We provide a range of software for users on ALICE. The software is organized in modules. Because nodes on ALICE feature Intel Skylake CPUs as well as AMD EPYC Zen II and III CPUs and because we build software optimized for the CPU architecture, we maintain two module trees for users. One tree is for the Intel and one for the AMD nodesFollowing the maintenance of ALICE in May 2024, we have moved to a single software stack that works on all CPUs on ALICE (e.g., Intel Skylake, AMD Zen II, Zen III, Zen IV). This makes it easier for you to run your jobs on different nodes, but it also means that we cannot build the software with full optimization for the underlying CPU architecture. However, for many workloads on ALICE this is not an issue. For users, who need optimized modules, we are planning a separate stack in the future or you can always build your software yourself in your user environment.
New software is added upon request by users send to the ALICE Helpdesk. While we usually install new software in both module trees, the module tree for AMD is newer than the tree for our Intel nodes, which means that some software might not be available in the AMD tree. If you are missing software in the AMD module tree, just send an e-mail to the ALICE Helpdesk.
Switching between both trees is easily done using module load ALICE/Intel or module load ALICE/AMD. Alternatively, you can use module load ALICE to automatically load the correct tree for the CPU architecture of the node, e.g., in Slurm batch scripts.
Because we build software for the CPU architecture, it is possible that you need to compile or set up environments twice if you want to use nodes with both type of CPUs on ALICE.In order to access the scientific software stack on ALICE, run the following command and add it to your Slurm batch file:
| Code Block |
|---|
module load ALICE/default |
For the time being, the old modules are still available. However, they may or may not work. You can access them by loading the following module:
| Code Block |
|---|
module load ALICE/legacy |
You can find information on how to use the module system here: Using available software - Environment Modules
...
When added | Module | Description | Intel software stack | AMD software stack | |
|---|---|---|---|---|---|
2024-02-16 | Pandoc/3.1.2 | Converting files from one markup format to another |
|
| |
2024-02-15 | cuDNN/8.9.7.29 | NVidia cuDNN toolkit |
|
| |
2024-02-15 | CUDA/12.3.2 | NVidia CUDA toolkit |
|
| |
2024-01-12 | JAGS/4.315 Nov 2024 | PyTorch/2.1.2-foss-2022b | Just Another Gibbs Sampler |
|
|
2023-12-08 | MATLAB/2023b | MATLAB |
|
| |
2023-12-08 | SageMath 10.2 | SageMath is a free open-source mathematics software system licensed under the GPL. It builds on top of many existing open-source packages: NumPy, SciPy, matplotlib, Sympy, Maxima, GAP, FLINT, R and many more |
|
| |
2023-11-13 | tesseract/5.3.0-GCCcore-11.3.0 | Optical character recognition engine |
|
| |
2023-10-25 | FragPipe/20.0-Java-11 | Java interface for the analysis of mass spectrometry-based proteomics data |
|
| |
2023-10-06 | torchvision/0.13.1-foss-2022a-CUDA-11.7.0 | Datasets, Transforms and Models specific to Computer Vision |
|
| |
2023-08-21 | breseq/0.38.1-foss-2022a | Computational pipeline for the analysis of short-read re-sequencing data |
|
| |
2023-08-09 | mpi4py/3.1.4-GCC-11.3.0 | MPI support for Python 3.10.4 based on OpenMPI |
|
| |
2023-08-09 | htop/3.2.1 | Process viewer for Linux (alternative to |
|
| |
2023-08-08 | impi/2021.8.0-intel-compilers-2023.0.0 | Intel MPI Library, compatible with MPICH ABI |
|
| |
2023-08-07 | intel-compilers/2023.0.0 | Intel C, C++ & Fortran compilers (classic and oneAPI) |
|
| Pytorch deep learning framework |
