Miscellaneous Benefits and Closing Thoughts

Overall, we've seen a dramatic boost in core counts across the entire mobile family. What we haven't seen is much in the way of bandwidth improvements. How this will affect actually gaming remains to be seen, but NVIDIA is claiming average performance increases of around 40% compared to the older 300M series. We heard 30% faster performance with 480M versus 285M when that part launched in May, and we didn't quite get that in all games, but newer titles did tend to benefit more than older games.

There are other benefits that NVIDIA is touting with the new GPUs, some new but mostly this is stuff we've seen before. Front and center is Optimus Technology, with six of the seven major OEMs now shipping (or preparing to ship) Optimus enabled laptops. If we want to name names, Acer, ASUS, Dell, Lenovo, Samsung, and Toshiba have or will shortly have Optimus laptops; we'll let you fill in the missing blank. While there will always be a market for discrete-only laptops, the switching technology makes a lot of sense for midrange GPUs. Obviously you need a CPU with an IGP, which means no one is likely to do a high-end Optimus notebook just yet, but once Sandy Bridge launches the situation could (re: should) change. While Fermi was a power hungry beast, this is less of a concern on midrange and lower laptops. They'll need to be able to cool the GPUs when gaming, but at least on battery power you won't have to worry about the GPU sucking down watts.

NVIDIA is also touting the benefits of their CUDA GPUs again, which is hardly surprising. With more users doing HD video clips (i.e. with the latest smart phones), a way to quickly convert those videos into online friendly formats is certainly useful. Badaboom isn't going to win an award for the highest quality encodes, but if you're uploading to YouTube (where your video gets re-encoded anyway) it gets the job done. Needless to say, all of these new 400M GPUs should tear through such encodes much faster than even desktop CPUs. Retouching photos in Photoshop CS5 also gets a boost to speed, there's tons of web content moving to GPU acceleration (HTML 5 Video, Flash 10.1, WebGL, and Scalable Vector Graphics for example), and Internet Explorer 9 along with Firefox 4 and Chrome 7 will all have GPU acceleration. Intel's HD Graphics and upcoming Sandy Bridge IGP may struggle in comparison with a few of those areas, but we'll withhold judgment until we get hardware for testing.

And of course, there's the games. The slowest of the slow 400M GPUs should still pack quite a wallop when it comes to gaming. With three times as many cores as G 310M and twice the memory bandwidth, we expect at least double the performance out of the GT 415M. Wondering what that means? Well, 310M is already about three times faster than Intel's HD Graphics and typically more than twice as fast as AMD's HD 4200 IGP. In fact, it's only slightly slower than HD 5470, so if we get twice that level of performance with the bottom-of-the-barrel discrete GPU from NVIDIA all we can say is… it's about time! Of course, our Sandy Bridge preview indicates that Intel may roughly match G 310M performance with their next IGP, so Optimus or no users will want more from discrete GPUs.

Wrapping things up, we have the other NVIDIA features like 3D Vision (GT 425M or higher required for gaming, because of the 60FPS target to render two separate views), and the new 3D notebooks will also support 3DTV Play. And if you've wondered about the utility of 3D Vision on notebooks—after all, who wants to carry around the extra USB shutter transmitter?—the new line of 3D Vision enabled laptops will be integrating the emitter into the display bezel.

One last win for NVIDIA comes from ASUS, who will be building an all-in-one 3D Vision PC with the GTX 460M driving the graphics. Like the new 400M notebooks, the 3D emitter is integrated in the display bezel, providing for less wire clutter. We don't have any other details on the ASUS ET2400XVT other than availability is scheduled for some time in the next month or two; hopefully we can get one to test drive and let you know how it works in the near future.

All told, the 400M lineup is looking pretty good right about now. AMD got there first with top to bottom DX11 mobile parts, but performance wasn't substantially higher in many cases than their previous 4000 series. DX11 was a big selling point though, and judging by the number of HD 5000 laptop design wins consumers like the feature. Now NVIDIA can strike back with not just DX11, but very likely higher performance and features like CUDA, PhysX, and Optimus. If you've been holding off buying a new laptop, this fall may finally have the new designs to tempt you into upgrading. Unfortunately, that makes the last few pre-400M laptops we have in hand for review just a little less compelling, but hopefully those who don't need DX11 will be able to find some great deals on the current "outdated" crop as a consolation prize. Have I mentioned how much I like competition?

Performance and Mainstream 400M
Comments Locked

39 Comments

View All Comments

  • Roland00 - Friday, September 3, 2010 - link

    The reason I ask is for this is the most popular "mainstream" gaming card in current designs of laptops right now. Yes the GTX 480m may be the fastest but if nobody uses it besides select Alienwares and Clevos what does it matter?
  • JarredWalton - Friday, September 3, 2010 - link

    The GT 335M is roughly at the same performance level as HD 5650, but obviously without DX11 support. Based on that, I would venture that even 420M might match the 5650; certainly 425M and up will be faster (unless you're bandwidth limited, which is entirely possible).
  • marraco - Friday, September 3, 2010 - link

    The CPU integrated video of Intel will rule out all the "entry level" discrete chips.

    Nvidia and AMD will be forced to offer more juicy entry level cards.

    I guess that the next generation of entry level will have at least geforce 8600 power.
  • JarredWalton - Friday, September 3, 2010 - link

    Our initial look suggest that the 12 EU version of the Sandy Bridge IGP will be at roughly the level of the G 310M. In other words, even the GT 415M looks to be around twice as fast, plus you get CUDA, OpenCL, DirectCompute, OpenGL 4.0, DX11, PhysX, etc. I'd say Sandy Bridge will make a direct replacement for G 310M (i.e. "G 410M") pointless, so perhaps that's why there's no castrated 24 core 400M chip with a 64-bit interface.
  • tviceman - Friday, September 3, 2010 - link

    Looks like a solid lineup from everything below the gtx480m. Hopefully like others have suggested they updated the 480m to be a little more powerful at the same TDP or offer the same performance at a lower TDP.

    I'm personally still waiting on any word or significant rumors regarding a a full 384 core GF104 desktop part.
  • blah238 - Friday, September 3, 2010 - link

    Most interested in the 12-14" size range with the fastest possible GPU and decent screen options. The Sony Vaio Z is the only machine that fits the bill currently but it's way out of my price range.

    Here's hoping something from this refresh gets stuck into a chassis that gives Sony some competition in this space.
  • patrickjchase - Saturday, September 4, 2010 - link

    Jarred makes reference to the fact that the GF1xx series strike a different balance between compute (shader) and memory bandwidths. I think that part of NVIDIA's motivation is indeed an expectation that future games will skew towards requiring more shader performance, but I think there's another factor: Fermi has an L1 data cache in each SM.

    I do OpenCL and CUDA programming professionally, and I think that it's important not to underestimate the impact of cache. Many algorithms in graphics and elsewhere have access patterns that are best described as "localized but unpredictable". This means that the algorithm's data accesses tend to "cluster" spatially and/or temporally, but it's very difficult to predict *where* they'll cluster and it's therefore impractical to explicitly pre-load data into local memory.When running such algorithms Fermi needs less DRAM bandwidth for any given performance level than any other GPU on the market (and again, I say this as somebody who develops for and benchmarks these things day in and day out).

    This is actually a bit of a repeat of how general-purpose CPUs and their associated memory systems progressed, beginning with the IBM 360/85 all the way back in 1969...
  • JackNSally - Monday, September 6, 2010 - link

    "OpenGL 40." in the supported features. I believe you mean "OpenGL 4.0" unless nVidia is jumping far, FAR into the future.
  • JarredWalton - Monday, September 6, 2010 - link

    The Alienware M15x has already done 1080p in a 15.4" chassis I think, and there are several other 1080p ~15" laptops around. ASUS G51JX-X1, ThinkPad W510, and MSI's GX660R-060US are all 15.6" 1080p. But then, they're also non-3D and cost $1300 minimum.

Log in

Don't have an account? Sign up now