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:20211207T054757Z
LOCATION:220-221
DTSTART;TZID=America/Chicago:20211116T110000
DTEND;TZID=America/Chicago:20211116T113000
UID:submissions.supercomputing.org_SC21_sess154_pap458@linklings.com
SUMMARY:FastZ: Accelerating Gapped Whole Genome Alignment on GPUs
DESCRIPTION:Paper\n\nFastZ: Accelerating Gapped Whole Genome Alignment on 
 GPUs\n\nGundabolu, Vijaykumar, Thottethodi\n\nRecognizing the importance o
 f whole genome alignment (WGA), the National Institutes for Health maintai
 ns LASTZ, a sequential WGA application. As genomic data grows, there is a 
 compelling need for scalable, high-performance WGA. Unfortunately, high-se
 nsitivity, ‘gapped’ alignment which uses dynamic programming (DP) is slow,
  whereas faster alignment with ungapped filtering is often less sensitive.
  We develop FastZ, a GPU-accelerated, gapped WGA software which matches ga
 pped LASTZ in sensitivity. FastZ employs a novel inspector-executor scheme
  in which (a) the lightweight inspector elides DP traceback except in comm
 on, extremely short alignments, where the inspector performs limited, eage
 r traceback to eliminate the executor, and (b) executor trimming avoids un
 necessary work. Further, FastZ employs register-based cyclic-buffering to 
 drastically reduce memory traffic, and groups DP problems by size for load
  balance. FastZ running on an RTX 3080 GPU and our multicore implementatio
 n of LASTZ achieve 111x and 20x speedups over the sequential LASTZ, respec
 tively.\n\nTag: Applications, Computational Science\n\nRegistration Catego
 ry: Tech Program Reg Pass
END:VEVENT
END:VCALENDAR