BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:An introduction to OpenCL
DTSTART;VALUE=DATE-TIME:20110616T070000Z
DTEND;VALUE=DATE-TIME:20110616T150000Z
DTSTAMP;VALUE=DATE-TIME:20130525T044556Z
UID:indico-event-138427@cern.ch
DESCRIPTION:OpenCL is a standard for programming heterogeneous computers b
 uilt from CPUs\, GPUs and other processors. It includes a framework to def
 ine the platform in terms of a host (e.g. a CPU) and one or more compute d
 evices (e.g. a GPU) plus a C-based programming language for writing progra
 ms for the compute devices. Using OpenCL\, a programmer can write task-bas
 ed and data-parallel programs that use all the resources of the heterogene
 ous computer. In this tutorial\, we will introduce OpenCL.\nThis will be a
  “programmer’s introduction” where we cover the ideas behind OpenCL 
 but also show how these ideas are translated into source code. We will do 
 this through a series of progressively more challenging examples\, thereby
  providing a set of pedagogically useful examples that experienced HPC pro
 grammers can use to quickly become productive OpenCL programmers.\nIn the 
 afternoon there will be an hands-on tutorial. Please\, bring your own lapt
 op. We will provide access to some machines with Intel OpenCL Linux instal
 led\, but it would be best if you had OpenCL installed on your own laptop.
  We will drive the tutorial around the Windows release from Intel\, but we
  invite to use Linux version. You can download the beta release of OpenCL 
 (Linux and Windows) from Intel at:\n        http://software.intel.c
 om/en-us/articles/opencl-sdk/\nFor Apple laptops\, OpenCL is included with
  Xcode for Mac OS X (Snow Leopard release and beyond). You can also use th
 e AMD release of OpenCL for x86 processors which can be downloaded at:\n 
        http://developer.amd.com/SDKS/AMDAPPSDK/Pages/default.aspxTim
  Mattson's bio.\n\nhttp://indico.cern.ch/conferenceDisplay.py?confId=13842
 7
LOCATION:CERN Training center\, room 11
URL:http://indico.cern.ch/conferenceDisplay.py?confId=138427
END:VEVENT
BEGIN:VEVENT
SUMMARY:CERN openlab/Intel Workshop on Numerical Computing
DTSTART;VALUE=DATE-TIME:20120207T080000Z
DTEND;VALUE=DATE-TIME:20120208T160000Z
DTSTAMP;VALUE=DATE-TIME:20130525T044556Z
UID:indico-event-166141@cern.ch
DESCRIPTION:\n	 \n\n	The registration to this workshop is now closed\, as
  all places have been taken.\n	A new workshop will take place in the third
  quarter of this year\, more information will follow.\n	Topics\n\n		Advanc
 ed Floating point computing on x86\n	\n		Pitfalls in High Energy Physics s
 oftware\n	\n		Floating point control in Intel Software\n	\n		Future direct
 ions in accuracy control\n	\n		Hands-on tutorials\n\n	 \n\n	Speakers\nJef
 f Arnold\, Intel\nMartyn Corden\, Intel\nFlorent de Dinechin\, ENS Lyon\nJ
 ohn Gustafson\, Intel Research\nVincenzo Innocente\, CERN\nLorenzo Moneta\
 , CERN\nMore information will follow shortly.\n\n	 \n\nhttp://indico.cern
 .ch/conferenceDisplay.py?confId=166141
LOCATION:CERN Building 593\, Room 11
URL:http://indico.cern.ch/conferenceDisplay.py?confId=166141
END:VEVENT
BEGIN:VEVENT
SUMMARY:Intel / CERN openlab workshop on Advanced Parallelism and Tuning
DTSTART;VALUE=DATE-TIME:20120703T070000Z
DTEND;VALUE=DATE-TIME:20120704T143000Z
DTSTAMP;VALUE=DATE-TIME:20130525T044556Z
UID:indico-event-195512@cern.ch
DESCRIPTION:Intel / CERN openlab workshop on Advanced Parallelism and Tuni
 ng \nThe modern computing era has seen an explosive growth of parallelism
  inherent in computing chips. Taking advantage of these new features is an
  opportunity\, but also a challenge. To better prepare for the road ahead\
 , Intel and CERN openlab are organizing an advanced workshop focused on pa
 rallel programming and tuning of software. The two day event\, led by expe
 rts from Intel\, will be split into two parts.\nOn the first day\, Levent 
 Akyil will demonstrate existing and upcoming elements of Intel Parallel St
 udio XE. Discussed advanced features will include the efficient usage of A
 PIs to contextualize performance information\, batch performance collectio
 n\, loop analysis and instrumentation with the PIN tool. Although the main
  focus will be on the VTune™ Amplifier XE performance tuning tool\, the 
 Intel Inspector XE correctness checker and Advisor XE will also be discuss
 ed. The participants will be able to get hands on experience with the VTun
 e™ Amplifier XE 2013 beta and see live demos.\nOn the second day\, Hans 
 Pabst will introduce advanced features of Intel Threading Building Blocks 
 (Intel TBB)\, coupled with an introduction to the logic of Intel TBB and p
 arallel programming patterns. A discussion of constructs such as parallel 
 for\, concurrent containers and interdependent tasks will be interspersed 
 with hands-on labs. About the speakers\n				\n			\n				Levent Akyil is a 
 staff software engineer and currently manages the EMEA Technical Computing
 \, Analyzers\, and Runtimes technical consulting engineering team within t
 he Software & Services Group at Intel. Over the past 11 years\, he has hel
 d several positions in various divisions at Intel. Akyil worked on various
  Itanium® platforms and enterprise MP Xeon® server projects before movin
 g to his current role. Based in Munich\, Germany\, he provides technical c
 onsulting support for Intel® Software Development Products in EMEA. His t
 eam works with internal and external strategic customers providing enablin
 g and optimization support on Intel products including Intel® Many Integr
 ated Core architecture. Akyil has an MS in Computer Science and an MBA in 
 Technology and Innovation Management.\n		\n				 \n			\n				Hans Pabst is 
 a senior technical consultant engineer at Intel Corporation (SSG/DPD). He 
 enables customers in the EMEA region to leverage Intel software developer 
 products (performance libraries\, compilers and tools).  Hans’ focus is
  on parallel algorithms and programming models that target HPC and scienti
 fic applications. Before he joined RapidMind Inc. of Canada (acquired by I
 ntel)\, Hans was part of the Virtual Reality Systems Group of Bauhaus Univ
 ersity Weimar (Germany). Hans holds a Diploma in Civil Engineering and Com
 puter Science (Dipl.-Ing.).\n		Notes\nTo register\, please go to http://in
 dico.cern.ch/event/apt2012. Registrations are limited to approximately 45 
 participants and handled on a “first come–first served” basis. Atten
 dees wishing to participate in the interactive hands-on need to bring thei
 r laptop\, which will be used to access multi-core exercise servers. Pleas
 e contact openlab.workshops@cern.ch if you have any questions.\nThe course
  will be given in English and is targeted at intermediate and advanced use
 rs. Please also note that familiarity with basic threading concepts\, C/C+
 + and compilation techniques is a prerequisite. All Intel tools are provid
 ed for CERN users by CERN IT and openlab at no extra charge.\n \n\nhttp:/
 /indico.cern.ch/conferenceDisplay.py?confId=195512
LOCATION:CERN Building 593
URL:http://indico.cern.ch/conferenceDisplay.py?confId=195512
END:VEVENT
BEGIN:VEVENT
SUMMARY:CERN openlab/Intel Workshop on Numerical Computing (2nd instance)
DTSTART;VALUE=DATE-TIME:20120925T064000Z
DTEND;VALUE=DATE-TIME:20120926T150000Z
DTSTAMP;VALUE=DATE-TIME:20130525T044556Z
UID:indico-event-202688@cern.ch
DESCRIPTION:\n	CERN openlab and Intel are pleased to announce a second ins
 tance of the Numerical Computing workshop\, scheduled for September 25th a
 nd 26th at CERN. The course will be taught by external experts and several
  CERN staff. The workshop is targeted at an audience with good programming
  experience who would like to understand and control the floating-point ca
 lculations in their scientific programs.\n	Topics\n\n		Advanced Floating p
 oint computing on x86\n	\n		Pitfalls in High Energy Physics software\n	\n	
 	Floating point control in Intel Software\n	\n		Future directions in accur
 acy control\n	\n		Hands-on tutorials\n\n	Please note that space is limited
  to 45 participants and registration through this webpage is required. Att
 endance is free (as for the regular openlab workshops). A laptop is needed
  for accessing the servers that will be used for the exercises.\n\n	Speake
 rs\nJeff Arnold\, Intel SSG\nMartyn Corden\, Intel SSG\nFlorent de Dinechi
 n\, ENS Lyon\nTim Mattson\, Intel Labs\n+ CERN staff from PH/SFT and openl
 ab\nMore information will follow shortly.\n\n	 \n\nhttp://indico.cern.ch/
 conferenceDisplay.py?confId=202688
LOCATION:CERN Building 593\, Room 11
URL:http://indico.cern.ch/conferenceDisplay.py?confId=202688
END:VEVENT
BEGIN:VEVENT
SUMMARY:Google/ATLAS/CERN openlab tutorial on advanced performance monitor
 ing
DTSTART;VALUE=DATE-TIME:20121017T070000Z
DTEND;VALUE=DATE-TIME:20121018T153000Z
DTSTAMP;VALUE=DATE-TIME:20130525T044556Z
UID:indico-event-210736@cern.ch
DESCRIPTION:Google/ATLAS/CERN openlab tutorial on advanced performance mon
 itoring\nOctober 17-18 2012\, CERNRegistration: https://edh.cern.ch/Docume
 nt/Personnel/TRN/new?course=123GPM01https://vidyoportal.cern.ch/flex.html?
 roomdirect.html&key=QBbcqazWkq1Y\nProfiting from David Levinthal’s* visi
 t at CERN\, a tutorial on advanced performance monitoring is being organiz
 ed jointly by Google\, ATLAS and CERN openlab. During the two day course t
 he participants will be able to get an advanced understanding of performan
 ce tuning theory and practice on modern PCs. In particular\, David will de
 monstrate a novel tool called GOODA\, the Generic Optimization Data Analyz
 er. GOODA leverages the widely available perf subsystem in Linux and is co
 -developed by Google and the ATLAS collaboration. The hands-on labs will c
 onsist in part of pre-developed exercises and in part of an analysis of th
 e attendees’ own applications. These examples will be used to explain ho
 w to debug and fix real performance issues.The tentative agenda is as foll
 ows:\n\n		Day 1 morning – Theory and lectures\n	\n		Day 1 afternoon – 
 GOODA exercises\n	\n		Homework: profile your own app\n	\n		Day 2 – Discu
 ssion of collected profiles and solving real performance issues\nRegistrat
 ion is free of charge but mandatory. Participants are asked to bring their
  own laptops which they will use to connect to multi-core openlab servers.
  Inquiries should be sent to openlab.workshops@cern.ch*) Dr. David Levinth
 al is one of the world’s top experts in the PC performance monitoring fi
 eld and a Staff engineer at Google. For a large part of his career he has 
 worked as a Principal Engineer at Intel\, designing and developing perform
 ance tuning software and hardware. Earlier\, David worked at CERN where he
  was a physicist in the ALEPH and CCOR experiments. Having followed that l
 ink many years later\, David has a history of collaboration with openlab o
 n performance tuning activities. David’s main occupation today is optimi
 zation work for Google which includes driving the development of GOODA –
  the Generic Optimization Data Analyzer.\n\nhttp://indico.cern.ch/conferen
 ceDisplay.py?confId=210736
LOCATION:CERN
URL:http://indico.cern.ch/conferenceDisplay.py?confId=210736
END:VEVENT
BEGIN:VEVENT
SUMMARY:CERN openlab-Intel MIC / Xeon Phi training
DTSTART;VALUE=DATE-TIME:20130411T070000Z
DTEND;VALUE=DATE-TIME:20130412T150000Z
DTSTAMP;VALUE=DATE-TIME:20130525T044556Z
UID:indico-event-238763@cern.ch
DESCRIPTION:Update: Registrations are closed\, the course is full\nWe are 
 planning a dedicated\, hands-on Intel MIC / Xeon Phi course at CERN\, orga
 nized by openlab and delivered by two experts from Intel on April 11th-12t
 h. The session will be at an introductory/intermediate level\, and it will
  be an excellent opportunity to ask the knowledgeable tutors questions. Th
 e tentative agenda\, which will be adjusted based on your comments\, is as
  follows:\n		Hardware and software overview\n	\n		Programming models\, inc
 luding threading\, vectorization\, offloading\, MPI\n	\n		Performance anal
 ysis with VTune and Intel Trace Analyzer/Collector\n	\n		Hands-on labs inc
 luding offload memory and MPI exercises\n\n \nWe would appreciate it if y
 ou could register in case you are interested\, and let us know by e-mail w
 hat you would like to learn and if you would like to attend the hands-on i
 n addition to the lectures. The program can and will be adapted to suit yo
 ur needs as far as possible. Any questions or technical issues signaled to
  the trainers in advance have a higher chance of being addressed in detail
 .\n \nWe look forward to your feedback.\n\nhttp://indico.cern.ch/conferen
 ceDisplay.py?confId=238763
LOCATION:CERN TBC
URL:http://indico.cern.ch/conferenceDisplay.py?confId=238763
END:VEVENT
BEGIN:VEVENT
SUMMARY:CERN openlab/Intel Workshop on Numerical Computing (3rd instance)
DTSTART;VALUE=DATE-TIME:20130527T064000Z
DTEND;VALUE=DATE-TIME:20130528T150000Z
DTSTAMP;VALUE=DATE-TIME:20130525T044556Z
UID:indico-event-247985@cern.ch
DESCRIPTION:\n	The Workshop\nCERN openlab and Intel are pleased to announc
 e a third instance of the Numerical Computing workshop\, scheduled for May
  27th and 28th at CERN. The course will be taught by external experts and 
 several CERN staff. The workshop is targeted at attendees with good progra
 mming experience who would like to understand and control the floating-poi
 nt calculations in their scientific programs.Please note the agenda is sti
 ll under construction.\n	Topics\n•             Advanced Floa
 ting point computing on x86\n•             Pitfalls in High 
 Energy Physics software\n•             Floating point contro
 l in Intel Software\n•             Exploration and future di
 rections in accuracy control\n•             Hands-on tutoria
 ls\n	Speakers\nJeff Arnold\, Intel SSG\nMartyn Corden\, Intel SSG\nFlorent
  de Dinechin\, ENS Lyon\nVincenzo Innocente\, CERN\nLorenzo Moneta\, CERN\
 nDanilo Piparo\, CERN\nAttendance is free\, as for the regular openlab wor
 kshops\, but but requires registration in EDH. If you don’t have EDH acc
 ess\, please let us know by e-mail that you’re planning to participate (
 openlab.workshops@cern.ch). A laptop is needed for accessing the servers t
 hat will be used for the exercises.\n \n \n\nhttp://indico.cern.ch/confe
 renceDisplay.py?confId=247985
LOCATION:CERN Building 593\, Room 11
URL:http://indico.cern.ch/conferenceDisplay.py?confId=247985
END:VEVENT
END:VCALENDAR