BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//juliacon2021//speaker//3C7UBC
BEGIN:VEVENT
SUMMARY:GPU programming in Julia - Valentin Churavy\, Tim Besard\, Julian 
 P Samaroo
DTSTART:20210720T140000Z
DTEND:20210720T170000Z
DTSTAMP:20260912T142556Z
UID:pretalx-juliacon2021-VK87Q3@pretalx.com
DESCRIPTION:In this workshop\, we will demonstrate three major packages fo
 r programming GPUs in Julia (CUDA.jl\, AMDGPU.jl\, oneAPI.jl)\, and the di
 fferent programming models\, tools and APIs that these packages support.
LOCATION:Green
URL:https://pretalx.com/juliacon2021/talk/VK87Q3/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Enzyme.jl -- Reverse mode differentiation on LLVM IR for Julia - V
 alentin Churavy\, William Moses
DTSTART:20210728T170000Z
DTEND:20210728T173000Z
DTSTAMP:20260912T142556Z
UID:pretalx-juliacon2021-UDJ7SJ@pretalx.com
DESCRIPTION:Enzyme (https://enzyme.mit.edu) is a reverse mode auto-differe
 ntiation tool that performs automatic differentiation over LLVM intermedia
 te representation and synthesis high-performance reverse-mode functions. W
 e will discuss how Enzyme.jl integrates with the Julia compiler and specia
 l considerations required for differentiating a dynamic programming langua
 ge such as Julia.
LOCATION:Green
URL:https://pretalx.com/juliacon2021/talk/UDJ7SJ/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Scaling of Oceananigans.jl on multi GPU and CPU systems - Valentin
  Churavy\, Ali Ramadhan\, Chris Hill\, Francis Poulin\, Gregory Wagner
DTSTART:20210729T130000Z
DTEND:20210729T131000Z
DTSTAMP:20260912T142556Z
UID:pretalx-juliacon2021-DZC7HN@pretalx.com
DESCRIPTION:This talk will present scaling and performance of the Oceanani
 gans.jl ocean model on CPU and GPU systems. Oceananigans.jl is an all Juli
 a code that is designed to study geophysical fluids problems ranging from 
 idealized turbulence to planetary scale circulation. It uses the KernelAbs
 tractions.jl package to support CPU and GPU single address space paralleli
 sm. It uses MPI.jl\,  to support multi-node and multi-GPU parallelism. MPI
 .jl is used both directly and through PencilArrays.jl.
LOCATION:Blue
URL:https://pretalx.com/juliacon2021/talk/DZC7HN/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Julia in High-Performance Computing - Valentin Churavy\, Simon Byr
 ne\, Carsten Bauer\, Michael Schlottke-Lakemper
DTSTART:20210729T163000Z
DTEND:20210729T171500Z
DTSTAMP:20260912T142556Z
UID:pretalx-juliacon2021-C3EBJM@pretalx.com
DESCRIPTION:The JuliaHPC community as a group maintains the infrastructure
  for using Julia in high-performance computing. In this BoF we invite newc
 omers\, application developers\, and maintainers to join us for an informa
 l discussion around the state of Julia in HPC.
LOCATION:BoF/Mini Track
URL:https://pretalx.com/juliacon2021/talk/C3EBJM/
END:VEVENT
BEGIN:VEVENT
SUMMARY:GPU programming in Julia BoF - Valentin Churavy\, Tim Besard\, Jul
 ian P Samaroo
DTSTART:20210729T171500Z
DTEND:20210729T180000Z
DTSTAMP:20260912T142556Z
UID:pretalx-juliacon2021-RXBMHE@pretalx.com
DESCRIPTION:This is a BoF to talk about the various GPU programming packag
 es in Julia:\n\n- CUDA.jl\n- AMDGPU.jl\n- oneAPI.jl\n- KernelAbstractions.
 jl\n- GPUArrays.jl\n- GPUCompiler.jl\n- ...\n\nIf you have any thoughts or
  questions about these packages\, or other approaches to GPU programming i
 n Julia\, please join this BoF to chat about it!
LOCATION:BoF/Mini Track
URL:https://pretalx.com/juliacon2021/talk/RXBMHE/
END:VEVENT
END:VCALENDAR