To present an overview of the GROMACS molecular dynamics performance and compare the simulation speed attainable on some of the most common hardware platforms we have constructed a benchmark of a few typical systems. The benchmarks all represent "real-life" examples, i.e. they have been taken from ongoing research projects either in our labs or from published articles.

    Benchmarks for GROMACS 5.0

    GROMACS 5.0 Benchmark report

    Old benchmark suite

    You can download our entire set of benchmark systems (it hasn't changed for version 3.1):



    The benchmarks are divided in two parts; the first concerns performance on single node machines (i.e. no parallelization outside the machine, but possibly using several CPUs), while the second one shows the scaling capabilities for a large membrane system when running in parallel over an external network.
    Performance is quoted as picoseconds of simulation performed per day for all benchmarks, and the parallel scaling over N processors is defined as


    S = p_N / ( N * p_1 )


    where p_x is the performance on x processors.

    GPU benchmarks

    The GPU landscape develops extremely fast, and while we frequently benchmark to make sure performance improves, we often don't have the time to update this page with data and plots. However, on the GPU page you can find both our older benchmark sets, and links to vendors who even provide GROMACS-specific benchmarks for systems they offer.

    Interested in helping us with benchmarking and testing???

    That's simply awesome! Feel very welcome to join our crew and please contact any of the following people:

    Page last modified 22:01, 19 Nov 2015 by lindahl