Search Results

Search found 5564 results on 223 pages for 'multi gpu'.

Page 2/223 | < Previous Page | 1 2 3 4 5 6 7 8 9 10 11 12  | Next Page >

  • Overclocked GPU quantum problem

    - by Thrawn
    Hi all, I overclocked my nVidia GPU, and now I get it to be much faster, but after a ~40% overclock, I start getting "mistakes" on the screen, like wrongly coloured pixels, glitches and the sort. Temperature is still within limits, as I added extra coolers. So my question is: is this a permanent problem which is damaging the GPU or is only something related to the intrinsic quantum mistake rate of processing calculations? Thanks for your opinion :-)

    Read the article

  • Reinitialize GPU on RADEON HD 7970 under linux

    - by user1610662
    I have got a RADEON HD 7970 sapphire on Debian Squeeze. Since I often use it with running GPU codes, sometimes the performances highly decrease as I test it with "glxgears" tool (I get only 20 FPS in fullscreen). So I would like to be able to reinitialize the GPU without reboot the system. I know the "clinfo" tool which display the features of the graphics card. Is there a tool which allows to do this reinitialization ?

    Read the article

  • whats the difference between GPU and framegrabber?

    - by user261002
    I am working on a project to monitor if human tissue has been fused with radio frequency during the surgery or not, therefore we are using a very fast camera (1800fps) and also laser illumination on the tissue and a framegrabber (1GB memory). I notice that, instead of a framegrabber, I'm able to use GPU as well, but I am not sure on what's the difference between them? Can any body explain what is the difference between a frame grabber and a GPU?

    Read the article

  • Intro to GPU programming

    - by Adam Davis
    Everyone has this huge massively parallelized supercomputer on their desktop in the form of a graphics card GPU. What is the "hello world" equivalent of the GPU community? What do I do, where do I go, to get started programming the GPU for the major GPU vendors? -Adam

    Read the article

  • Overclocking a nVIDIA GTX 660M GPU?

    - by heron1000
    I have a MSI GE60 0ND laptop with a GTX 660M GPU. When I play games like Minecraft or Portal 2, the core clock is stable at 835 MHz. Recently I tried to overclock it using MSI Afterburner but it wouldn't let me change the voltages or the clock speed no matter what I tried. Various Google searches yielded solutions that all didn't work. Is there any way I can overclock the GPU? Further Info: I have the nVIDIA 310.70 drivers and Windows 8.

    Read the article

  • I want to upgrade my GPU to MSI NVIDIA N630GT-MD4GD3 4 GB DDR3 Graphic card

    - by jatin singh
    Hello every body this is my first post here.. I want to know about my motherboard's PCI express version , my motherboard as I don't have 10 reputation so I am providing image link here http://i.stack.imgur.com/6PWV9.png I have PCI express slot and I want to upgrade it to MSI NVIDIA N630GT-MD4GD3 4 GB DDR3 Graphic card.. this GPU has PCI exp version 2. Here in my city,the shopkeeper said that we have to check if the PCI express of my board is compatible to that GPU but I want to purchase it from flipkart because they sell it for less money (sorry for bad English :/) I mailed to my computers company (Acer) but they didn't reply to any of my mail so my friend told me about Super User.

    Read the article

  • Chipset GPU causes a massive slowdown

    - by zyboxenterprises
    My AMD Radeon HD 7700 recently broke (fan stopped working and GPU overheated), and now I'm running on internal chipset graphics, and it causes a massive slowdown of the whole PC. I've changed the graphics memory from 32MB (minimum) to 256MB (highest), and it hasn't made any difference whatsoever. I'm using Windows Aero, and disabling it should have made a small difference, but it didn't; the whole PC is still slow. I know that it's not the computer build, because I built it myself, and it was a lot faster when it had the AMD Radeon HD 7700 in it, which is the reason why I believe it's the internal chipset graphics that are causing the problem. Is this behavior normal? I don't have the cash right now to go out and buy a new dedicated GPU. I'm using an ASRock N68C-GS FX motherboard with an AMD FX 4100 (overclocked to 4.3GHZ), with 4GB RAM. The overclock was an attempt to resolve this issue, and it isn't related to this issue that the integrated graphics is causing a slowdown.

    Read the article

  • How to resolve CGDirectDisplayID changing issues on newer multi-GPU Apple laptops in Core Foundation

    - by Dave Gallagher
    In Mac OS X, every display gets a unique CGDirectDisplayID number assigned to it. You can use CGGetActiveDisplayList() or [NSScreen screens] to access them, among others. Per Apple's docs: A display ID can persist across processes and system reboot, and typically remains constant as long as certain display parameters do not change. On newer mid-2010 MacBook Pro's, Apple started using auto-switching Intel/nVidia graphics. Laptops have two GPU's, a low-powered Intel, and a high-powered nVidia. Previous dual-GPU laptops (2009 models) didn't have auto-GPU switching, and required the user to make a settings change, logoff, and then logon again to make a GPU switch occur. Even older systems only had one GPU. There's an issue with the mid-2010 models where CGDirectDisplayID's don't remain the same when a display switches from one GPU to the next. For example: Laptop powers on. Built-In LCD Screen is driven by Intel chipset. Display ID: 30002 External Display is plugged in. Built-In LCD Screen switches to nVidia chipset. It's display ID changes: 30004 External Display is driven by nVidia chipset. ...at this point, the Intel chipset is dormant... User unplugs External Display. Built-In LCD Screen switches back to Intel chipset. It's display ID changes back to original: 30002 My question is, how can I match an old display ID to a new display ID when they alter due to a GPU change? Thought about: I've noticed that the display ID only changes by 2, but I don't have enough test Mac's available to determine if this is common to all new MacBook Pro's, or just mine. Kind of a kludge if "just check for display ID's which are +/-2 from one another" works, anyway. Tried: CGDisplayRegisterReconfigurationCallback(), which notifies before-and-after when displays are going to change, has no matching logic. Putting something like this inside a method registered with it doesn't work: // Run before display settings change: CGDirectDisplayID directDisplayID = ...; io_service_t servicePort = CGDisplayIOServicePort(directDisplayID); CFDictionaryRef oldInfoDict = IODisplayCreateInfoDictionary(servicePort, kIODisplayMatchingInfo); // ...display settings change... // Run after display settings change: CGDirectDisplayID directDisplayID = ...; io_service_t servicePort = CGDisplayIOServicePort(directDisplayID); CFDictionaryRef newInfoDict = IODisplayCreateInfoDictionary(servicePort, kIODisplayMatchingInfo); BOOL match = IODisplayMatchDictionaries(oldInfoDict, newInfoDict, 0); if (match) NSLog(@"Displays are a match"); else NSLog(@"Displays are not a match"); What's happening above is I'm caching oldInfoDict before display settings change, letting them change, and then comparing it to newInfoDict by using IODisplayMatchDictionaries(), which will say either "yes, both displays are the same!" or "no, both displays are not the same." Unfortunately, it does not return YES if GPU's have changed for a monitor. Example of the dictionary's it's comparing: // oldInfoDict (Display ID: 30002) oldInfoDict: { DisplayProductID = 40144; DisplayVendorID = 1552; IODisplayLocation = "IOService:/AppleACPIPlatformExpert/PCI0@0/AppleACPIPCI/IGPU@2/AppleIntelFramebuffer/display0/AppleBacklightDisplay"; } // newInfoDict (Display ID: 30004) newInfoDict: { DisplayProductID = 40144; DisplayVendorID = 1552; IODisplayLocation = "IOService:/AppleACPIPlatformExpert/PCI0@0/AppleACPIPCI/P0P2@1/IOPCI2PCIBridge/GFX0@0/NVDA,Display-A@0/NVDA/display0/AppleBacklightDisplay"; } As you can see, the IODisplayLocation key changes when GPU's are switched, hence IODisplayMatchDictionaries() doesn't work. I can, theoretically, compared just the DisplayProductID and DisplayVendorID keys, but I'm writing end-user software, and am worried of a situation where users have two or more identical monitors plugged in. Any help is greatly appreciated! :)

    Read the article

  • Port scientific software to GPU and publish it

    - by Werner
    Hi, let's say that I am a physicist and that I am the master of the universe when it comes to port salready existing oftware to GPU's with 100x or more speedups. Let's say that I find that some other scientist, which does not know how to program GPU, publishes the Open Source code in his/her website of a physical simulation program, in the field I am expert on. Let's say that I realize "I can port that code to GPU", and I suggest him, but he shows no interest. My interest here is, 1) to port it to GPU, 2) to publish this result in a scientific journal related with physics and/or computer science My question for you is 1- would you proceed here to port the code to GPU (or other new arch) and publish it? 2- how would you do it and which journal do you suggest? Thanks

    Read the article

  • ATI gpu (video accel, decode, encode, ATI Stream, DXVA)

    - by Shiki
    Okay its a long question title for sure. I'm looking for a new video card (yes,SU is not a page for that, but wait). I've been a loyal NVidia customer ever since, now using a 8600gts. Old but still somewhat good, its a bit slow though. I want an upgrade because 8600gts wont support better vdpau and new features. I checked out the prices and the documents, I would need a GTX260 card. Which costs ..well.. a lot. ATI performs much better for that price. (At least on every test it outperforms GTX260). However, as far as I know there is no gpu accel with ATI. The things you can use is DXVA only, no other method. Could you correct me out there? Will be there a gpu accel for ATI also? Or is there one available? (DXVA is not bad, but kinda slow compared to NVIdia's CUDA.) What about openCL? How does ATI support that? (I'm talking about the 5850 ATI card at the minute, I would buy that instead of the NVidia.)

    Read the article

  • How to stop switchable graphics from switching to high-power GPU when charging the laptop?

    - by Saifallah
    I've an Acer laptop with Windows 7 64 bit and an ATI Radeon HD 6550M Graphics card. Whenever I connect the power to charge the battery it automatically switches to the high-power GPU (ATI) instead of the low-power (Intel) GPU. There's an option in the bios to stop such thing but it makes the GPU runs always on high-power and I can't switch to the low-power GPU. How can I prevent the switchable graphics from automatically using the high-power GPU when charging?

    Read the article

  • Playing HD video accelerated by GPU? (Linux)

    - by data_jepp
    I know that this laptop (Asus UL30A) does support playing HD material with the help of the GPU on windows. The question is how can I do this under linux? The CPU load as is implies that this is not activated. I assume that it's limited to a handful of codecs. But which player supports this, if its even supported at all?

    Read the article

  • System won't boot: Gigabyte HD 7790 1GB OC GPU issue or Corsair VS550 PSU issue?

    - by MGOwen
    Installed a new GPU, and PC won't boot. Turn it on and: No monitor signal at all (tried HDMI and VGA via DVI, on 2 working monitors). CPU and GPU fans DO spin, but No system beeps, no sounds from drives (they might make a small noise in the first 1 second or so, but there's definitely no OS loading or anything like that) If hit "power off" button it turns off immediately (no holding down for 3 seconds like usual) If I put my old HD 5670 GPU back in, everything works fine. But (plot twist!) card is not totally dead. My friend put it in his PC, and it works fine (he even played a game for 15 minutes, no issues). He has a Corsair TX850 850W and a Gigabyte MB. So my main theory is: the GPU isn't getting enough power from the PSU. But is it: Bad PSU? Seems unlikely, since it works fine with the other GPU. Also, the PSU Is brand new and 550W (single 42A/504W 12V rail). Overkill for this GPU. Corsair is a decent brand, but maybe just mine is faulty? Bad GPU? Could it be drawing more power than it should be, somehow, or something? Supposedly HD 7790 needs only 21A/75W on the 12v rail, though this one is factory overclocked a bit... but should that triple the power requirement? Something else? Could there be a motherboard incompatibility somehow? Both MB and GPU are less than a year old and PCI Express 3.0 x16. Things I've tried: Re-seating the video card Testing PC with old GPU (works fine, same PCIe slot). Checked AMD's stated amp/watt requirements of a 7790 and my PSU (see above). My PSU can output twice the amps (single rail) and 5x the Wattage a 7790 needs. Here are the full specs: Gigabyte HD 7790 1GB OC GPU Corsair VS550 550W PSU 4GB RAM AsRock H61M U3S3 motherboard i3-2100 500GB SATA HDD (2007-ish) blu-ray drive (new) PCI 802.11g card Edit: Motherboard BIOS Update seems to have fixed it. (If anyone has same problem and it doesn't work, comment here).

    Read the article

  • GPU Debugging with VS 11

    - by Daniel Moth
    With VS 11 Developer Preview we have invested tremendously in parallel debugging for both CPU (managed and native) and GPU debugging. I'll be doing a whole bunch of blog posts on those topics, and in this post I just wanted to get people started with GPU debugging, i.e. with debugging C++ AMP code. First I invite you to watch 6 minutes of a glimpse of the C++ AMP debugging experience though this video (ffw to minute 51:54, up until minute 59:16). Don't read the rest of this post, just go watch that video, ideally download the High Quality WMV. Summary GPU debugging essentially means debugging the lambda that you pass to the parallel_for_each call (plus any functions you call from the lambda, of course). CPU debugging means debugging all the code above and below the parallel_for_each call, i.e. all the code except the restrict(direct3d) lambda and the functions that it calls. With VS 11 you have to choose what debugger you want to use for a particular debugging session, CPU or GPU. So you can place breakpoints all over your code, then choose what debugger you want (CPU or GPU), and you'll only be able to hit breakpoints for the code type that the debugger engine understands – the remaining breakpoints will appear as unbound. If you want to hit the unbound breakpoints, you'd have to stop debugging, and start again with the other debugger. Sorry. We suck. We know. But once you are past that limitation, I think you'll find the experience truly rewarding – seriously! Switching debugger engines With the Developer Preview bits, one way to switch the debugger engine is through the project properties – see the screenshots that follow. This one is showing the CPU option selected, which is basically the default that you are all familiar with: This screenshot is showing the GPU option selected, by changing the debugger launcher (notice that this applies for both the local and remote case): You actually do not have to open the project properties just for switching the debugger engine, you can switch the selection from the toolbar in VS 11 Developer Preview too – see following screenshot (the effect is the same as if you opened the project properties and switched there) Breakpoint behavior Here are two screenshots, one showing a debugging session for CPU and the other a debugging session for GPU (notice the unbound breakpoints in each case) …and here is the GPU case (where we cannot bind the CPU breakpoints but can the GPU breakpoint, which is actually hit) Give C++ AMP debugging a try So to debug your C++ AMP code, pull down the drop down under the 'play' button to select the 'GPU C++ Direct3D Compute Debugger' menu option, then hit F5 (or the 'play' button itself). Then you can explore debugging by exploring the menus under the Debug and under the Debug->Windows menus. One way to do that exploration is through the C++ AMP debugging walkthrough on MSDN. Another way to explore the C++ AMP debugging experience, you can use the moth.cpp code file, which is what I used in my BUILD session debugger demo. Note that for my demo I was using the latest internal VS11 bits, so your experience with the Developer Preview bits won't be identical to what you saw me demonstrate, but it shouldn't be far off. Stay tuned for a lot more content on the parallel debugger in VS 11, both CPU and GPU, both managed and native. Comments about this post by Daniel Moth welcome at the original blog.

    Read the article

  • Why aren't we programming on the GPU???

    - by Chris
    So I finally took the time to learn CUDA and get it installed and configured on my computer and I have to say, I'm quite impressed! Here's how it does rendering the Mandelbrot set at 1280 x 678 pixels on my home PC with a Q6600 and a GeForce 8800GTS (max of 1000 iterations): Maxing out all 4 CPU cores with OpenMP: 2.23 fps Running the same algorithm on my GPU: 104.7 fps And here's how fast I got it to render the whole set at 8192 x 8192 with a max of 1000 iterations: Serial implemetation on my home PC: 81.2 seconds All 4 CPU cores on my home PC (OpenMP): 24.5 seconds 32 processors on my school's super computer (MPI with master-worker): 1.92 seconds My home GPU (CUDA): 0.310 seconds 4 GPUs on my school's super computer (CUDA with static domain decomposition): 0.0547 seconds So here's my question - if we can get such huge speedups by programming the GPU instead of the CPU, why is nobody doing it??? I can think of so many things we could speed up like this, and yet I don't know of many commercial apps that are actually doing it. Also, what kinds of other speedups have you seen by offloading your computations to the GPU?

    Read the article

  • Next programming paradigm for CBE/GPU in the next years

    - by Werner
    Hi, in the last five years, there has been a rise in the use of GPU and CBE for parallelization of applications. Around 2005-2007 verything seemed to be programmed by hand, C, etc. Afterwards new unifying alternatives emerged like CUDA for GPU and lastly OpenCL. What do you think will be the programming paradigm for GPU/CBE in the forthcoming years? My vote goes for OpenCL Thanks

    Read the article

  • Snapshot/Save GPU Drivers

    - by ashes999
    Since I'm running XP/32-bit, my GPU drivers are quite fragile. I've spent several hours trying to back up and restore from old versions, on at least two separate occasions. Writing down the device drivers is not enough. In the short term, I would like to somehow save, zip, backup, snapshot, or something so that if I need to reinstall my OS in the short-term, I have a reliable way to get the drivers. ATI's website doesn't have the install kit anymore, and I don't have it saved; I googled, but didn't find the exact same version. How can I backup/save my drivers so that I can reinstall them later?

    Read the article

  • Structuring multi-threaded programs

    - by davidk01
    Are there any canonical sources for learning how to structure multi-threaded programs? Even with all the concurrency utility classes that Java provides I'm having a hard time properly structuring multi-threaded programs. Whenever threads are involved my code becomes very brittle, any little change can potentially break the program because the code that jumps back and forth between the threads tends to be very convoluted.

    Read the article

  • Multi-touch mouse gestures in Ubuntu 13.10?

    - by Alex Li
    I have Ubuntu 13.10 and Windows 8 installed as dual boot. There is a mousepad specific driver in Windows 8 that lets me use multi-touch gestures such as two finger swipe to go back/forward, pinch to zoom in/out, and pivot rotate. The driver/touchpad is made by Alps. But on Ubuntu 13.10 there is no multi-touch support like those I can use on Windows. How can I get the same mouse gestures on Windows to work on Ubuntu 13.10?

    Read the article

  • Dual monitor in Ubuntu 12.04 + Nvidia GPU with CUDA drivers?

    - by Aphex
    I'm thinking about setting up dual monitors on my desktop PC, running Ubuntu 12.04 with a Nvidia GTX 570. I use the GPU for CUDA programming so it's set up with the CUDA drivers. Is it possible/easy to set up dual monitors with this configuration? The only questions I saw related to this were for GPUs without cuda drivers. If anyone knows how dual monitors work with CUDA drivers, it would be much appreciated. It was enough of a pain getting everything running with the GPU and CUDA in the first place, I'd hate to ruin it all by attempting dual monitors.

    Read the article

  • Is there a simple, safe way to trigger a GPU lockup on a susceptible computer?

    - by Abe
    Answers to my previous question, Ubuntu 12.04 froze, requiring powercycle. What should I look / grep for in the logs?, have led me to suspect that my computer is experiencing an intermittent GPU lockup. It has been happening about once a week, usually when I am using Chrome. Today it happened when I was creating a diagram on lucidchart I have a Dell Optiplex 755 with an ATI Radeon HD 2400 XT and dual monitors running in Xinerama mode. I am using 12.04 with the proprietary ATI driver installed. When the computer locks-up, I can still ssh in. And I would like to follow the instructions on reporting this provided at https://wiki.ubuntu.com/X/Troubleshooting/Freeze Is there a (safe) way to cause a GPU lockup so that I can go ahead and file a bug, rather than waiting until it happens again?

    Read the article

  • What OpenGL functions are not GPU accelerated?

    - by Xavier Ho
    I was shocked when I read this (from the OpenGL wiki): glTranslate, glRotate, glScale Are these hardware accelerated? No, there are no known GPUs that execute this. The driver computes the matrix on the CPU and uploads it to the GPU. All the other matrix operations are done on the CPU as well : glPushMatrix, glPopMatrix, glLoadIdentity, glFrustum, glOrtho. This is the reason why these functions are considered deprecated in GL 3.0. You should have your own math library, build your own matrix, upload your matrix to the shader. For a very, very long time I thought most of the OpenGL functions use the GPU to do computation. I'm not sure if this is a common misconception, but after a while of thinking, this makes sense. Old OpenGL functions (2.x and older) are really not suitable for real-world applications, due to too many state switches. This makes me realise that, possibly, many OpenGL functions do not use the GPU at all. So, the question is: Which OpenGL function calls don't use the GPU? I believe knowing the answer to the above question would help me become a better programmer with OpenGL. Please do share some of your insights.

    Read the article

  • Which OpenGL functions are not GPU-accelerated?

    - by Xavier Ho
    I was shocked when I read this (from the OpenGL wiki): glTranslate, glRotate, glScale Are these hardware accelerated? No, there are no known GPUs that execute this. The driver computes the matrix on the CPU and uploads it to the GPU. All the other matrix operations are done on the CPU as well : glPushMatrix, glPopMatrix, glLoadIdentity, glFrustum, glOrtho. This is the reason why these functions are considered deprecated in GL 3.0. You should have your own math library, build your own matrix, upload your matrix to the shader. For a very, very long time I thought most of the OpenGL functions use the GPU to do computation. I'm not sure if this is a common misconception, but after a while of thinking, this makes sense. Old OpenGL functions (2.x and older) are really not suitable for real-world applications, due to too many state switches. This makes me realise that, possibly, many OpenGL functions do not use the GPU at all. So, the question is: Which OpenGL function calls don't use the GPU? I believe knowing the answer to the above question would help me become a better programmer with OpenGL. Please do share some of your insights.

    Read the article

  • Safari Mobile Multi-Line <Select> aka GWT Multi-Line ListBox

    - by McTrafik
    Hi guys. Working on a webapp here that must run on the iPad (so, Safari Mobile). I have this code that works fine in just about anything except iPad: <select class="gwt-ListBox" size="12" multiple="multiple"> <option value="Bleeding Eyelashes">Bleeding Eyelashes</option> <option value="Smelly Pupils">Smelly Pupils</option> <option value="Bushy Eyebrows">Bushy Eyebrows</option> <option value="Green Vessels">Green Vessels</option> <option value="Sucky Noses">Sucky Noses</option> </select> What it's supposed to look like is a box with 12 lines ans 5 of them filled up. It works fine in FF, IE, Chrome, Safari Win. But, when I open it on iPad, it's just a single line! Styling it with CSS doesn't work. It just makes the single line bigger if I set the height. Is there a way to make it behave the same way as in normal browsers, or do I nave to make a custom component? Thanks.

    Read the article

< Previous Page | 1 2 3 4 5 6 7 8 9 10 11 12  | Next Page >