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:20250626T233527Z
LOCATION:B302-B305
DTSTART;TZID=America/New_York:20241120T100000
DTEND;TZID=America/New_York:20241120T170000
UID:submissions.supercomputing.org_SC24_sess533_post209@linklings.com
SUMMARY:A Zero-Copy Storage with Metadata-Driven File Management Using Per
 sistent Memory
DESCRIPTION:Guangxing Hu (North Carolina State University), Awais Khan (Oa
 k Ridge National Laboratory (ORNL)), and Frank Mueller (North Carolina Sta
 te University)\n\nPersistent Memory (PM) is a promising next-generation st
 orage device, combining features of both volatile memory (like DRAM) and n
 on-volatile memory (like SSDs). Many studies use PM to optimize training t
 o advance deep learning technology. However, these studies have not addres
 sed the issue of multiple copies of training data during deep learning, le
 ading to reduced training efficiency. In this study, we first analyze the 
 characteristics of PM and mainstream file systems. We then explore PM's by
 te addressability to manage metadata and data efficiently. This approach m
 inimizes multiple I/O operations of tasks involving repeated read-write da
 ta accesses, such as machine learning datasets, enabling zero-copy data ha
 ndling and significant speedups of read-and-write operations.\n\nRegistrat
 ion Category: Tech Program Reg Pass, Exhibits Reg Pass\n\nSession Chairs: 
 Ayesha Afzal (Friedrich-Alexander University, Erlangen-Nuremberg; Erlangen
  National High Performance Computing Center); Sally Ellingson (University 
 of Kentucky); and Alan Sussman (University of Maryland)\n\n
END:VEVENT
END:VCALENDAR