Search 61 Results

Can't Find What You Are Looking For? Sign In Now
You are currently not logged in and some search results only show up if you login.

Tools for Researchers

  1. Knowledge Base
  2. Research Computing
, data storage, Caligari Web and database servers Accounts for Researchers - For general research computing, data storage, and Discovery cluster accounts Software Resources - Applications in

Single-Core Job Example

  1. Knowledge Base
  2. Research Computing
  3. Discovery Cluster
  4. SBATCH (job submission)
sample script are exampled in a comment line that precedes the directive. The full list of available directives is explained in the man page for the sbatch command which is available on discovery

Scheduling Jobs

  1. Knowledge Base
  2. Research Computing
  3. Discovery Cluster
  4. SBATCH (job submission)
The Batch System The batch system used on Discovery is Slurm. Users login, via ssh,  to one of the submit nodes and submit jobs to be run on the compute nodes by writing a script file that

GPU Job Example

  1. Knowledge Base
  2. Research Computing
  3. Discovery Cluster
  4. SBATCH (job submission)
#!/bin/bash # Name of the job #SBATCH --job-name=gpu_job # Number of compute nodes #SBATCH --nodes=1 # Number of cores, in this case one #SBATCH --ntasks-per-node=1 # Request the GPU

Multi-Core Job Example

  1. Knowledge Base
  2. Research Computing
  3. Discovery Cluster
  4. SBATCH (job submission)
Below is an example script which will submit for 4 cores on a single compute node. Feel free to copy and paste it as a job template.   #!/bin/bash #SBATCH --job-name=multicore_job #SBATCH

Leaving Dartmouth - Research Computing resources

  1. Knowledge Base
  2. Leaving Dartmouth
When you leave Dartmouth you will no longer be able to login to the multi-user Linux systems such as Polaris, Andes, and the Discovery cluster.    You will also lose access to DartFS network

When do I need to use the VPN client?

  1. Knowledge Base
  2. Wifi, Network, VPN and Phone
solution has enough capacity by only using it when you need to. Requires VPN DartFS-Networked Attached Storage used in labs, HPC and web applications Discovery (HPC) MyFiles/OurFiles (File

Job array example

  1. Knowledge Base
  2. Research Computing
  3. Discovery Cluster
  4. SBATCH (job submission)
JOB ARRAYS Job arrays are multiple jobs to be executed with identical or related parameters. Job arrays are submitted with -a <indices> or --array=<indices>. The indices specification identifies

Graduating Students - Research Computing Resources

  1. Knowledge Base
  2. Leaving Dartmouth
  3. Graduating Students - Arts & Sciences
Discovery cluster You will also lose access to DartFS network storage. Deadline Approximately 60 days after graduating, any DartFS storage that is in your name will be deleted. After 60

User commands

  1. Knowledge Base
  2. Research Computing
  3. Discovery Cluster
  4. Torque commands & Slurm equivalent
Option MOAB Torque command (mksub) Slurm command (sbatch) Job Submission mksub <file name> sbatch <file name> Job Deletion qdel / mjobctl -c scancel

Job directives

  1. Knowledge Base
  2. Research Computing
  3. Discovery Cluster
  4. Torque commands & Slurm equivalent
Option MOAB Torque command (mksub) Slurm command (sbatch) Job Name -N <name> --job-name=<name> Account -a <account> --account=<account

Research Computing Bill of Rights

  1. Services
  2. Research
Performance Computing (HPC), GIS, data visualization, statistical analysis, software development and more access to HPC resources (Discovery, Andes, and Polaris) DartFS: personal and shared data storage

Recover files/folders from a DartFS snapshot

  1. Knowledge Base
  2. Research Computing
  3. DartFS
From a Mac or Linux The easiest way to recover these files is to: Log into Andes/Polaris/Discovery from a Terminal application Go to the hidden .snapshot folder – note, you cannot see

Important update regarding our service charges collection policy, effective from July 1, 2023.

  1. Knowledge Base
  2. Research Computing
  3. High Performance Computing
financial year or at the beginning of service. Specifically, data storage and compute charges, including but not limited to DartFS, virtual servers, containers, and Discovery shares, will be

Example: Interactive job (srun)

  1. Knowledge Base
  2. Research Computing
  3. Discovery Cluster
  4. SRUN (Interactive job submission)
An interactive job is launched on a compute node and provides you with a command line prompt. Interactive jobs are useful when debugging or interacting with an application. You will use thesruncommand