HPC

Rivanna is the University of Virginia’s High-Performance Computing (HPC) system. As a centralized resource it has hundreds of pre-installed software packages available for computational research across many disciplines. Currently the Rivanna supercomputer has over 8,000 cores and 8PB of various storage.

All UVA faculty, staff, and postdoctoral associates are eligible to use Rivanna, or students when part of faculty research.

The sections below contain important information for new and existing Rivanna users. Please read each carefully.

New users are invited to attend one of our free orientation sessions ("Introduction to the HPC System") held throughout the year during office hours or by appointment.


Get Started

Access / Allocations

Learn how to request an allocation and add collaborators.

Logging In

Log in through a Web browser or a command-line tool.

File Transfer

Moving files between Rivanna and other systems.

Software

See a listing of available software.

Storage

Options for free short-term and leased long-term storage

Running Jobs in SLURM

Submitting jobs to Rivanna through the SLURM resource manager

Queues

Determine the best queue (or “partition”) for running your jobs.

Usage Policies

Understand the terms and conditions for using Rivanna.

FAQs

Frequently Asked Questions.


Overview

A high performance computing cluster is typically made up of at least four service layers:

  1. Interactive nodes - Where you log in, interact with data and code, and submit jobs.
  2. Worker nodes - Where larger jobs are run. These nodes are heterogenous, with some having higher CPU, some with more memory, some with GPUs. The type of nodes your job runs in is specified by what queue you select.
  3. Storage - Where files and data are stored, accessible by all nodes in the cluster.
  4. Job scheduler - A management system that takes job requests and optimizes their execution.

Click on elements of the image to learn more:

Parts of a High Performance Computing cluster Interactive Nodes Worker Nodes Storage Job Scheduler

System Details

Rivanna is a managed resource; users must submit jobs to queues controlled by a resource manager, also known as a queueing system. The manager in use on Rivanna is SLURM. SLURM refers to queues as partitions because they divide the machine into sets of resources. There is no default partition and each job must request a specific partition. Partitions and access policies are subject to change, but the following table shows the current structure. Note that memory may be requested per core or for the overall job. If the total memory required for the job is greater than the number of cores requested multiplied by the maximum memory per core, the job will be charged for the additional cores whether they are used or not. In addition, jobs running on more than one core may still require a request of total memory rather than memory per core, since memory per core is enforced by the system but some multicore software packages (ANSYS, for example) may exceed that for a short time even though they never exceed cores x memory/core.

Partition Max time per job Max nodes per job Max cores per job Max memory per core Max memory per node per job SU Charge Rate
standard 7 days 1 40 9GB 375GB 1.00
parallel 3 days 45 900 9GB 120GB 1.00
largemem 4 days 1 16 64GB 975GB 1.00
gpu 3 days 4 8 32GB 240GB 3.00 *
knl 3 days 8 512 cores / 2048 threads 3GB (per physical core) 192GB 1.00
dev 1 hour 2 8 6GB 36GB 0.00

* GPU charge rate = number of cores + 2 * number of GPU devices.

Cores/node RAM/node Nodes
20 128GB 195
28 256GB 25
40 384GB 80
16 1TB 5
28+8 K80 GPU 256GB 8
28+4 P100 GPU 256GB 4
28+4 V100 GPU 256GB 1
64 Knight's Landing 196GB 8

Usage Policies

Research computing resources at the University of Virginia are for use by faculty, staff, and students of the University and their collaborators in academic research projects. Personal use is not permitted. Users must comply with all University policies for access and security to University resources. The HPC system has additional usage policies to ensure that this shared environment is managed fairly to all users. UVA’s Research Computing (RC) group reserves the right to enact policy changes at any time without prior notice.

Frontends

Exceeding the limits on the frontend will result in the user’s process(es) being killed. Repeated violations will result in a warning; users who ignore warnings risk losing access privileges.

Standard Partition

Each job in the standard partition is restricted to a single node. Users may submit multiple jobs or job arrays, but the maximum aggregate cpu cores allowed for a single user’s running jobs is 1000.

Parallel Partition

Users must request a minimum of two nodes and four cpu cores (and no more than 900 cpu cores) when submitting a job to the parallel partition.

GPU Partition

The gpu partition is dedicated to jobs that can utilize a general purpose graphics processing unit (GPGPU). Any job submitted to the gpu partition must request at least one GPU device through the gres option; jobs that do not utilize any GPUs are not allowed in this partition. Users may submit multiple jobs or job arrays, but the maximum aggregate number of GPU devices allowed for a single user’s running jobs is 16.

Scratch Directory

Rivanna’s scratch file system has a limit of 10TB and 350,000 files per user. This policy is in place to guarantee the stability and performance of the scratch file system. Scratch is intended as a temporary work directory. It is not backed up and files that have not been accessed for more than 90 days are marked for deletion. Users are encouraged to back up their important data.

Software Licenses

Excessive consumption of licenses for commercial software, either in time or number, if determined by system and/or RC staff to be interfering with other users’ fair use of the software, will subject the violator’s processes or jobs to termination without warning. Staff will attempt to issue a warning before terminating processes or jobs but inadequate response from the violator will not be grounds for permitting the processes/jobs to continue.

Inappropriate Usage

Any violation of the University’s security policies, or any behavior that is considered criminal in nature or a legal threat to the University, will result in the immediate termination of access privileges without warning.