BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20211207T055352Z
LOCATION:Online
DTSTART;TZID=America/Chicago:20211114T090000
DTEND;TZID=America/Chicago:20211114T173000
UID:submissions.supercomputing.org_SC21_sess326@linklings.com
SUMMARY:HPCSysPros21 Workshop
DESCRIPTION:Workshop\n\nHPCSysPros21\n\nBlaas, Enos\n\nThe complexity of h
 igh-performance computing (HPC) systems necessitates advanced techniques i
 n system administration, configuration and engineering and (by proxy), sta
 ff well-versed on the best practices in this field. HPC systems profession
 als include system engineers, system administrators, networ...\n\n--------
 -------------\nKubernetes with Open OnDemand Using Kyverno\n\nDockendorf\n
 \nKubernetes with Open OnDemand using Kyverno (Lightning talk)<br /><br />
 Supporting Kubernetes through Open OnDemand presents many challenges with 
 regard to safely allowing users to run applications inside Kubernetes in a
  similar manner to how jobs would run in an High Performance Computing bat
 ch env...\n\n---------------------\nOpen Discussion\n\nBlaas\n\nOpen discu
 ssion time in which we have some conversation on any pain points in the co
 mmunity as well as the sharing of success stories either at a home institu
 te or in a collaboration with other sites.\n\n---------------------\nLight
 ning Talk: Storing of Secrets for Retrieval by Configuration Management\n\
 nKing\n\nWe were storing secrets in a private git repository that has secu
 rity implications. Admins that would be working on a Puppet control reposi
 tory would also have the secrets local to their systems even if the secret
  is encrypted.\n\nUsing Vault by Hashicorp with Consul as encrypted storag
 e. This use’s P...\n\n---------------------\nLightning Talk: Chameleon Clo
 ud\n\nSherman\n\nChameleon cloud and how to leverage it to test and evalua
 te new hardware platforms and architectures.\n\n---------------------\nHPC
 SysPros21:  Afternoon Break (3-3:30)\n\n\n\n---------------------\nKuberne
 tes for HPC Administration\n\nKnight\n\nHPC software stacks require admini
 strators to deploy and maintain a complex collection of software. Historic
 ally this was done on bare-metal nodes, which present challenges when main
 taining a coherent suite of software. This paper describes hosting adminis
 trative HPC software on a Kubernetes platfor...\n\n---------------------\n
 Closing Remarks\n\nHough\n\nClosing remarks and Traxler Family Award for C
 ommunity Service\n\n---------------------\nEnabling Research and Education
  through the Geddes Composable Platform\n\nGough, Werts, Weekly, Smith\n\n
 The Geddes Composable Platform is an on-premise Kubernetes-based private c
 loud at Purdue University and was designed to meet the increased demand fo
 r the deployment of flexible, persistent, edge and supporting services for
  scientific data analysis and to promote "SciOps", the application of DevO
 ps p...\n\n---------------------\nOpening Remarks\n\nBlaas\n\nOpening rema
 rks for the SIGHPC SYSPROS workshop at SC21.\n\n---------------------\nOok
 ami – The First Year of a Computing Technology Testbed\n\nSiegmann, Harris
 on\n\nOokami [1] is a computing technology testbed funded by NSF (grant OA
 C 1927880). It provides researchers worldwide with free access to Fujitsu 
 A64FX compute nodes. Those are the same as in the world’s current fa
 stest machine, Fugaku at the RIKEN supercomputing center in Japan. The mot
 ivation be...\n\n---------------------\nHPCSysPros21:  Lunch Break (12:30-
 2)\n\n\n\n---------------------\nHPCSysPros21:  Morning Break (10-10:30)\n
 \n\n\n---------------------\nBenchmarking Panel\n\nNam, Kelly, Bauer, Ferr
 ell\n\nFor this panel we will spend an hour talking about benchmarking on 
 HPC resources and the infrastructure behind them. We will discuss how to s
 elect the right benchmarks to use, when to benchmark your resources, and h
 ow to improve or remedy performance degradation.\n\n---------------------\
 nTechnical Underpinnings of Azure HPC & AI Supercomputing\n\nBurness\n\nTh
 is talk will provide an overview of Azure HPC & AI supercomputing architec
 tures, their technical underpinnings and capabilities for large scale HPC 
 workloads, and how Azure distributes and supports these resources globally
  to support one of the largest customer and user bases in the world.\n\n\n
 Tag: Online Only, SIGHPC, State of the Practice, System Administration\n\n
 Registration Category: Workshop Reg Pass
END:VEVENT
END:VCALENDAR