Author Archives:

Readings in GPU: “Understanding performance bottlenecks in numerical kernels on GPUs” by Vasily Volkov

Volkov’s article is made up of a set of presentation slides, 53 in number, and specifically deals with performance bottlenecks for LU factorization and matrix multiplication. To the extent that these computations share numerical operations in common with other compute intensive tasks, the advice given in the article provides a general overview of performance bottlenecks [...]

Readings in GPU: “CUBLAS Library” by Nvidia

BLAS stands for “Basic Linear Algebra Subprograms” and is a collection of functions for linear algebra operations with vectors and matrices. It provides many of the basic building blacks for other numerical libraries, such as LAPACK (“Linear Algebra PACKage”). The “CUBLAS Library” [1] is Nvidia’s GPU/CUDA implementation (with contributions from Vasily Volkov, Davide Barbieri and from [...]

Hello world!

Hi, my name is Andrew Sheppard and welcome to my blog on GPU programming. I have a sister blog called “Multicore Magic” that you might also want to take a look at. Here you will find my thoughts and experiments with programming with GPUs. There is a bias towards application of GPUs in finance, but [...]

Follow

Get every new post delivered to your Inbox.