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:20260422T000616Z
LOCATION:401-402
DTSTART;TZID=America/Denver:20231114T153000
DTEND;TZID=America/Denver:20231114T170000
UID:submissions.supercomputing.org_SC23_sess179@linklings.com
SUMMARY:GPU Middleware and System Software
DESCRIPTION:Scalable Tuning of (OpenMP) GPU Applications via Kernel Record
  and Replay\n\nHPC is a heterogeneous world in which host and device code 
 are interleaved throughout the application. Given the significant performa
 nce advantage of accelerators, device code execution time is becoming the 
 new bottleneck. Tuning the accelerated parts is consequently highly desira
 ble but often impra...\n\n\nKonstantinos Parasyris and Giorgis Georgakoudi
 s (Lawrence Livermore National Laboratory (LLNL)), Esteban Rangel (Argonne
  National Laboratory (ANL)), and Ignacio Laguna and Johannes Doerfert (Law
 rence Livermore National Laboratory (LLNL))\n---------------------\nInterf
 erence-Aware Multiplexing for Deep Learning in GPU Clusters: A Middleware 
 Approach\n\nA common strategy for improving efficiency in training deep le
 arning entails multiplexing tasks on a single GPU. To mitigate the interfe
 rence caused by multiplexing, existing approaches primarily employ kernel-
 level solutions to regulate GPU kernel execution, or harness hardware-leve
 l techniques to ...\n\n\nWenyan Chen (University of Macau; Shenzhen Instit
 ute of Advanced Technology, Chinese Academy of Sciences); Zizhao Mo and Hu
 anle Xu (University of Macau); Kejiang Ye (Shenzhen Institute of Advanced 
 Technology, Chinese Academy of Sciences); and Chengzhong Xu (University of
  Macau)\n---------------------\nHPAC-Offload: Accelerating HPC Application
 s with Portable Approximate Computing on the GPU\n\nThe end of Dennard sca
 ling and the slowdown of Moore's law led to a shift in technology trends t
 oward parallel architectures, particularly in HPC systems. To continue pro
 viding performance benefits, HPC should embrace Approximate Computing (AC)
 , which trades application quality loss for improved per...\n\n\nZane Fink
  (Lawrence Livermore National Laboratory (LLNL), University of Illinois) a
 nd Konstantinos Parasyris, Giorgis Georgakoudis, and Harshitha Menon (Lawr
 ence Livermore National Laboratory (LLNL))\n\nTag: Accelerators, Distribut
 ed Computing, Middleware and System Software, Performance Measurement, Mod
 eling, and Tools, Post-Moore Computing\n\nRegistration Category: Tech Prog
 ram Reg Pass\n\nAward Finalist: Best Paper Finalist\n\nReproducibility Bad
 ges: Artifact Available, Artifact Functional, Results Reproduced\n\nSessio
 n Chair: Hari Subramoni (The Ohio State University)
END:VEVENT
END:VCALENDAR