BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260924T172348Z
LOCATION:B309
DTSTART;TZID=America/New_York:20241119T153000
DTEND;TZID=America/New_York:20241119T170000
UID:submissions.supercomputing.org_SC24_sess401@linklings.com
SUMMARY:Parallel Program Analysis and Code Optimization
DESCRIPTION:MCFuser: High-performance and Rapid-fusion of Memory-bound Com
 pute-intensive Operators\n\nOperator fusion enhances data locality and red
 uces GPU memory bandwidth pressure. but struggles with multiple compute-in
 tensive operators due to saturated computation throughput. The variability
  in tensor sizes can make these operators memory-bound, necessitating effi
 cient fused kernel generation, c...\n\n\nZheng Zhang (Wuhan University Sch
 ool of Computer Science); Donglin Yang (NVIDIA Corporation); Xiaobo Zhou (
 University of Macau, Department of Computer and Information Sciences); and
  Dazhao Cheng (Wuhan University School of Computer Science)\n-------------
 --------\nStatic Generation of Efficient OpenMP Offload Data Mappings\n\nI
 ncreasing heterogeneity in HPC architectures and compiler advancements hav
 e led to OpenMP being frequently used to enable computations on heterogene
 ous devices. However, the efficient movement of data on heterogeneous comp
 uting platforms is crucial for achieving high utilization. Programmers mus
 t e...\n\n\nLuke Marzen, Akash Dutta, and Ali Jannesari (Iowa State Univer
 sity)\n---------------------\nHiRace: Accurate and Fast Data-Race Checking
  for GPU Programs\n\nData races are egregious concurrency bugs that are es
 pecially problematic in performance-oriented GPU codes where large thread 
 counts and multiple shared memory regions tend to exacerbate them. In this
  work, we present a new dynamic data-race checker called HiRace, whose key
  novelty is an innovative...\n\n\nJohn Jacobson (University of Utah), Mart
 in Burtscher (Texas State University), and Ganesh Gopalakrishnan (Universi
 ty of Utah)\n\nTag: Accelerators, Compilers, Heterogeneous Computing, Perf
 ormance Evaluation and/or Optimization Tools\n\nRegistration Category: Tec
 h Program Reg Pass\n\nSession Chair: Sascha Hunold (Technical University o
 f Vienna)
END:VEVENT
END:VCALENDAR
