General Policy

• The use of the Vikram-100 is restricted for academic and research purposes only. It must NOT be used in relation to any commercial activities, consultancy services, illegal or unethical practices, etc.
• Users shall cite the use of Vikram-100 in their published paper.
• Do not run any computationally intensive jobs on the master node.
• Do not over allocate parallel jobs. Make certain that your job uses the number of processors that you have requested or reserved.
• Do not run highly experimental code that might compromise the usability of the master nodes, the network fabric, any of the compute nodes, or the shared storage system.
• Do not ssh into compute nodes. Unless for very specific reason mentioned in FAQs.
• Users are responsible for using the Vikram-100 system, resources and facilities in an efficient, effective, ethical and lawful manner.
• Users are requested to report any weaknesses in Vikram-100 computer security, and incidents of possible misuse or violation of the account policies to the HPC administrators ([email protected]).
• Users shall not purposely engage in activities to circumvent Vikram-100 computer security or system administrative measures.
• Users shall not make copies of system configuration files (e.g. the password file) for unauthorized personal use nor to provide them for other people/users.
• Users shall not download, install or run security programs or utilities which reveal weaknesses in the security of the Vikram-100 system.
• Users shall not attempt to access any data or programs contained on the Vikram-100 for which they do not have authorization or explicit consent of the owner of the data/program.

Account Policy

• Users shall change password immediately after getting their account and then change password within every 12 months.
• Users shall use strong passwords with:
  • At-least 10 characters.
  • Must include alphabets, numbers and special characters.
  • Must not be guessable, like date of birth, pet's name, etc.
• Users shall not share their Vikram-100 account(s) with others. This includes sharing the password of the account, providing access via a .rhost entry, sharing their public keys, or other means of sharing.

Queue Policy

• Users can run a total of 5 jobs across any queue (except for ‘serial’ and ‘gpu’ queue) at a time and queue 5 more.
• In ‘gpu’ queue, users can run 5 jobs and queue 10 more. Jobs submitted in this queue does not count towards jobs submitted across any other queues.
• In ‘serial’ queue, users can run 48 jobs and queue 96 more, but each job can only access one CPU. Jobs submitted in this queue does not count towards jobs submitted across any other queues.

Storage Policy

• Only store data that will be used for computation. Do not use HPC’s high performance parallel file system as a means of backup for your data. Take the data out if you think you will no longer run computation on it. Or at-least compress your data that is currently not in use but you think will be used in future.
• Users are currently granted a quota size of 3 TB.
• Users data is subject to deletion 6 months after their account expiry (which is the same as expiry date of their email account). It is the responsibility of user to take their data out or to take proper approval for extending their account from competent authority.