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:20230831T095747Z
LOCATION:Flüela
DTSTART;TZID=Europe/Stockholm:20230628T123000
DTEND;TZID=Europe/Stockholm:20230628T130000
UID:submissions.pasc-conference.org_PASC23_sess144_msa104@linklings.com
SUMMARY:Hardware-Level Performance Monitoring in Julia
DESCRIPTION:Minisymposium\n\nCarsten Bauer (Paderborn University)\n\nJulia
  is a dynamic programming language that combines two features important fo
 r high-productivity scientific computing: interactivity and high performan
 ce. These features enable the interactive development of scientific applic
 ation codes for HPC systems. However, to efficiently utilize the resources
  of HPC clusters, it is essential to gain a thorough understanding of the 
 performance of the critical computational kernels on the available hardwar
 e. While many HPC performance tools have been developed over time, they ty
 pically target static programming languages and either do not support Juli
 a at all or do not exploit the potential of Julia's dynamic nature. In my 
 talk, I will present LIKWID.jl, a Julia interface to the eponymous perform
 ance benchmarking suite, which has been developed within the German Nation
 al High-Performance Computing Alliance (NHR) to tackle this issue for intr
 a-node performance analyses. In particular, LIKWID.jl enables interactive 
 monitoring of the performance of a computational kernel on the hardware le
 vel by examining hardware performance counters built into CPUs (and GPUs).
  I will demonstrate how to use LIKWID.jl's Marker API to analyze specific 
 sections of larger scientific codes and gain important insights into float
 ing-point performance, vectorization, and data transfer. I will showcase t
 hese techniques using some illustrative examples inspired by real-world ap
 plications.\n\nDomain: Computer Science, Machine Learning, and Applied Mat
 hematics 
\n\nSession Chair: Samuel Omlin (ETH Zurich / CSCS)
END:VEVENT
END:VCALENDAR