Hands-On GPU Programming with Python and CUDA

Summary

We started this chapter by looking at how to use the wrappers for the cuBLAS library from Scikit-CUDA; we have to keep many details in mind here, such as when to use column-major storage, or if an input array will be overwritten in-place. We then look at how to perform one- and two-dimensional FFTs with cuFFT from Scikit-CUDA, and how to create a simple convolutional filter. We then showed you how to apply this for a simple Gaussian blurring effect on an image. Finally, we looked at how to perform a singular value decomposition (SVD) on the GPU with cuSolver, which is normally a very computationally onerous operation, but which parallelizes fairly well onto the GPU. We ended this chapter by looking at how to use the SVD for basic ...