BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260422T000618Z
LOCATION:507
DTSTART;TZID=America/Denver:20231113T090000
DTEND;TZID=America/Denver:20231113T123000
UID:submissions.supercomputing.org_SC23_sess444@linklings.com
SUMMARY:Tenth Workshop on Accelerator Programming and Directives (WACCPD 2
 023)
DESCRIPTION:Analysis of MURaM – A Solar Physics Application, for Scalabili
 ty, Performance, and Portability\n\nWith the advent of GPUs in parallel co
 mputing several languages, tools and compilers are being developed. Many i
 mpactful applications can benefit from the performance capabilities these 
 GPUs provide, but moving large, complex code bases to GPU execution often 
 poses many hurdles and growing pains as ...\n\n\nEric F. Wright (Universit
 y of Delaware), Cena Brown (National Center for Atmospheric Research (NCAR
 )), Damien Przybylski (MPS Solar System Research), Matthias Rempel and Sup
 reeth Suresh (National Center for Atmospheric Research (NCAR)), and Sunita
  Chandrasekaran (University of Delaware)\n---------------------\nWACCPD 20
 23 – Morning Break\n---------------------\nPerformance-Portable GPU Accele
 ration of the EFIT Tokamak Plasma Equilibrium Reconstruction Code\n\nWe pr
 esent the steps followed to GPU-offload parts of the core solver of EFIT-A
 I, an equilibrium reconstruction code suitable for tokamak experiments and
  burning plasmas.  For this work, we will focus on the fitting procedure t
 hat consists of a Grad–Shafranov (GS) equation inverse solver that ...\n\n
 \nOscar Antepara and Samuel Williams (Lawrence Berkeley National Laborator
 y (LBNL)); Scott Kruger (Tech-X Corporation); and Torrin Bechtel, Joseph M
 cClenaghan, and Lang Lao (General Atomics)\n---------------------\nTenth W
 orkshop on Accelerator Programming and Directives (WACCPD2023) – Closing R
 emarks\n\nJose M. Monsalve Diaz (Argonne National Laboratory (ANL)), Macie
 j Cytowski (Pawsey Supercomputing Centre), and Veronica Melesse Vergara (O
 ak Ridge National Laboratory (ORNL))\n---------------------\nCharacterizin
 g the Performance of Triangle Counting on Graphcore's IPU Architecture\n\n
 In recent years, we have seen an emergence of novel spatial architectures 
 to accelerate domain-specific workloads like Machine Learning. There is a 
 need to investigate their performance characteristics for traditional HPC 
 workloads for their tighter integration with current and future heterogene
 ous ...\n\n\nReet Barik (Argonne National Laboratory (ANL), Washington Sta
 te University) and Siddhisanket Raskar, Murali Emani, and Venkatram Vishwa
 nath (Argonne National Laboratory (ANL))\n---------------------\nSpecializ
 ed Kernels for Optimizing GPU Offload in OpenMP\n\nProgramming models for 
 general purpose GPU (GPGPU) computing include grid and non-grid languages.
   Grid languages like CUDA and HIP map directly to the GPU hardware and ca
 n extract high performance from applications.  However, this low-level pro
 gramming approach makes them more difficult to program ...\n\n\nDhruva Cha
 krabarti, Gregory Rodgers, Carlo Bertolli, Gheorghe-Teodor Bercea, Jan-Pat
 rick Lehr, Lynd Stringer, Jan Leyonberg, Dan Palermo, and Ron Lieberman (A
 dvanced Micro Devices (AMD) Inc)\n---------------------\nMemory Transfer D
 ecomposition: Exploring Smart Data Movement through Architecture-Aware Str
 ategies\n\nWe provide an automated framework that utilizes complex hardwar
 e links while preserving the simplified abstraction level for the user. Th
 rough the decomposition of user-issued memory operations into architecture
 -aware sub-tasks, we automatically exploit generally underused connections
  of the system....\n\n\nDiego A. Roa Perdomo (University of Delaware, CAPS
 L; Argonne National Laboratory (ANL)); Rodrigo Ceccato and Rémy Neveu (Uni
 versity of Campinas, Argonne National Laboratory (ANL)); Hervé Yviquel (Un
 iversity of Campinas); Xiaoming Li (University of Delaware); Jose M. Monsa
 lve Diaz (Argonne National Laboratory (ANL)); and Johannes Doerfert (Lawre
 nce Livermore National Laboratory (LLNL))\n---------------------\nPorting 
 and Optimizing Meso-NH to AMD MI250X GPUs\n\nThis paper presents the resul
 ts of our efforts to port Meso-NH, an atmospheric non-hydrostatic research
  model, to AMD MI250X GPUs using OpenACC on the ADASTRA Machine, a technol
 ogy similar to the Frontier system [1]. Meso-NH is a versatile model that 
 covers a wide range of resolutions from synoptic ...\n\n\nNaima Alaoui Ism
 aili (CINES, Hewlett Packard Enterprise (HPE))\n---------------------\nTen
 th Workshop on Accelerator Programming Using Directives (WACCPD 2023)\n\nH
 eterogeneous node architectures are becoming omnipresent in today’s HPC sy
 stems. Exploiting the maximum compute capability out of such systems, whil
 e also maintaining code portability and\nmaintainability, necessitates acc
 elerator programming approaches such as OpenMP offloading, OpenACC, stan..
 .\n\n\nMaciej Cytowski (Pawsey Supercomputing Research Center), Jose M. Mo
 nsalve Diaz (Argonne National Laboratory (ANL)), and Verónica G. Melesse V
 ergara (Oak Ridge National Laboratory (ORNL))\n---------------------\nComp
 aring a Naive and a Tree-Based N-Body Algorithm Using Different Standard S
 YCL Implementations on Various Hardware\n\nN-body algorithms aim to calcul
 ate the interactions between n different bodies with the goal to obtain th
 eir trajectories.  Algorithms that solve the n-body problem can leverage s
 ignificant amounts of parallelism.  Today, GPUs are commonly used besides 
 CPUs for the execution of parallel algorithms. ...\n\n\nTim Thüring, Marce
 l Breyer, and Dirk Pflüger (University of Stuttgart)\n--------------------
 -\nInvited Talk:  MareNostrum5 – Access and User Support to This New Highl
 y Heterogeneous System\n\nFollowing the joint effort by the Spanish, Portu
 guese and Turkish governments, together with EuroHPC JU (EC), the new supe
 rcomputer MareNostrum 5 will entry in operation in the following weeks. Th
 is highly heterogeneous supercomputer, with an aggregated peak performance
  above 300 PFlop/s, will inclu...\n\n\nOriol Pineda (Barcelona Supercomput
 ing Center (BSC))\n\nTag: Accelerators, Artificial Intelligence/Machine Le
 arning, Algorithms, Applications, Compilers, Data Movement and Memory, Het
 erogeneous Computing, Modeling and Simulation, Performance Optimization, P
 rogramming Frameworks and System Software, Runtime Systems\n\nRegistration
  Category: Workshop Reg Pass\n\nSession Chairs: Maciej Cytowski (Pawsey Su
 percomputing Research Centre; Commonwealth Scientific and Industrial Resea
 rch Organisation (CSIRO), Australia); Verónica G. Melesse Vergara (Oak Rid
 ge National Laboratory (ORNL)); and Jose Manuel Monsalve Diaz (Advanced Mi
 cro Devices (AMD))
END:VEVENT
END:VCALENDAR