Results 1 to 25 of 107

Thread: NVIDIA Announces GeForce GTX 480M Mobile GPU

Threaded View

  1. #11
    I am Xtreme zanzabar's Avatar
    Join Date
    Jul 2007
    Location
    SF bay area, CA
    Posts
    15,871
    Quote Originally Posted by Sam_oslo View Post
    It was actually pretty fast, after all Fermi is just a few months old. Why should we call it "castrated Fermi"? nobody puts a full blown desktop GPU in a notebook. Maybe a flexible and scalable Fermi-architecture is making this possible so fast?
    that dose not show flexibility a new chip would, this shows that it can be castrated, cutting those clusters out dose not help power consumption so its clocked lower and will suck up extra power for no reason.

    Quote Originally Posted by Macadamia View Post
    Hmm, if the way they cut the units are the same...

    0.7x core clock
    ~0.75x memory clock

    So you get 0.8x (max) perf of a GTX 465, which itself like a GTX 285/275 or so...
    GTX260 performance or so?

    It will definitely be the fastest mobile GPU, no thanks to the anemic 128-bit memory interface of Juniper (you can't really clock RAM fast on notebooks). But the gap should be less than expected- about 15-20% more performance? For double the TDP...


    I'm still seeing HP's Envy 15 (if it didn't have that many problems)/17 as the perfect notebook blend for the majority of gamers (who really game)- definitely enough graphics performance, without the heft or uglyness associated with a gaming notebook. These are just gonna sell way more than any Alienware/Clevo, so nVidia really needs a 20-40W lineup on Fermi soon, and hopefully GF104 is (part) of the answer.

    But really, congrats to nVidia on making a 530mm2 chip fit with 100W cooling on a design, and actually selling it! ATI would have a hard time doing that for several reasons.
    there is no chance of this beating the 5870m, the clock speed is to low and that low clock speed will make its texture processing way to slow like close to a mobile g92 but with more geometry like what a 260 original would have. there is no chance that it will compete with the 5870m. the 5870m is close to the 5770 so since the desktop 465 is slower than the desktop 5850 and the desktop 5770 isnt to far behind so with this massive clock down i would expect it to be bottleneck its self in the texture fill rate.

    i will agree that its an accomplishment to get it sub 100W but i would expect that for the gpu not the platform.

    we really need that new fermi die to bring the prices down, it should even match the stupidly giant die in performance with normal power and normal cooling
    Last edited by zanzabar; 05-25-2010 at 01:04 PM.
    5930k, R5E, samsung 8GBx4 d-die, vega 56, wd gold 8TB, wd 4TB red, 2TB raid1 wd blue 5400
    samsung 840 evo 500GB, HP EX 1TB NVME , CM690II, swiftech h220, corsair 750hxi

Bookmarks

Bookmarks

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •