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:20241120T082409Z
LOCATION:HG E 3
DTSTART;TZID=Europe/Stockholm:20240605T090000
DTEND;TZID=Europe/Stockholm:20240605T110000
UID:submissions.pasc-conference.org_PASC24_sess131@linklings.com
SUMMARY:MS5E - Julia for HPC: Tools and Applications - Part I
DESCRIPTION:Minisymposium\n\nPerformance portability and scalability on la
 rge-scale heterogeneous hardware represent crucial aspects challenging cur
 rent scientific software development. Beyond software engineering consider
 ations, workflows making further use of large datasets to constrain physic
 al models are also emerging and are indispensable to develop, e.g., digita
 l twins. GPU computing and differentiable programming constitute leading-e
 dge tools that provide a promising way to combine physics-based simulation
 s with novel machine learning and AI based methods to address interdiscipl
 inary problems in science. The Julia language leverages both tools, as it 
 includes first-class support for various accelerator types and an advanced
  compiler interface that supports native automatic differentiation capabil
 ities. Julia makes it possible to differentiate efficiently through both C
 PU and GPU code without significant impact on performance. The goal of thi
 s minisymposium is to bring together scientists who work on or show intere
 st in large-scale Julia HPC development, with a particular focus on the ne
 cessary tool stack for automatic differentiation and machine learning in t
 he Julia GPU ecosystem, and on applications built on top of it. The select
 ion of speakers, with expertise spanning from computer to domain science, 
 offers a unique opportunity to learn about the latest development of Julia
  for HPC to drive discoveries in natural sciences.\n\nEnzyme.jl: High-Perf
 ormance, Cross-Language, and Parallel Automatic Differentiation in Julia\n
 \nAutomatic differentiation (AD) is key to training neural networks, Bayes
 ian inference, and scientific computing. Applying these techniques require
 s rewriting code in a specific machine learning framework or manually prov
 iding derivatives. This talk presents Enzyme, a high-performance automatic
  diffe...\n\n\nWilliam Moses (University of Illinois Urbana-Champaign)\n--
 -------------------\nMulti-GPU Optimization of a Large-Scale Cortical Mode
 l of Human-Like Gaze Behaviour\n\nWe introduce a large-scale biophysical m
 odel for dynamic visual target selection, mimicking human gaze behavior, o
 ptimized using Julia programming on multiple GPUs. Our dynamic mean-field 
 model sequentially generates visual targets, accommodating network sizes u
 p to 25600 neural populations,  with c...\n\n\nVaishnavi Narayanan (Maastr
 icht University), Samuel Omlin (ETH Zurich / CSCS), and Mario Senden (Maas
 tricht University)\n---------------------\nAMD GPU Programming in Julia fo
 r High-Performance Real-Time Neural Rendering\n\nAMD GPU programming in Ju
 lia has seen significant improvements in performance and stability over th
 e past year, transitioning from two disjoined runtime APIs to a single sta
 ck, improving the device support and adding new features.\nIn this present
 ation, we demostrate key changes that have been made t...\n\n\nAnton Smirn
 ov (AMD)\n---------------------\nTowards High-Performant, Large-Scale Tens
 or Network Simulations\n\nTensor Networks are in the center of every dispr
 oval of quantum advantage claims in these recent years. Achieving quantum 
 advantage, the predicted theoretical moment when quantum computers will be
 at classical computers on some problems, is key for the general adoption o
 f quantum computers. But provi...\n\n\nSergio Sánchez Ramírez (Barcelona S
 upercomputing Center)\n\nDomain: Climate, Weather, and Earth Sciences, Phy
 sics, Computational Methods and Applied Mathematics\n\nSession Chairs: Sam
 uel Omlin (ETH Zurich / CSCS); Ludovic Raess (University of Lausanne, ETH 
 Zurich); and Michael Schlottke-Lakemper (University of Augsburg)
END:VEVENT
END:VCALENDAR