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:20210402T160210Z
LOCATION:Track 7
DTSTART;TZID=America/New_York:20201119T150000
DTEND;TZID=America/New_York:20201119T153000
UID:submissions.supercomputing.org_SC20_sess294_drs102@linklings.com
SUMMARY:Runtime Data Management on Non-Volatile Memory-Based  High Perform
 ance Systems
DESCRIPTION:Doctoral Showcase\n\nRuntime Data Management on Non-Volatile M
 emory-Based  High Performance Systems\n\nWu, Li\n\nNon-volatile memory (NV
 M) is expected to substitute DRAM in the memory hierarchy, due to the stre
 ngths of non-volatility, high density and near-zero standby power. Compare
 d with DRAM, however, NVM as the main memory can be challenging. First, pr
 omising NVM solutions (e.g., PCM, ReRAM and 3D XPoint), although providing
  faster data access speed than storage devices (e.g., hard drive and SSD),
  can have higher latency and lower bandwidth than DRAM. As a result, NVM i
 s often paired with DRAM to build a heterogeneous memory system (HMS). HMS
  must carefully place application data to NVM and DRAM for the best perfor
 mance. Second, ensuring data persistence on NVM is not trivial because oth
 er memory components (e.g., CPU cache) remain volatile and memory writes t
 o NVM are out of order. Programmers need to use assembly instructions
  (e.g., clflush) to explicitly flush data from the cache to NVM, but frequ
 ent cache flushes bring considerable performance overhead to the applicati
 on. My dissertation focuses on using software solutions to address the abo
 ve challenges. First, I present Unimem runtime and Tahoe runtime to effici
 ently and effectively direct data placement on NVM-based HMS for MPI-based
  iterative HPC applications and task-parallel programs, respectively. Seco
 nd, I introduce the Ribbon system, which is a runtime system that improves
  the performance of the cache-line flushing mechanism on NVM to achieve hi
 gh-performance data persistence without modifying the application semantic
 s.\n\nRegistration Category: Tech Program Reg Pass
END:VEVENT
END:VCALENDAR