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:20210402T160545Z
LOCATION:Poster Module
DTSTART;TZID=America/New_York:20201119T083000
DTEND;TZID=America/New_York:20201119T170000
UID:submissions.supercomputing.org_SC20_sess337_rpost119@linklings.com
SUMMARY:Enabling Faster NGS Analysis on Optane-Based Heterogeneous Memory
DESCRIPTION:Posters, Research Posters\n\nEnabling Faster NGS Analysis on O
 ptane-Based Heterogeneous Memory\n\nLuo, Guo, Ren, Wu, Li\n\nNext-Generati
 on Sequencing (NGS) analysis technologies are a pioneering approach for ge
 nome sequencing. The computation of NGS analysis exhibits a unique pattern
 , in which the execution requests a high density of small I/Os in the proc
 ess de novo genome assembly. The small I/Os can have a huge impact on perf
 ormance and delineate sequencing performance. To solve the problem caused 
 by small I/Os, we leverage the byte-addressable feature of emerging persis
 tent memory, which has largely transformed the computation architectures o
 f HPC. We first conduct experiments to study the impact of persistent memo
 ry on NGS analysis. Furthermore, we propose an optimization mechanism, whi
 ch converts POSIX read/write calls to pure memory LOAD/STORE instructions 
 at runtime, to significantly advance I/O efficiency. Our evaluation demons
 trates the effectiveness of the devised optimization mechanism, in which w
 e achieve a performance improvement of 31%.\n\nRegistration Category: Tech
  Program Reg Pass, Exhibits Reg Pass
END:VEVENT
END:VCALENDAR