BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//compute-paris-2026//talk//BMDG9H
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:from hardware import linalg - İlhan Polat
DTSTART;TZID=Europe/Paris:20261125T100500
DTEND;TZID=Europe/Paris:20261125T103500
DTSTAMP:20260930T121004Z
UID:pretalx-compute-paris-2026-BMDG9H@pretalx.com
DESCRIPTION:Scientific software is often summarized as\, rather jokingly\,
  "_your problem somehow converted into matrix algebra_". In this talk we w
 ill go over the state of affairs of matrix algebra libraries\, why SciPy d
 ecided to translate all its 90000 SLOC codebase to remove its very famous 
 Fortran libraries\, why we even depend on Fortran in the first place and m
 any other details. The attendees will have a contemporary understanding of
  mechanisms how BLAS/LAPACK/NumPy and other fundamental libraries interact
 . We will also opine on the next steps to go beyond the current performanc
 e levels\, and to exploit the hardware we own but do not really use in ful
 l capacity. \n\nThe talk is informal and no expertise in any of the subjec
 ts mentioned needed. The researchers/scientists\, who did not have the opp
 ortunity to dive into this part of the stack before\, are in particular en
 couraged to attend.
LOCATION:Room 108
URL:https://pretalx.com/compute-paris-2026/talk/BMDG9H/
END:VEVENT
END:VCALENDAR