BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//juliacon-2026//speaker//GRFD9D
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-juliacon-2026-YGSNMR@pretalx.com
DTSTART;TZID=CET:20260813T124500
DTEND;TZID=CET:20260813T130000
DESCRIPTION:Stencil operations are a cornerstone in many fields\, including
  fluid and gas flow simulations\, machine learning/AI\, computer graphics\
 , image processing\, and many more. Stencil operations (also known as wind
 owed operations) allow a normal elementwise operation to additionally acce
 ss neighboring elements\, instead of just the currently-selected element. 
 The are a number of stencil computation libraries in Julia\, such as Image
 Filtering.jl\, ParallelStencil.jl\, Stencils.jl\, and now Dagger.jl (the f
 ocus of this talk). Dagger in particular makes it easy to define stencil o
 perations that run across multiple CPUs\, multiple GPUs\, and across multi
 ple nodes\, and supports many kinds of boundary conditions\, arbitrary num
 bers of dimensions\, and flexible neighborhood sizing. We will discuss and
  compare the differences between the various stencil libraries\, and see h
 ow easy it is to write parallel stencils in each library. We will also loo
 k at Dagger’s stencil performance in a variety of microbenchmarks.
DTSTAMP:20260502T094005Z
LOCATION:Room 3
SUMMARY:Sketch me an HPC program: Stencils with Dagger.jl - Julian P Samaro
 o\, Felipe Tomé\, Rabab Alomairy
URL:https://pretalx.com/juliacon-2026/talk/YGSNMR/
END:VEVENT
BEGIN:VEVENT
UID:pretalx-juliacon-2026-VC7Q39@pretalx.com
DTSTART;TZID=CET:20260813T143000
DTEND;TZID=CET:20260813T144500
DESCRIPTION:Multi-GPU execution is the future - as data sizes grow\, and as
  more work is pushed to the GPU\, a single GPU no longer suffices. Unfortu
 nately\, programming an algorithm for multi-GPU is more complicated than s
 ingle-GPU - you now have to deal with the complexity of multi-device data 
 movement and multi-stream synchronization\, which puts more burden on the 
 algorithm author and takes away from just writing the algorithm in the sim
 plest\, most readable manner. Thankfully\, Dagger.jl makes programming mul
 ti-GPU algorithms much easier with its Datadeps framework\, which lets you
  focus on writing the algorithm at a high level while Dagger handles the d
 etails of managing multiple GPUs.\n\nThis talk will explain the problems a
 round multi-GPU programming\, and show how Dagger handles them. We will sh
 ow how the Datadeps framework makes it much easier to write algorithms whi
 ch naturally support multi-GPU execution\, and show the tools that Dagger 
 and Datadeps provide to make algorithm design a breeze.
DTSTAMP:20260502T094005Z
LOCATION:Room 3
SUMMARY:Multi-GPU Algorithms with Dagger.jl - Julian P Samaroo\, Felipe Tom
 é
URL:https://pretalx.com/juliacon-2026/talk/VC7Q39/
END:VEVENT
BEGIN:VEVENT
UID:pretalx-juliacon-2026-TVKAZB@pretalx.com
DTSTART;TZID=CET:20260814T143000
DTEND;TZID=CET:20260814T153000
DESCRIPTION:Round-table open discussion of everything about Dagger.jl. Succ
 ess or failure stories\, gripes and joys\, ideas for new features\, discus
 sion of existing bugs or missing documentation\, and more!
DTSTAMP:20260502T094005Z
LOCATION:Room 5
SUMMARY:Dagger.jl Birds of a Feather - Julian P Samaroo\, Felipe Tomé
URL:https://pretalx.com/juliacon-2026/talk/TVKAZB/
END:VEVENT
END:VCALENDAR