BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250316T231109Z
LOCATION:B306
DTSTART;TZID=America/New_York:20241122T110000
DTEND;TZID=America/New_York:20241122T113000
UID:submissions.supercomputing.org_SC24_sess767_ws_ftxs103@linklings.com
SUMMARY:Octopus: Experiences with a Hybrid Event-Driven Architecture for D
 istributed Scientific Computing
DESCRIPTION:Workshop\n\nHaochen Pan (University of Chicago); Ryan Chard (A
 rgonne National Laboratory (ANL)); Sicheng Zhou and Alok Kamatar (Universi
 ty of Chicago); Rafael Vescovi (Argonne National Laboratory (ANL)); Valeri
 e Hayot-Sasson, André Bauer, and Maxime Gonthier (University of Chicago); 
 and Kyle Chard and Ian Foster (University of Chicago, Argonne National Lab
 oratory (ANL))\n\nScientific research increasingly relies on distributed c
 omputational resources, storage systems, networks, and instruments, rangin
 g from HPC and cloud systems to edge devices. Event-driven architecture (E
 DA) benefits applications targeting distributed research infrastructures b
 y enabling the organization, communication, processing, reliability, and s
 ecurity of events generated from many sources. To support the development 
 of scientific EDA, we introduce Octopus, a hybrid, cloud-to-edge event fab
 ric designed to link many local event producers and consumers with cloud-h
 osted brokers. Octopus can be scaled to meet demand, permits the deploymen
 t of highly available triggers for automatic event processing, and enforce
 s fine-grained access control. We identify requirements in self-driving la
 boratories, scientific data automation, online task scheduling, epidemic m
 odeling, and dynamic workflow management use cases, and present results de
 monstrating Octopus’ ability to meet those requirements. Octopus supports 
 producing and consuming events at a rate of over 4.2 M and 9.6 M events pe
 r second, respectively, from distributed clients.\n\nTag: Distributed Comp
 uting, Fault-Tolerance, Reliability, Maintainability, and Adaptability\n\n
 Registration Category: Workshop Reg Pass\n\nSession Chairs: John Daly (US 
 Department of Defense), Bo Fang (Pacific Northwest National Laboratory (PN
 NL)), Scott Levy (Sandia National Laboratories), and Keita Teranishi (Oak 
 Ridge National Laboratory (ORNL))
END:VEVENT
END:VCALENDAR