Description
16 nodes each with four NVIDIA A100 Tensor Core GPUs providing 1.5 PF of single-precision performance to support machine learning and artificial intelligence applications.
RP Description
Anvil GPU is a compute cluster consisting of 16 nodes, each with four NVIDIA A100 GPUs and two 64-core AMD EPYC 7763 processors with 512 GB of memory. It is particularly well suited for work that keeps several GPUs busy at once, and is often used for model training, inference and GPU-accelerated simulation. It includes a great deal of AI and machine learning software, with CUDA-enabled builds of the common frameworks loaded through the module system.
Top Software (cached)
[{"name":"python","job_count":3671,"description":"Python is a high-level, interpreted programming language known for its simplicity and readability. It supports multiple programming paradigms and has a vast ecosystem of libraries and frameworks.","research_field":"Computer & Information Sciences, Software Engineering, Systems & Development","web_page":"https:\/\/www.python.org\/","documentation":"https:\/\/docs.python.org"},{"name":"amber","job_count":1810,"description":"Amber is a suite of highly extensible molecular simulation programs. It is designed for simulations of biomolecules such as proteins, nucleic acids, and carbohydrates, and can also be used for small molecules.","research_field":"Biological Sciences","web_page":"https:\/\/ambermd.org\/","documentation":"https:\/\/ambermd.org\/doc12\/Amber23.pdf"},{"name":"namd","job_count":400,"description":"NAMD (NAnoscale Molecular Dynamics) is a parallel molecular dynamics code designed for high-performance simulation of large biomolecular systems. It is optimized for the simulation of biomolecular systems containing millions of atoms.","research_field":"Biochemistry and Molecular Biology","web_page":"https:\/\/www.ks.uiuc.edu\/Research\/namd\/","documentation":"https:\/\/www.ks.uiuc.edu\/Research\/namd\/current\/ug\/"},{"name":"gromacs","job_count":351,"description":"GROMACS (GROningen MAssive Parallel MD for Molecular Dynamics) is a versatile package for molecular dynamics simulations with a strong emphasis on high-performance computing capabilities.","research_field":"Biological Sciences","web_page":"https:\/\/www.gromacs.org\/","documentation":"https:\/\/manual.gromacs.org\/current\/index.html"},{"name":"oxdna","job_count":19},{"name":"lattice boltzmann","job_count":12},{"name":"cp2k","job_count":11,"description":"CP2K is an open-source quantum chemistry and solid state physics software package designed to perform atomistic simulations of solid-state, liquid, molecular, and biological systems. It can be used to study a wide range of properties, including electronic structures, molecular dynamics, and vibrational spectra.","research_field":"Physical Sciences","web_page":"https:\/\/www.cp2k.org\/","documentation":"https:\/\/manual.cp2k.org\/trunk\/"},{"name":"vmd","job_count":11,"description":"Visual Molecular Dynamics (VMD) is a molecular visualization program for displaying, animating, and analyzing large biomolecular systems using 3-D graphics and built-in scripting.","research_field":"Biological Sciences","web_page":"https:\/\/www.ks.uiuc.edu\/Research\/vmd\/","documentation":"https:\/\/www.ks.uiuc.edu\/Research\/vmd\/current\/docs.html"},{"name":"bwa","job_count":5,"description":"Burrows-Wheeler Aligner (BWA) is a software package for mapping low-divergent sequences against a large reference genome, such as the human genome. It consists of three algorithms: BWA-backtrack, BWA-SW, and BWA-MEM. The BWA-backtrack algorithm is designed for Illumina sequence reads up to 100bp, while BWA-SW and BWA-MEM are for longer Illumina reads, including 100bp reads produced by the HiSeq 2000 platform.","research_field":"Biological Sciences","web_page":"https:\/\/bio-bwa.sourceforge.net\/","documentation":"https:\/\/bio-bwa.sourceforge.net\/bwa.shtml"},{"name":"hh-suite","job_count":3,"description":"HH-suite is a software package for sensitive protein sequence searching based on profile hidden Markov models. It includes tools for the alignment of protein sequences, detecting remote homologs, and predicting protein structures.","research_field":"Biological Sciences","web_page":"https:\/\/github.com\/soedinglab\/hh-suite","documentation":"https:\/\/github.com\/soedinglab\/hh-suite\/wiki#summary-of-command-line-parameters"}]
Jobs Information
You can run jobs at different sizes and durations on Anvil GPU. The following lists the different queues that you can submit to, describing how many nodes you get, how long you can run, the type of resources you get, and the average wait time.
Jobs are submitted through the Slurm scheduler. Run batch jobs with sbatch, start interactive work with srun or salloc, or launch an application through Open OnDemand.
GPU work is charged against a GPU allocation, not your CPU allocation, and the allocation name is given with -A. Always name the partition with -p: gpu-debug shares a node between jobs, while gpu gives exclusive access to the GPU nodes. No more than 12 GPUs may be in use per user and 32 per allocation at one time.
Per-queue wall-clock limits are in the queue table; if you do not set one, the partition default applies, which scontrol show partition reports.
For more information about running jobs on Anvil, see [Anvil Running Jobs].