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:20260605T154541Z
LOCATION:Bldg. 6 - Room 002
DTSTART;TZID=Europe/Stockholm:20260629T160000
DTEND;TZID=Europe/Stockholm:20260629T180000
UID:submissions.pasc-conference.org_PASC26_sess114@linklings.com
SUMMARY:MS2A - Fostering an Exascale-Ready Distributed and Accelerated Den
 se Numerical Linear Algebra Library: The ExaNLA Experience
DESCRIPTION:Organizer(s): Edoardo Di Napoli (Forschungszentrum Jülich)\n\n
 The rapid shift toward GPU-accelerated architectures in current and upcomi
 ng exascale supercomputers has exposed a critical gap in distributed dense
  numerical linear algebra software, particularly within the European HPC e
 cosystem. The deployment of JUPITER, Europe’s first exascale booster, unde
 rscores the absence of a mature NLA library capable of fully exploiting su
 ch massively accelerated systems, creating a significant barrier for both 
 scientific and industrial applications that rely on large-scale linear alg
 ebra. To address this challenge, an international group of experts launche
 d the ExaNLA initiative in 2025 as an open, community-driven effort to def
 ine and guide the development of a next-generation NLA library. ExaNLA bri
 ngs together specialists in numerical analysis, high-performance computing
 , and software engineering to shape a shared technical vision, define core
  functionalities, and promote best practices for scalability, interoperabi
 lity, resilience, and performance portability. Its activities are organize
 d through focused working groups that explore algorithms, programming mode
 ls, benchmarking strategies, and community support. This minisymposium ser
 ves as a platform to present current progress from these working groups an
 d to discuss the future roadmap of the ExaNLA library through invited talk
 s and a panel discussion, fostering broad engagement and collective planni
 ng for the initiative’s next steps.\n\nDense Numerical Linear Algebra (NLA
 ) Under the Microscope: What Scientific Applications Really Need\n\nDense 
 numerical linear algebra (NLA) is a fundamental building block in many sci
 entific applications, supporting simulations, data analysis, and modeling 
 workflows across diverse domains. While significant advances have been mad
 e in algorithms and high-performance implementations, the evolution of N..
 .\n\n\nXinzhe Wu (Jülich Supercomputing Centre) and Edoardo Di Napoli (For
 schungszentrum Jülich)\n---------------------\nPanel Discussion on Needs a
 nd Challenges for the Development of a Distributed and Accelerated Dense N
 umerical Linear Algebra Library\n\nThis session will be an open discussion
  on current developments and future directions in the development of an ex
 ascale-ready distributed and accelerated Numerical Linear Algebra library.
  The focus will be on the existing  challenges and the current and future 
 efforts made by the ExaNLA committee to...\n\n\nXinzhe Wu (Forschungszentr
 um Jülich), Davor Davidovic (Rudger Boskovic Institute), Raffaele Solca (E
 TH Zurich / CSCS), Fabio Affinito (CINECA), and Hartwig Antz (Technical Un
 iversity of Munich)\n---------------------\nPutting Accelerated NLA to the
  Test: A Benchmarking Study of State-of-the-Art Libraries\n\nAs high-perfo
 rmance computing enters the exascale era, numerical linear algebra (NLA) r
 emains a critical performance bottleneck for scientific applications in ma
 terials science, quantum chemistry, and climate modelling. These fields re
 quire NLA solvers capable of efficiently performing operations su...\n\n\n
 Davor Davidović (Rudjer Boskovic Institute)\n---------------------\nThe Ch
 allenge of a Universal Interface for High-Performance and Multiplatforms L
 ow-Level Libraries\n\nHigh-performance numerical libraries remain a corner
 stone of scientific computing, yet their integration across heterogeneous 
 architectures, programming languages, and evolving software ecosystems rem
 ains challenging. Exascale systems require libraries that can operate effi
 ciently across CPUs, GPUs,...\n\n\nLuigi Genovese (CEA Grenoble)\n\nDomain
 : Chemistry and Materials, Climate, Weather, and Earth Sciences, Computati
 onal Methods and Applied Mathematics\n\nSession Chair: Edoardo Di Napoli (
 Forschungszentrum Jülich)
END:VEVENT
END:VCALENDAR