Environnements logiciels standards
Description
Nos environnements logiciels sont rendus disponibles par un ensemble de modules qui vous permettent d'alterner entre différentes versions d'un paquet logiciel. Ces modules sont organisés selon une structure en arbre dont le tronc est composé des mêmes utilitaires que ceux offerts par les environnements Linux. Les branches principales de ce tronc sont les versions des compilateurs auxquelles sont rattachées des sous-branches pour chaque version de MPI ou CUDA.
Un environnement logiciel standard est composé d’une combinaison particulière de modules de compilation et de modules MPI groupés dans un module appelé StdEnv. Ces environnements sont communément utilisés par notre équipe technique pour construire d’autres logiciels.
As of October 2020, there are three such standard environments, versioned 2016.4, 2018.3, and 2020, with each new version incorporating major improvements.
This page describes these changes and explains why you should upgrade to a more recent version.
In general, new versions of software packages will get installed with the newest software environment.
StdEnv/2016.4
This is the initial version of our software environment released in 2016 with the deployment of Cedar and Graham. It features GCC 5.4.0 and Intel 2016.4 as default compilers, and Open MPI 2.1.1 as its default implementation of MPI. Most of the software compiled with this environment does not support AVX512 instructions provided by the Skylake processors on Béluga, Niagara, as well as on the most recent additions to Cedar and Graham.
Activez cet environnement avec la commande
[name@server ~]$ module load StdEnv/2016.4
StdEnv/2018.3
This is the second version of our software environment. It was released in 2018 with the deployment of Béluga, and shortly after the deployment of Niagara. Defaults were upgraded to GCC 7.3.0, Intel 2018.3, and Open MPI 3.1.2. This is the first version to support AVX512 instructions.
Activez cet environnement avec la commande
[name@server ~]$ module load StdEnv/2018.3
StdEnv/2020
This is the most recent iteration of our software environment with the most changes so far. It uses GCC 9.3.0, Intel 2020.1, and Open MPI 4.0.3 as defaults.
Activez cet environnement avec la commande
[name@server ~]$ module load StdEnv/2020
Performance improvements
Binaries compiled with the Intel compiler now automatically support both AVX2 and AVX512 instruction sets. In technical terms, we call them multi-architecture binaries, also known as fat binaries. This means that when running on a cluster such as Cedar and Graham which has multiple generations of processors, you don't have to manually load one of the arch modules if you use software packages generated by the Intel compiler.
Many software packages which were previously installed either with GCC or with Intel are now installed at a lower level of the software hierarchy, which makes the same module visible, irrespective of which compiler is loaded. For example, this is the case for many bioinformatics software packages as well as the R modules, which previously required loading the gcc module. This could be done because we introduced optimizations specific to CPU architectures at a level of the software hierarchy lower than the compiler level.
We also installed a more recent version of the GNU C Library, which introduces optimizations in some mathematical functions. This has increased the requirement on the version of the Linux Kernel (see below).
Change in the compatibility layer
Another enhancement for the 2020 release was a change in tools for our compatibility layer. The compatibility layer is between the operating system and all other software packages. This layer is designed to ensure that compilers and scientific applications will work whether they run on CentOS, Ubuntu, or Fedora. For the 2016.4 and 2018.3 versions, we used the Nix package manager, while for the 2020 version, we used Gentoo Prefix.
Change in kernel requirement
Versions 2016.4 and 2018.3 required a Linux kernel version 2.6.32 or more recent. This supported CentOS versions starting at CentOS 6. With the 2020 version, we require a Linux kernel 3.10 or better. This means it no longer supports CentOS 6, but requires CentOS 7 instead. Other distributions usually have kernels which are much more recent, so you probably don't need to change your distribution if you are using this standard environment on something other than CentOS.
How can I change which version of StdEnv is my default?
Our clusters use different versions of StdEnv as their default version. As of August 2020, Cedar and Graham use StdEnv/2016.4, while Béluga uses StdEnv/2018.3. Niagara also defaults to StdEnv/2018.3 if you module load CCEnv StdEnv. In the future, we will probably switch all of them to use StdEnv/2020. However, users can specify their own default by running the following command (example provided for the 2020 version)
[name@server ~]$ echo "module-version StdEnv/2020 default" >> $HOME/.modulerc
Do I need to reinstall/recompile my code if the StdEnv version changes?
Yes. If you compile your own code, or install R or Python packages, you should recompile or reinstall the packages you need using the newest version of the standard environment.