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:20211207T054807Z
LOCATION:227-228
DTSTART;TZID=America/Chicago:20211117T143000
DTEND;TZID=America/Chicago:20211117T150000
UID:submissions.supercomputing.org_SC21_sess146_pap212@linklings.com
SUMMARY:Enabling and Scaling the HPCG Benchmark on the Newest Generation S
 unway Supercomputer with 42 Million Heterogeneous Cores
DESCRIPTION:Paper\n\nEnabling and Scaling the HPCG Benchmark on the Newest
  Generation Sunway Supercomputer with 42 Million Heterogeneous Cores\n\nZh
 u, Luo, Yang, Ding, Yin...\n\nWe study and evaluate performance optimizati
 on techniques for the HPCG benchmark on the newest generation Sunway super
 computer. Specifically, a two-level blocking scheme is proposed to expose 
 adequate parallelism in the symmetric Gauss-Seidel kernel while keeping a 
 fast convergence rate; a fine-grained kernel fusion technique is developed
  to alleviate the bandwidth load on local storage with small capacity; and
  a low overhead thread collaboration method is presented to efficiently mo
 ve data between threads and hide its cost with data transfer operations. T
 est results show that the optimized HPCG code is able to exploit 73.0% of 
 the theoretical memory bandwidth, and scale to over 42 million heterogeneo
 us cores with 95.5% weak-scaling efficiency and 5.91 PFLOPS performance. W
 e also study how the performance can be improved if the specific rules of 
 HPCG are not fully obeyed, and design dependency-preserving parallelizatio
 n and vectorization methods, further boosting performance to 27.6 PFLOPS.\
 n\nTag: Algorithms, Extreme Scale Computing, Heterogeneous Systems\n\nRegi
 stration Category: Tech Program Reg Pass\n\nAward Finalist: Best Paper Fin
 alist, Best Student Paper Finalists
END:VEVENT
END:VCALENDAR