BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20190719T085753Z
LOCATION:HG F 3
DTSTART;TZID=Europe/Stockholm:20190613T141500
DTEND;TZID=Europe/Stockholm:20190613T161500
UID:submissions.pasc-conference.org_PASC19_sess130@linklings.com
SUMMARY:MS30 - Mapping Parallel Scientific Applications onto Complex Archi
 tectures Portably and Efficiently
DESCRIPTION:Minisymposium\nComputer Science and Applied Mathematics\n\nUti
 lity Thread Interface: A System-Wide Resource Management Framework for Hel
 per/Compute Threads\n\nTakagi, Gerofi, Pedretti, Riesen\n\nThe processor a
 nd memory structure in HPC system is getting more and more complex. For ex
 ample, tens of cores and a memory module comprises a NUMA-node, and some o
 f them are connected by network-on-chip. Cores in one NUMA-node could
  even be divided into two types, i.e. those dedicated to s...\n\n----
 -----------------\nmpipin: Towards Portable Process Pinning for MPI Applic
 ations\n\nGerofi\n\nAs architectural complexity of node resources in high-
 performance computing (HPC) keeps increasing, topology aware process place
 ment becomes utmost important for efficiently utilizing the underlying har
 dware. Although most MPI implementations provide interfaces to control pro
 cess placement, existing...\n\n---------------------\nCross-Architecture A
 ffinity for Exascale Computing\n\nLeon, Hautreux\n\nTo reach exascale comp
 uting, vendors are developing complex systems that include many-core techn
 ologies, hybrid machines with throughput-optimized cores and latency-optim
 ized cores, and multiple levels of memory. The complexity involved in extr
 acting the performance benefits these systems offer chal...\n\n-----------
 ----------\nA Supercomputer OS Approach to Affinity\n\nRiesen\n\nThe multi
 -OS for HPC at Intel Corp. has been specifically designed for extreme scal
 e HPC systems. It employs lightweight kernel technology that enabled the b
 reaking of the teraflops barrier in the 1990s and combines it with a moder
 n Linux kernel. While Linux compatibility is crucial in today's super...\n
END:VEVENT
END:VCALENDAR