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:20260522T150127Z
LOCATION:C141/143/149
DTSTART;TZID=America/Chicago:20181115T133000
DTEND;TZID=America/Chicago:20181115T150000
UID:submissions.supercomputing.org_SC18_sess192@linklings.com
SUMMARY:Resilience 3: GPUs
DESCRIPTION:Fault Tolerant One-Sided Matrix Decompositions on Heterogeneou
 s Systems with GPUs\n\nCurrent algorithm-based fault tolerance (ABFT) appr
 oach for one-sided matrix decomposition on heterogeneous systems with GPUs
  have following limitations: (1) they do not provide sufficient protection
  as most of them only maintain checksum in one dimension; (2) their checki
 ng scheme is not efficient ...\n\n\nJieyang Chen, Hongbo Li, Sihuan Li, an
 d Xin Liang (University of California, Riverside); Panruo Wu (University o
 f Houston); Dingwen Tao (University of Alabama); Kaiming Ouyang, Yuanlai L
 iu, and Kai Zhao (University of California, Riverside); Qiang Guan (Kent S
 tate University); and Zizhong Chen (University of California, Riverside)\n
 ---------------------\nOptimizing Software-Directed Instruction Replicatio
 n for GPU Error Detection\n\nApplication execution on safety-critical and 
 high-performance computer systems must be resilient to transient errors. A
 s GPUs become more pervasive in such systems, they must supplement ECC/par
 ity for major storage structures with reliability techniques that cover mo
 re of the GPU hardware logic.  In...\n\n\nAbdulrahman Mahmoud (University 
 of Illinois) and Siva Kumar Sastry Hari, Michael B. Sullivan, Timothy Tsai
 , and Stephen W. Keckler (Nvidia Corporation)\n---------------------\nPRIS
 M: Predicting Resilience of GPU Applications Using Statistical Methods\n\n
 As Graphics Processing Units (GPUs) become more pervasive in HPC and safet
 y-critical domains, ensuring that GPU applications can be protected from d
 ata corruption grows in importance. Despite prior efforts to mitigate erro
 rs, we still lack a clear understanding of how resilient these application
 s ar...\n\n\nCharu Kalra, Fritz Previlon, and Xiangyu Li (Northeastern Uni
 versity); Norman Rubin (Nvidia Corporation); and David Kaeli (Northeastern
  University)\n\nTag: Algorithms, Architectures, GPUs, Linear Algebra, Netw
 orks, Resiliency\n\nRegistration Category: Tech Program Reg Pass\n\nSessio
 n Chair: Steven A. Wright (University of York, England)
END:VEVENT
END:VCALENDAR