Meraculous-Sapelo2
Category
Other
Program On
Sapelo2
Version
2.25, 2.27-1-AVX, 2.27-1-AVX2, 2.27-1-AVX2-CUDA-10
Author / Distributor
Please see http://magma.maths.usyd.edu.au/magma/: "Magma is distributed by the Computational Algebra Group at the University of Sydney."
Description
From http://magma.maths.usyd.edu.au/magma/: "Magma is a large, well-supported software package designed for computations in algebra, number theory, algebraic geometry and algebraic combinatorics. It provides a mathematically rigorous environment for defining and working with structures such as groups, rings, fields, modules, algebras, schemes, curves, graphs, designs, codes and many others. Magma also supports a number of databases designed to aid computational research in those areas of mathematics which are algebraic in nature. "
Running Program
Also refer to Running Jobs on Sapelo2
For more information on Environment Modules on Sapelo2 please see the Lmod page.
- Version 2.25 (CPU version), installed in /apps/gb/Magma-AU/2.25
To use this version of magma, please first load the module with
module load Magma-AU/2.25
- Version 2.27-1-AVX (CPU version), installed in /apps/gb/Magma-AU/2.27-1-AVX
To use this version of magma, please first load the module with
module load Magma-AU/2.27-1-AVX
- Version 2.27-1-AVX2 (CPU version), installed in /apps/gb/Magma-AU/2.27-1-AVX2
To use this version of magma, please first load the module with
module load Magma-AU/2.27-1-AVX2
Use the --constraint Slurm header with the value EDR to ensure that your job lands on a node that supports AVX2.
- Version 2.27-1-AVX2-CUDA-10 (GPU version), installed in /apps/gb/Magma-AU/2.27-1-AVX2-CUDA-10
To use this version of magma, please first load the module with
module load Magma-AU/2.27-1-AVX2-CUDA-10
Use the --constraint Slurm header with the value EDR to ensure that your job lands on a node that supports AVX2.
When running Magma, please request the node feature magma, as only nodes with this feature are included in our Magma license file. To do that, please add the Slurm option --constraint=magma, as in the sample job submission script below.
Example of how to run magma in a batch job
1. Create a magma script. In the example below this script is called test.txt and its content is
print 3+5;
2. Create a job submission script, called sub.sh in the example here, with the sample content
#!/bin/bash
#SBATCH --job-name=testmagma
#SBATCH --partition=batch
#SBATCH --ntasks=1
#SBATCH --nodes=1
#SBATCH --mem=5gb
#SBATCH --time=12:00:00
#SBATCH --output=%x.%j.out
#SBATCH --error=%x.%j.err
#SBATCH --constraint=magma,EDR #request the node features magma & EDR
cd $SLURM_SUBMIT_DIR
module load Magma-AU/2.27-1-AVX2
magma test.txt > output_${SLURM_JOB_ID}.log
where test.txt needs to be replaced by the name of your magma program. Other parameters of the job, such as the maximum wall clock time, maximum memory, and the job name need to be modified appropriately as well. In this example, the standard output of the magma command will be saved into a file called "output_${SLURM_JOB_ID}.log", where ${SLURM_JOB_ID} will automatically be replaced by the jobid number.
3. Submit the job to the queue with
sbatch sub.sh
Documentation
Tutorials and user guide are available at http://magma.maths.usyd.edu.au/magma/documentation/
Installation
- Binaries for Intel and AMD processors with AVX support downloaded from http://magma.maths.usyd.edu.au/magma/
System
64-bit Linux