BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//juliacon-2026//talk//FX73BU
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-FX73BU@pretalx.com
DTSTART;TZID=CET:20260813T164500
DTEND;TZID=CET:20260813T170000
DESCRIPTION:CUDA is well known for its SIMT programming model\, available i
 n Julia through CUDA.jl. This year\, NVIDIA introduces cuTile\, a new tile
 -based programming model for writing high-performance GPU kernels\, with a
 utomatic tensor core utilization. cuTile.jl brings this model to Julia\, c
 ompiling Julia kernels through a custom pipeline to Tile IR bytecode. In t
 his talk\, we'll cover the programming model\, the compiler design\, and p
 erformance benchmarks on Blackwell GPUs.
DTSTAMP:20260502T082757Z
LOCATION:Room 3
SUMMARY:Tile-Based GPU Programming with cuTile.jl - Tim Besard
URL:https://pretalx.com/juliacon-2026/talk/FX73BU/
END:VEVENT
END:VCALENDAR