NVIDIA Optimus - Truly Seamless Switchable Graphics and ASUS UL50Vf
by Jarred Walton on February 9, 2010 9:00 AM ESTNVIDIA Optimus Demonstration
So how well does Optimus actually work in practice? Outside of a few edge cases which we will mention in a moment, the experience was awesome. Some technophiles might still prefer manual control, but the vast majority of users will be extremely happy with the Optimus solution. You no longer need to worry about what video mode you're currently using, as the Optimus driver can switch dynamically. Even when you run several applications that can benefit from discrete graphics, we didn't encounter any anomalies. Load up a Flash video and the GPU turns on; load a CUDA application and the GPU stays on, even if you then close the Flash video. It's seamless and it takes the guesswork out of GPU power management.
NVIDIA provided a demonstration video showing second-generation switchable graphics compared to Optimus. We've uploaded the video to our server for your enjoyment. (Please note that QuickTime is required, and the sample video uses the H.264 codec so you'll need a reasonable CPU and/or GPU to view it properly.) At the Optimus Deep Dive, NVIDIA provided two other demonstrations of engineering platforms to show how well Optimus works. Sadly, we couldn't take pictures or record videos, but we can talk about the demonstrations.
The first demonstration was an open testbed notebook motherboard using engineering sample hardware. This definitely wasn't the sort of system you run at home, since there was a notebook LCD connected via a standard notebook power/video cable to the motherboard, exposed hardware, etc. The main purpose was to demonstrate how quickly the GPU turns on/off, as well as the fact that the GPU is really OFF. NVIDIA started by booting up Win7, at which point the mobile GPU is off. A small LED on the GPU board would light up when the GPU was on, and the fans would also spin. After Windows finished loading, NVIDIA fired up a simple app on the IGP and nothing changed. Next they started a 3D app and the GPU LED/fan powered up as the application launched; when they shut down the application, the LED/fan powered back off. At one point, with the GPU powered off, NVIDIA removed the GPU module from the system and disconnected its fan; they again loaded a simple application to demonstrate that the system is still fully functional and running of the IGP. (Had they chosen to launch a 3D application at this point, the system would have obviously crashed.) So yes, the GPU in an Optimus laptop is really powered down completely when it's not needed. Very cool!
The second demonstration wasn't quite as impressive, since no one removed a GPU from a running system. This time, Lenovo provided a technology demonstration for NVIDIA showing power draw while running various tasks. The test system was an engineering sample 17" notebook, and we weren't given other details other than the fact that it had an Arrandale CPU and some form of Optimus GPU. The Lenovo notebook had a custom application showing laptop power draw, updating roughly once per second. After loading Windows 7, the idle power was shown at 17W. NVIDIA launched a 3D app on the IGP and power draw increased to 32W, but rendering performance was quite slow. Then they launched the same 3D app on the dGPU and power use hit 39W, but with much better 3D performance. After closing the application, power draw dropped right back to 17W in a matter of seconds. At present there is no word on if/when this Arrandale-based laptop will ship, but it's a safe bet that if Lenovo can provide sample engineering hardware they're likely to ship Optimus laptops in the future.
The final "demonstration" is going to be more in line with what we like to see. Not only did and NVIDIA show us several running Optimus notebooks/laptops, but they also provided each of the attendees with an ASUS UL50Vf sample for review. The UL50Vf should be available for purchase today, and it sounds like the only reason NVIDIA delayed the Optimus launch until now was so that they could have hardware available for end-user purchase. The final part of our Optimus overview will be a review of the ASUS UL50Vf.
Facebook
Twitter
RSS
49 Comments
View All Comments
jkr06 - Saturday, February 27, 2010 - link
From all the articles I read, one thing is still not clear to me. I have a laptop with core i5(which has IGP) and nvidia 330M. So can I utilize the optimus solution with just SW. Or the laptop manufacturers specifically need to add something to truly make it work.JonnyDough - Friday, February 19, 2010 - link
was a wasted effort. Seems sort of silly to switch between two GPU's when you can just use one powerful one and shut off parts of it.iwodo - Thursday, February 18, 2010 - link
First, the update, they should definitely set up something like Symantec or Panda Cloud Database, where users input are stored and shared and validated worldwide. The amount of games that needs to be profiled is HUGE. Unless there is a certain simple and damn clever way of catching games. Inputting every single games / needed apps running exe names sounds insane to me. There has to be a much better way to handle this.I now hope Intel would play nice, and gets a VERY power efficient iGPU inside SandyBridge to work with Optimus, Instead of botching even more transistors for GPU performance.
secretanchitman - Saturday, February 13, 2010 - link
any chance of this going to the macbook pros? im hoping when they get updated (soon i hope), it will have some form of optimus inside. if not, something radeon based.strikeback03 - Thursday, February 11, 2010 - link
As I don't need a dGPU, I would like to see a CULV laptop with the Turbo33 feature but without any dGPU in order to save money. Maybe with Arrandale.jasperjones - Wednesday, February 10, 2010 - link
Jarred,As you imply, graphics drivers are complex beasts. It doesn't make me happy at all that now Optimus makes them even more complex.
Optimus will likely require more software updates (I don't think it matters whether they are called "driver" or "profile" updates).
That puts you even more at the mercy of the vendor. Even prior to Optimus, it bothered me that NVIDIA's driver support for my 3 1/2 year old Quadro NVS 110m is miserable on Win 7. But, with Optimus, it is even more critical to have up-to-date software/driver support for a good user experience! Furthermore, software solutions are prone to be buggy. For example, did you try to see if Optimus works when you run virtual machines?
Also, I don't like wasting time installing updates. Why can't GPUs just work out of the box like CPUs?
Lastly, these developments are completely contrary to what I believe are necessary steps towards more platform independence. Will NVIDIA ever support Optimus on Linux? While I suspect the answer is yes, I imagine it will take a year and a half at the very least.
obiwantoby - Wednesday, February 10, 2010 - link
I think it is important to note, that the demo video, even though it is a .mov, works in Windows 7's Windows Media Player. It works quite well, even with hardware acceleration.Keep encoding videos in h.264, it works on both platforms in their native players.
No need for Quicktime on Windows, thank goodness.
dubyadubya - Wednesday, February 10, 2010 - link
"Please note that QuickTime is required" FYI Windows 7 will play the mov file just fine so no need for blowtime. Why the hell would anyone use a codec that will not run on XP or Vista without Blowtime is beyond me. For anyone wanting to play mov files on XP or Vista go get Quicktime alternative.beginner99 - Wednesday, February 10, 2010 - link
Did I read that right, HD video is always decoded on the dGPU even if the (Intel) IGP could deal with it?I mean it sounds nice but is there also an option prevent certain apps from using de dGPU?
Or preventing the usage of dGPU completely like when one really needs the longest battery time possible? -> some users like to have control themselves.
intel IGP might offer worse quality with their videao decode feature (but who really sees that on laptop lcd?) but when travelling the whole day and watching movies, I would like to use as little power as possible.
JarredWalton - Wednesday, February 10, 2010 - link
It sounds like this is really just a case of the application needing a "real profile". Since I test x264 playback using MPC-HC, I had to create a custom profile, but I think that MPC-HC detected the GMA 4500MHD and decided that was perfectly acceptable. I couldn't find a way to force decoding of an .mkv x264 video within MPC-HC, but other video playback applications may fare better. I'll check to see what happens with WMP11 as well tomorrow (once I install the appropriate VFW codec).