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:20260422T000712Z
LOCATION:303
DTSTART;TZID=America/Denver:20231113T133000
DTEND;TZID=America/Denver:20231113T170000
UID:submissions.supercomputing.org_SC23_sess234_tut137@linklings.com
SUMMARY:Scalable Big Data Processing on High Performance Computing Systems
DESCRIPTION:Dhabaleswar K. (DK) Panda, Aamir Shafi, and Jinghan Yao (Ohio 
 State University)\n\nThere are several popular Big Data processing framewo
 rks including Apache Spark and Dask. These frameworks are not capable of e
 xploiting high-speed and low-latency networks like InfiniBand, Omni-Path, 
 Slingshot, and others.  In the High Performance Computing (HPC) community,
  the Message Passing Interface (MPI) libraries are widely adopted to tackl
 e this issue by executing scientific and engineering applications on paral
 lel hardware connected via fast interconnect.\n\nThis tutorial introduces 
 MPI4Spark and MPI4Dask that are enhanced Spark and Dask frameworks, respec
 tively, and capable of utilizing MPI for communication in a parallel and d
 istributed setting on HPC systems.  MPI4Spark can launch the Spark ecosyst
 em using MPI launchers to utilize MPI communication. It also maintains iso
 lation for application execution by forking new processes using Dynamic Pr
 ocess Management (DPM). MPI4Spark also provides portability and performanc
 e benefits as it can utilize popular HPC interconnects.  MPI4Dask is an MP
 I-based custom Dask framework that is targeted for modern HPC clusters bui
 lt with CPU and NVIDIA GPUs.\n\nThis tutorial provides a detailed overview
  of the design, implementation, and evaluation of MPI4Spark and MPI4Dask o
 n state-of-the-art HPC systems. Later, we also cover writing, running, and
  demonstrating user Big Data applications on HPC systems.\n\nTag: Architec
 ture and Networks, Data Movement and Memory, Message Passing\n\nRegistrati
 on Category: Tutorial Reg Pass\n\n
END:VEVENT
END:VCALENDAR