BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//juliacon2024//speaker//8A7MJS
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-juliacon2024-N8UDQS@pretalx.com
DTSTART;TZID=CET:20240710T183000
DTEND;TZID=CET:20240710T190000
DESCRIPTION:Deep Learning models are often composed of a few building block
 s operating on tensors with relatively little control flow compared to mor
 e traditional code. Coil proposes a mechanism to extract the tensor subpro
 gram from the model call graph and lift its operations to the MLIR represe
 ntation. By leveraging the IREE compiler stack\, Coil is able to fuse and 
 optimize operations across Julia function calls since the whole model can 
 be observed.
DTSTAMP:20260312T202325Z
LOCATION:Else (1.3)
SUMMARY:꩜ Coil.jl - Lifting Julia array operations to MLIR. - Paul Berg
URL:https://pretalx.com/juliacon2024/talk/N8UDQS/
END:VEVENT
END:VCALENDAR