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_post124@linklings.com
SUMMARY:P10 - SpFFT: A Library for Distributed Computation of Sparse 3D FF
 T with GPU Acceleration
DESCRIPTION:Poster\n\nP10 - SpFFT: A Library for Distributed Computation o
 f Sparse 3D FFT with GPU Acceleration\n\nFrasch\n\nFast Fourier Transforma
 tions are an essential part of many applications and libraries for the gen
 eral dense case are widely used. However, some applications can benefit fr
 om more specialized implementations. In particular, data with spherical cu
 toff is required in some computational material science applications, whic
 h provided the initial motivation for developing SpFFT. The library target
 s the more general case of transforming sparse 3D data and supports a wide
  variety of system configurations through a single hardware agnostic API.<
 br /> Parallelization is achieved through the use of MPI for inter-process
  communication and OpenMP for multithreading, while the optional use of CU
 DA (Nvidia) or HIP (AMD) allows for GPU acceleration. Initial work on inte
 gration into some applications indicate significant performance benefits. 
 The SIRIUS library already successfully uses SpFFT and full integration in
 to Quantum ESPRESSO and other codes is being explored.
END:VEVENT
END:VCALENDAR