Can anyone explain or point to an explanation (or at least to some clues) of how rendering in multi-gpu/multi-monitors setup work?
For example I got 5 NVIDIA Quadro 4000 video cards installed and 9 displays connected to them. The displays are not grouped whatsoever. Just arranged in Windows 7 that the total resolution is 4098x2304. The cards are not connected with SLI either.
I got a Flash app which sees a 4096x2304 window as a single Stage3d context (using dx9) and can work with this quite unusual setup as though it was just a huge display with only one video card.
How does the rendering work internally? What video cards are actually doing? Do they share resources? Who renders all the stuff? Why do I get 29.9 fps doing mostly nothing in the app?
Thank you.
I don't know for DX, but for OpenGL I've collected this information here: http://www.equalizergraphics.com/documentation/parallelOpenGLFAQ.html
In short, on Windows with new nVidia drivers one GPU (typically the first) renders everything and the others get the content blitted. If you enable SLI Mosaic Mode, the GL commands are sent to all GPUs, giving you scalability for the fill rate.
Related
I'm not sure if this is the right place to ask ... please tell me if there are better places for this question.
When writing Direct3d 11 programs, I observed the following problem:
I have two GPUs on my laptop: intel and nvidia (GT640M). Usually the nvidia card is not default (i.e. not the first one enumerated by IDXGIFactory::EnumAdapters).
In that case, I can still creat a D3D11Device using D3D11CreateDevice or D3D11CreateDeviceAndSwapChain, and set the pAdapter to the adapter of the nvidia card. The program runs correctly.
However, when the program terminates, the nvidia card is still doing SOMETHING... I have no idea what it is doing, but it obviously is: the icon is colorful, and the temperature of my laptop raises quickly.
If I set nvidia card as the default for this particular program (which I did in the control panel of nvidia), the problem disappears.
After many experiments, I have drawn the conclusion that the problem occurs if and only if I want to create device with a non-default adapter.
Is this an issue of the nvidia card, or of Direct3D? Is there a solution to it?
I'm trying to port an android/iOS game to windows phone 8(cocos2dx v 2.2). I'm using the exact same code base that I've used for android and iOS. The game functions just fine, but I facing some major FPS drop. The game runs flawlessly at 60FPS in android and iOS, but I'm getting roughly about 35FPS on wp8. Has this got to do anything with differences in OpenGL and directX?
I doubt its got to do with the game's logic and calculations because when the game starts in windows phone, it starts with 60FPS on the main menu, which has got like 5 sprites. But as I add more sprites on the screen, say about 30 of them(average number of sprites when I'm IN the game) the FPS rapidly drops to 35-40 range. Note that there are no schedulers or update functions running at this point. I did the same test on Android, but the FPS didn't drop. Does the win8 port of cocos2dx suck?
Any help,comments or redirection to useful articles would be appreciated.
Thank you.
In case anyone runs into similar issue, I reduced the number of children in the scene and deployed the build in release mode. Gave a major boost to the FPS. Also, I had a bunch of float to string and int to string conversions happening in every frame inside the update function. That was eating away on the processing speed too.
Actually, the Cocos2dx port for WP8 is ok, but outdated. Cocos2d-x is now at 3.0 beta, but the WP8 was left at 2.0 alpha.
Anyway... in Cocos there are some recursive drawing functions which are very heavy on the CPU, and also, keep in mind that even though WP8 is supposed tu support arrays, lists, maps etc. they are very slow on WP8.
And since you came to this subject, Please let me know if you managed to successfully put cocos2d-x on an XAML+D3D Interop project. I am getting tons of crashes.
EDIT: Indeed, the recursive calls which process (draw or update) child "CCNode"s are very heavy on the device. However, after putting Cocos2d-x ver. 2.0alpha for WP8 into a XAML+D3D interop project, I found a whole lot of memory related issues. Apparently, after doing this (or just because I don't know how to properly configure my VS project and allow loose addressing), a lot of uninitialized pointers and data cause some memory overlaps, leading to major crashes.
This proves only that it was truely an alpha release :) Too bad no newer version of Cocos2d-x for Wp8 is available.
Currently I am using the DTWGestureRecognizer open source tool for Kinect SDK v1.5. I have recorded a few gestures and use them to navigate through Windows 7. I also have implemented voice control for simple things such as opening PowerPoint, Chrome, etc.
My main issue is that the application uses quite a bit of my CPU power which causes it to become slow. During gestures and voice commands, the CPU usage sometimes spikes to 80-90%, which causes the application to be unresponsive for a few seconds. I am running it on a 64 bit Windows 7 machine with an i5 processor and 8 GB of RAM. I was wondering if anyone with any experience using this tool or Kinect in general has made it more efficient and less performance hogging.
Right now I removed sections which display the RGB video and the Depth video but even doing that did not make a big impact. Any help is appreciated, thanks!
Some of the factors I can think of are
Reduce the resolution.
Reduce the frames being recorded/processed by the application using polling model i.e. OpenNextFrame(int millisecondsWait) method of DepthStream, ColorStream & SkeletonStream
instead of event model.
Tracking mode is Default instead of Seated(sensor.SkeletonStream.TrackingMode =
SkeletonTrackingMode.Default) as seated consumes more resources.
Use sensor.MapDepthFrameToColorFrame instead of calling sensor.MapDepthToColorImagePoint method in a loop.
Last and most imp. is the algorithm used in the open source tool.
I've a question regarding IOSurface on Cocoa.
After an extensive research required to switch my OPENGL realtime application to 64 bit, I've taken the only path to support Quicktime playback spawning a background thread that pulls the frames installing a frame-ready callback and then with QTVisualContextCopyImageForTime , and pass the IOSurfaceRef through RPC to the parent process.
Everything works fine but there's one main issue. In my 32 bit application I was able to serialize any call to the GL subsystem by rendering a frame, pull the QT frames for the next pass and then wait for the next V-sync. This produced a very smooth and stable result.
Using the IOSurface technique gives me no way to synchronize when my app draws a frame and when the background process pulls the IOSurface from the quicktime movie. The result is that, on a random basis, I experience performances SPYKES. Indeed using the OPENGL driver monitor raises the CPU WAIT cycles up to 10% in my 64 bit app, while I have 0% CPU Wait graph under 32 bit.
Anyone here used IOSurface in a real world application and faced issues like this one ? I've though about an interprocess mutex/lock , but considering I need to lock/unlock about 120 times x second, I was not able to find a valid solution, it doesn't seems that darwin has something like the NAMED SIGNALS available in Win32...
Any suggestion, or I should take a totally different approach to the problem ?
Thanks !
I'm using the Windows Media Player OCX in a program runned on hundreds of computers (dedicated).
I have found out that when video acceleration is turned on to "full", on some computers it will cause the video to fail to play correct, with green squares between movies and so on. Turn the acceleration to "None" and everything is fine.
This program is runned on ~800 computers that will autoupdate my program. So I want to add to the startup to my program that it turns off the video acceleration.
The question is, how do I turn off video Acceleration programmatically?
All computers are running XP and at least the second service pack.
It would take me ages to manually logg in to all those computers and change that setting so thats why I want the program to be able to do it automagically for me.
Using the suggested process of running procmon, and filtering out unnecessary data, I was able to determine the changes in the registry when this value changed:
Full Video Acceleration:
[HKEY_CURRENT_USER\Software\Microsoft\MediaPlayer\Preferences\VideoSettings]
"PerformanceSettings"=dword:00000002
"UseVMR"=dword:00000001
"UseVMROverlay"=dword:00000001
"UseRGB"=dword:00000001
"UseYUV"=dword:00000001
"UseFullScrMS"=dword:00000000
"DontUseFrameInterpolation"=dword:00000000
"DVDUseVMR"=dword:00000001
"DVDUseVMROverlay"=dword:00000001
"DVDUseVMRFSMS"=dword:00000001
"DVDUseSWDecoder"=dword:00000001
No Video Acceleration:
[HKEY_CURRENT_USER\Software\Microsoft\MediaPlayer\Preferences\VideoSettings]
"PerformanceSettings"=dword:00000000
"UseVMR"=dword:00000000
"UseVMROverlay"=dword:00000000
"UseRGB"=dword:00000000
"UseYUV"=dword:00000000
"UseFullScrMS"=dword:00000001
"DontUseFrameInterpolation"=dword:00000001
"DVDUseVMR"=dword:00000000
"DVDUseVMROverlay"=dword:00000000
"DVDUseVMRFSMS"=dword:00000000
"DVDUseSWDecoder"=dword:00000000
So, in short, set
PerformanceSettings
UseVMR
UseVMROverlay
UserRGB
UseYUV
DVDUseVMR
DVDUseVMROverlay
DVDUseVMRFSMS
DVDUseSWDecoder
to 0, and set
UseFullScrMS
DontUseFrameInterpolation
to 1.
It seems you're not the only one with this problem. Here's a link to a blog - the author solves his problem by lowering the hardware acceleration level. Tested on Media Player 9, 10 and 11 with REG script to set appropriate settings.
http://thebackroomtech.com/2009/04/15/global-fix-windows-media-player-audio-works-video-does-not/
As well as applying this fix, you might check the affected machines have the latest drivers and codec versions. Finally, if possible, you may consider re-coding the content to a format that doesn't produce the display problems (if the bug is codec related.)
Using hardware acceleration is certainly more energy-efficient - according to this Intel report, almost twice as much energy is used without acceleration, and as there are 800 machines, there's reason to seek out a green solution.