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:20210916T132529Z
LOCATION:Jean-Jacques Rousseau
DTSTART;TZID=Europe/Stockholm:20210708T110000
DTEND;TZID=Europe/Stockholm:20210708T130000
UID:submissions.pasc-conference.org_PASC21_sess129@linklings.com
SUMMARY:Productivity, Performance, and Portability for Scientific Computin
 g with Continuous Integration, Containers, and Build Systems, Part I
DESCRIPTION:Minisymposium\n\nNowadays the complexity of scientific computi
 ng in conjugation with the hardware complexity has become significant. On 
 one side, scientific software applications require several dependencies fo
 r their compilation. On the other side, users and developers of scientific
  applications target a wide range of diverse computing platforms, such as 
 their laptops to supercomputers. This complexity poses challenges during t
 he entire workflow of the applications. We can distinguish at least five c
 ritical areas:\n\n1) applications building, including all dependencies;\n2
 ) testing during the application development with Continuous Integration (
 CI) and automated build and testing techniques;\n3) deployment of the appl
 ications via Continuous Deployment (CD) techniques;\n4) packaging of the a
 pplications with dependencies for easy user-level installation and product
 ivity;\n5) software performance portability.\n\nThe challenge in High Perf
 ormance Computing is to develop techniques that allow maximizing the three
  software applications characteristics: productivity, performance, and por
 tability for the five areas aforementioned. In this Minisymposium research
 ers and developers will discuss their successes and failures concerning th
 is challenge. This is split into two sessions, each of two hours. The firs
 t session will cover the building tools and CI/CD techniques, while the se
 cond session focuses on packaging applications and performance portability
 .\n\nBuilding Community through xSDK Software Policies\n\nLuszczek, Yang\n
 \nThe development of increasingly complex Hardware and software ecosystems
  continues unabated with ever more heterogeneous designs. Both the multiph
 ysics modeling simulations and thecoupling of modeling and data analytics 
 applications require more than ever the combined use of software packages 
 develo...\n\n---------------------\nDeploying HPC Software with Spack\n\nC
 ulpo\n\nThe modern scientific software stack includes thousands of package
 s, from C, C++, and Fortran libraries, to packages written in interpreted 
 languages like Python and R. HPC applications may have hundreds of depende
 ncies spanning all of these ecosytems and they need to leverage low-level 
 and difficul...\n\n---------------------\nDeveloping HPC Software with Spa
 ck\n\nStoppels\n\nWhether it is bugfixing across packages or simply testin
 g a particular branch of one of your dependencies, software development of
 ten requires one to work with development versions of dependencies. And re
 versely, in continuous integration one typically tests their development v
 ersion against the lat...\n\n---------------------\nDeploying Scientific S
 oftware at Scale and Enabling Continuous Testing of HPC Systems\n\nKarakas
 is, Peretti-Pezzi, Manitaras\n\nThe scientific software stack of a HPC sys
 tem is highly complex, often comprising packages with multiple dependencie
 s and requiring close interactions with the underlying system in order to 
 deliver the high performance required by the end users of such systems. Du
 e to the large number of interdepend...\n\n\nDomain: CS and Math, Emerging
  Applications, Chemistry and Materials, Climate and Weather, Solid Earth D
 ynamics, Life Sciences, Engineering
END:VEVENT
END:VCALENDAR