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:20260522T150153Z
LOCATION:D174
DTSTART;TZID=America/Chicago:20181116T083000
DTEND;TZID=America/Chicago:20181116T120000
UID:submissions.supercomputing.org_SC18_sess146@linklings.com
SUMMARY:Workshop on Fault-Tolerance for HPC at Extreme Scale (FTXS)
DESCRIPTION:Introduction - Workshop on Fault-Tolerance for HPC at Extreme 
 Scale (FTXS)\n\nAddressing failures in extreme-scale systems remains a sig
 nificant challenge to reaching exascale.  Current projections suggest that
  at the scale necessary to sustain exaflops of computation, systems could 
 experience failures as frequently as once per hour.  As a result, robust a
 nd efficient fault t...\n\n\nNathan DeBardeleben (Los Alamos National Labo
 ratory), Scott Levy and Keita Teranishi (Sandia National Laboratories), an
 d John Daly (Laboratory for Physical Sciences at University of Maryland)\n
 ---------------------\nWorkshop Morning Break\n\nScott Levy (Sandia Nation
 al Laboratories)\n---------------------\nExtending and Evaluating Fault-To
 lerant Preconditioned Conjugate Gradient Methods\n\nWe compare and refine 
 exact and heuristic fault-tolerance extensions for the preconditioned conj
 ugate gradient (PCG) and the split preconditioner conjugate gradient (SPCG
 ) methods for recovering from failures of compute nodes of large-scale par
 allel computers. In the exact state reconstruction (ESR)...\n\n\nCarlos Pa
 chajoa, Markus Levonyak, and Wilfried N. Gansterer (University of Vienna)\
 n---------------------\nAnalyzing the Impact of System Reliability Events 
 on Applications in the Titan Supercomputer\n\nExtreme-scale computing syst
 ems employ Reliability, Availability and Serviceability (RAS) mechanisms a
 nd infrastructure to log events from multiple system components. In this p
 aper, we analyze RAS logs in conjunction with the application placement an
 d scheduling database, in order to understand the ...\n\n\nRizwan A. Ashra
 f and Christian Engelmann (Oak Ridge National Laboratory)\n---------------
 ------\nFault Tolerant Cholesky Factorization on GPUs\n\nDirect Cholesky-b
 ased solvers are typically used to solve large linear systems where the co
 efficient matrix is symmetric positive definite. These solvers offer faste
 r performance in solving such linear systems, compared to other more gener
 al solvers such as LU and QR solvers. In recent days, graphic...\n\n\nFeli
 x Loh, Kewal K. Saluja, and Parameswaran Ramanathan (University of Wiscons
 in)\n---------------------\nInfluence of A-Posteriori Subcell Limiting on 
 Fault Frequency in Higher-Order DG Schemes\n\nSoft error rates are increas
 ing as modern architectures require increasingly small features at low vol
 tages. Due to the large number of components used in HPC architectures, th
 ese are particularly vulnerable to soft errors. Hence, when designing appl
 ications that run for long time periods on large m...\n\n\nAnne Reinarz, J
 ean-Mathieu Gallard, and Michael Bader (Technical University Munich)\n----
 -----------------\nToward Ad Hoc Recovery For Soft Errors\n\nThe coming ex
 ascale era is a great opportunity for high performance computing (HPC) app
 lications. However, high failure rates on these systems will hazard the su
 ccessful completion of their execution. Bit-flip errors in dynamic random 
 access memory (DRAM) account for a noticeable share of the failur...\n\n\n
 Nuria Losada (University of A Coruña, Spain) and Leonardo Bautista-Gomez, 
 Kai Keller, and Osman Unsal (Barcelona Supercomputing Center)\n-----------
 ----------\nCPU Overheating Characterization in HPC Systems: a Case Study\
 n\nWith the increase in size of supercomputers, the number of abnormal eve
 nts also increases. Some of these events might lead to an application fail
 ure. Others might simply impact the system efficiency. CPU overheating is 
 one such event that decreases the system efficiency: when a CPU overheats,
  it red...\n\n\nMarc Platini (University of Grenoble, Atos); Thomas Ropars
  (University of Grenoble); Benoit Pelletier (Atos); and Noël De Palma (Uni
 versity of Grenoble)\n---------------------\nSaNSA - the Supercomputer and
  Node State Architecture\n\nIn this work, we present SaNSA, the Supercompu
 ter and Node State Architecture, a software infrastructure for historical 
 analysis and anomaly detection. SaNSA consumes data from multiple sources 
 including system logs, the resource manager, scheduler, and job logs. Furt
 hermore, additional context such...\n\n\nNeil Agarwal (University of Calif
 ornia, Berkeley) and Hugh Greenberg, Sean Blanchard, and Nathan DeBardeleb
 en (Los Alamos National Laboratory)\n---------------------\nImproving Appl
 ication Resilience by Extending Error Correction with Contextual Informati
 on\n\nExtreme-scale systems are growing in scope and complexity as we appr
 oach exascale. Uncorrectable faults in such systems are also increasing, s
 o resilience efforts addressing these are of great importance. In this pap
 er, we extend a method that augments hardware error detection and correcti
 on (EDAC) ...\n\n\nAlexandra L. Poulos and Dylan E. Wallace (Coastal Carol
 ina University); Robert Robey, Laura Monroe, Vanessa Job, and Sean Blancha
 rd (Los Alamos National Laboratory); William M. Jones (Coastal Carolina Un
 iversity); and Nathan A. DeBardeleben (Los Alamos National Laboratory)\n--
 -------------------\nA Comprehensive Informative Metric for Analyzing HPC 
 System Status Using the LogSCAN Platform\n\nLog processing by Spark and Ca
 ssandra-based ANalytics (LogSCAN) is a newly developed analytical platform
  that provides flexible and scalable data gathering, transformation and co
 mputation. One major challenge is to effectively summarize the status of a
  complex computer system, such as the Titan supe...\n\n\nYawei Hui, Byung 
 Hoon Park, and Christian Engelmann (Oak Ridge National Laboratory)\n\nTag:
  Resiliency, Scientific Computing\n\nRegistration Category: Workshop Reg P
 ass
END:VEVENT
END:VCALENDAR