Thursday, May 29, 2014

FDS 6.1.0 Released

We are releasing today a minor release of FDS, version 6.1.0. Note that a minor release means that there are some minor changes in functionality between FDS 6.0.x and FDS 6.1.0. For a list of these changes, consult the release notes:

For most of you, the most significant change is that we are now releasing the OpenMP version of FDS as the default. In the past, we released the OpenMP version as an option. Now, if you run FDS in what we used to call "serial" mode, i.e.

fds job_name.fds

the executable will exploit multiple cores of your machine, typically four but it depends on your specs. We have found via benchmark testing that four cores seems to be the optimum number for a typical Windows-based PC. It provides approximately a factor of 2 in speed-up, although we would like to hear from you if you experience something dramatically different. More details are provided in the User's Guide.

Keep in mind that OpenMP and MPI are two very different kinds of parallel processing. The MPI version of FDS, which is still the same as it was, exploits shared or distributed memory architectures; that is, it can exploit multiple cores on a single machine or on multiple machines on a network. To make MPI work, you must  divide the computational domain into multiple meshes. However, OpenMP, which can only exploit shared memory architectures, can make either single or multiple mesh calculations run faster, but you are limited to a single machine. We are exploring the possibility of using both OpenMP and MPI to exploit multiple cores on multiple machines of a network. For the moment, we want to make sure that the OpenMP version works reliably.

The implementation of OpenMP in FDS was started by Christian Rogsch several years ago and more recently by Daniel Haarhoff. Thanks also to Boris Stock and Cian Davis who helped work out a few kinks in the new release. Thanks also to all of you who have contributed results of your benchmarking exercises. This greatly helps us better understand how both the MPI and OpenMP versions work under the various operating systems we develop for. We're going to continue to put together benchmarking cases as we continue to improve the parallel processing. Let us know via the FDS-SMV Discussion Group if there is any trouble with the new version.