BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//compute-paris-2026//speaker//GXHBXX
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:STANDARD
DTSTART:20251125T000000
TZNAME:CET
TZOFFSETFROM:+0100
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20260329T030000
RDATE:20270328T030000
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20261025T030000
RDATE:20271031T030000
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:Scaling up GPU acceleration in the Polars dataframe library - Lawr
 ence Mitchell
DTSTART;TZID=Europe/Paris:20261125T140500
DTEND;TZID=Europe/Paris:20261125T143500
DTSTAMP:20260930T112635Z
UID:pretalx-compute-paris-2026-9N8K3B@pretalx.com
DESCRIPTION:Large scale analysis of structured data underpins much of ente
 rprise decision making. These analyses are often formulated using datafram
 e libraries\, of which Polars is a popular example. It has a domain specif
 ic language for writing dataframe queries\, exposed as a lazy API in Pytho
 n\, a query optimiser and multiple different execution engines.\n\nIn this
  talk\, I will cover recent work developing the multi-GPU accelerated engi
 ne in Polars. I will give an overview of the computational patterns that a
 ppear in large scale data analytics\, where they present challenges to eff
 icient execution and how we address them. I'll show how this multi-engine 
 offering allows seamless scaling of data analyses from laptop\, to worksta
 tion\, and beyond\, providing an "interactive" experience even at terabyte
  scale.\n\nIf you've ever written dataframe code and wondered "what is act
 ually going on here?"\, this talk might be for you.
LOCATION:Room 108
URL:https://pretalx.com/compute-paris-2026/talk/9N8K3B/
END:VEVENT
END:VCALENDAR