Fun with Alea.CUDA, F# Interactive, Charts

Source code for this post can be found on my GitHub. It's great to see technologies evolving over the years. Alea.CUDA has done so in leaps and bounds since the first time I laid eyes on it a couple of years ago. At the time the name seemed unfortunate and hinted at the "aleatic" programming … Continue reading Fun with Alea.CUDA, F# Interactive, Charts →

Computing Self-Organizing Maps in a Massively Parallel Way with CUDA. Part 2: Algorithms

In the previous post I spoke briefly about motivations for implementing self-organizing maps in F# using GPU with CUDA. I have finally been able to outperform a single threaded C++ implementation by a factor of about 1.5. This is quite modest, but on the other hand rather impressive since we started out by being 60 … Continue reading Computing Self-Organizing Maps in a Massively Parallel Way with CUDA. Part 2: Algorithms →

Computing Self-Organizing Maps in a Massively Parallel Way with CUDA. Part 1: F#

By 2017, it is expected that GPUs will no longer be an external accelerator to a CPU; instead, CPUs and GPUs will be integrated on the same die with a unified memory architecture. Such a system eliminates some of accelerator architectures’ historical challenges, including requiring the programmer to manage multiple memory spaces, suffering from bandwidth … Continue reading Computing Self-Organizing Maps in a Massively Parallel Way with CUDA. Part 1: F# →

Outperforming MathNet with Task Parallel Library

Math.NET is a great project that brings numerics to .NET the OS way. Perusing their blog, I found this post on the on-line algorithm for std calculation. A simple Wiki search revealed this article that describes a parallel algorithm due to Chan for calculating variance (std = sqrt(variance)). So, I set to figure out whether … Continue reading Outperforming MathNet with Task Parallel Library →