BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260724T151407Z
LOCATION:Bldg. 6 - 102
DTSTART;TZID=Europe/Stockholm:20260701T090000
DTEND;TZID=Europe/Stockholm:20260701T110000
UID:submissions.pasc-conference.org_PASC26_sess152@linklings.com
SUMMARY:MS4D - Performance through Co-Design: Toward Trustworthy, Reproduc
 ible, and Scalable Exascale Workflows
DESCRIPTION:Access the recording\n\nOrganizer(s): Ali Mohammed, Utz-Uwe Ha
 us (HPE), Florina Ciorba (University of Basel), Marta Garcia (Barcelona Su
 percomputing Center), and Sarah Neuwirth (Johannes Gutenberg University Ma
 inz)\n\nExascale systems expand the frontier for simulation-driven discove
 ry, data-centric analytics, and operational digital twins. However, scient
 ific impact depends on more than peak performance. It requires co-design t
 hat aligns architectures, system software, algorithms, workflows, and data
  pathways with domain objectives and scientific validity constraints. This
  minisymposium examines workflow-centric co-design as a key practical stra
 tegy for delivering HPC results that are fast, interpretable, reproducible
 , and dependable at scale. Topics include context-aware performance measur
 ement, I/O and data movement as first-class design concerns, automated pro
 venance capture and FAIR artifact publication, and the resilience and pred
 ictability requirements of digital twin deployments, and others. By connec
 ting time-to-solution with trust-to-solution, the minisymposium aims to su
 rface reusable design patterns and open challenges that must be addressed 
 to translate exascale capability into validated, reusable, and widely trus
 ted science.\n\nLost in Translation: Interpreting Metrics in I/O Performan
 ce Analysis Tools and Benchmarks.\n\nI/O Performance analysis for modern H
 PC systems often involves a diverse ecosystem of tools and benchmarks due 
 to the multiple layers of abstraction in the parallel I/O infrastructure. 
 Despite various advances in instrumentation and benchmarking technology, t
 he resulting measurements rarely provide ...\n\n\nRadita Liem (Johannes Gu
 tenberg University Mainz)\n---------------------\nDestination Earth: Scala
 ble Workflows for Earth System Digital Twins\n\nThe European Commission’s 
 Destination Earth (DestinE) initiative is building digital twins of the Ea
 rth system to support tailored, high-resolution simulations of extreme wea
 ther and climate scenarios. A key enabler of this vision is the Digital Tw
 in Engine, which connects Earth system models,...\n\n\nIoan Hadade, Nils W
 edi, and Balthasar Reuter (ECMWF)\n---------------------\nFrom Execution t
 o FAIR Publication: Automating Artifacts for Reproducible Workflows\n\nCom
 putational science increasingly relies on large, complex workflows to proc
 ess data, explore parameter spaces, and validate hypotheses at scale. As e
 xperiments grow, workflow governance—tracking elements such as configurati
 ons, execution environments, results, and runtime decisions—bec...\n\n\nFr
 ancesc Lordan (Barcelona Supercomputing Center)\n---------------------\nWo
 rkflow-Centric Co-Design for Trustworthy, Agentic Exascale Science\n\nExas
 cale systems enable unprecedented computational power, but scientific impa
 ct depends on workflows that jointly deliver performance, trust, and scala
 bility. This talk presents a workflow-centric co-design perspective in whi
 ch workflows are treated as first-class abstractions for aligning architec
 ...\n\n\nPatrick Widener (Oak Ridge National Laboratory)\n\nDomain: Climat
 e, Weather, and Earth Sciences, Computational Methods and Applied Mathemat
 ics\n\nSession Chairs: Ali Mohammed (HPE), Florina Ciorba (University of B
 asel), and Utz-Uwe Haus (HPE HPC/AI EMEA Research Lab)
END:VEVENT
END:VCALENDAR