BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20200129T163556Z
LOCATION:E Concourse
DTSTART;TZID=America/Denver:20191119T083000
DTEND;TZID=America/Denver:20191119T170000
UID:submissions.supercomputing.org_SC19_sess238_spostg119@linklings.com
SUMMARY:Poster 21: Optimization of GPU Kernels for Sparse Matrix Computati
ons in Hypre
DESCRIPTION:ACM Student Research Competition: Graduate Posters, ACM Studen
t Research Competition: Undergraduate Posters, Posters\n\nPoster 21: Optim
ization of GPU Kernels for Sparse Matrix Computations in Hypre\n\nZhang\n\
nThe acceleration of sparse matrix computations on GPUs can significantly
enhance the performance of iterative methods for solving linear systems. I
n this work, we consider the kernels of Sparse Matrix Vector Multiplicatio
ns (SpMV), Sparse Triangular Matrix Solves (SpTrSv) and Sparse Matrix Matr
ix Multiplications (SpMM), which are often demanded by Algebraic Multigrid
(AMG) solvers. With the CUDA and the hardware support of the Volta GPUs o
n Sierra, the existing kernels should be further optimized to fully take t
he advantage of the new hardware, and the optimizations have shown signifi
cant performance improvement. The presented kernels have been put in HYPRE
for solving large scale linear systems on HPC equipped with GPUs. These s
hared-memory kernels for single GPU are the building blocks of distributed
matrix operations required by the solver across multiple GPUs and compute
nodes. The implementations of these kernels in Hypre and the code optimiz
ations will be discussed.\n\nTag: Tech Program Reg Pass, Exhibits Reg Pass
, Exhibits - Exhibit Hall Only Reg Pass, Student Program\n\nRegistration C
ategory: Tech Program Reg Pass, Exhibits Reg Pass, Exhibits - Exhibit Hall
Only Reg Pass, Student Program
URL:https://sc19.supercomputing.org/presentation/?id=spostg119&sess=sess23
8
END:VEVENT
END:VCALENDAR