Details of the Cards

There are actually 4 products being launched today, three of which we were able to get our hands on for this article. We have actually spotted all three of these cards we tested around the internet today, so availability is immediate, and we couldn't be happier. As for pricing, ATI's MSRPs are as follows:

Radeon X1900 XTX -- $650
Radeon X1900 CrossFire Edition -- $600
Radeon X1900 XT -- $550

The CrossFire Edition version of the X1900 is clocked the same as the X1900 XT except for its I/O connectors and compositing engine. The X1900 XT weighs in with some very high clock speeds, especially for the number of pixel pipelines it supports. If you are worried about the CrossFire card bringing down the XTX, don't be. The XTX only sees about a 4% increase in core clock speed and a 7% increase in memory clock speed over the stock X1900 XT.

ATI X1000 Series Features
Radeon X1900 XT(X)
Radeon X1600
Radeon X1800 XL
Radeon X1800 XT
Vertex Pipelines
8
5
8
8
Pixel Pipelines
48
12
16
16
Core Clock
625(650)
590
500
625
Memory Size
512MB
256MB
256MB
512MB
Memory Data Rate
1.45GHz (1.55GHz)
1.38GHz
1GHz
1.5GHz
Texture Units
16
4
16
16
Render Backends
16
4
16
16
Z Compare Units
16
8
16
16
Maximum Threads
512
128
512
512


So, while the price gap between the XTX, XT, and CrossFire versions of the card would seem to indicate sizeable performance differences, we can definitively say that this is not the general case. The XTX is only marginally faster even on paper, and, as we will see, in the real world, real performance is what matters. Our advice is to save your money and go with the cheaper XT. 18% more cost for at best 7% more performance is all that the XTX gives.

R580 Architecture One Last Thing, there’s an All-in-Wonder Version too
Comments Locked

120 Comments

View All Comments

  • Live - Tuesday, January 24, 2006 - link

    Thanks for the explanation! Derek I think this merits a mention in the review.
  • NullSubroutine - Tuesday, January 24, 2006 - link

    perhaps a flash system where you can pick the card within the benchmark and it will show it on the line graph. just simply activate/deactivate feature.
  • bldckstark - Tuesday, January 24, 2006 - link

    I have to agree that a group color for the multi-GPU setups would be helpful on the bar graphs. The outline you used to denote negative gains would work well for this. Then ATI and Nvidia bars would still have a different major color, but the multi-GPU setups could have a yellow outline. E.G. ATI = red, ATI X-fire = Red w/ yellow outline, Nvidia = blue, Nvidia SLI = blue w/ yellow outline.
  • Rock Hydra - Tuesday, January 24, 2006 - link

    I don't know if you meant this or not, on the page mentioning the new crossfire board. There is url, I don't know if it was intended to be active or plain text, but I thought I would just bring that to your attention.
  • DerekWilson - Tuesday, January 24, 2006 - link

    thanks, fixed
  • emilyek - Tuesday, January 24, 2006 - link

    Good article.


    You have two typos in your article.

    In the system specs you have OZC Powerstreams instead of ...stream

    When you use the words 'eek out' as a verb that means 'squeeze out', it is spelled 'eke'-- 'eke out'.
  • DerekWilson - Tuesday, January 24, 2006 - link

    I had no idea there was a correct spelling for eke ...

    thanks
  • beggerking - Tuesday, January 24, 2006 - link

    Did anyone notice it? the breakdown graphs doesn't quite reflect the actual data..

    the breakdown is showing 1900xtx being much faster than 7800 512, but in the actual performance graph 1900xtx is sometimes outpaced by 7800 512..
  • DerekWilson - Tuesday, January 24, 2006 - link

    We didn't aggregate performance of each card under each game.

    for the percent improvment breakdown we only looked at 2048x1536 with 4xAA which clearly shows the x1900xtx in the lead.

    our reasoning is that this is the most stressful stock test we throw at the cards -- it shows what the cards can handle under the highest stress.
  • beggerking - Tuesday, January 24, 2006 - link

    umm.. what about 8xAA or higher? or lower resolution? w/wo AA?

    if you don't aggregate performance, then won't the graphic be misleading?

    isn't max quality the most stressful test ?

Log in

Don't have an account? Sign up now