NVIDIA 400M: DX11 Top to Bottom Solutions Now Available
by Jarred Walton on September 3, 2010 12:02 AM ESTPerformance and Mainstream 400M
After the high-end parts, the drop in performance can become precipitous. This has been particularly bad for AMD GPUs, where the drop from Mobility 5800 series down to the 5700 and 5600 parts often means less than half the performance. NVIDIA has had a few more upper-midrange parts floating around, though, and that looks to continue.
| NVIDIA Performance and Mainstream 400M Specifications | |||||
| GeForce GT 445M | GeForce GT 435M | GeForce GT 425M | GeForce GT 420M | GeForce GT 415M | |
| Codename | GF106 | GF108 | GF108 | GF108 | GF108 |
| CUDA Cores | 144 | 96 | 96 | 96 | 48 |
| Graphics Clock (MHz) | 590 | 650 | 560 | 500 | 500 |
| Processor Clock (MHz) | 1180 | 1300 | 1120 | 1000 | 1000 |
| Memory Clock (MHZ) | 800/1250 | 800 | 800 | 800 | 800 |
| Standard Memory Configuration | DDR3/GDDR5 | DDR3 | DDR3 | DDR3 | DDR3 |
| Memory Interface Width | 128/192-bit | 128-bit | 128-bit | 128-bit | 128-bit |
| Memory Bandwidth (GB/sec) | 25.6/60.0 | 25.6 | 25.6 | 25.6 | 25.6 |
| SLI Ready | No | No | No | No | No |
First, you'll notice that none of these "Performance and Mainstream" parts supports SLI. That's hardly surprising, as SLI with lower-end mobile GPUs has never been our recommended approach. First get to the high-end for performance reasons, and then worry about SLI. Other than that limitation, all of these parts have the same features as the faster parts on the previous page.
The new GT 445M is the first part to come with split specifications. Given the option for 128-bit and 192-bit bus widths, it appears the 445M will use the full GF106 memory controller for the higher bandwidth version and cut off one of the 64-bit interfaces for the low bandwidth model. Many of our gaming results have looked bandwidth limited, so we'd definitely recommend going for the GDDR5 192-bit model if possible, but that will be up to the notebook manufacturers. 445M looks to compete in a similar space as 460M with the higher bandwidth model, but it cuts computational power quite a bit at roughly two-thirds of the 460M. The difficulty here is that 445M can be either substantially faster than some of the older parts, or if you get the 128-bit DDR3 model you're suddenly cut down to less than half the bandwidth. Heavy use of shaders, tessellation, etc. might make the lack of bandwidth less painful, but without hardware and future games it's difficult to say how things will play out.
The 435M is a more straightforward replacement of GT 335M. (Did someone ask for a remake of M11x with a DX11 GPU? Hopefully they can do something about the LCD this time around….) 335M has 72 cores at 1080MHz, with 34.1GB/s of bandwidth. Unless something changes, 435M will actually have less bandwidth but substantially more computational power—60% more to be exact (plus architectural changes, obviously). This is a pattern that holds throughout the 400M lineup, so NVIDIA appears to be betting heavily that shader performance rather than bandwidth will become important.
Along with the 435M come several more GPUs; the 425M and 420M have the same bandwidth and core counts, but lower core/shader clocks. This is similar to the current 325M/330M, which have 48 cores but the same amount of bandwidth as the 335M. Even the lowest 420M has around 25% more compute power than 335M, but they all have less bandwidth. It would have been nice to see a move to GDDR5 on more of the Performance and Mainstream parts, as that would have improved overall performance substantially.
Finally, wrapping up the low end we have the GT 415M. Here we can actually see something to celebrate, since the previous generation parts largely consisted of 16 core models with a 64-bit bus (i.e. the G 310M). On the compute side, we're looking at nearly twice the power of the G 310M. Bandwidth also gets a kick in the pants, going from 12.8GB/s to 25.6GB/s. In short, our entry-level mobile GPUs just doubled their performance. Note also that if NVIDIA wanted to cuts things down even further, they'd need to make yet another chip (i.e. GF110), since 48 cores is a single SM. Most likely, for anything below GT 415M they'll just continue to sell their older 300M parts.
Facebook
Twitter
RSS
39 Comments
View All Comments
LtGoonRush - Friday, September 3, 2010 - link
You know what really grinds my gears? When GPU manufacturers release different parts with the same model number. First the GTX 460 and now the GT 445M, not to mention all the low-end parts from either company that might be either GDDR5 or DDR3, or come in wildly varying clock speeds (I'm not even talking about pre-overclocked cards, sometimes low-end cards especially are just clocked lower than standard). How do manufacturers justify confusing consumers like this?dingetje - Friday, September 3, 2010 - link
they justify it with their huge mansions and fat bank accountsthey think they PWN us
Ushio01 - Friday, September 3, 2010 - link
GF104 8x48, GF106 4x48, GF108 2x48 at least according to most sites making GTX 470M and probably a re-release of GTX480M consisting of a GF104, GTX 460M and GT 445M based on GF106 and the remaining four gpu's based on GF108.JarredWalton - Friday, September 3, 2010 - link
You're correct. I looked at the chip images NVIDIA sent, and 470M is clearly a different chip from 460M; 460M and 445M use the same chip shot (GF106), but apparently there will be a crippled 445M with 64-bits of the memory controller disabled. The remainder all use the same chipshot, presumably GF108, but as others speculate below there's still potential for another G 410M type chip that cuts GF108 down to 24 cores or something silly. Man I hope that doesn't happen....The Crying Man - Friday, September 3, 2010 - link
Any idea when information on AMD's Radeon 6xxx will be available to compare them to nVidia's 400Ms?drfelip - Friday, September 3, 2010 - link
I seriously doubt that. Either Nvidia is going to stay with the 310M series for the low end, or there is a 410M in the works.JarredWalton - Friday, September 3, 2010 - link
Given Sandy Bridge looks to compete with G 310M, would you really want to "upgrade" to a discrete GPU that's only 50% faster than the Sandy Bridge IGP? I *really* hope that NVIDIA doesn't go any lower than the GT 415M; sadly, you're probably right and we'll see some silly "made for OEMs" garbage chip that has 24 cores and a 64-bit memory interface.FXi - Friday, September 3, 2010 - link
Since Nvidia has almost never upgraded the core (referring to the switch possible to a GF104 core for the 480M) and left the model number the same, I highly suspect a refined 485M is coming based on GF104. Nvidia got a lot of roasting for its hot chip. They may keep the power level and offer higher performance (typical) or lower the power, but I suspect they'll want to update the 480M for two reasons:Give it a tiny bit more distance from the 470M
Utilize the cheaper GF104 core from a manufacturing cost standpoint
Get out from under the criticism that the 480M is too power hungry.
We shall see, but I smell a small update to the 480M. It won't really make current 480M owners all that sad because any step up in ability won't be very large. But it will get manufacturing costs in line and may help pricing.
YellowWing - Friday, September 3, 2010 - link
Right now, nVidia parts are off the table for HTPC, because of lack of support for HD audio bitstreams. Was that feature mentioned? If not, will these parts bitstream HD audio, like AMD and Intel do now?andy o - Friday, September 3, 2010 - link
The 460GTX can already bitstream TrueHD and DTS-HD with ffdshow and WinDVD 2010 (with AnyDVD HD for encrypted blu-ray). It seems both the drivers and the players will need to be updated in the case of the other commercial players though, but the card already is capable. It would be pretty stupid if the next GF104 and 106, etc. desktop cards didn't bitstream. The mobile parts will likely also do.