Slashdot Mirror

← Back to Stories (view on slashdot.org)

Matlab Integrates GPU Support For UberMath Computation

Posted by Roblimo on from the more-calculations-faster dept.

An anonymous reader writes "Matlab now comes with GPU native support in the 2010b version. This means loads of Matlab commands can be parallelized onto the GPU without having to re-code things in C++ or Fortran using CUDA. Pretty sweet for the HPC community."

4 of 89 comments (clear)

  1. Nice by Anonymous Coward · · Score: 2, Interesting

    But can't Octave do that already?

  2. Re:How long until R supports this? by Anonymous Coward · · Score: 2, Interesting

    http://cran.r-project.org/web/views/HighPerformanceComputing.html

    See "Parallel computing: GPUs"

  3. Re:Old news by guruevi · · Score: 3, Interesting

    I think they meant 2011b which is not out yet (it's in beta). GPUmat as well as nVIDIA had toolboxes for MATLAB for a while now (although the CUDA toolboxes require manual code edits and compiling to get it to work) but there is only limited function support (eg. FFT on large arrays works wonders on CUDA) and even those had limited support (only single floating point precision for example). There is also the commercial Accelereyes with Jacket.

    --
    Custom electronics and digital signage for your business: www.evcircuits.com
  4. MAGMA by l00sr · · Score: 3, Interesting

    For those interested in an open-source alternative, there's MAGMA, which provides a bunch of linear algebra routines implemented in CUDA. I haven't tried it myself yet, but it looks promising.