ASA Connect

 View Only

  • 1.  FP128 (quad float point ) calculations with multithreaded lapack and blas in R

    Posted 01-02-2017 15:14

    Hey everyone, 

    I need to run some calculations using quadruple float point calculations. Currently I am using MRO with the mkl. I'm running into issues with the float point calculations. Can anyone tell me a way to get FP128 calcs with matrix multiplication in R? I need to use a multithreaded math library like the MKL too.

    My research project is at a stand still until I get this fixed. 

    Thanks.

    ------------------------------
    Andrew Ekstrom

    Statistician, Chemist, HPC Abuser;-)
    ------------------------------


  • 2.  RE: FP128 (quad float point ) calculations with multithreaded lapack and blas in R

    Posted 01-03-2017 13:23

    This might get you part way there:

     

    https://cran.r-project.org/web/packages/Rmpfr/index.html

     

     




    Original Message


  • 3.  RE: FP128 (quad float point ) calculations with multithreaded lapack and blas in R

    Posted 01-05-2017 22:50

    I looked at that package. As best I can tell, I can use it for a single value. I need to extend that to the entire matrix though. Not sure how I can do that.

    Thanks. 

    ------------------------------
    Andrew Ekstrom

    Statistician, Chemist, HPC Abuser;-)

    Original Message


  • 4.  RE: FP128 (quad float point ) calculations with multithreaded lapack and blas in R

    Posted 01-06-2017 07:59

    Hi,

    The 'Multi-Precision Arithmetic and Symbolic Mathematics' section of this task view might offer some way forward.

    CRAN Task View: Numerical Mathematics

    Cheers,

    Ben

    R-project remove preview
    CRAN Task View: Numerical Mathematics
    This task view on numerical mathematics lists R packages and functions that are useful for solving numerical problems in linear algebra and analysis. It shows that R is a viable computing environment for implementing and applying numerical methods, also outside the realm of statistics.
    View this on R-project >

    ------------------------------
    Ben Tupper

    Original Message


Related Content