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:20230831T095746Z
LOCATION:Flüela
DTSTART;TZID=Europe/Stockholm:20230628T110000
DTEND;TZID=Europe/Stockholm:20230628T113000
UID:submissions.pasc-conference.org_PASC23_sess144_msa157@linklings.com
SUMMARY:Portable and Efficient Julia Code for Heterogeneous Hardware Syste
 ms
DESCRIPTION:Minisymposium\n\nJulian Samaroo (Massachusetts Institute of Te
 chnology)\n\nAs we are entering the exascale era of supercomputing, hetero
 geneous hardware architectures have become the norm for new systems. At th
 e same time, vendors provide competing APIs to their accelerators, making 
 it harder to write and maintain portable code. The Julia programming langu
 age tries to tackle this challenge by providing useful and usable abstract
 ions that allow a near-seamless transition between different systems with 
 minimal or no code changes. In this talk, we will present the AMDGPU.jl pa
 ckage and discuss how it makes the power of AMD GPUs as easily accessible 
 within Julia as other accelerators. We will compare it to its sister packa
 ge CUDA.jl, and show how the differences in design lead to uniquely useful
  features for each platform while retaining compatible APIs. We will also 
 look at how AMDGPU.jl integrates with the rest of Julia's GPU ecosystem, s
 uch as in KernelAbstractions.jl, ImplicitGlobalGrid.jl, and ParallelStenci
 l.jl. Finally, we will talk about where we see AMDGPU.jl's development hea
 ding, and what great things are in store for users over the next few years
 .\n\nDomain: Computer Science, Machine Learning, and Applied Mathematics &#8232;
 \n\nSession Chair: Samuel Omlin (ETH Zurich / CSCS)
END:VEVENT
END:VCALENDAR
