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:20240605T100000
DTEND;TZID=Europe/Stockholm:20240605T103000
UID:submissions.pasc-conference.org_PASC24_sess131_msa243@linklings.com
SUMMARY:AMD GPU Programming in Julia for High-Performance Real-Time Neural
  Rendering
DESCRIPTION:Minisymposium\n\nAnton Smirnov (AMD)\n\nAMD GPU programming in
  Julia has seen significant improvements in performance and stability over
  the past year, transitioning from two disjoined runtime APIs to a single 
 stack, improving the device support and adding new features.\nIn this pres
 entation, we demostrate key changes that have been made to the AMDGPU.jl p
 ackage, which provides support for programming AMD GPUs, enabling a host o
 f new applications.\n\nTo showcase the impact of these changes, we present
  state-of-the-art real-time neural rendering algorithms developed entirely
  in Julia in a backend-agnostic manner.\nGiven a set of images, these algo
 rithms reconstruct an environment in a matter of minutes and allow the use
 r to interact with it during training and evaluation.\nTo achieve real-tim
 e performance, these implementations incorporate optimized hand-written GP
 U kernels that integrate with Automatic Differentiation systems, offering 
 a high-level interface without sacrificing performance.\n\nSimplicity of i
 mplementation, seamless support for multiple backends, and real-time perfo
 rmance of these algorithms position the Julia language as a strong candida
 te for high-performance computing.\n\nDomain: Climate, Weather, and Earth 
 Sciences, Physics, Computational Methods and Applied Mathematics\n\nSessio
 n Chairs: Samuel Omlin (ETH Zurich / CSCS); Ludovic Raess (University of L
 ausanne, ETH Zurich); and Michael Schlottke-Lakemper (University of Augsbu
 rg)
END:VEVENT
END:VCALENDAR