Computational Resources

The ERIS Linux Cluster is an ecosystem of scientific computing resources centered around a cluster of remote-desktop and compute nodes connected to very high speed storage. A large selection of popular scientific applications are installed and you can request additional software packages to be added.  The cluster runs a Linux operating system and requires some familiarity with Linux for efficient use. 

This platform is ideal for workflows that run many jobs in parallel, and for those that read and write many files or require very high speed access to data files.  A job scheduling system queues jobs for dispatch to the compute nodes, allowing submission of many jobs at once.  Linux remote-desktop nodes allow graphical applications for data visualization to interacting with data stored on the cluster, as well as software development and application testing.  Some research groups also dispatch analysis pipeline jobs to the cluster through custom web-portals.   

Typical Uses

• Medical image processing
• Genome sequencing
• Monte-carlo modeling
• MPI parallel workloads
• Very large memory jobs
• AI/ML and Deep Learning using NVIDIA GPUs

Supported methods of connecting to the cluster 

• SSH command line terminal for job submission
• NoMachine Linux remote desktops for graphical applications
• Network file share (SMB/CIFS) for data transfer
• Web portals and applications (R Studio, Jupyter, etc)

Getting an account?

• Use the registration link 

ERIS Scientific Computing has implemented a new deep learning GPU Cluster, ERISXdl (ERIS Extreme Deep Learning). This system is built with NVIDIA DGX-1, an integrated system that includes high-performance GPU interconnection, delivering industry-leading performance for AI and deep learning. ERISXdl platform provides efficient, high-bandwidth streaming of training data, multi-GPU performance designed for HPC and Deep Learning applications.  The platform supports Docker containerized environments to easily emulate the entire software workflow and maintain portability and reproducibility, as well as Jupyter notebooks for rapid development, integration with Github, and HPC scheduler Slurm to distribute the workload across the system.  We provide access to high-bandwidth, low-latency Briefcase storage for the data required for analytics.

ERISXdl has a free basic tier for test and quick debugging of jobs. The main available partitions are available via a chargeback model at a rate of $0.01 min GPU. Users can sign up at rcservices.partners.org. More details about this platform can be found here.

Typical Uses

• Deep Learning development for fast Image Neutral Network model development
• TensorFlow applications for highly efficient GPU-enabled workloads.
• Deployment of Docker containerized applications with GPU requirements. 

Supported methods of connecting to the cluster 

• SSH command line terminal.
• JupyterLab webportal for fast development.

Launched in 2020, the Analytics Enclave, "Enclave Platform", is a highly secure, privacy-aware, data ecosystem equipped with self-service AI, machine learning, and research data tools that facilitate on-demand data analysis at the project-, program-, or institution-level.

The controlled and protected environment offers authorized users a dedicated, centralized, scalable, and customizable workspace for collaboration on highly confidential or sensitive data with predictable timeframe for completing planned or exploratory analyses.

The Enclave Platform supports cross-institution collaboration (for example: MGB research community and external clinical industry partners) on MGB data or curated data marts. At present, the Enclave platform has several COVID-19 data marts and project-specific databases.

Learn more about Analytics Enclave Resources, Accessing the Enclave, and Enclave Support.

The Windows Analysis Servers are large-memory computers with a variety of free and commercial scientific applications installed. Running your data analysis in a remote desktop on these servers is easy, using Microsoft Remote Desktop. Some files may be stored locally on the server and for additional storage space they can connect to other network file shares at Partners. LINK TO STORAGE, APP

Typical Uses

• Statistical analysis, spreadsheets and charting 
• Data visualization

Supported methods of connecting to the servers 

• Microsoft Remote Desktop Connection
• Network file share (SMB/CIFS) for data transfer

Getting an account?

• Use the registration form