BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20200129T163556Z
LOCATION:704-706
DTSTART;TZID=America/Denver:20191118T163000
DTEND;TZID=America/Denver:20191118T164500
UID:submissions.supercomputing.org_SC19_sess136_ws_canopie101@linklings.co
 m
SUMMARY:On-Node Resource Manager for Containerized HPC Workloads
DESCRIPTION:Workshop\n\nOn-Node Resource Manager for Containerized HPC Wor
 kloads\n\nVallee, Arango Gutierrez, Clerget\n\nThis document presents a ne
 w containerized architecture to enable fine-grain control over the managem
 ent of on-node resources for complex scientific high-performance workloads
 .  Our approach is introducing a node-local, application-specific resource
  manager by extending a container runtime, which can coordinate with the g
 lobal resource manager, i.e., the system-wide manager that assigns resourc
 es to jobs.  The proposed work is based on the extension of a container ru
 ntime to interface running containers with global resource managers, as we
 ll as the implementation of advanced resource management capabilities to a
 ddress all the running application's needs.\n\nBased on this design, the v
 arious runtimes that are required for the execution of scientific applicat
 ions can interact with the container runtime under which it is running. Th
 is interaction enables the scalable and dynamic allocation of resources ba
 sed on runtime requirements, in opposition to job-level requirements that 
 are traditionally handled by the global resource manager. It also enables 
 fine-grain control over the placement of all processes and threads running
  in a container on specific hardware components, which is critical to achi
 eve performance.\n\nOur approach therefore enables an efficient, scalable,
  dynamic and trackable management of resources on behalf of scientific app
 lications; bridging a gap observed with current solutions.\n\nTag: Worksho
 p Reg Pass, Containers, HPC\n\nRegistration Category: Workshop Reg Pass, C
 ontainers, HPC
URL:https://sc19.supercomputing.org/presentation/?id=ws_canopie101&sess=se
 ss136
END:VEVENT
END:VCALENDAR