CUDACasts Episode #1: Installing CUDA on Windows

Today I’m excited to announce CUDACasts, a brand new series of short, useful screencast videos about parallel programming on the CUDA platform. I’ll be bringing you new CUDACasts every week covering topics including step-by-step beginner how-tos, programming techniques and CUDA Pro Tips, and overviews of new CUDA features and tools.

CUDACasts Episode #1 gives an introduction to CUDACasts and the CUDA Platform, and shows you how to install the CUDA Toolkit on a Windows computer.

Each week you’ll be able to find new CUDACasts here at the Parallel Forall Blog, or on YouTube. Next week on CUDACasts I’ll show you how to write your first CUDA Program.


About Mark Ebersole

As CUDA Educator at NVIDIA, Mark Ebersole teaches developers and programmers about the NVIDIA CUDA parallel computing platform and programming model, and the benefits of GPU computing. With more than ten years of experience as a low-level systems programmer, Mark has spent much of his time at NVIDIA as a GPU systems diagnostics programmer in which he developed a tool to test, debug, validate, and verify GPUs from pre-emulation through bringup and into production. Before joining NVIDIA, he worked for IBM developing Linux drivers for the IBM iSeries server. Mark holds a BS degree in math and computer science from St. Cloud State University. Follow @cudahamster on Twitter
  • abdullahi

    Hello SIr,
    im really interested in doing my postgraduate research on cuda pogramming model. The challenge im facing is that my computer is intel, with HD Graphics 4000.

    How can i install cuda on my computer which does not have Nvidia GPU?

    Thanks alot
    abdullahi ibrahim

    • You can certainly install the CUDA Toolkit. And you will be able to compile CUDA programs. However you won’t be able to run them on your local machine. If you have access to a remote Linux server with a GPU, you could develop on it over VNC, SSH, etc. You can even use NSight Eclipse edition on a local Linux machine to develop and run on a remote Linux machine. You can also run in the cloud on Amazon AWS nodes with GPUs. Finally, you could buy a new GPU if your computer is a desktop machine, or try out a Jetson TX1 for embedded / low power development with CUDA.

      • DuLinRain

        Hello,I have a problem.
        When I use cuda4.2,the fftPlan1d or fftPlanMany is very fast which nearly only need 2ms;
        but when I use cuda6.5 and other high version ,it cost nearly 600ms. why???
        my email is

  • Manoj Nagar

    Hello sir i am a photographer and i am using intel i5 vth gen.
    board-intel DH87RL plz suggest me the nvidia graphic card for photoshop and after effect also