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:20260422T143039Z
LOCATION:B311
DTSTART;TZID=America/New_York:20241118T090000
DTEND;TZID=America/New_York:20241118T123000
UID:submissions.supercomputing.org_SC24_sess755@linklings.com
SUMMARY:Programming and Performance Visualization Tools
DESCRIPTION:Understanding program behavior is critical to overcome the exp
 ected architectural and programming complexities, such as limited power bu
 dgets, heterogeneity, hierarchical memories, shrinking I/O bandwidths, and
  performance variability, that arise on modern HPC platforms. To do so, HP
 C software developers need intuitive support tools for debugging, performa
 nce measurement, analysis, and tuning of large-scale HPC applications. Mor
 eover, data collected from these tools such as hardware counters, communic
 ation traces, and network traffic can be far too large and too complex to 
 be analyzed in a straightforward manner. We need new automatic analysis an
 d visualization approaches to help application developers intuitively unde
 rstand the multiple, interdependent effects that algorithmic choices have 
 on application correctness or performance. This workshop brings together H
 PC application developers, tool developers, and researchers from the visua
 lization, performance, and program analysis fields for an exchange of new 
 approaches to assist developers in analyzing, understanding, and optimizin
 g programs for extreme-scale platforms.\n\nPerformance Measurement on Hete
 rogeneous Processors with PAPI\n\nModern computer processors improve their
  computing power by having multiple cores. Traditionally these cores were 
 homogeneous: many identical cores with the same capabilities. Instead it i
 s possible to create processors that have heterogeneous (or hybrid) cores,
  where the various cores have differin...\n\n\nVincent Weaver and Willow C
 unningham (University of Maine)\n---------------------\nChallenges and Opp
 ortunities for Tools in a Changing HPC Landscape\n\nHPC is undergoing prof
 ound changes as AI workloads reshape hardware architectures, directly impa
 cting software development. This shift has led to increased diversity in s
 oftware stacks, with higher-level languages and new parallel programming i
 nterfaces emerging. In this evolving landscape, we aim t...\n\n\nJean-Bapt
 iste Besnard (ParaTools, Inc.)\n---------------------\nOverhead-Guided Ins
 trumentation Refinement\n\nInstrumentation is a widely used technique for 
 gathering performance data.\nHowever, excessive instrumentation can lead t
 o significant runtime overheads, potentially skewing performance analysis 
 results.\nIn this work, we propose a novel approach to automatically gener
 ate and refine instrumentation co...\n\n\nSebastian Kreutzer, Peter Arzt, 
 and Jonas Rickert (Technical University Darmstadt); Jan-Patrick Lehr (Tech
 nical University Darmstadt; AMD, Inc.); and Christian Iwainsky and Christi
 an Bischof (Technical University Darmstadt)\n---------------------\nAnalyz
 ing HPC Utilization with PIKA and Vampir\n\nWe present a set of tools to s
 upport analysis of the utilization of high performance computing (HPC) res
 ources by extending PIKA, a site-level monitoring tool, and Vampir, a well
 -known performance analysis tool. We show an approach to transforming site
 -level data into a form that Vampir (and other a...\n\n\nBill Williams (Te
 chnical University Dresden); Maximilian Knespel and Frank Winkler (Technic
 al University Dresden, ZIH); and Bert Wesarg (Technical University Dresden
 , ZIH; GWT-TUD GmbH)\n---------------------\nAn Incremental Multi-Level, M
 ulti-Scale Approach to Assessment of Multifidelity HPC Systems\n\nWith the
  growing complexity in architecture and the size of large-scale computing 
 systems, monitoring and analyzing system behavior and events has become da
 unting. Monitoring data amounting to terabytes per day are collected by se
 nsors housed in these massive systems at multiple fidelity levels and ...\
 n\n\nShilpika Shilpika, Bethany Lusch, and Venkatram Vishwanath (Argonne N
 ational Laboratory (ANL)) and Michael Papka (Argonne National Laboratory (
 ANL), University of Illinois Chicago)\n---------------------\nMorning Brea
 k\n---------------------\nAre Noise-Resilient Logical Timers Useful for Pe
 rformance Analysis?\n\nIn modern HPC systems, performance measurements are
  often disturbed by noise.\nBecause repeating measurements to increase con
 fidence in their results is costly, alternative noise-resilient techniques
  are desirable. \nTherefore, we implement a logical clock, which does not 
 rely on real-time measurement...\n\n\nGregor Corbin, Nour Daoud, and Bernd
  Mohr (Forschungszentrum Jülich) and Gustavo de Morais and Felix Wolf (Tec
 hnical University Darmstadt)\n---------------------\nP-MOVE: Performance M
 onitoring and Visualization with Encoded Knowledge\n\nP-MoVE is a modern, 
 open-source framework designed to monitor and visualize live and/or record
 ed performance data with the ultimate goal of being a digital twin for HPC
  systems. Leveraging a Knowledge Base (KB), built upon an HPC-specific ont
 ology with an intuitive encoding for comprehending the per...\n\n\nFatih T
 aşyaran (Sabanci University); Osman Yasal (Koc University); José A. Morgad
 o and Aleksandar Ilic (INESC-ID, University of Lisbon); Didem Unat (Koc Un
 iversity); and Kamer Kaya (Sabanci University)\n---------------------\nWel
 come\n\nKate Isaacs (University of Utah) and David Boehme (Lawrence Liverm
 ore National Laboratory (LLNL))\n---------------------\nInspection of I/O 
 Operations from System Call Traces using Directly-Follows-Graph\n\nWe aim 
 to identify the differences in Input/Output (I/O) behavior between multipl
 e user programs through the inspection of system calls (i.e., requests mad
 e to the operating system). A typical program issues a large number of I/O
  requests to the operating system, thereby making the process of inspec...
 \n\n\nAravind Sankaran, Ilya Zhukov, and Wolfgang Frings (Forschungszentru
 m Jülich) and Paolo Bientinesi (Umea Universitet, Sweden)\n---------------
 ------\nActorProf: A Framework for Profiling and Visualizing Fine-grained 
 Asynchronous Bulk Synchronous Parallel Execution\n\nA Fine-grained Asynchr
 onous Bulk Synchronous Parallel (FA-BSP) model is an extended version of t
 he existing BSP model that facilitates fine-grained asynchronous point-to-
 point messages with automatic message aggregation. \n\nWhile there are man
 y large irregular applications written with the FA-BSP mod...\n\n\nJiawei 
 Yang, Shubhendra Pal Singhal, Jun Shirako, Akihiro Hayashi, and Vivek Sark
 ar (Georgia Institute of Technology)\n\nTag: Debugging and Correctness Too
 ls, Performance Evaluation and/or Optimization Tools\n\nRegistration Categ
 ory: Workshop Reg Pass\n\nSession Chairs: David Boehme (Lawrence Livermore
  National Laboratory (LLNL)); Kate Isaacs (University of Utah); Carmen Nav
 arrete (Leibniz Supercomputing Centre (LRZ)); and Emmanuelle Saillard (CEA
 , DAM, DIF)
END:VEVENT
END:VCALENDAR