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:20190719T085744Z
LOCATION:HG D 3.2
DTSTART;TZID=Europe/Stockholm:20190613T174500
DTEND;TZID=Europe/Stockholm:20190613T181500
UID:submissions.pasc-conference.org_PASC19_sess152_msa126@linklings.com
SUMMARY:Write Once, Scale Everywhere: using Alpaka for Future-Proof HPC Ke
 rnels
DESCRIPTION:Minisymposium\nComputer Science and Applied Mathematics, Emerg
 ing Application Domains, Climate and Weather, Physics, Life Sciences\n\nWr
 ite Once, Scale Everywhere: using Alpaka for Future-Proof HPC Kernels\n\nB
 astrakov, Worpitz, Huebl, Widera, Zenker...\n\nAlpaka is a modern, open so
 urce C++ library for accelerator development. Based on zero-overhead abstr
 actions in standard C++, Alpaka implements a CUDA-like programming model s
 uitable for performance-portable application and library development. That
  means for users: write your code once, with explicit parallelism, and let
  the compiler generate perfectly tuned binaries without ever changing the 
 code again. Running on many diverse architectures on today's supercomputer
 s, such as many-core CPUs, Nvidia and now also AMD GPUs, Xeon Phi's, Alpak
 a is well suited for deep, extensible, scientific software stacks. Alpaka 
 is designed facing the reality that domain-specific integrations will buil
 d on top of custom containers and parallel iterators and provides the in-n
 ode kernel task parallelization model for such endeavors. Today, Alpaka is
  used in diverse HPC applications, such as particle-mesh plasma physics, f
 luid dynamics and high-throughput imaging methods.
END:VEVENT
END:VCALENDAR