Timing simulations for preprocessCore 1.1.9 (Simulation 1)

Written by Ben Bolstad email bmb@bmbolstad.com

Background

The goal here was to investigate the speed of normalize.quantiles() as a function of number of threads used (on a dual core machine) for varying numbers of rows and columns.

Source code

The test machine was configured with an AMD X2 5600+ processor, 8GB of RAM, 10GB of swap memory and Fedora 8.

R and its package configuration was as follows:
R version 2.7.0 Under development (unstable) (2008-03-21 r44836) x86_64-unknown-linux-gnu locale: LC_CTYPE=en_US.UTF-8;LC_NUMERIC=C;LC_TIME=en_US.UTF-8;LC_COLLATE=en_US.UTF-8;LC_ MONETARY=C;LC_MESSAGES=en_US.UTF-8;LC_PAPER=en_US.UTF-8;LC_NAME=C;LC_ADDRESS=C;L C_TELEPHONE=C;LC_MEASUREMENT=en_US.UTF-8;LC_IDENTIFICATION=C attached base packages: [1] stats graphics grDevices utils datasets methods base other attached packages: [1] preprocessCore_1.1.9

Results

Discussion

Moving from single to double threaded resulted in runtime being reduced by about 45%.