BRC-Facilitated Computational Resources

This page is a list of computational resources both directly provided and facilitated by Berkeley Research Computing (BRC). It is meant to be a summary and overview of the research computing landscape and is not exhaustive. For more information about any of the resources listed here, please click the linked name of the resource to see how to get in touch with BRC consulting so that we may discuss the system(s) most appropriate for your workflows.

Resources directly provided by BRC:

Name Best Suited For Max. Job Time Storage Options Data Transfer Options Sensitive data*? Cost Webpage
Savio Traditional HPC
Linux workflows
Batch job submission
72 hours 10GB Home Directory storage
Condo Storage
lftp to Berkeley Box
gdrive CLI tool to bDrive
Globus endpoints via dtn.brc.berkeley.edu
PL0 Free (optional purchasing) Savio webpage
Analytics Environments
on Demand (AEoD)
Interactive work
Windows environments
Scalable memory needs (2-64GB of RAM or more)
Variable based
on MOU
5GB personal storage
Optional CIFS NAS mounting
bDrive via Google Drive folder sync (recommended)
Berkeley Box via Box Sync or CyberDuck
PL0 Free (with MOU) AEoD webpage

Resources facilitated (not directly provided) by BRC:

Name Best Suited For Max. Job Time Storage Options Data Transfer Options Sensitive data*? Cost Webpage
Comet (available thorugh XSEDE and HPC@UC) Rapid access
Test accounts
GPU applications
Traditional HPC
48 hours 5GB Home Directory 
SSD Scratch
Parallel Lustre Scratch
XSEDE Storage Allocations for persistent project space
Globus No Free Comet webpage
Bridges (XSEDE resource) Extreme (~TB) memory needs
Web server use
Hadoop/Spark use
GPU applications
Traditional HPC
48 hours 10GB Home Directory 
Node-local scratch
Memory-local scratch
Temporary file storage
XSEDE Storage Allocations for persistent project space
Globus    

 

No Free Bridges webpage
Jetstream (XSEDE resource) Virtual machines
Reproducibility
Interactive work
N/A XSEDE Storage Allocations for custom-size VM-mountable block devices (similar to AWS EBS volumes) scp/rsync to/from VMs    

Globus Connect Personal to/from VMs

No Free Jetstream webpage
XStream (XSEDE resource) GPU applications 48 hours 5GB Home directory 
Lustre Object Storage Target
XSEDE Storage Allocations
Globus No Free XStream webpage
Stampede (XSEDE resource) GPU applications
Visualization
Traditional HPC
48 hours 5GB Home directory 
1TB temporary file storage
Scratch filesystem
XSEDE Storage Allocations for Long-term tape archival storage
Globus    

scp to Ranch for long-term tape archival storage

No Free Stampede webpage
Amazon Web Services (AWS) Virtual machines
Website hosting
Networking
Cloud Storage
N/A AWS S3 
AWS EBS
AWS Glacier
S3 API using various 3rd party tools 
scp/rsync to VMs 
Yes* (link to BAA) Varies AWS webpage
Microsoft Azure Virtual machines
Website hosting
Cloud Storage
Mobile developement
N/A Azure storage options
Cool Blob Storage
TBD Yes* (link to BAA) Varies Azure webpage
Google Cloud Platform Virtual machines
Website hosting
Networking
Cloud Storage
N/A Google Cloud Storage    

Nearline Storage

TBD Yes* (link to BAA) Varies GCP webpage

Savio

If you are interested in using the Savio cluster, please see the System Overview page for more information, including technical specifications. If you have questions about the cluster and how it might fit into your workflow, please email us at brc@berkeley.edu with a brief description of your project, a concise overview of the software and data you're using, and a summary of what stage you are at in your research process.

Analytics Environments on Demand (AEoD)

If you are interested in using AEoD with your Windows software, please email us at brc@berkeley.edu.

XSEDE

If you are interested in using any of the XSEDE resources, please contact us at brc@berkeley.edu so that we can work with you directly to obtain access to the appropriate resource(s).

Cloud Providers

If you are interested in using a cloud provider (AWS, Azure, or GCP), please contact us at brc@berkeley.edu with a brief description of your project, a concise overview of the software and data you're using, and a summary of what stage you are at in your research process. Additionally, you may be also interested in attending the Cloud Working Group meetings.

 

*Compliance depends upon the terms of the data use agreement, IRB approval, license, contract or other policy or policies that govern confidentiality of the particular data.