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:20210916T132528Z
LOCATION:Ernesto Bertarelli
DTSTART;TZID=Europe/Stockholm:20210705T153000
DTEND;TZID=Europe/Stockholm:20210705T173000
UID:submissions.pasc-conference.org_PASC21_sess113@linklings.com
SUMMARY:Architecture and Performance of Hardware-Independent Frameworks fo
 r Particle-In-Cell Methods, Part I
DESCRIPTION:Minisymposium\n\nHeterogeneous computing architectures are una
 voidable moving towards the era of exascale computing. Computing nodes are
  being built with the ever-increasing depth of the hierarchy. Hardware as 
 well as performance portability are key capabilities to make efficient use
  of them. Particle-in-cell (PIC) methods are the method of choice in compu
 tational simulations of many physical applications including but not limit
 ed to particle accelerators, nuclear fusion, and astrophysics. Hence, port
 ability in the context of PIC schemes is the need of the hour to carry out
  these extreme-scale simulations in current and next-generation architectu
 res. This mini-symposium will serve as a platform to discuss the architect
 ure and performance of hardware-independent and, thus, portable frameworks
  regarding particle and grid computations.\n\nDiscussion Session on Archit
 ecture and Performance of Hardware-Independent Frameworks for Particle-In-
 Cell Methods, Part 1\n\nAdelmann\n\nIn this session, we discuss the experi
 ences of the presenters and the audience towards achieving performance por
 tability in modern computing architectures. We will brainstorm on best pra
 ctices that will enable us to utilize exascale machines efficiently and ac
 hieve maximum performance.\n\n---------------------\nRecent Advances in Ma
 xwell Solvers for PIC Simulations Across Architectures\n\nHu, Glusa\n\nIn 
 this talk we present our experiences in developing architecture-independen
 t linear solversfor a particle-in-cell simulation code.  The algebrai
 c multigrid solvers are part of theTrilinos library MueLu.  The solve
 rs utilize the Kokkos ecosystem (Kokkos core and KokkosKernels) for portab
 i...\n\n---------------------\nTowards Exascale with IPPL Version 2.0\n\nF
 rey, Muralikrishnan, Adelmann\n\nIPPL is a generic library written in C/C+
 + and MPI for high performance Eulerian, Lagrangian and mixed Eulerian-Lag
 rangian applications. Since its development around the turn of the millenn
 ium, the variety of hardware architectures has grown and software develope
 rs are challenged in the design and m...\n\n---------------------\nPerform
 ance Portable Space Filling Curve Algorithms for Efficient Mesh Management
  in Mars with Kokkos.\n\nGanellari, Fink, Fadel, Zulian\n\nMars is an open
 -source mesh management library featuring parallel mesh generation, confor
 ming mesh data-structure, mesh quality estimators, and performance-portabl
 e algorithms and data-structures. It targets multi-core CPUs and GPUs usin
 g the C++ Kokkos programming model. The mesh is constructed and...\n\n\nDo
 main: CS and Math, Physics, Engineering
END:VEVENT
END:VCALENDAR