NVIDIA – GeForce FX Go5600 and GeForce FX Go5650

For high-end mobile systems, NVIDIA brings the GeForce FX Go5600 (NV31M), which is appropriately based on the GeForce FX 5600 (NV31), the specs of which can be found here. The specification of the Go version compared to its desktop big brother is virtually the same. As we cited in our preview, it is produced on a 0.13 micron process, is a full DX9 part, shares a number of similarities with the NV30, and consumes 1.0V while running.

The original GeForce FX 5600 Ultra graphics processor, which includes the Go part, are supposed to be clocked at 350MHz core clock and 350MHz memory clock (700MHz effective). However, we have only been aware of original GeForce FX Go5600 shipping at the highest of 270MHz core clock and 300MHz memory clock. The reason why we use the term “original” is because the GeForce FX Go5600 has undergone a refresh. Like the GeForce FX 5600 Ultra, the Go part has two versions now. One is the GeForce FX Go5600 and the other, the GeForce FX Go5650. The first of the two is based on the wire bond design, and the second is the flip-chip. The flip-chip design allows the GeForce FX Go5650 to hit higher frequencies when compared to its predecessor. The flip-chip version of the desktop GeForce FX 5600 Ultra is clocked at 400MHz core and 400MHz memory (800MHz effective). As of late, we have only seen a shipping version of the GeForce FX Go5650 clocked at 325MHz core clock and 295MHz memory clock. So basically, there are two versions of the desktop NV31 and the NV31M. Though, the desktop version doesn’t have a new name incantation like the mobile line. NVIDIA has informed us that they have already started the transition, and we expect to see all future mobile systems (and those announced within a few weeks) to hit the shelves with the new flip-chip version of NV31M.

In the GeForce FX Go5200 and GeForce FX Go5600 preview, we mentioned the support for component output and a MPEG2 decode assist engine. However, we still have yet to test these two features, and will report back once we do, accordingly. For a more detailed look into GeForce FX Go5200 and GeForce FX Go5650, read our original preview.

ATI - Mobility Radeon 9600 The Test


View All Comments

  • Anonymous User - Thursday, October 23, 2003 - link

    The Mobility Radeon 9600 with 128MB is available from Compaq/HP.

    MR9600 Pro:

    Mobility FireGL T2:

    So go get yourself one today! Coz I am!

  • Anonymous User - Thursday, October 9, 2003 - link

    There are some people around that are developers. I personally use OpenGL for all my CG projects and there is no comparison for OpenGL. Traditionally nvidia used to have the upper hand in OpenGL (my Golden Sample Ti4200 runs better than Radeon 9700). I'm not favouring nvidia or ati. What I need is something that performs under OpenGL and not DX9...

    Dell inspiron 8600 is a great choice, but it comes with 5650 Go. It is reasonably cheap and extremely powerfull. Easy to get (online) or via a university (my case). Although ATI is faster under DX9, it is not supported by the big names (Dell, Toshiba, Compaq...). So if 5650 is even 80% as fast as 9600 under OpenGL, it IS a choice for me... If it is yet again 400% slower... NO

    Please give us some OpenGL numbers!!!

    Even Quake 3 will do, GLExcess, whatever...



    Norwich, UK
  • Andrew Ku - Monday, September 29, 2003 - link

    #43 Well the different results aren't unexpected. You used a different resolution. :) Reply
  • Anonymous User - Saturday, September 27, 2003 - link

    I'd like to see a couple openGL tests included in the comparison.

  • Anonymous User - Thursday, September 18, 2003 - link

    I get different results!

    I have a Dell Inspiron 8600 with the NVidia 5650 running AquaMark3. I'm using the driver that Dell ships with the 8600 (version I get VASTLY better results on than what's posted in this article. Below, I'm taking my results vs. the article's Radeon numbers:

    Frames per second (FPS)
    My results Results from article
    Chapter Go5650 Go5650 Radeon9600 fps
    1 22.30 11.64 25.97
    2 9.38 4.23 6.68
    3 16.15 8.87 15.00
    4 6.52 5.15 11.27
    5 14.72 9.31 19.93
    6 14.28 8.47 17.96
    7 18.27 9.92 17.08
    8 13.00 6.63 12.56
    9 9.47 4.67 7.93

    I submitted my results to Aquatech's results board under my user name "RonSchaaf" I ran the test multiple times with the same results, running with the Aquatech defaults.

    Big Note: I just double-checked everything and I ran my tests at 1024x768x32, No FSAA, 4x Anisotropy, Maximum Details, with the Driver set to Maximum Quality. But I can't run at 1280x1024 like was done for the article because the Aquatech program won't let me change setting without springing for the "Professional" version.
  • Anonymous User - Wednesday, September 17, 2003 - link

    Nice review.
    It is a good idea you tested the DX9 power of the cards and not some driver or game "optimisations"
  • Anonymous User - Tuesday, September 16, 2003 - link

    #34 Said: "Download 51.75 and run the test. Then tell us what you see. What a bunch of CRAP."

    Your right... with Det 51.75 they'd see a bunch of CRAP. Take a look at these image quality results: http://www.gamersdepot.com/hardware/video_cards/at...

    btw, the accoding to nVidia, the det 51.75 isn't ready to be installed on any machine yet. Kind of funny how that didn't stop them from saying it was the only valid version for benching hl 2...
  • Anonymous User - Tuesday, September 16, 2003 - link

    I agree with shalmanese

  • Anonymous User - Tuesday, September 16, 2003 - link

    I didn't see a mention of the speed of the CPU used.

    Anyone know? (I might have missed it, but it wasn't on the benchmark setup page)

    I know it's a P-M, but at what speed?
  • Shalmanese - Monday, September 15, 2003 - link

    Eh, I thought all in all ,it was a pretty ordinary review, lots of mistakes throughout.

    First of all, your graph numbers are up to 6 significant figures, round them down to even fps or 1 decimal place at the very least.

    While theoretical comparisons laughing at how much the ATI card beat the nVidia card are all very pleasant, some indication for people who may have wanted to BUY these cards, what sort of performance they were in for might be nice as well. This means adding the NV3X and the DX8 codepath figures for HL2 etc. Also, a Go4200 and a Mobility 9000 thrown in might have been good as well but I understand that time may have not been adequate.

    I also noticed that the CPU wasn't listed for the laptop. Is this part of the NDA info? Seems unusual as this is normally given.


    "Mobility Radeon 9600 in North America" should be "THE Mobility..."

    "...between Mobility Radeon 9600..." again, missed a THE ... infact, its all throughout the article.

    " You may have seen other media report benchmark scores that have been called into question. In our time spent benchmarking the two mobile graphics processors, we have yet to be able to recreate a similar scenario."

    huh? you've yet to create a benchmark that has been called into question? What are you trying to say?


    "specifies that the Mobility Radeon 9600 consumes 1.0V while running, and 0.5W in Windows idle." Is that V or W? theres no point telling us what voltage the chip is running at when working. Give us wattage figures.

    pg3: again, you give a V figure.


Log in

Don't have an account? Sign up now