ATI's X1000 Series: Extended Performance Testing
by Derek Wilson on October 7, 2005 10:15 AM EST- Posted in
- GPUs
Introduction
With our recent architecture and feature set coverage over the ATI Radeon X1000 series launch, we were a little bit light on the performance numbers. Rather than fill out some of the tests and update the article, we decided to take a little more time and do it up right. We have heard the call for more game tests, and today, we bring them on in spades. Our expanded tests include the games mentioned in our earlier coverage, the much requested Battlefield 2, and we illustrate the stellar way in which the new X1000 series handles enabling 4xAA on the games that we tested.
While scaling-with-aa on the new X1000 series is very good, will it be good enough to make up for the price difference with competitive NVIDIA hardware? Certainly, the feature set is of value with ATI offering the added benefit of MSAA on MRT and floating point surfaces, high quality AF, SM3.0, and Avivo. But performance is absolutely critical on current and near term games. Currently, many HDR methods avoid floating point output and MRTs in order to maintain compatibility with AA on current hardware. Until game developers shift to full floating point framebuffers or make heavy use of multiple render targets, ATI's added AA support won't make much difference to gamers. High quality anisotropic filtering is definitely something that we have begged of NVIDIA and ATI for a long time and we are glad to see it, but the benefits just aren't that visible in first-person shooters and the like. Shader Model 3.0 and Avivo are good things to have around as well; better API support, image quality, and video output are things that everyone wants.
However, the bottom line is that performance sells video cards. The first thing that people question when they are looking for a new card is just how well it runs in their favorite game. Hopefully, we will be able to shed some light on the issue here.
We will look at resolutions from 800x600 up to 2048x1536 and antialiasing tests will be included where possible. In games where we tested both with and without antialiasing, we will also show a graph of how performance drops due to AA scales with resolution. This data will be a lower-is-better graph (less drop in frame rate is a good thing) and will be shown scaled over resolution (as a performance drop will increase in percentage with resolution). The test system that we employed is the one used for our initial tests of the hardware.
With our recent architecture and feature set coverage over the ATI Radeon X1000 series launch, we were a little bit light on the performance numbers. Rather than fill out some of the tests and update the article, we decided to take a little more time and do it up right. We have heard the call for more game tests, and today, we bring them on in spades. Our expanded tests include the games mentioned in our earlier coverage, the much requested Battlefield 2, and we illustrate the stellar way in which the new X1000 series handles enabling 4xAA on the games that we tested.
While scaling-with-aa on the new X1000 series is very good, will it be good enough to make up for the price difference with competitive NVIDIA hardware? Certainly, the feature set is of value with ATI offering the added benefit of MSAA on MRT and floating point surfaces, high quality AF, SM3.0, and Avivo. But performance is absolutely critical on current and near term games. Currently, many HDR methods avoid floating point output and MRTs in order to maintain compatibility with AA on current hardware. Until game developers shift to full floating point framebuffers or make heavy use of multiple render targets, ATI's added AA support won't make much difference to gamers. High quality anisotropic filtering is definitely something that we have begged of NVIDIA and ATI for a long time and we are glad to see it, but the benefits just aren't that visible in first-person shooters and the like. Shader Model 3.0 and Avivo are good things to have around as well; better API support, image quality, and video output are things that everyone wants.
However, the bottom line is that performance sells video cards. The first thing that people question when they are looking for a new card is just how well it runs in their favorite game. Hopefully, we will be able to shed some light on the issue here.
We will look at resolutions from 800x600 up to 2048x1536 and antialiasing tests will be included where possible. In games where we tested both with and without antialiasing, we will also show a graph of how performance drops due to AA scales with resolution. This data will be a lower-is-better graph (less drop in frame rate is a good thing) and will be shown scaled over resolution (as a performance drop will increase in percentage with resolution). The test system that we employed is the one used for our initial tests of the hardware.
Facebook
Twitter
RSS
93 Comments
View All Comments
tfranzese - Friday, October 7, 2005 - link
These points were brought up about the first article too. It's a big improvement, I agree, but it's still not to the level that this site was founded on.DerekWilson - Friday, October 7, 2005 - link
We already commented on the FEAR Demo -- we won't test a game that doesn't show shipping performance characteristics. We are working on getting our hands on a prerelease copy of the shipping game for testing.We have had black and white 2 in house since it became available at best buy (as today is the official US launch, we got it a couple days early). We just haven't had enough time to finalize tests for it.
We will look into the recently released call of duty 2 demo among others. I agree that we could have done things better, and hopefully our coming follow up will hit all the points people want covered.
If you have any other suggestions, please let us know -- we will try our best to include them.
PrinceGaz - Friday, October 7, 2005 - link
As for other suggestions, how about some games other than FPS or FPS-view (EQ2) style games? A driving game like NFS:U2 or colin McRae Rally 2005 would be an excellent addition. Then you should have some sort of flight/space-sim, like maybe X2. And a roleplaying game that isn't viewed from a first-person perspective. By including games that have a totally different style of graphics, you'll get a better idea of how well the card performs. X2 for instance would require totally different graphics performance than Half-Life 2.I know some of the games I've mentioned don't have a benchmarking mode, but use FRAPS to get the average framerate. And the minimum framerate. In fact the minimum framerate is more important than the average so you should include it as a matter of course in *all* tests, even to the point of dropping the average framerate if you don't have space. No one is too bothered if the average framerate while playing is 45 or 50fps while playing a game, but the difference between minimum framerates of 20 and 25fps would definitely be noticeable. I'm sure others will agree.
This (and many other) site seems to think FPS games are all people play, but a lot of us play games from all genres, so including them would be useful.
coldpower27 - Saturday, October 8, 2005 - link
I support the use of X2: The Threat as a benchmark, I also support the use of shipping games to compare numbers, so Anandtech should benchmark Black & White 2 as it is now available, plus Call of Duty 2 & Fear when they become available.bob661 - Friday, October 7, 2005 - link
Even though I found the original article very informative (I guess I can read well), this one was much better. The bar graphs don't show how the performance goes down as you raise the resolution and turn on the eye candy.zmanww - Friday, October 7, 2005 - link
what no Overclocking?come on I want to see that this baby can really do.
Peldor - Friday, October 7, 2005 - link
I don't think the usual overclocking utilities are working for the X1x00 cards yet.DerekWilson - Friday, October 7, 2005 - link
this is true -- we wanted to test slower versions and couldn't because of this.also reference board overclocking isn't always the best indication of retail board performance.
Lonyo - Friday, October 7, 2005 - link
Would be nice to see some analysis of ATi's SM3 implimentation, with SM2 vs SM3 benchmarks in the games which do support SM2 and SM3 paths.tfranzese - Friday, October 7, 2005 - link
From the article:I think the analysis and the conclusions up to this point have been far short sighted. Seems that the games that are using SM3.0 are taking considerable advantage of the new architecture. The Tech Report, Hexus and others were able to show that much.