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:20230124T171523Z
LOCATION:C148
DTSTART;TZID=America/Chicago:20221114T143000
DTEND;TZID=America/Chicago:20221114T145000
UID:submissions.supercomputing.org_SC22_sess460_ws_pdsw107@linklings.com
SUMMARY:Drishti:  Guiding End-Users in the I/O Optimization Journey
DESCRIPTION:Workshop\n\nDrishti:  Guiding End-Users in the I/O Optimizatio
 n Journey\n\nBez, Ather, Byna\n\nThe complex software and hardware I/O sta
 ck of HPC platforms makes it challenging for end-users to extract performa
 nce and understand the root causes of I/O bottlenecks they encounter. Desp
 ite continuous efforts from the community to profile I/O performance and p
 ropose new optimization techniques and tuning options to improve performan
 ce, there is still a translation gap between profiling and tuning. In this
  paper, we propose Drishti, a solution to guide end-users in optimizing I/
 O in their applications by detecting typical I/O performance pitfalls and 
 providing recommendations. We illustrate its applicability in two case stu
 dies and evaluate its robustness and performance by summarizing the issues
  detected in over a hundred thousand Darshan logs collected by the Nationa
 l Energy Research Scientific Computing Center on the Cori supercomputer. D
 rishti can empower end-users and guide them in the I/O optimization journe
 y by shedding some light on everyday I/O performance pitfalls and how to f
 ix them.\n\nSession Format: Recorded\n\nRegistration Category: Workshop Re
 g Pass
END:VEVENT
END:VCALENDAR