
NSF Org: |
CNS Division Of Computer and Network Systems |
Recipient: |
|
Initial Amendment Date: | September 11, 2018 |
Latest Amendment Date: | September 11, 2018 |
Award Number: | 1828593 |
Award Instrument: | Standard Grant |
Program Manager: |
Marilyn McClure
mmcclure@nsf.gov (703)292-5197 CNS Division Of Computer and Network Systems CSE Directorate for Computer and Information Science and Engineering |
Start Date: | October 1, 2018 |
End Date: | September 30, 2021 (Estimated) |
Total Intended Award Amount: | $1,504,396.00 |
Total Awarded Amount to Date: | $1,504,396.00 |
Funds Obligated to Date: |
|
History of Investigator: |
|
Recipient Sponsored Research Office: |
4111 MONARCH WAY STE 204 NORFOLK VA US 23508-2561 (757)683-4293 |
Sponsor Congressional District: |
|
Primary Place of Performance: |
VA US 23508-2561 |
Primary Place of
Performance Congressional District: |
|
Unique Entity Identifier (UEI): |
|
Parent UEI: |
|
NSF Program(s): | Major Research Instrumentation |
Primary Program Source: |
|
Program Reference Code(s): |
|
Program Element Code(s): |
|
Award Agency Code: | 4900 |
Fund Agency Code: | 4900 |
Assistance Listing Number(s): | 47.070 |
ABSTRACT
This project acquires a reconfigurable computing system that wiil support a broad spectrum of research projects in an appropriately tailored computer environment using state-of the-art technologies. It offers substantial computational power to support a number of critical research initiatives at the institution.
This infrastructure, named DISCOVER, enables big data and high-performance computing research. Three key thrusts are emphasized: Cybersecurity, Resilience, and Data Intensive Science and Engineering. Each thrust includes multiple applications, as follows.
Cybersecurity: hardware security for cryptographic circuit verification; modeling learning with homomorphic encryption; malware and anomaly detection; and modeling cyber-attack paths and their mitigation.
Resilience: computational simulations to model sea level rise; understanding social media for emergency preparedness for natural disasters; and data-driven understanding of massive geospatial traffic patterns.
Data Intensive Science and Engineering: high-accuracy finite element mesh generation; analysis of brain imaging and image-guided surgery; and modelling of power-consumption and resource allocation for high-performance computing clusters.
The acquired computing system will stimulate multi-disciplinary collaborations with other institutions in Hampton Roads, including Norfolk State University, Tidewater Community College, and Thomas Nelson Community College. Training workshops and a summer institute will be organized to help students in various research fields to gain high-performance computing skills. The insitution will leverage the National Initiative for Cybersecurity Education (NICE) framework to address cyber workforce needs by increasing the pipeline of students pursuing cybersecurity careers.
This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
PROJECT OUTCOMES REPORT
Disclaimer
This Project Outcomes Report for the General Public is displayed verbatim as submitted by the Principal Investigator (PI) for this award. Any opinions, findings, and conclusions or recommendations expressed in this Report are those of the PI and do not necessarily reflect the views of the National Science Foundation; NSF has not approved or endorsed its content.
This project acquires a reconfigurable high-performance computing (HPC) infrastructure, named Wahab, to support three interdisciplinary and collaborative science and engineering research initiatives, i.e., cybersecurity, resilience, and data-intensive science and engineering, that are crucial to the long-term sustainability of the Old Dominion University (ODU), the City of Norfolk, and the Hampton Roads region. The initiatives are interdisciplinary in nature, aiming to form consortia of leading scholars and weave together disparate threads of programmatic and facility resources in Hampton Roads to develop sound and effective solutions. The initiatives heavily utilize computation, modeling, and/or large amounts of data, leading to surging demand for diverse and reconfigurable computing resources. As a result, the researchers in the University and Hampton Roads region are currently facing several fundamental challenges. Many ongoing research endeavors under the new initiatives do not have access to sufficient and/or suitable computing facilities. The problem is exacerbated due to the interdisciplinary nature of these new initiatives, where a research project often involves a diverse group of researchers in need of various types of computing resources to accomplish their goals. While national HPC infrastructures are available, they are difficult to adapt to agile and newly fledged collaborations and to reconfigure to the research needs at hand. Past experiences also show insufficient training resources, resulting in a steep learning curve, especially for interdisciplinary teams without HPC expertise.
Wahab effectively supports the critical initiatives at ODU and Hampton Roads. Presently, Wahab consists of over 6200 CPU cores, 72 NVIDIA Volta GPUs, about 60 TB aggregated memory, and 350 TB scratch space (an existing 2 PB storage for home and long-term data directory is also connected to Wahab). It provides ample computational power to support the new research initiatives as well as the projected growth of usage for at least five years from the time it is acquired. It is reconfigurable to effectively support a broad spectrum of research projects in a rightly-tailored computing environment using state-of-the-art technologies. A web-based user portal has been deployed as a convenient single point of entry to all resources at Wahab. It allows users to manage their data and workloads, submit resource allocation requests, perform interactive computation and data analyses. The portal lowers the steep learning curve of the traditional HPC interface, particularly from domains where the adoption of HPC has been very low. It becomes a platform that the researchers visit to not only run their programs but also interact with their project team members and other peer researchers. To further reduce the learning curve for entry-level users and advise researchers on how to maximize their productivity, ODU has dramatically expanded the support services related to Wahab, including extensive documentation, learning resources, user forum, office hours, and regular training events. From 2019 through 2021, the Wahab cluster has directly benefited 67 faculty and researchers (including collaborators), 313 graduate and undergraduate students, and 32 short-term guest users during the project period. Through ODU?s participation with the Open Science Grid since 2021, Wahab has contributed about 5 million CPU core hours to the US open science community.
The new cluster enhances and complements the existing computing resources available at ODU and Hampton Roads, substantially expanding and enhancing the regional capabilities to conduct leading-edge research. It contributes to improving the quality and effectiveness of faculty research and career development. It strengthens research consortia and various local and national collaborations, leading to multidisciplinary projects involving equipment users from different science and engineering fields. It greatly enhances curriculum development for multiple majors, minors, and certificate programs and enables a range of exciting outreach activities. ODU is a minority-serving institution. The PIs are committed to the mission of inspiring and improving the participation of underrepresented groups, as well as military service personnel, veterans, and their affiliates. The PIs also work with regional consortia to support workforce development.
Last Modified: 01/26/2022
Modified by: Hongyi Wu
Please report errors in award information by writing to: awardsearch@nsf.gov.