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.