BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20210916T132456Z
LOCATION:
DTSTART;TZID=Europe/Stockholm:20210706T173000
DTEND;TZID=Europe/Stockholm:20210706T190000
UID:submissions.pasc-conference.org_PASC21_sess182_post175@linklings.com
SUMMARY:P36 - High Performance Training for Support Vector Machines
DESCRIPTION:Poster\n\nP36 - High Performance Training for Support Vector M
achines\n\nCormican\n\nThis project developed a new method for parall
el training of support vector machines using the conjugate gradient algori
thm. The work built on the serial implementation proposed by Wen, Tong, et
al (2003). The algorithm has been implemented in C and parallelised using MPI and openmp. The results sho
w significant potential. Large portions of the algorithm are triviall
y parallel with openmp, while a near linear speed up was achieved
for two to four nodes running on MPI. This is an active research
area and could be useful to researchers interested in developing a GPU im
plementation or exploring alternative options for parallelisation.
END:VEVENT
END:VCALENDAR