Map U-M Data Science Space
To be announced
Advanced Research Computing (ARC), a division of ITS, is pleased to offer a pilot called Scientific Computing and Research Consulting Services to help researchers implement data analytics and workflows within their research projects. This includes navigating technical resources like high-performance computing and storage.
The ARC Scientific Computing and Research Consulting Services team will be your guide to navigating the complex technical world: from implementing intense data projects, to teaching you how the technical systems work, to assist in identifying proper tools, to guiding you on how to hire a programmer.
The ARC Scientific Computing and Research Consulting Services team works in partnership with the Consulting for Statistics, Computing, and Analytics Research team (CSCAR), Biomedical Research Core Facilities, and others. ARC may refer or engage complimentary groups as required by the project.
Send an email to arc-consulting@umich.edu with the following information:
If you have any questions or wish to setup a consult, please contact us at arc-consulting@umich.edu. Be sure to include as much information as possible from the “Get started” section noted above.
If you have more general questions about ARC services or software please contact us at arc-support@umich.edu
Virtual office hours are also available on Tuesdays, Wednesdays, and Thursdays. Get help with machine learning, algorithms, modeling, coding, computing on a cluster, survey sampling, using records across multiple surveys, and more. Anyone doing any type of research at any skill level is welcome!
We are available to assist researchers along the entire lifecycle of the data workflow, from the conceptual stage to ingest, preprocessing, cleansing, and storage solutions. We can advise in the following areas:
The data science consulting team can assist with data analytics to support research:
Machine learning is an application of artificial intelligence (AI) that focuses on the development of computer programs to learn information from data.
We are available to consult on the following. This includes a general overview of concepts, discussion into what tools and architectures best fit your needs, or technical support on implementation.
| Language | Tools/Architectures | Models |
|---|---|---|
| Python | Python data tools (scikit, numpy, etc) | Neural networks |
| C++ | TensorFlow | Decision trees |
| Java | Jupyter notebooks | Support vector machines |
| Matlab |
We also provide consulting on programming in a variety of programming languages (including but not limited to: C++, Java, and Python) to support your data science needs. We can assist in algorithm design and implementation, as well as optimizing and parallelizing code to efficiently utilize high performance computing (HPC) resources where possible/necessary. We can help identify available commercial and open-source software packages to simplify your data analysis.
If you have any questions or wish to setup a consult please contact us at arcts-consulting@umich.edu
The Cavium/ThunderX Hadoop Cluster has been shut down.
The Cavium/ThunderX Hadoop Cluster was a next-generation Hadoop cluster available to U-M researchers. It was an on-campus resource that holds 3PB of storage for researchers to approach and analyze data science problems. The cluster consisted of 40 servers each containing 96 ARMv8 cores and 512GB of RAM per server. It was made possible through a partnership with Marvell.
What should I use instead of the Cavium/ThunderX Hadoop Cluster?
Cavium/ThunderX users are recommended to transition to the Great Lakes High Performance Computing Cluster. Visit the Great Lakes page for details and account creation instructions.
If you are not familiar with the U-M Research Computing Package, please check to see if your work is eligible for a no-cost allocation of compute resources.
If you used Spark or PySpark on Cavium/ThunderX, try the web-based Jupyter Notebook application on Great Lakes that provides Spark integration. Spark is available under the menu “Interactive Apps” > “Jupyter + Spark Basic.”
If you prefer running Spark batch jobs from the terminal rather than from a Jupyter Notebook, ARC has the Spark on HPC project that will demonstrate how to run a Spark cluster from a Slurm job.
The Twitter datasets have been made available on Great Lakes. Additional details about Twitter datasets are in the getting started guide.
For assistance or questions, please contact ARC at arc-support@umich.edu.
For other topics, contact the ITS Service Center:
New requests are not being accepted at this time because the Cavium/ThunderX Hadoop Cluster was shut down on August 1, 2022. Contact ARC if you need assistance, arc-support@umich.edu.
The Yottabyte Research Cloud, powered by Verge.io, is a partnership between the ITS and Yottabyte that provides U-M researchers with high-performance, secure, and flexible computing environments enabling the analysis of sensitive data sets restricted by federal privacy laws, proprietary access agreements, or confidentiality requirements.
Yottabyte (Blue) will retire on April 4, 2022. Yottabyte (Maize) for sensitive data will continue to be offered as a service. You can determine if your virtual server is hosted in ‘Blue’ if the hostname has ‘blue’ in its name, such as ‘yb-hostname.blue.ybrc.umich.edu.’
A member of the ARC Yottabyte team or someone from your unit will reach out to you to determine your needs and help you develop migration plans.
ARC’s Yottabyte (Blue) provides U-M researchers with high-performance, secure, and flexible computing environments through the following services:
Yottabyte (Blue) will retire on April 4, 2022. Yottabyte (Maize) for sensitive data will continue to be offered as a service.
Check your virtual server name to confirm that your virtual server is hosted in YBRC ‘Blue’ (the hostname has ‘blue’ in its name, such as ‘yb-hostname.blue.ybrc.umich.edu’).
The YBRC ‘Blue’ services are underutilized making it difficult to build an affordable service with its current and projected user base.
Researchers who are using these YBRC ‘Blue’ services for their work can leverage other services provided by Information & Technology Services. See below as possible replacements:
| If you’re currently using: | Try one of these services: |
| YBRC (Blue) Research Database Hosting | MiDatabase |
| Docker Container Service | MCloud Kubernetes Container Service |
| Virtual Desktops for Research | MiServer |
Please note: The above-mentioned services provided by ITS (MiDatabase, MCloud Kubernetes Service, and MiServer) all have costs associated with use.
If you are not currently using or not planning to use your virtual machine, please let ARC know that machine can be decommissioned by sending us an email at arc-support@umich.edu. You can then remove your data as soon as feasible to prevent a rush leading up to Monday, April 4, 2022.
If you are currently using your machine, a member of your Unit IT group or a member of the ARC staff will reach out to you regarding the decommissioning of your system and work with you for alternate hosting options.
The system is built on Yottabyte’s composable, software-defined infrastructure platform called Cloud Composer, and represents U-M’s first use of software-defined infrastructure for research, allowing the on-the-fly personalized configuration of any-scale computing resources.
Cloud Composer software inventories the physical CPU, RAM and storage components of Cloud Blox appliances into definable and configurable virtual resource groups that may be used to build multi-tenant, multi-site infrastructure as a service.
See the September 2016 press release for more information.
The YBRC platform can accommodate sensitive institutional data classified up to High — including CUI — as identified in the Sensitive Data Guide.
The Yottabyte Research Cloud supports the following platforms for researchers at the University of Michigan:
The following Services are deprecated in the current implementation of YBRC, and will not be replicated in future versions of the ARC Private Cloud environment. We are not taking new customers for any of these services.
Researchers who need to use Hadoop or Spark for data-intensive work should explore ARC’s separate Hadoop cluster.
Contact arc-support@umich.edu for more information.
The system deploys 40 high performance Hyper-converged YottaBlox nodes (H2400i-E5), each consisting of two, Intel Xeon E5-2680V4 CPU (1,120 cores total), 512GB DDR4 2400MHz RAM (20,480GB total), dual port 40GbE network adapters (80 total) and (2) 800GB NVMe SSD DC P3700 drives (64TB); and 20 storage YottaBlox nodes (S2400i-E5-HDD), each consisting of two, Intel Xeon E5-2620V4 CPU (320 cores total), 128 GB DDR4 2133MHz RAM (2,560 GB total), quad port 10GbE network adapters (80 total), (2) 800 GB DC S3610 SSD (32 TB total) and 12 x 6 TB 7200 RPM (1,440TB total).
These tools are offered to all researchers at the University of Michigan free of charge, provided that certain usage restrictions are not exceeded. Large-scale users who outgrow the no-cost allotment may purchase additional YBRC resources. All interested parties should contact arcts-support@umich.edu.
The U-M Research Ethics and Compliance webpage on Controlled Unclassified Information provides details on handling this type of data. The U-M Sensitive Data Guide to IT Services is a comprehensive guide to sensitive data.
The Yottabyte Research Cloud (YBRC) is the University’s private cloud environment for research. It’s a collection of processors, memory, storage, and networking that can be subdivided into smaller units and allocated to research projects on an as-needed basis to be accessed by virtual machines and containers.
Access to Yottabyte Research Cloud resources involves a single email to us at arcts-support@umich.edu. Please include:
Someone from your unit IT staff or an ARC staff member will reach out to you and arrange details to determine the best path to make your request work within the Yottabyte Cloud environment.
Yottabyte Research Cloud resources are aimed squarely at research and the teaching and training of students involved in research. Primarily, Yottabyte resources are for sponsored research. Yottabyte Research Cloud is not for administrative or clinical use (business of the university or the hospital). Clinical research is acceptable as long as it is sponsored research.
In total, Yottabyte Research Cloud (YBRC) has 960 processing cores for each Yottabyte cluster, 7.5 Terabytes, and roughly 330 TB of scratch storage available in Maize and Blue each.
Yottabyte resources are divided up between two clusters of computing and storage. Maize YBRC is for restricted data analyses and storage, and Blue YBRC is for unrestricted data analyses and storage.
The initial offering of YBRC is focused on a few different types of use cases:
No! Contact us at arcts-support@umich.edu if you want to learn whether or not your idea can be done within YBRC!
The best way to get help is to send an email to arcts-support@umich.edu with a brief description of the issues you are seeing.
Yottabyte is supported between the hours of 9 a.m. to 5 p.m. Monday through Friday. Response times for support outside of these hours will be longer.
Because of the way that YBRC divides up resources, the largest Virtual Machine within the cluster is 12 processing cores, and 96 GB of RAM.
ARC policy is to limit no-cost individual allocations to 100 cores, so that access is always open to multiple research groups.
If you need to use more than 100 cores of YBRC, we recommend that you purchase YBRC physical infrastructure of your own and add it to the cluster. Physical infrastructure can be purchased in 96 physical core chunks, which can be oversubscribed as memory allows. For every block purchased, the researcher will also receive 4 years of hardware and OS support for that block in the case of failure. For a cost estimate of buying your own blocks of infrastructure and adding to the cluster, please email arcts-support@umich.edu.
Scratch storage for Yottabyte Research Cloud is the storage area network that OS storage and active data storage on the local virtual machines that are not actively being backed up or replicated to a separate infrastructure. Like the scratch storage on Flux, we don’t recommend storing any data solely on the local disk of any machines. Make sure that you have backups on other machines, like Turbo, Locker, or some other service.
For researchers with restricted data with a HIPAA classification, we provide a small menu of Linux and Windows workstations to be installed within your enclave. We do not delegate administrative rights for those workstations to researchers or research staff. We may delegate administrative rights for workstations and services in your enclaves to IT staff in your unit who have successfully completed the HIPAA IT training coursework given by ITS or HITS, and are familiar with desktop and virtual machine environments.
Machines in the HIPAA network enclaves are encircled by a deny first firewall that prevents most traffic from entering the enclaves. Researchers can still visit external-to-campus websites from within a HIPAA network enclave. Researchers within a HIPAA network enclave can use storage services such as Turbo and MiStorage Silver (via CIFS) to host data for longer-term storage.
All researchers, staff, and students that use YBRC when analyzing restricted data have a shared responsibility in keeping their restricted data secure.
Staff will work with researchers using CUI-classified data to determine the types of analysis that can be conducted on YBRC resources that comply with relevant regulations.
All researchers, staff, and students that use YBRC when analyzing restricted data have a shared responsibility in keeping their restricted data secure.
ConFlux is a cluster that seamlessly combines the computing power of HPC with the analytical power of data science. The next generation of computational physics requires HPC applications (running on external clusters) to interconnect with large data sets at run time. ConFlux provides low latency communications for in- and out- of-core data, cross-platform storage, as well as high throughput interconnects and massive memory allocations. The file-system and scheduler natively handle extreme-scale machine learning and traditional HPC modules in a tightly integrated work flow—rather than in segregated operations—leading to significantly lower latencies, fewer algorithmic barriers and less data movement.
The ConFlux cluster is built with ~58 IBM Power8 CPU two-socket “Firestone” S822LC compute nodes providing 20 cores in each. Seventeen Power8 CPU two-socket “Garrison” S822LC compute nodes provide an additional 20 cores and host four NVIDIA Pascal GPUs connected via NVIDIA’s NVLink technology to the Power8 system bus. Each GPU based node has a local high-speed NVMe flash memory for random access.
All compute and storage is connected via a 100Gb/s InfiniBand fabric. The IBM and NVLink connectivity, combined with IBM CAPI Technology provide an unprecedented data transfer throughput required for the data-driven computational physics researchers will be conducting.
ConFlux is funded by a National Science Foundation grant; the Principal Investigator is Karthik Duraisamy, Assistant Professor of Aerospace Engineering and Director of the Center for Data-Driven Computational Physics (CDDCP). ConFlux and the CDDCP are under the auspices of the Michigan Institute for Computational Discovery and Engineering.
ARC is a division of ITS
