BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Optimizing sparse vector-matrix multiplication on GPUs - Alexander
  Monakov\, ISP-RAS and Moscow State University
DTSTART:20091215T141500Z
DTEND:20091215T151500Z
UID:TALK21909@talks.cam.ac.uk
CONTACT:Alan Mycroft
DESCRIPTION:Graphics processors are highly parallel computational units em
 ploying multiple levels of computational parallelism and memory hierarchy.
   Due to their high computational power they are increasingly used in scie
 ntific applications.  However\, optimizing algorithms for high performance
  on GPUs is not trivial.\n\nWe discuss optimizing sparse linear algebra on
  GPUs (specifically\, sparse matrix-vector multiplication\, SpMV\, which i
 s the most time-consuming step in many applications).  We describe several
  known sparse matrix storage formats and present a new storage format that
  allows SpMV performance to be improved.\n\n[This paper is to appear in Hi
 PEAC'10]\n\nAbout the speaker:\nAlexander Monakov is a PhD student at Mosc
 ow State University and an employee at Institute for System Programming of
  Russian Academy of Sciences (ISP-RAS)\, where he works on improving the G
 CC compiler.  His interests include general-purpose GPU computing\, compil
 er optimization technology and in particular using polyhedral model for pa
 rallelism and locality optimization.\n
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR