[Eecs_mscs] EECS Research Seminar Talk-Task-based Runtime for High-Performance Computing Applications at Extreme-Scale

[Hunter, Tiffany]

EECS Research Seminar Talk
Dr. Qinglei Cao
Task-based Runtime for High-Performance Computing Applications at Extreme-Scale
Monday, April 17, 2023
11:45 am - 12:45 pm
Academic and Research Center (ARC) 315
And Microsoft Teams

Bio:
Qinglei Cao received his PhD in computer science from the Innovative Computer Laboratory (ICL) of the University of Tennessee, Knoxville (UTK), advised by Prof. Jack Dongarra (Turing Award, 2021) in August 2022. After graduation, he worked for five months at Cerebras Systems (an AI chip startup company). Right now, he serves as Post-Doctoral Research Associate at ICL. His research interests involve high-performance computing (HPC), linear algebra, task-based runtime systems, and large-scale machine learning. He has published many papers in top-rated journals and conferences in the HPC field, including SC, TPDS, IPDPS, PARCO, CLUSTER, PASC, CCGRID, etc. Moreover, one of his first-authored papers was a finalist for the ACM Gordon Bell Prize 2022.

Talk Abstract:
The last decades have witnessed a rapid improvement of computational capabilities in high-performance computing (HPC) platforms thanks to hardware technology scaling. In the HPC landscape of potentially million-way parallelism, task-based programming models associated with dynamic runtime systems have gained popularity as a potential candidate to address the programming complexity in the era of exascale computing. In this context, my research highlights how a software bundle powered by a task-based programming model can handle the heterogeneous workloads engendered by HPC applications. The proposed software scales on multiple supercomputers, including AMD-based (Hawk at HLRS), Intel-based (Shaheen II at KAUST), ARM-based (Fugaku at RIKEN) CPU systems, and IBM-based multi-GPU system (Summit at ORNL). This multidisciplinary work emphasizes the need for runtime systems to go beyond their primary responsibility of task scheduling on massively parallel hardware systems for servicing the next-generation scientific applications.


________________________________________________________________________________
Microsoft Teams meeting
Join on your computer, mobile app or room device
Click here to join the meeting<https://teams.microsoft.com/l/meetup-join/19%3ameeting_MzM0MDA0ZTctZDZmZi00MjMxLTg3MDUtZDE3MmI4ZjNkNDFj%40thread.v2/0?context=%7b%22Tid%22%3a%22f3308007-477c-4a70-8889-34611817c55a%22%2c%22Oid%22%3a%22685c3f4f-29d5-4141-ada5-0fdeab8480e4%22%7d>
Meeting ID: 215 311 615 279
Passcode: 5tE6Zk
Download Teams<https://www.microsoft.com/en-us/microsoft-teams/download-app> | Join on the web<https://www.microsoft.com/microsoft-teams/join-a-meeting>
Or call in (audio only)
+1 614-706-6572,,527570069#<tel:+16147066572,,527570069#>   United States, Columbus
Phone Conference ID: 527 570 069#
Find a local number<https://dialin.teams.microsoft.com/8f5f7319-0053-4423-a154-4f8b6e7fb7dd?id=527570069> | Reset PIN<https://dialin.teams.microsoft.com/usp/pstnconferencing>
[https://www.ohio.edu/sites/default/files/2018-11/invite_logo_teams.jpg]
If you encounter issues with this meeting, please visit the Help link. If you are not able to resolve the problems, please contact the meeting organizer to let them know you are having difficulty.
Learn More<https://aka.ms/JoinTeamsMeeting> | Help<https://www.ohio.edu/oit/services/collaboration/teams/help> | Meeting options<https://teams.microsoft.com/meetingOptions/?organizerId=685c3f4f-29d5-4141-ada5-0fdeab8480e4&tenantId=f3308007-477c-4a70-8889-34611817c55a&threadId=19_meeting_MzM0MDA0ZTctZDZmZi00MjMxLTg3MDUtZDE3MmI4ZjNkNDFj@thread.v2&messageId=0&language=en-US>
________________________________________________________________________________

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listserv.ohio.edu/pipermail/eecs_mscs/attachments/20230413/e67b5bad/attachment.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: text/calendar
Size: 10732 bytes
Desc: not available
URL: <http://listserv.ohio.edu/pipermail/eecs_mscs/attachments/20230413/e67b5bad/attachment.ics>