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:20260422T000711Z
LOCATION:601
DTSTART;TZID=America/Denver:20231113T170000
DTEND;TZID=America/Denver:20231113T173000
UID:submissions.supercomputing.org_SC23_sess458_ws_mtsa103@linklings.com
SUMMARY:Dynamic Memory Provisioning on Disaggregated HPC Systems
DESCRIPTION:Felippe Zacarias (Universitat Politècnica de Catalunya, Barcel
 ona Supercomputing Center (BSC)); Paul Carpenter (Barcelona Supercomputing
  Center (BSC)); and Vinicius Petrucci (Micron Technology Inc)\n\nDisaggreg
 ated memory intends to break the rigid boundaries between node memory hier
 archies by providing memory as a pooled resource. The resource manager all
 ocates system’s memory at job’s submission time. But it is hard for users 
 to know the job's precise peak memory footprint, and prior work has shown 
 users have an incentive to overestimate. It leads to significant overalloc
 ation, and most of the physical memory in the system is wasted. We present
  a way to reclaim much of this overallocated memory. We extend the Slurm j
 ob scheduler to dynamically reallocate memory, according to the job’s curr
 ent memory footprint. We enhance an existing Slurm simulator to model this
  situation and combine publicly available traces to model an HPC system on
  up to 1490 nodes. We show that dynamic memory provisioning approach incre
 ases the throughput per dollar by up to 38%, compared to a system with sta
 tic allocation of disaggregated memory.\n\nTag: Applications, Architecture
  and Networks, Data Movement and Memory, Heterogeneous Computing, I/O and 
 File Systems, Large Scale Systems, Middleware and System Software, Perform
 ance Measurement, Modeling, and Tools, Performance Optimization\n\nRegistr
 ation Category: Workshop Reg Pass\n\nSession Chairs: Tyler Allen (NVIDIA),
  Ron Brightwell (Sandia National Laboratories), Maya Gokhale (Lawrence Liv
 ermore National Laboratory (LLNL)), and Ivy Peng (KTH Royal Institute of T
 echnology)\n\n
END:VEVENT
END:VCALENDAR