releases, but performance gains are limited. I am NOT disapointed with the results. ATI's claims for driver improvements are rarely across the board. More often than not, the claim of a gain is focused on a particular generation, segment, or resolution.
One important fact that was left out of the review was compatibility. A central focus of each Catalyst release is fixing bugs to make the drivers more stable. The commitment from the Catalyst crew to providing incremental optimizations has mainly been secondary this year to resolving driver issues. The graphs might show an image that looks like not a whole lot has been done. However, if you included a total of bug fixes from Catalyst 3.0 to 5.12 the image of that graph would be impressive indeed.
ATI's monthly Catalyst updates have been invaluable to their reputation as a provider of graphics solutions. How many companies have checked-in and checked-out within a couple of years due to drivers never "maturing". ATI has a positive image today in regards to drivers and that alone is a barrier to entry for new competition.
I could go on and on, but if by chance you get down to my post please feel free to pat yourself on the back and share this with Anand.
Thanks again,
Jeffrey
timmiser - Tuesday, December 13, 2005 - link
I agree. This article was definitely outside the mold and nothing like this had been done before. (To see driver improvements over years instead of months.)Nighteye2 - Monday, December 12, 2005 - link
Nice article. Now I want to see the same test for Nvidia drivers :)MrJim - Monday, December 12, 2005 - link
Mr Ryan Smith>It would be nice to see a flightsim or a racing sim! Maybe a newer one with impressive graphics like Lock-On/Lo-Mac(Flightsim) for example. Interesting article!ShadowVlican - Monday, December 12, 2005 - link
now to anyone that still says ATi has bad drivers... i will refer them to this review (6)bldckstark - Monday, December 12, 2005 - link
I don't see where this proves they have GOOD drivers either. They had on average some minor improvements in FPS and fixed some IQ issues. Yes there were some nuggets of enlightenment, but overall the greatest increase was in eventually eliminating a huge IQ flaw in soft lighting.