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:20260522T150116Z
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 Afternoon Break\n---------------------\nIntroduction 
 - Workshop on Exascale MPI (ExaMPI)\n\nThe aim of workshop is to bring tog
 ether researchers and developers to present and discuss innovative algorit
 hms and concepts in the Message Passing programming model and to create a 
 forum for open and potentially controversial discussions on the future of 
 MPI in the Exascale era. Possible workshop ...\n\n\nRyan E. Grant (Sandia 
 National Laboratories); Anthony Skjellum (University of Tennessee, Chattan
 ooga); Purushotham V. Bangalore (University of Alabama, Birmingham); and D
 aniel Holmes (University of Edinburgh)\n---------------------\nA Novel App
 roach to Supporting Communicators for In-Switch Processing of MPI Collecti
 ves\n\nMPI collective operations can often be performance killers in HPC a
 pplications, and we seek to solve this bottleneck by offloading them to sw
 itch hardware. We've seen from previous works including our own that movin
 g collectives into the network offers significant performance benefits. Ho
 wever, ther...\n\n\nJoshua Stern and Martin Herbordt (Boston University)\n
 ---------------------\nExaMPI Panel\n\nRyan E. Grant (Sandia National Labo
 ratories)\n---------------------\nWorkshop Morning Break\n----------------
 -----\nWorkshop Lunch (on your own)\n---------------------\nExaMPI Invited
  Talk\n\nRon Brightwell (Sandia National Laboratories)\n------------------
 ---\nExaMPI Keynote\n\nTorsten Hoefler (ETH Zurich)\n---------------------
 \nAnycast: Rootless Broadcasting with MPI\n\nFlexible communication routin
 es that enable high-performance computing (HPC) applications to operate wi
 th less synchronization are a great benefit to application algorithm creat
 ion and developer productivity.  Further, communication operations that re
 duce synchronization in HPC applications while co...\n\n\nTonglin Li, Quin
 cey Koziol, Houjun Tang, and Suren Byna (Lawrence Berkeley National Labora
 tory)\n---------------------\nUnderstanding the Usage of MPI in Exascale P
 roxy Applications\n\nThe Exascale Computing Project (ECP) focuses on the d
 evelopment of future exascale-capable applications. Most ECP applications 
 use the Message Passing Interface (MPI) as their parallel programming mode
 l and create mini-apps to serve as proxies. This paper explores the explic
 it usage of MPI in ECP pr...\n\n\nNawrin Sultana (Auburn University)\n----
 -----------------\nOptimal Algorithms for Half-Duplex Inter-Group All-to-A
 ll Broadcast on Fully Connected and Ring Topologies\n\nHalf-duplex inter-g
 roup collective communications are bipartite message transfer patterns suc
 h that the processes in a sender group pass messages to the processes in a
  receiver group. These communication patterns serve as basic operations fo
 r scientific application workflows. In this paper, we prese...\n\n\nQiao K
 ang, Alok Choudhary, Ankit Agrawal, and Wei-keng Liao (Northwestern Univer
 sity)\n---------------------\nAITuning: Machine Learning-Based Tuning Tool
  for Run-Time Communication Libraries\n\nIn this work, we address the prob
 lem of tuning communication libraries by using a deep reinforcement learni
 ng approach.  Reinforcement learning is a machine learning technique incre
 dibly effective in solving game-like situations.  In fact, tuning a set of
  parameters in a communication library in ord...\n\n\nAlessandro Fanfarill
 o and Davide Del Vento (National Center for Atmospheric Research)\n-------
 --------------\nTree-Based Fault-Tolerant Collective Operations for MPI\n\
 nWith the increase in size and complexity of high-performance computing sy
 stems, the probability of failures and the cost of recovery grow. Parallel
  applications running on these systems should be able to continue running 
 in spite of node failures at arbitrary times. Collective operations are es
 senti...\n\n\nAlexander Margolin (Hebrew University of Jerusalem)\n\nTag: 
 Exascale, MPI, Networks, System Software\n\nRegistration Category: Worksho
 p Reg Pass\n\nSession Chairs: Purushotham Bangalore (University of Alabama
 ); Ryan Grant (Queen's University, Canada; Power API); Daniel Holmes (Coll
 is-Holmes Innovations); and Anthony Skjellum (Tennessee Technological Univ
 ersity, ASCEND-TNTECH)
END:VEVENT
END:VCALENDAR