BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//juliacon-2022//speaker//ZTATFJ
BEGIN:VEVENT
SUMMARY:Teaching GPU computing\, experiences from our Master-level course 
 - Ludovic Räss\, Samuel Omlin\, Mauro Werder
DTSTART:20220727T130000Z
DTEND:20220727T133000Z
DTSTAMP:20260815T184640Z
UID:pretalx-juliacon-2022-YPGNCS@pretalx.com
DESCRIPTION:In the Fall Semester 2021 at ETH Zurich\, we designed and taug
 ht a new course: **Solving PDEs in parallel on GPUs with Julia**. We prese
 nt technical and teaching experiences we gained: we look at our tech-stack
  `CUDA.jl`\, `ParallelStencils.jl` and `ImplictGlobalGrid.jl` for GPU-comp
 uting\; and `Franklin.jl`\, `Literate.jl`\, `IJulia.jl`/Jupyter for web\, 
 slides\, and exercises. We look into the crash-course in Julia\, teaching 
 software-engineering (git\, CI) and project-based student evaluations.
LOCATION:Blue
URL:https://pretalx.com/juliacon-2022/talk/YPGNCS/
END:VEVENT
BEGIN:VEVENT
SUMMARY:GPU4GEO - Frontier GPU multi-physics solvers in Julia - Ludovic R
 äss\, Samuel Omlin\, Albert de Montserrat\, Boris Kaus
DTSTART:20220727T134000Z
DTEND:20220727T135000Z
DTSTAMP:20260815T184640Z
UID:pretalx-juliacon-2022-7FVVF3@pretalx.com
DESCRIPTION:The accelerating outflow of ice in Antarctica or Greenland due
  to a warming climate or the geodynamic processes shaping the Earth share 
 common computational challenges: extreme-scale high-performance computing 
 (HPC) which requires the next-generation of numerical models\, parallel so
 lvers and supercomputers. We here present a fresh approach to modern HPC a
 nd share our experience running Julia on thousands of graphical processing
  units (GPUs).
LOCATION:Blue
URL:https://pretalx.com/juliacon-2022/talk/7FVVF3/
END:VEVENT
BEGIN:VEVENT
SUMMARY:High-performance xPU Stencil Computations in Julia - Ludovic Räss
 \, Samuel Omlin
DTSTART:20220727T152000Z
DTEND:20220727T153000Z
DTSTAMP:20260815T184640Z
UID:pretalx-juliacon-2022-AKVUKM@pretalx.com
DESCRIPTION:We present an efficient approach for writing architecture-agno
 stic parallel high-performance stencil computations in Julia. Powerful met
 aprogramming\, costless abstractions and multiple dispatch enable writing 
 a single code that is usable for both productive prototyping on a single C
 PU and for production runs on GPU or CPU workstations or supercomputers. P
 erformance similar to CUDA C is achievable\, which is typically a large im
 provement over reachable performance with `CUDA.jl` Array programming.
LOCATION:Purple
URL:https://pretalx.com/juliacon-2022/talk/AKVUKM/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Distributed Parallelization of xPU Stencil Computations in Julia -
  Ludovic Räss\, Samuel Omlin
DTSTART:20220727T153000Z
DTEND:20220727T154000Z
DTSTAMP:20260815T184640Z
UID:pretalx-juliacon-2022-RJYBLA@pretalx.com
DESCRIPTION:We present a straightforward approach for distributed parallel
 ization of stencil-based Julia applications on a regular staggered grid us
 ing GPUs and CPUs. The approach allows to leverage remote direct memory ac
 cess and was shown to enable close to ideal weak scaling of real-world app
 lications on thousands of GPUs. The communication performed can be easily 
 hidden behind computation.
LOCATION:Purple
URL:https://pretalx.com/juliacon-2022/talk/RJYBLA/
END:VEVENT
END:VCALENDAR