BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260711T055009Z
UID:4a22f19e-dbff-4b98-aea8-c98d739bae5a
DTSTART:20170208T090000Z
DTEND:20170210T173000Z
DESCRIPTION:Performance Analysis Workshop\n\nGoals\n\nThis workshop is orga
 nized by VI-HPS for the UK PRACE Advanced Training Centre in collaboration
  with the EU Horizon 2020 Performance Optimisation &amp\; Productivity Cen
 tre of Excellence to:\n\ngive an overview of the VI-HPS programming tools 
 suite\n	explain the functionality of individual tools\, and how to use the
 m effectively\n	offer hands-on experience and expert assistance using the 
 tools\nOn completion participants should be familiar with common performan
 ce analysis and diagnosis techniques and how they can be employed in pract
 ice (on a range of HPC systems). Those who prepared their own application 
 test cases will have been coached in the tuning of their measurement and a
 nalysis\, and provided optimization suggestions.\n\nProgramme Overview\n\n
 Presentations and hands-on sessions are on the following topics:\n\nBSC to
 ols for trace analysis and performance prediction\n	Score-P instrumentatio
 n and measurement\n	Scalasca automated trace analysis\n	MAP+PR profiling a
 nd performance reports\nA brief overview of the capabilities of these and 
 associated tools is provided in the VI-HPS Tools Guide.\n\nThe workshop wi
 ll be held in English and run from 09:00 to not later than 18:00 each day\
 , with breaks for lunch and refreshments. There is no fee for participatio
 n\, however\, participants are responsible for their own travel and accomm
 odation.\n\nClassroom capacity is limited\, therefore priority will be giv
 en to applicants with MPI\, OpenMP and hybrid OpenMP+MPI parallel codes al
 ready running on the workshop computer systems\, and those bringing codes 
 from similar systems to work on. Workstations are provided to connect to t
 he workshop computer systems\, however\, (eduroam) wifi will be available 
 so participants could also use personal notebook computers with SSH and X1
 1 configured.\n\nOutline\n\nThe workshop introduces tools that provide a p
 ractical basis for portable performance analysis of parallel application e
 xecution\, covering both profiling and tracing. It will be delivered as a 
 series of presentations with associated hands-on practical exercises using
  the UK's ARCHER Cray XC30 supercomputer.\n\nWhile analysis of provided ex
 ample codes will be used to guide the class through the relevant steps and
  familiarise with usage of the tools\, coaching will also be available to 
 assist participants to analyse their own parallel application codes and ma
 y suggest opportunities for improving their execution performance and scal
 ability.\n\nProgramme (preliminary)\n\nDay 1:\n			Wednesday 8th February\
 n		09:00\n			Welcome messages [Nico de Tullio &amp\; Michael Bareford]\n		
 09:15\n			Introduction\n			Introduction to VI-HPS &amp\; overview of tools
  [Brian Wylie\, JSC]\n				Introduction to parallel performance engineering
  [Wadud Miah\, NAG]\n				Lab setup\n				Archer Cray XC30 computer system a
 nd software environment\n				Building and running NPB-MZ-MPI/BT-MZ on Arch
 er Cray XC30\n			\n		10:30\n			(break)\n		11:00\n			BSC performance tools 
 [Judit Gimenez\, BSC]\n			BSC tools hands-on exercises\n			\n		12:30\n			(
 lunch)\n		14:00\n			Hands-on coaching to apply tools to analyze participan
 ts' own code(s).\n		17:00\n			Review of day and schedule for remainder of 
 workshop\n		17:30\n			(adjourn)\n		 \n		Day 2:\n			Thursday 9th February
 \n		09:00\n			Instrumentation &amp\; measurement with Score-P [Brian Wylie
 \, JSC]\n			Score-P hands-on exercisesExecution profile analysis report ex
 ploration with CUBE [JSC]\n				CUBE hands-on exercises\n			\n		10:30\n			(
 break)\n		11:00\n			Configuring &amp\; customising Score-P measurements [B
 rian Wylie\, JSC]\n			Score-P hands-on exercisesAutomated trace analysis w
 ith Scalasca [JSC]\n				Scalasca hands-on exercises\n			\n		12:30\n			(lun
 ch)\n		14:00\n			Hands-on coaching to apply tools to analyze participants'
  own code(s).\n		17:00\n			Review of day and schedule for remainder of wor
 kshop\n		17:30\n			(adjourn)\n		 \n		Day 3:\n			Friday 10th February\n		
 09:00\n			Allinea performance tools suite [Florent Lebeau\, Allinea]\n			A
 llinea hands-on exercises\n			\n		10:30\n			(break)\n		11:00\n			POP CoE m
 ission &amp\; services\n			Review of workshop\n		12:30\n			(lunch)\n		14:0
 0\n			Hands-on coaching to apply tools to analyze participants' own code(s
 ).\n		16:00\n			(adjourn)\n		Hardware and Software Platforms\n\nARCHER: Cr
 ay XC30 with 3008 compute nodes consisting of two 12-core Intel E5-2697 (I
 vyBridge) processors sharing 64GB (or 128GB) of NUMA memory\, Aries dragon
 fly interconnect\, Cray MPI\, Cray\, GCC &amp\; Intel compilers\, PBS Pro 
 job management system. Training accounts will be provided!\n\nOther system
 s where up-to-date versions of the tools are installed can also be used wh
 en preferred\, though support may be limited. Participants are expected to
  already possess user accounts on non-local systems they intend to use\, a
 nd should be familiar with the procedures for compiling and running parall
 el applications.\n\nRegistration\n\nPlease register via the Registration t
 ab on this page. Note: the number of participants is limited\, and prefere
 nce will be given to those bringing parallel application(s) to analyse and
  tune as part of the workshop.\n\nLocal organisers information page.\n\nht
 tps://events.prace-ri.eu/event/582/
SUMMARY:24th VI-HPS Tuning Workshop @ EPCC at Southampton
URL;VALUE=URI:https://events.prace-ri.eu/event/582/
END:VEVENT
END:VCALENDAR
