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:20210402T160104Z
LOCATION:Track 2
DTSTART;TZID=America/New_York:20201119T110000
DTEND;TZID=America/New_York:20201119T113000
UID:submissions.supercomputing.org_SC20_sess151_pap571@linklings.com
SUMMARY:Scaling the Hartree-Fock Matrix Build on Summit
DESCRIPTION:Paper\n\nScaling the Hartree-Fock Matrix Build on Summit\n\nBa
 rca, Poole, Galvez Vallejo, Alkan, Bertoni...\n\nUsage of Graphics Process
 ing Units (GPU) has become strategic for simulating the chemistry of large
  molecular systems, with many top supercomputers utilizing GPUs as their m
 ain source of computational horsepower. In this paper, a new fragmentation
 -based Hartree-Fock matrix build algorithm designed for scaling on many-GP
 U architectures is presented. The new algorithm uses a novel dynamic load 
 balancing scheme based on a binned shell-pair container to distribute batc
 hes of significant shell quartets with the same code path to different GPU
 s. This maximizes computational throughput and load balancing, and elimina
 tes GPU thread divergence due to integral screening. Additionally, the cod
 e uses a novel Fock digestion algorithm to contract electron repulsion int
 egrals into the Fock matrix, which exploits all forms of permutational sym
 metry and eliminates thread-synchronization requirements. The implementati
 on demonstrates excellent scalability on the Summit computer, achieving go
 od strong scaling performance up to 4096 nodes, and linear weak scaling up
  to 612 nodes.\n\nTag: Applications, Scalable Computing\n\nRegistration Ca
 tegory: Tech Program Reg Pass
END:VEVENT
END:VCALENDAR