The Card

The X1650 XT is based on the older X1600 cards, but it's really a completely new spin on the silicon. Although the X1650 has lower clock speeds than the older X1600 XT, we will see better performance out of the X1650 XT because it has twice as many pixel pipelines (24 vs. 12) and internal bridges for CrossFire, which we will touch on later in the review. This new ATI card is fabbed on TSMC's 80 nanometer process. That means the chip is smaller, and it should run cooler as well. This also means it's cheaper for ATI to produce, which could be part of why ATI is offering a part with more pipelines for a (potentially) lower price. The 24 pipeline configuration also fills the gap between the 12 and 36 pipeline parts ATI has been offering. This should give them a little more clock speed flexibility in the mainstream arena.

In performance, the X1650 XT is poised to nudge a few of the current cards on the market out of the way, including the X1650 Pro. Despite the similar product names, like the X1600 XT the X1650 Pro and XT are very different cards. In the past, the X1600 XT was meant by ATI to be competition for the NVIDIA 7600 GT, but as such it was a miserable failure. Its current replacement, the X1650 Pro isn't able to do any better with only a 10MHz boost in core and memory clock speed over the X1600 XT. With the X1650 XT, however, ATI seems to have finally come up with some competition for this mainstream NVIDA card. Of course price will be a factor when trying to determine actual competition and card value, but we will see in our performance section how they compete strictly in the gaming arena.

Speaking of price, as we said in the introduction, the card comes with an ATI MSRP of $150. Whether it will actually be available at this price is anyone's guess, but we feel that given the performance (which we will see next), at this price the X1650 XT would be a good deal. As we've talked about before, price plays a vital role in the success of a graphics card, and no amount of power will make a card worth buying if the price isn't competitive. The value is important when shopping for a new card, and because the GPU market can be very fickle sometimes from week to week, pinning this down can be difficult.



Looking at the X1650 XT, we are initially struck by how it seems nearly identical to the X1600 XT which launched what seems like ages ago. Only by holding the two cards next to each other can you see the subtle differences. Both have dual DVI connections and a matte black heatsink with a small fan in them. Component selection and placement was tweaked probably to accommodate internal CrossFire connectors. As looks go, the X1650 XT isn't nearly as impressive as the X1950 Pro, in fact it's just the opposite. The original reference X1600 XT looked a bit crude in our opinion, and the X1650 XT is no different. But we realize these are only the reference designs, so we'll wait to see what different vendors do before passing aesthetic judgments. Besides, a card's looks are not of any consequence when compared to its performance and value. So moving on, let's take a look at how the X1650 XT's specifications stack up against the rest of the cards out there. Then we'll see how well this ugly duckling from ATI performs.

NVIDIA Graphics Card Specifications
Vert Pipes Pixel Pipes Raster Pipes Core Clock Mem Clock Mem Size (MB) Mem Bus (bits) Price
GeForce 7950 GX2 8x2 24x2 16x2 500x2 600x2 512x2 256x2 $600
GeForce 7900 GTX 8 24 16 650 800 512 256 $450
GeForce 7950 GT 8 24 16 550 700 512 256 $300-$350
GeForce 7900 GT 8 24 16 450 660 256 256 $280
GeForce 7900 GS 7 20 16 450 660 256 256 $200-$250
GeForce 7600 GT 5 12 8 560 700 256 128 $160
GeForce 7600 GS 5 12 8 400 400 256 128 $120
GeForce 7300 GT 4 8 2 350 667 128 128 $100
GeForce 7300 GS 3 4 2 550 400 128 64 $65

ATI Graphics Card Specifications
Vert Pipes Pixel Pipes Raster Pipes Core Clock Mem Clock Mem Size (MB) Mem Bus (bits) Price
Radeon X1950 XTX 8 48 16 650 1000 512 256 $450
Radeon X1900 XTX 8 48 16 650 775 512 256 $375
Radeon X1900 XT 8 48 16 625 725 256/512 256 $280/$350
Radeon X1950 Pro 8 36 12 575 690 256 256 $200-300
Radeon X1900 GT 8 36 12 575 600 256 256 $220
Radeon X1650 XT 8 24 8 575 675 256 128 $150-250
Radeon X1650 Pro 5 12 4 600 700 256 128 $99
Radeon X1600 XT 5 12 4 590 690 256 128 $150
Radeon X1600 Pro 5 12 4 500 400 256 128 $100
Radeon X1300 XT 5 12 4 500 400 256 128 $89
Radeon X1300 Pro 2 4 4 450 250 256 128 $79


With more vertex power and a higher potential fill rate, we can expect the RV560 (the chip behind the X1650 XT) to perform in a more well balanced manner than RV530 (the heart of the X1600 XT). Double the raster pipes not only means better frame rates at higher resolution, but better Antialiasing and Z/stencil performance as well. More stencil and Z power should contribute to higher performance in advanced shadow rendering techniques, and the benefit of higher performance AA on a mainstream part speaks for itself.

Index Test Settings
Comments Locked

33 Comments

View All Comments

  • guidryp - Thursday, November 2, 2006 - link

    They spec like this:

    1650XT: 8 vertex Pipes, 24 pixel pipes, 8 Raster pipes, 575MHz, Mem 675MHz X 128 bus.
    7600GT: 5 vertex Pipes, 12 pixel pipes, 8 Raster pipes 560MHz, Mem 700MHz X 128 bus.

    And the ATI card barely holds it's own? I was expecting a walkaway after reading the specs.
  • coldpower27 - Saturday, November 4, 2006 - link

    It should be 24 Pixel Shaders vs 12 Pixel Shaders.

    while both have 8 ROP's, it is probably the X1650 XT only has 8 TMU while the 7600 GT has 12 as both are half their flagship derivatives. Ignore vertex amounts those tpyically aren't half and don't contribute to much on the most part to performance it seems anyway.

    X1900 XTX 48 Pixel Shaders, 16 Rasterization Operators, 650MHZ, Mem 775MHZ x 256 Bit Bus
    7900 GTX 24 Pixel Shaders, 16 Rasterization Operators, 650MHZ, Mem 800MHZ x 256 Bit Bus

    The X1900 XTX doesn't walkaway from the 7900 GTX on the whole either.
  • trinibwoy - Wednesday, November 1, 2006 - link

    Do you guys do other testing that you comment on that is not represented by the graphs? The numbers show a 1 fps difference, yet you use terms like "significant" and "clearly beats". Maybe some median low fps numbers would help demonstrate what you're saying.

    quote:

    An interesting thing about Oblivion is that it favors ATI hardware over NVIDIA, and this is evident here when we look at the X1650 XT compared with the 7600 GT. In this case, the X1650 XT has a small but significant performance lead over the 7600 GT. Because of this, the X1650 XT is more likely to be playable at 1024x768 than the 7600 GT. This is one case where the X1650 XT clearly beats the 7600 GT just in terms of performance. Oblivion players may want to consider this card once it's available, but only assuming the price is reasonable.
  • soydeedo - Monday, October 30, 2006 - link

    hey i know i can make an educated guess as to where the x1650xt would end up on q4 benches compared to nvidia's offerings, but i'm still curious why this game was not included in the testing? with quakewars around the corner i think people are still interested in doom 3 engine performance.
  • johnsonx - Monday, October 30, 2006 - link

    I suppose this name is part of ATI's general trend lately. It used to be that the XT moniker meant the same GPU with slightly higher clocks. Now it seems like the XT parts are a separate family. The X1300XT has nothing to do with the other X1300's (rather it's a rebadged X1600Pro), the X1900XT has more pipes than non-XT members of the X1900 family, and now the X1650XT has nothing to do with the rest of the X1600/1650 family.

    It all makes it a bit hard to choose.
  • Kougar - Monday, October 30, 2006 - link

    On page 10 it is mentioned that

    quote:

    Something that jumps out at us here is that the X1650 XT got slightly better performance than the 7600 GT in both of these games with 4xAA enabled. Without AA enabled, the 7600 GT did better than the X1650 XT in these games. The amount of difference between the performance of both of these cards is about the same with and without AA.


    This is completely going against the bar graphs, specifically the HL Episode One graph. The x1650XT got up and began walking away from the 7600GT without AA, but with AA it tripped and slide into place just behind the 7600GT. At resolutions below 1600by1200 it even began losing by a sizeable margin.
  • Josh Venning - Monday, October 30, 2006 - link

    This paragraph has been tweaked a little bit. In HL2 Episode one the X1650 XT only does better than the 7600 GT at the highest resolution with AA enabled, but in Battlefield 2 it performs a little better over most of the resolutions.
  • Cybercat - Monday, October 30, 2006 - link

    How many vertex units does this thing have?
  • JarredWalton - Monday, October 30, 2006 - link

    See (updated) table on page 2: it has 8 vertex units, 24 pixel pipes, and 8 ROPs. Basically, lots more power than the X1600 XT. I would guess the pixel pipes are more like R580 pipes (i.e. more shader power, but not necessarily the same as an NVIDIA pixel pipeline in raw power).
  • Cybercat - Monday, October 30, 2006 - link

    Alright, cool. I keep a chart with stats of graphics cards, so I'm just making sure I have the vertice throughput correct. Other than the useless X1650 Pro, ATI seems to have a much more competitive mainstream line now. There is now more confusion than ever, though.

Log in

Don't have an account? Sign up now