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:20260422T000713Z
LOCATION:702
DTSTART;TZID=America/Denver:20231113T111800
DTEND;TZID=America/Denver:20231113T114200
UID:submissions.supercomputing.org_SC23_sess449_ws_pawatm103@linklings.com
SUMMARY:Design and Analysis of the Network Software Stack of an Asynchrono
 us Many-Task System – The LCI Parcelport of HPX
DESCRIPTION:Jiakun Yan (University of Illinois), Hartmut Kaiser (Louisiana
  State University), and Marc Snir (University of Illinois)\n\nThe HPX asyn
 chronous many-task runtime system has been using TCP and MPI as its commun
 ication backends (parcelports). We developed a new HPX parcelport using a 
 new communication library, the Lightweight Communication Interface (LCI) t
 hat was designed to better match the needs of systems such as HPX. We eval
 uate its performance with various microbenchmarks and a real-world astroph
 ysics application, Octo-Tiger. Compared to the best configuration of the M
 PI parcelport, microbenchmarks show that the new LCI parcelport improves t
 he message rate by up to 30x and decreases latencies by up to 5x. It also 
 reduces the total execution time of Octo-Tiger by up to 1.175x compared to
  the best configuration of the MPI parcelport and up to 13.6x compared to 
 the same configuration of the MPI parcelport. We discuss the performance i
 mpacts of different design choices.\n\nTag: Accelerators, Artificial Intel
 ligence/Machine Learning, Algorithms, Applications, Architecture and Netwo
 rks, Distributed Computing, Compilers, Data Analysis, Visualization, and S
 torage, Exascale, Heterogeneous Computing, Linear Algebra, Message Passing
 , Performance Optimization, Programming Frameworks and System Software, Qu
 antum Computing, Runtime Systems, Software Engineering, Sustainability, Ta
 sk Parallelism, Tensors\n\nRegistration Category: Workshop Reg Pass\n\nSes
 sion Chairs: Engin Kayraklioglu (Hewlett Packard Enterprise (HPE)), Daniel
 e Lezzi (Barcelona Supercomputing Center (BSC)), Bill Long (Retired), Karl
 a Vanessa Morris Wright (Sandia National Laboratories), Irene Moulitsas (C
 ranfield University), and Elliott Slaughter (SLAC National Accelerator Lab
 oratory)\n\n
END:VEVENT
END:VCALENDAR
