BEGIN:VCALENDAR VERSION:2.0 PRODID:icalendar-ruby CALSCALE:GREGORIAN BEGIN:VEVENT DTSTAMP:20260715T211522Z UID:c044281c-4ab3-4b6e-b21a-11bc8724cfeb DTSTART:20160706T080000Z DTEND:20160708T163000Z DESCRIPTION:* * * *   REGISTRATION: Now closed - course full.\n\nCurrent and future supercomputing architectures face a dramatic growth of parallel ism and heterogeneity on multiple levels. As a result\, it is close to imp ossible for researchers being code developers to predict which parts of th eir code perform well\, which development decisions impact the scalability \, which choice of data structures are reasonable for a specific architect ure\, and so forth. Most decisions are based upon experience\, upon intuit ion and upon a limited understanding of the code's performance.\n\n \n\nT o get a better understanding of code performance and to guide performance engineering\, it is essential for computational scientists and engineers t o conduct measurements in order to study the code performance in detail. P erformance analysis tools\, a generalisation of the classic profiler\, are the right tools to obtain this insight. However\, they themselves require a decent level of understanding\, experience and expertise to be used eco nomically – which adds to the hardness and complexity of the underlying problem. This workshop introduces several performance analysis tools and p rovides hands-on training.\n\n \n\nThe workshop will be given by Sameer S hende (University of Oregon)\, Marc-André Hermanns (Juelich Supercomputin g Centre)\, Joachim Protze (RWTH Aachen) and Florent Lebeau (Allinea Softw are Ltd).\n\n \n\nTarget Audience\n\nComputational scientists and researc hers that already use high performance computing (HPC) facilities for comp utationally demanding challenges\, that are actively involved in HPC code development\, and who can directly benefit in their research from a better understanding of why their code performs in a certain way.\n\n \n\nDurat ion\n\nThree days (Wed 6 Jul - Fri 8 Jul)\n\n \n\nFormat\n\nEach day will be split into three sessions\, lectures and hands-on exercises followed b y an afternoon session that gives attendees an opportunity to apply previo usly discussed tools to their own research codes.\n\n \n\nTopics covered\ n\nTAU\, Scalasca\, Score-P\, Cube\, MUST\, ARCHER\, Allinea MAP + PerfRep ort\n\n \n\nTaught using\n\nThe lecture and hands-on exercise sessions wi ll require a screen and a projector that can be connected to a laptop.\n\n Access to a whiteboard will also be required.\n\nThe attendees will typica lly bring their own laptops to use for the exercises and for applying the performance tools to their own research codes\; alternatively\, they could use the provided workstations.\n\nInternet access will also be required s o that instructors/attendees can access their ARCHER/DiRAC HPC accounts.\n \n \n\nProgramme Overview\n\nPresentations and hands-on sessions are on t he following topics:\n\nTAU performance system\n Score-P instrumentation a nd measurement\n Scalasca automated trace analysis\n MUST runtime error d etection for MPI\n ARCHER runtime error detection for OpenMP\nA brief ove rview of the capabilities of these and associated tools is provided in the VI-HPS Tools Guide.\n\nThe workshop will be held in English and run from 09:00 to not later than 18:00 each day\, with breaks for lunch and refresh ments. There is no fee for participation\, however\, participants are resp onsible for their own travel and accommodation.\n\nClassroom capacity is l imited\, therefore priority will be given to applicants with MPI\, OpenMP and hybrid OpenMP+MPI parallel codes already running on the workshop compu ter systems\, and those bringing codes from similar systems to work on.\n\ nOutline\n\nThe workshop introduces the open-source community-developed Sc ore-P instrumentation and measurement infrastructure\, together with the S calasca and TAU tools\, in order to provide a practical basis for portable performance analysis of parallel applications. The workshop will be deliv ered as a series of presentations with associated hands-on practical exerc ises\, starting with basic application instrumentation and measurement to generate execution profiles\, then improving measurement quality via custo mization capabilities\, and progressing to interactive and automated analy ses of execution traces.\n\nWhile analysis of provided example codes will be used to help familiarise the class with the various measurement/diagnos tic tools\, coaching will also be available to assist participants in anal ysing their own parallel application codes and thereby reveal opportunitie s for improving execution performance and scalability.\n\nFor the (prelimi nary) programme: www.vi-hps.org/training/tws/tw22.html\n\nhttps://events.p race-ri.eu/event/490/ SUMMARY:Performance Analysis Workshop @ EPCC at University of Cambridge URL;VALUE=URI:https://events.prace-ri.eu/event/490/ END:VEVENT END:VCALENDAR