The Fastest Mobile GPU in the World: NVIDIA's GeForce GTX 480M

We'll cut to the chase: NVIDIA's GeForce GTX 480M does indeed reclaim the crown of fastest mobile GPU from ATI's strangely anemic Mobility Radeon HD 5870. And it ought to: after all, in a break with tradition the GeForce GTX 480M is actually properly named. The GPU core of the GeForce GTX 480M is indeed a Fermi GF100 lovingly crammed into a notebook form factor. NVIDIA cut that same 3.1 billion transistor you've all come to know and love down to a still-egregious 100-watt TDP, the highest of any mobile graphics hardware to date.

While the GeForce GTX 285M was just another rehash of the G92 and ATI's Mobility Radeon HD 5870 is a mobile version of their desktop Radeon HD 5770, NVIDIA's GTX 480M uses the same cut-down—but still Fermi—core found in desktop GeForce GTX 465 cards. That means 352 of NVIDIA's "CUDA cores" and a 256-bit memory bus connected to GDDR5 memory. The difference is that while the GTX 465 only gets 1GB of GDDR5, the GTX 480M gets a full 2GB in our review notebook. Clock speeds aren't as comparable, though, with the 480M's clock speed down from the GTX 465's 607 MHz to just 425 MHz. The shader clocks get cut down, too, dropping from 1.2 GHz to 800 MHz. Probably the most alarming drop is the GDDR5: running at 3.2 GHz on the desktop card, the 480M has its effective speed cut to just 2.4 GHz, the lowest speed we've ever seen on GDDR5 and actually a slower effective clock speed than the GDDR3 on the desktop GeForce GTX 285!

It's not unreasonable to expect cuts had to be made to fit Fermi into a notebook form factor, but given how underwhelming the performance of the desktop GTX 465 that the GTX 480M borrows its hardware from is, one can begin to become genuinely concerned about NVIDIA cutting too deep to get the GTX 480M to fit into its 100-watt TDP. Both ATI's Radeon HD 5830 and NVIDIA's GeForce GTX 465 have proven that it's possible to hit a wall of diminishing returns when harvesting high-end GPU die; both of these cards are barely faster than their substantially smaller predecessors.

Still, it's impressive Fermi made it into a notebook form factor at all. 352 of NVIDIA's CUDA cores are nothing to sneeze at, and a 256-bit memory interface connected to 2.4 GHz GDDR5 still produces a healthy 76.8GB/sec of bandwidth. The GeForce GTX 480M also brings to the table full DirectX 11 support along with all of NVIDIA's usual trimmings: CUDA, PhysX, and 3D Vision. With Eyefinity largely out of the equation in notebooks, the Mobility Radeon HD 5870 can certianly begin to feel feature light compared to NVIDIA's hardware.

So that's all well and good, but how does the GeForce GTX 480M actually fare in practice?

Introducing the Fermi-in-Your-Backpack Synthetic Benchmarks
POST A COMMENT

46 Comments

View All Comments

  • anactoraaron - Thursday, July 8, 2010 - link

    I really don't care one bit anymore about DX9. Please stop putting this in your testing. I doubt anyone else cares about DX9 numbers anymore... I mean why not put in DX8 numbers too???

    And why are DX9 numbers only shown for nVidia products? Are they asking you to do so?
    Reply
  • anactoraaron - Thursday, July 8, 2010 - link

    it downright tears past the competition in Far Cry 2 and DiRT 2- yeah and people want to NOT play those in DX11... <sigh> Reply
  • anactoraaron - Thursday, July 8, 2010 - link

    And you say that in DIRT 2 it holds a 25% lead- yeah when comparing the DX9 numbers of the 480M to the DX11 numbers of the mobility 5870. The real difference is actually .1 fps (look at the W880CU-DX11 line)... yep I'm not reading the rest of this article. Not a very well written article...

    btw sorry bout the double post earlier...
    Reply
  • JarredWalton - Thursday, July 8, 2010 - link

    You're not reading the chart properly. We put DX11 in the appropriate lines and colored then different for a reason. Bright green compares with blue, and dark green compares with purple. The yellow/orange/gold are simply there to show performance at native resolution (with and without DX11).

    In DX9, 480M gets 79.6 vs. 5870 with 59.9. 480M wins by 33%
    In DX11, 480M gets 60.0 vs. 5870 with 48.1. 480M wins by 25%.

    As for including DX9, it's more a case of using something other than DX11 for cards that don't support DX11, as well as a check to see if DX11 helps or hurts performance. DiRT 2 doesn't have a DX10 path, so we drop to DX9 if we don't have DX11 hardware. Another example, in Metro 2033 enabling DX11 results in a MASSIVE performance hit. So much so that on notebooks it's essentially useless unless you run at 1366x768 with a 480M.
    Reply
  • Dustin Sklavos - Thursday, July 8, 2010 - link

    While it's swell that you don't care about DX9 anymore, the fact is that a substantial number of games released today STILL use it. DX10 never really took off, and while DX11 is showing strong signs of adoption moving forward, a large number of games still run in DX9 mode. Reply
  • GTVic - Thursday, July 8, 2010 - link

    Is the author an NVIDIA fanboi? Apparently the 5870M is anemic while the 480M is the "fastest mobile GPU on the planet". Of course the more moderate comments are hidden in the details while "fastest on the planet" is screamed in bold letters.

    Never mind that unless you have an FPS counter on your display you couldn't tell the difference, apparently a few extra FPSs and a name that starts with "N" is all you need to get a glowing review complete with stupendous superlatives.

    Also apparently it is OK to dismiss certain games because they are known to favour ATI hardware. But lets not mention anything about cough, Far Cry, cough.
    Reply
  • JarredWalton - Thursday, July 8, 2010 - link

    I'd love to see what NVIDIA thinks of your comment, because I know they felt Dustin was overly harsh. He's also been accused of being an AMD Fanboi, so apparently he's doing his job properly. ;-)

    The gaming performance is a case of looking at what's required to play a game well, as well as focusing on the big picture. Sure, L4D2 is a Source engine game and favors AMD architectures traditionally. It also happens to run at 62 FPS 1080p with 4xAA (which is faster than the 58 FPS the 5870 manages at the same settings). Mass Effect 2 performance has changed quite a bit between driver versions on 5870, and it isn't as intensive as other games. Just because 5870 leads at 1600x900 in two out of nine titles doesn't mean it's faster. At 1080p the margins generally favor 480M, and with 4xAA enabled they favor it even more.

    Even with that, we go on to state that the 480M doesn't deliver a resounding victory. It's the world's fastest mobile GPU, yes, but it ends up being 10-15% on average which is hardly revolutionary. I said the same thing in the G73Jh review on the 5870, and it got an editor's choice while this doesn't. Seriously, read the conclusion (pages 6 and 7) and tell me that we come off as being pro-NVIDIA and anti-AMD in this review.
    Reply
  • frozentundra123456 - Thursday, July 8, 2010 - link

    I did re-read those parts also. I didn't even notice it myself on the first reading, but I can see how one would see some "ATI bashing" (although I would not use that strong a word), in that the article is about the 480M, but you spend a considerable amount of time criticizing(justifiably) the HD5870M. It just seems that you emphasized the shortcomings of the ATI part in an article primarily about the 480M, while being rather easy on the 480M itself in most sections.
    That said, I dont think you are unfair in general or intentionally, I just think the article was somewhat skewed in that particular section.
    And actually, as you are, I am quite disappointed in both GPUs, but more-so in the 480m in that it is more expensive and power hungry for a rather small performance increase.
    Reply
  • erple2 - Thursday, July 8, 2010 - link

    I disagree. The "bashing" that's done for the 5870M I think sets the tone for how "lame" the 480M ultimately is.

    I found that the bashing of the 5870 really brought to me in perspective just how relatively uninteresting the 480M really is. I mean, if the 5870 was only marginally faster than an "archaic" G92 part, what does that say about NVidia's self-proclaimed ushering in a "revolution" in graphical performance?

    I see it as a giant "thud", much like the GTX465 is alluded to in page 5..
    Reply
  • GTVic - Thursday, July 8, 2010 - link

    As I mentioned, I did see the more moderate comments, what I was trying to get across was that the attention grabbing headline was out of balance with the actual review.

    And if you discount one game for being favoured by ATI then you should probably mention Far Cry being favoured by NVIDIA. Those type of issues are being highlighted again with recent revelations that NVIDIA is hobbling CPU benchmarks of PhysX performance with unoptimized code.

    One additional comment, it is always difficult to compare graphs with long titles for the different configurations, especially when the colors and the order keep changing.
    Reply

Log in

Don't have an account? Sign up now