BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Drupal//recurring_events_ical//2.0//EN
BEGIN:VEVENT
UID:1d305b06-8f29-4914-a994-093e5cdb1174@support.access-ci.org
DTSTAMP:20251121T121331Z
DTSTART:20260212T190000Z
DTEND:20260212T203000Z
SUMMARY:Batch Computing: Working with the Linux Scheduler
DESCRIPTION:SummaryUnderstanding what a scheduler is and how it works is fu
 ndamental to learning how to run your batch computing workloads on high-pe
 rformance computing (HPC) systems well. A scheduler manages all aspects of
  how your application will access and consume the compute, memory, storage
 , I/O, and network resources available to you on these systems. There are 
 a number of different distributed batch job schedulers — also sometimes 
 referred to as workload or resource managers — that you might encounter 
 on an HPC system. For example, the Slurm Workload Manager is the most popu
 lar one in use today on HPC systems. However, at the core of every such sy
 stem sits the Linux scheduler. In this first part of our series on Batch 
 Computing, we will introduce you to the concept of a scheduler — what th
 ey are, why they exist, and how they work — using the Linux scheduler as
  our reference implementation and testbed. You will then learn how to inte
 ract with the Linux scheduler on your personal computer by running a serie
 s of example exercises intended to teach you about the most fundamental as
 pects of scheduling, including turning foreground processes into backgroun
 d ones and controlling their priority relative to the other processes runn
 ing on your system. To complete the exercises covered in Part I, you will
  need access to a computer with either:a Linux operating system (OS)a Unix
 -like OS such as macOSa Linux-compatible OS environment such as the Window
 s Subsystem for Linuxa virtual machine running a Linux OS through a hyperv
 isor like VirtualBox.InstructorMarty Kandes a Computational and Data Scien
 ce Research Specialist in the High-Performance Computing User Services Gro
 up at SDSC. He currently helps manage user support for Comet — SDSC’s 
 largest supercomputer. Marty obtained his Ph.D. in Computational Science i
 n 2015 from the Computational Science Research Center at San Diego State U
 niversity, where his research focused on studying quantum systems in rotat
 ing frames of reference through the use of numerical simulation. He also h
 olds an M.S. in Physics from San Diego State University and B.S. degrees i
 n both Applied Mathematics and Physics from the University of Michigan, An
 n Arbor. His current research interests include problems in Bayesian stati
 stics, combinatorial optimization, nonlinear dynamical systems, and numeri
 cal partial differential equations.See a complete list of SDSC's upcoming 
 training and events here.--- COMPLECS (COMPrehensive Learning for end-use
 rs to Effectively utilize CyberinfraStructure) is a new SDSC program where
  training will cover non-programming skills needed to effectively use supe
 rcomputers. Topics include parallel computing concepts, Linux tools and ba
 sh scripting, security, batch computing, how to get help, data management 
 and interactive computing. Each session offers 1 hour of instruction follo
 wed by a 30-minute Q&A. COMPLECS is supported by NSF award 2320934.
URL:https://support.access-ci.org/events/8711
END:VEVENT
END:VCALENDAR