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:20230124T171526Z
LOCATION:C143-149
DTSTART;TZID=America/Chicago:20221113T084000
DTEND;TZID=America/Chicago:20221113T091000
UID:submissions.supercomputing.org_SC22_sess426_misc198@linklings.com
SUMMARY:Invited Talk: In Situ Inference of Machine Learning Models through
  Remote Procedure Calls
DESCRIPTION:Workshop\n\nInvited Talk: In Situ Inference of Machine Learnin
 g Models through Remote Procedure Calls\n\nBoyer, Brewer, Jude, Dettwiller
 \n\nMachine learning (ML) has become ubiquitous within the sciences due to
  its ability to perform a wide array of tasks which add value within tradi
 tional workflows. These models can provide advanced data analytics through
  dimensionality reduction, pattern recognition, and clustering.  For large
 -scale simulations, post hoc data analysis requires writing and reading la
 rge quantities of data, which can severely limit the rate. In situ analysi
 s can reduce the frequency and quantity of data written to disk but requir
 es the integration of simulations with ML methods, which poses a software 
 development challenge. In this talk, we will present an approach to integr
 ating simulations with ML models through an inference server and remote pr
 ocedure calls (RPCs).  By separating the machine learning into one or more
  independent processes, the inference calls can be made within drop-in fun
 ctions using RPCs with minimal modifications to the existing code and can 
 be scaled across parallel processes with MPI. While the deep learning plat
 form, TensorFlow, is typically considered a Python tool, RPCs can couple a
  TensorFlow model server with applications written in a wide variety of la
 nguages. We will demonstrate the computational efficiency and scalability 
 of the approach across a series of use cases, such as deploying machine-le
 arned surrogate models in simulations and enabling ML super-resolution in 
 visualization tools.\n\nSession Format: Recorded\n\nTag: Accelerator-based
  Architectures, Data Analytics, In Situ Processing, Scientific Computing, 
 Visualization, Workflows\n\nRegistration Category: Workshop Reg Pass
END:VEVENT
END:VCALENDAR