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:20181221T160908Z
LOCATION:D166
DTSTART;TZID=America/Chicago:20181111T090000
DTEND;TZID=America/Chicago:20181111T173000
UID:submissions.supercomputing.org_SC18_sess174@linklings.com
SUMMARY:Workshop on Exascale MPI (ExaMPI)
DESCRIPTION:Workshop\nExascale, Networks, System Software, Workshop Reg Pa
 ss\n\nWorkshop Afternoon Break\n\n\n\n---------------------\nWorkshop Lunc
 h (on your own)\n\n\n\n---------------------\nIntroduction - Workshop on E
 xascale MPI (ExaMPI)\n\nGrant, Skjellum, Bangalore, Holmes\n\nThe aim of w
 orkshop is to bring together researchers and developers to present and dis
 cuss innovative algorithms and concepts in the Message Passing programming
  model and to create a forum for open and potentially controversial discus
 sions on the future of MPI in the Exascale era. Possible workshop ...\n\n-
 --------------------\nExaMPI Panel\n\nGrant\n\n---------------------\nTree
 -Based Fault-Tolerant Collective Operations for MPI\n\nMargolin\n\nWith th
 e increase in size and complexity of high-performance computing systems, t
 he probability of failures and the cost of recovery grow. Parallel applica
 tions running on these systems should be able to continue running in spite
  of node failures at arbitrary times. Collective operations are essenti...
 \n\n---------------------\nWorkshop Morning Break\n\n\n\n-----------------
 ----\nOptimal Algorithms for Half-Duplex Inter-Group All-to-All Broadcast 
 on Fully Connected and Ring Topologies\n\nKang, Choudhary, Agrawal, Liao\n
 \nHalf-duplex inter-group collective communications are bipartite message 
 transfer patterns such that the processes in a sender group pass messages 
 to the processes in a receiver group. These communication patterns serve a
 s basic operations for scientific application workflows. In this paper, we
  prese...\n\n---------------------\nAnycast: Rootless Broadcasting with MP
 I\n\nLi, Koziol, Tang, Byna\n\nFlexible communication routines that enable
  high-performance computing (HPC) applications to operate with less synchr
 onization are a great benefit to application algorithm creation and develo
 per productivity.  Further, communication operations that reduce synchroni
 zation in HPC applications while co...\n\n---------------------\nAITuning:
  Machine Learning-Based Tuning Tool for Run-Time Communication Libraries\n
 \nFanfarillo, Del Vento\n\nIn this work, we address the problem of tuning 
 communication libraries by using a deep reinforcement learning approach.  
 Reinforcement learning is a machine learning technique incredibly effectiv
 e in solving game-like situations.  In fact, tuning a set of parameters in
  a communication library in ord...\n\n---------------------\nA Novel Appro
 ach to Supporting Communicators for In-Switch Processing of MPI Collective
 s\n\nStern, Herbordt\n\nMPI collective operations can often be performance
  killers in HPC applications, and we seek to solve this bottleneck by offl
 oading them to switch hardware. We've seen from previous works including o
 ur own that moving collectives into the network offers significant perform
 ance benefits. However, ther...\n\n---------------------\nExaMPI Invited T
 alk\n\nBrightwell\n\n---------------------\nExaMPI Keynote\n\nHoefler\n\n-
 --------------------\nUnderstanding the Usage of MPI in Exascale Proxy App
 lications\n\nSultana\n\nThe Exascale Computing Project (ECP) focuses on th
 e development of future exascale-capable applications. Most ECP applicatio
 ns use the Message Passing Interface (MPI) as their parallel programming m
 odel and create mini-apps to serve as proxies. This paper explores the exp
 licit usage of MPI in ECP pr...\n
END:VEVENT
END:VCALENDAR

