Adapting to Parallelism: Catalyst 5.12 More Dual Core Friendly?
by Derek Wilson on December 4, 2005 10:45 AM EST- Posted in
- GPUs
Introduction
Friday afternoon we got an email pointing us to the latest beta driver from ATI. One of the key features of this driver is a performance boost for dual core systems. Building a driver to take advantage of parallel processing is quite a task, and extracting any noticeable performance gain out of it is even more difficult. So we are here today to see just what ATI has gotten out of their efforts thus far.
Admittedly, the highest performance gains come from low resolutions without antialiasing. It stands to reason that the more CPU limited a test is, the more benefit the game will get from freeing up CPU resources. The real benefit to end users if only lower resolutions benefit is questionable, but every step helps. With the future of computer hardware firmly planted in parallelism, the burden of improving performance shifts a little further towards software developers. Coming up with new and interesting ways to parallelize code efficiently is going to be quite a new task for desktop software programmers to tackle. And in the end, Amdahl's Law reminds us that we are still limited by the benefit we can get from parallelism. The percentage of code that must remain sequential will become the limiting factor. But every little bit of parallelization still helps.
There are really quite a few questions to be asked about this driver. After adding up everything we wanted to do, the sheer number of tests we had laid out was enormous. In an effort to be more efficient ourselves, we decided to break our analysis of the 5.12 driver up. This article is meant as a quick look at the benefits of ATI's dual core enhancements on a few select games running on X1K series hardware. We will compare this driver to the old one as well as dual core performance to single core performance.
Our next look at the 5.12 driver will include a comparison to NVIDIA performance in single and dual core systems, more than one ATI card, more games, and as many more things as we can pack in. Of course we are open to suggestion. But for now, we'll take a look at what we've got to work with.
Friday afternoon we got an email pointing us to the latest beta driver from ATI. One of the key features of this driver is a performance boost for dual core systems. Building a driver to take advantage of parallel processing is quite a task, and extracting any noticeable performance gain out of it is even more difficult. So we are here today to see just what ATI has gotten out of their efforts thus far.
Admittedly, the highest performance gains come from low resolutions without antialiasing. It stands to reason that the more CPU limited a test is, the more benefit the game will get from freeing up CPU resources. The real benefit to end users if only lower resolutions benefit is questionable, but every step helps. With the future of computer hardware firmly planted in parallelism, the burden of improving performance shifts a little further towards software developers. Coming up with new and interesting ways to parallelize code efficiently is going to be quite a new task for desktop software programmers to tackle. And in the end, Amdahl's Law reminds us that we are still limited by the benefit we can get from parallelism. The percentage of code that must remain sequential will become the limiting factor. But every little bit of parallelization still helps.
There are really quite a few questions to be asked about this driver. After adding up everything we wanted to do, the sheer number of tests we had laid out was enormous. In an effort to be more efficient ourselves, we decided to break our analysis of the 5.12 driver up. This article is meant as a quick look at the benefits of ATI's dual core enhancements on a few select games running on X1K series hardware. We will compare this driver to the old one as well as dual core performance to single core performance.
Our next look at the 5.12 driver will include a comparison to NVIDIA performance in single and dual core systems, more than one ATI card, more games, and as many more things as we can pack in. Of course we are open to suggestion. But for now, we'll take a look at what we've got to work with.
Facebook
Twitter
RSS
56 Comments
View All Comments
huges84 - Sunday, December 4, 2005 - link
How much RAM did the test system have?Furen - Sunday, December 4, 2005 - link
Since integrated graphics cards are the ones that (currently) lack things like vertex shaders, they probably will get a much more "dramatic" performance increase from dual-core drivers.Cybercat - Sunday, December 4, 2005 - link
amazing improvements! At 800x600...Pannenkoek - Sunday, December 4, 2005 - link
Indeed, I guess this article has only been posted because someone at Anandtech has worked on it, and didn't want to have wasted his time entirely for some beta drivers no one cares about.Cygni - Sunday, December 4, 2005 - link
Ya, im sure all those people with Dual Core rigs, and all the people that will have Dual Core rigs by the end of this year (probably everybody on this board), doesnt care about Dual Core driver improvements.In other news, i hope that post was a joke...
Pannenkoek - Sunday, December 4, 2005 - link
This is a _beta_ driver, not a released driver. Anandtech could have waited for the actual release. Now we won't be seeing any article on the real thing when it will come out is my guess.Yeah, I'm sure all those people with bleeding edge dual core processors and newest generation ATi cards will rejoice at their 5 extra frames per second at the lowest humanly tolarable screen resolution in this age.
Besides, it can only be pathetic if they actually get real performance improvements. On higher resolutions it would only show how lousy their drivers would be if they use that much CPU power to make an impact in benchmarks if the driver is off-loaded to another core. And on lower resolutions they apparently stall their rendering pipeline with current drivers. Thumbs up.
Andyvan - Sunday, December 4, 2005 - link
Are you seriously saying that it would be better to not know this? I was also under the impression that they were going to post a followup with more tests.-- Andyvan
Pannenkoek - Sunday, December 4, 2005 - link
I never said it would be better to not know this, whatever this may be. The article states explicitely that there'll be a follow up, I was a bit too cynic perhaps. ;-)The point is, there's a lot of fluff about some beta driver which "takes advantage of dual core". Earthshattering. It's the least any graphic card driver developer could do. And I welcome any comprehensive tests and article by Anandtech on real products. I just don't see any point in this article, especially not in the light of an upcoming "complete" article. (I see one: self-advertisement). Good effort by the Anandtech crowd, but it annoys me after all the other prerelease & beta & exclusive vapourware reviews.
Ryan Smith - Sunday, December 4, 2005 - link
Keep in mind that ATI's drivers seldom change once they hit beta. Once they're in beta, ATI is usually done with any coding and internal testing, and they're simply handing these drivers out to their partners for testing to see if in the unlikely event a problem crops up. So I certainly wouldn't consider these drivers vaporware, since they will be in everyones hands in another week or so.As for why we did this article instead of waiting for the complete article, we felt it was more important for you to be able to see what ATI's dual-core changes are capable of now on the best of hardware, rather than wait longer for a full-comparison article. With the need to swap CPUs on top of everything else, it's going to take us some time to finish the full article. We can certainly wait until we have every last benchmark done, but we'd rather show what we have now and get feedback from you guys, rather than keep you in the dark any longer.=)
bob661 - Monday, December 5, 2005 - link
Don't mind him Ryan. Some people won't shop for a Ferrari until they can afford one.