Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 8 years ago.
Improve this question
I want to check the free memory on the device while executing a CUDA kernel. cuMemGetInfo(&free, &total) is a host (CPU) based command which gives free memory on the Device.
But is there any way to check free memory inside a CUDA kernel code during execution ?
Use profiler - The NVIDIA Visual Profiler is a cross-platform performance profiling tool that delivers developers vital feedback for optimizing CUDA C/C++ applications.
First introduced in 2008, Visual Profiler supports all 350 million+ CUDA capable NVIDIA GPUs shipped since 2006 on Linux, Mac OS X, and Windows.
The NVIDIA Visual Profiler is available as part of the CUDA Toolkit.
See User's Guide Here
Related
Closed. This question is not about programming or software development. It is not currently accepting answers.
This question does not appear to be about a specific programming problem, a software algorithm, or software tools primarily used by programmers. If you believe the question would be on-topic on another Stack Exchange site, you can leave a comment to explain where the question may be able to be answered.
Closed 2 days ago.
Improve this question
I'm working on a virtual machine that has been given 12 GB of RAM and has a Quadro RTX 6000 with 24 GB of VRAM. I'm trying to do machine learning on this virtual machine.
My intuition right now suggests that it is not using the video card as efficiently as it could be with the limited amount of RAM, and would work better with more. Is this correct?
The following suggests it is so, but is not very clear on that.
OpenCL - what happens if GPU memory is larger than system RAM
In short, how much RAM should I expect to need for machine learning and computer vision for this video card typically?
It very much depends on the software you are using. In some cases, GPU software can use significantly more VRAM than RAM, when the model runs only on the GPU and there is no need to have a copy of it in RAM.
As an example, although CFD and not ML, the FluidX3D software uses between 3.2x and 5.4x more VRAM than RAM. Here in your case the 24GB VRAM capacity would still be the limiting factor.
If it's 1:1 RAM:VRAM allocation, then you're limited by the 12GB RAM. In the end, you have to test your software and check the allocation ratio with tools like top/htop and nvidia-smi.
Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
This question does not appear to be about a specific programming problem, a software algorithm, or software tools primarily used by programmers. If you believe the question would be on-topic on another Stack Exchange site, you can leave a comment to explain where the question may be able to be answered.
Closed 5 years ago.
Improve this question
I am just about to start working on iOS side of my application, and then move onto Android and Windows Mobile perhaps, but I do not own a mac and I have read mixed reviews on Mac in Cloud for me to decide against it.
As far as the hardware, I found a refurbished OS10 Macbook on Newegg for around $200 Canadian, and I was wondering if anyone has used Xamarin with the networked Mac Agent system on this old of hardware. It seems to be the cheapest way to 'start' anyway, and I wanted to know what kind of performance there is on such old hardware. Will I be waiting for hours to compile basic software :P
Here is the description of the hardware in question:
Apple Grade C Laptop MacBook MC516LL/A-C
Intel Core 2 Duo P8600 (2.40 GHz)
2 GB Memory
250 GB HDD
13.3" Display
Mac OS X
It will be slow. But how slow it is cannot be tell. Because slow is something you need to feel.
Also, one more thing you will need to consider is whether the old mac can upgrade to Sierra OS or not. This is because latest Xcode 8.3 will only able to install on Sierra OS. Without Xcode 8.3, you will need to downgrade xamarin version too. This is much more troublesome.
Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
This question does not appear to be about a specific programming problem, a software algorithm, or software tools primarily used by programmers. If you believe the question would be on-topic on another Stack Exchange site, you can leave a comment to explain where the question may be able to be answered.
Closed 7 years ago.
Improve this question
I need run a 16bits application on a windows 64bits without virtualization or XP mode.
Do you have a solution ?
My application have an user interface and she need to print and to access the disk.
It's a old monster, we don't have the source code (Delphi) and it's very specific (made on demand).
I think about a sort of encapsulation or a "translator" between the OS and the binary.
An idea ?
I need run a 16 bit application on a Windows 64 bit system without virtualization.
That is not possible. The only way to run this application on such a system is via a virtualized environment of one form or another.
You wonder about some form of translator or adapter, but that is of course exactly what virtualization is. A 64 bit system cannot run a 16 bit process natively, ergo you need a virtualized environment in order to run it.
Closed. This question is off-topic. It is not currently accepting answers.
Want to improve this question? Update the question so it's on-topic for Stack Overflow.
Closed 10 years ago.
Improve this question
We just received the stable version of CUDA 5. There are some new terms like Kepler and ability of using MPI with better performance, and running the same card with 32 applications at the same time. I am a bit confused though and looking for the answers of such questions:
Which cards and compute capabilities are required to fully utilize CUDA 5's features?
Are new features only available for Kepler architecture, like GPUDirect, Dynamic Parallelism, Hyper Q and Dynamic Parallelism.
If we have Fermi architectures, what are the benefits of using CUDA 5. Does it bring benefits other than ability of using NSight at Linux and Eclipse. I think the most important feature is ability of building libraries?
Did you see any performance improvements by just passing from CUDA 4 to CUDA 5. (I got some speed ups at Linux machines)
I found out some documents like
http://developer.download.nvidia.com/compute/DevZone/docs/html/C/doc/Kepler_Compatibility_Guide.pdf
http://www.nvidia.com/content/PDF/kepler/NVIDIA-Kepler-GK110-Architecture-Whitepaper.pdf
http://blog.cuvilib.com/2012/03/28/nvidia-cuda-kepler-vs-fermi-architecture/
However a better, short description may make our minds clearer.
PS: Please do not limit the answer to the questions above. I might be missing some similar questions.
Compute capability 3.5 (GK110, for example) is required for dynamic parallelism because earlier GPUs do not have the hardware required for threads to launch kernels or directly inject other API calls into the hardware command queue.
Compute capability 3.5 is required for Hyper-Q.
SHFL intrinsics require CC 3.0 (GK104)
Device code linking, NSight EE, nvprof, performance improvements and bug fixes in CUDA 5 benefit Fermi and earlier GPUs.
Closed. This question is not about programming or software development. It is not currently accepting answers.
This question does not appear to be about a specific programming problem, a software algorithm, or software tools primarily used by programmers. If you believe the question would be on-topic on another Stack Exchange site, you can leave a comment to explain where the question may be able to be answered.
Closed 4 months ago.
The community reviewed whether to reopen this question 4 months ago and left it closed:
Original close reason(s) were not resolved
Improve this question
How can I monitor how much of the graphics card is used when I run a certain application? I want to see how much my application uses the GPU.
If you develop in Visual Studio 2013 and 2015 versions, you can use their GPU Usage tool:
GPU Usage Tool in Visual Studio (video) https://www.youtube.com/watch?v=Gjc5bPXGkTE
GPU Usage Visual Studio 2015 https://msdn.microsoft.com/en-us/library/mt126195.aspx
GPU Usage tool in Visual Studio 2013 Update 4 CTP1 (blog) http://blogs.msdn.com/b/vcblog/archive/2014/09/05/gpu-usage-tool-in-visual-studio-2013-update-4-ctp1.aspx
GPU Usage for DirectX in Visual Studio (blog) http://blogs.msdn.com/b/ianhu/archive/2014/12/16/gpu-usage-for-directx-in-visual-studio.aspx
Screenshot from MSDN:
Moreover, it seems you can diagnose any application with it, not only Visual Studio Projects:
In addition to Visual Studio projects you can also collect GPU usage data on any loose .exe applications that you have sitting around. Just open the executable as a solution in Visual Studio and then start up a diagnostics session and you can target it with GPU usage. This way if you are using some type of engine or alternative development environment you can still collect data on it as long as you end up with an executable.
Source: http://blogs.msdn.com/b/ianhu/archive/2014/12/16/gpu-usage-for-directx-in-visual-studio.aspx
From Unix.SE: A simple command-line utility called gpustat now exists: https://github.com/wookayin/gpustat.
It is free software (MIT license) and is packaged in pypi. It is a wrapper of nvidia-smi.