rscimark

This package offers a single function rscimark, which is a simple wrapper around the ANSI C version of the SciMark2 benchmark. SciMark is a benchmark for numerical computing and scientific computing. Concicely the performance measurements for the computational kernels Fast Fourier Transformation (FFT), Gauss-Seidel relaxation, Sparse matrix-multiply, Monte Carlo integration, and dense LU factorization are used as indicators for the performance.

Installation

Run the following command in R to install the current GitHub version. For further installation instructions take a glance at our guide.

devtools::install_github("berndbischl/rscimark")

HowTo

To run the SciMark 2.0 benchmark from within R just open a R session and type the following:

library(rscimark)
rscimark()

To address performance of the memory subsystem with problems sizes which to not fit in the cache set the large parameter to TRUE.

rscimark(large = TRUE)