Skip to main content

Nvidia's CUDA Now Features Python Support

At this year's GPU Technology Conference (GTC), Nvidia announced that the company's CUDA parallel programming technology has support for Python and consequently can take "full advantage of GPU acceleration for their high performance computing (HPC) and big data analytic applications."

This support comes from NumbaPro, a Python compiler in the new Anaconda Accelerate product from Continuum Analytics and is a result of the company's contribution of the CUDA compiler source code into the core and parallel thread execution backend of LLVM.

"Hundreds of thousands of Python programmers will now be able to leverage GPU accelerators to improve performance on their applications," said Travis Oliphant, co-founder and CEO of Continuum Analytics. "With NumbaPro, programmers have the best of both worlds: they can take advantage of the flexibility and high productivity of Python with the high performance of NVIDIA GPUs."

Anaconda Accelerate is available for Continuum Analytics' Anaconda Python offering and as part of the Wakari browser-based data exploration and code development environment.

Contact Us for News Tips, Corrections and Feedback

  • jazz84
    This is great news, Python's extremely versatile and approachable; I'm very excited to see what people will be able to accomplish. Also, this is mandatory: http://xkcd.com/353/
    Reply
  • dragonsqrrl
    jazz84Also, this is mandatory: http://xkcd.com/353/Nice, I loved that one.
    Reply
  • weierstrass
    I hate white space sensitive languages, one it took me a day find bug caused by one dev using spaces and the other correction something in a look indenting it with a tab...
    Reply
  • WINTERLORD
    hey can someone tell me if amd radeon supports python
    Reply
  • Onihikage
    WINTERLORDhey can someone tell me if amd radeon supports pythonThere's at least one wrapper that enables use of OpenCL computations by Python apps. PyOpenCL, for example.
    Reply
  • IndignantSkeptic
    Why would someone use CUDA when there is OpenCL or OpenMP?
    Reply