Thanks for visiting Scientific Computing World.

You're trying to access an editorial feature that is only available to logged in, registered users of Scientific Computing World. Registering is completely free, so why not sign up with us?

By registering, as well as being able to browse all content on the site without further interruption, you'll also have the option to receive our magazine (multiple times a year) and our email newsletters.

GPULib 1.6

Share this on social media:

Tech-X Corporation has announced the release of GPULib 1.6. This is the latest release of the tool for speeding up interactive data language (IDL) calculations using GPU hardware based on the Cuda library from Nvidia.

GPULib is designed to improve existing IDL applications with minimal effort, and provide a framework for enabling users to accelerate custom kernels. With  improved  linear  algebra,  better  performance,  and  better  installers, GPULib is better than ever for IDL users to get their analysis done faster.

Features of GPULib include:

  • Simple IDL interface;
  • GPU accelerated BLAS/LAPACK;
  • Custom CUDA kernels;
  • FFT (1-, 2-, and 3-dimensional with batching);
  • Basic vector and matrix arithmetic;
  • Array indexing/subarray operations;
  • Use of streams to perform computation and memory transfer simultaneously;
  • Use of CPU emulation where CUDA hardware not available; and
  • Interface to Tech-X's FastDL for multi-GPU processing.