Tag: parallelization

smqsched – Simple Multi Queue Scheduler

smqsched – Simple Multi Queue Scheduler

smqsched Simple Multi Queue Scheduler smqsched is a simple multi-threaded task scheduling module with support for multiple queues and directed acyclic graph (DAG) dependencies. Introduction smqsched was designed with the following objectives in mind: Allow existing code to be parallelized without significant refactoring To this end, smqsched uses promise-style creation […]

Cross-platform super lightweight one file qsub replacement

Useful for people running their jobs on UNIX clusters, who for some reason need from time to time to launch them on Windows with business logic similar to original qsub command. It works like this: starts an HTTP server which is running 8 worker threads (adjust to the max number […]

parallelize_matlabbatch

This script loads selected SPM batch, tries to intelligently guess which fields are potential candidates for “parallel splits” and after interactively asking for confirmation: splits your batch into multiple .mat, .m and .sh files (placing them in the same directory as the original batch) – the latter being ready for […]

Faster dot product for SVM

If you’ve ever used SVM for classification of 3D images, you’re probably a big fan of the kernel trick as it improves SVM performance significantly when working with such huge sets of features. I’m working in neuroscience at the moment and I think it’s fair to say that using SVM […]

OpenMPI and Precomputed Values in Shared Memory

Think OpenMPI. Let’s say you have a 12-node cluster at your disposal. Every node has 16GB of RAM and two 4-core processors which in normal situations enables you to run 8 processes per node. What happens if you want to precompute a huge constant lookup table (e.g. 3GB in size) […]

Project Euler #311

Yay! It’s finally getting hard again! The thrill of many hours of computing and being uncertain whether the result will be correct to the last digit… I love it ;D Now I have to figure out the _correct_ (i.e. non semi-brute-force with smart-ass pruning and nifty little optimizations) method of […]

Project Euler #300

In a very simplified form, we can consider proteins as strings consisting of hydrophobic (H) and polar (P) elements, e.g. HHPPHHHPHHPH. For this problem, the orientation of a protein is important; e.g. HPP is considered distinct from PPH. Thus, there are 2n distinct proteins consisting of n elements. When one […]

Paralell DP, BGL and other fun stuff ;)

I haven’t been posting for the past few days because I’ve been in Wrocław (Breslau) for the weekend and then I was kinda busy playing with new coding quests, this time from topcoder.com, my second big love after Project Euler (jeez, why nobody told me about these two before? 😉 […]

Open MPI convenience functions

I could start by lecturing you on the basics of usage and principles of operation of MPI and Open MPI in particular, but I think it might not be a good idea, because you (or even more probably me 😉 ) could get bored really quickly. To cut long story […]