ATI is also announcing the Radeon 9600 XT; a much more exciting derivative of the Radeon 9600 Pro based on a low-k dielectric 0.13-micron process. The benefits of a low-k dielectric are mainly related to shielding from crosstalk in high transistor density chips; the benefit of a low-k process is mainly the ability to scale up clock speeds, which is why you will see that ATI is able to clock the 9600 XT at 500MHz. According to ATI, the Radeon 9600 XT should be the first mainstream part to outperform the Radeon 9700 Pro in all situations – not bad for a $199 card.

The Radeon 9600 XT will hit the streets sometime in November and we’ll be sure to bring you coverage of that card as soon as we get our hands on one.

Finally we have the NV38, NVIDIA’s Fall refresh part; we won’t see NV40 and R4x0 until next Spring so both companies are bringing out higher clocked versions of their current cards in order to compete during the holidays.

Just like the Radeon 9800 XT, the NV38 is basically a higher clocked version of the NV35 (GeForce FX 5900 Ultra) with a new cooling system. Now running at 475/475 (950MHz DDR), the NV38 boasts a 5% increase in core clock and an 11% increase in memory frequency.

The card will officially be launched next month but we’re going to be able to bring you a preview of the NV38’s performance today.

The Newcomers The New Test Suite
Comments Locked

263 Comments

View All Comments

  • Anonymous User - Wednesday, October 1, 2003 - link

    How come cards likes the new XT can only get 50fps en jediknight3 ( old Q3 engine ) and reach for the 215 for UT 2k3? ( witch have way better graphic )
  • Anonymous User - Wednesday, October 1, 2003 - link

    I really wonder what happened to Anandtech. I once liked and trusted their reviews so much that I did not read any other ones.

    Now I see the first review of the NV38 and do not see it benchmarked in any way that would interest me. No Tomb Raider: AOD, no Shadermark, no AA/AF, no image quality comparisons and no Half-Life 2 (okay, this might not be Anandtechs fault).

    This means no DX9.0 title that is demanding when it comes to Pixel Shader 2.0 power (no, Aquamark isn't). So please not not bench a ton of CPU/Memory limited games even without AA/AF.

    "The performance crown under Doom3 is still in NVIDIA’s camp apparently". Doom3 is mainly DirecX8. Period.

    "ATI is still ahead in Half Life 2. The numbers we’ve seen indicate that in most tests ATI only holds single digit percentage leads (< 5%), although in some cases ATI manages to pull ahead by double digits." What does that mean? Is this only with the NV30 optimised (degraded IQ) code path. If so, too bad for them.

    Finally what I liked to know is if NVidia required Anandtech to benchmark this way...
  • Anonymous User - Wednesday, October 1, 2003 - link

    How can Anand use det. 52, It's well know to cheat with lower IQ in Aquamark etc!
  • Anonymous User - Wednesday, October 1, 2003 - link

    Are you really using:
    2.8GHz Intel Processor Prescott
  • Anonymous User - Wednesday, October 1, 2003 - link

    It was great to see so many games represented, not the least of which is one of my favorites: Neverwinter Nights.

    One game that I would be thrilled to see is Star Trek Armada II. The game is a blast to play, and under situations with many ships (ESPECIALLY multiplayer) the game can slow to a crawl even on high-end systems. I would hazard to guess that this game is more CPU bound, but a graphics analysis wouldn't hurt anything.
  • Anonymous User - Wednesday, October 1, 2003 - link

    I thought it was a little ridiculous that almost every benchmark had the stipulation that "AA didn't seem to be applied. We'll investigate later." or "Image Quality wasn't up to snuff. We'll investigate later." and yet you still included the results for the Nvidia cards.

    After the article from Lars Wienand from THG where he states that if the driver reduces image quality to gain Framerate they gray it out, I expect the same thing from Anandtech. Especially since the drivers you used are unreleased for public consumption and may never even reach the public.

    At this point image quality is indeed king. Who wants to spend $500 on a video card that will not provide top notch image quality? I know I don't.
  • Anonymous User - Wednesday, October 1, 2003 - link

    the only thing i would have like to have seen though, was an indication on the performance graphs as to whether the game being used was a dx8 game, or dx9 game...

    i think most of those games were dx8...but i cant be certain, so it would have been nice to have known for sure...
  • Anonymous User - Wednesday, October 1, 2003 - link

    i cant wait for part 2 !

    :)
  • Anonymous User - Wednesday, October 1, 2003 - link

    Would be Cool if Anandtech could start to use Shadermark 2.0 :)
  • Anonymous User - Wednesday, October 1, 2003 - link

    The sleepless are rewarded once more!

Log in

Don't have an account? Sign up now