BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260706T014131Z
UID:321c0a0b-b7c8-4aea-a81a-4cb4d72e98d0
DTSTART:20171031T090000Z
DTEND:20171101T173000Z
DESCRIPTION:ARCHER has a small Cray XC40 cluster containing Intel's Knights
  Landing (KNL) processors. This system is intended to allow the UK computa
 tional simulation community to test their codes on the KNL processors\, op
 timise codes for this new hardware\, and evaluate the suitability of KNL f
 or their applications. In this course we will introduce the KNL system ass
 ociated with ARCHER\, descibe how it can be used\, and present the technic
 al details of the KNL processor.\n\nDetails\n\nKnights Landing is Intel's 
 latest Xeon Phi many-core processor. It offers large amounts of floating p
 oint performance (the theoretical peak is 3TFlop/s using double precision 
 data) in a single processor for applications that can use it efficiently. 
 The KNL hardware is significantly different to the previous generation of 
 Xeon Phi\, and contains specialised hardware that may beneficial for scien
 tific applications.\nIn this course we will describe the KNL hardware\, ex
 plain how to use the various new features it presents\, and explain how to
  access and use KNL processors through the ARCHER service.\nThere will be 
 a number of hands-on practical sessions\, and all attendees will be given 
 KNL access for the duration of the course.\n\nThis course is free to all a
 cademics.\n\nIntended learning outcomes\n\nOn completion of this course st
 udents should be able to:\n\nUnderstand the Knights Landing (KNL) processo
 r.\n	Understand how to access and run jobs on the ARCHER KNL cluster.\n	Un
 derstand the impact of vectorisation on performance on KNL.\n	Understand h
 ow to check if an application is vectorising and modify applications to im
 prove vectorisation\n	Use the different memory available in the nodes.\nPr
 e-requisites\n\nSome understanding of at least one of the following progra
 mming Languages:\n\nFortran\, C or C++.\nTimetable\n\nDay 1\n\n09:30 - 09:
 45 : Course introduction\n	09:45 - 10:45 : Introduction to the KNL hardwar
 e and the ARCHER KNL system\n	10:45 - 11:15 : Break\n	11:15 - 12:00 : Prac
 tical: Running on the ARCHER KNLs\n	12:00 - 12:30 : Memory modes programmi
 ng\n	12:30 - 14:00 : Lunch\n	14:00 - 15:00 : Practical: Investigating Memo
 ry on the KNL\n	15:00 - 15:30 : Cluster modes\n	15:30 - 16:00 : Break\n	16
 :00 - 17:00 : Vectorisation\nDay 2\n\n09.30 - 09:45 : Vectorisation recap\
 n	09.45 - 11:00 : Practical: Vectorisation\n	11.00 - 11:30 : Break\n	11:30
  - 12:30 : Serial Optimisation\n	12.30 - 14:00 : Lunch\n	14.00 - 15:30 : P
 ractical: Serial optimisation\n	15.30 - 16:00 : Break\n	16.00 - 17:00 : Pr
 actical: Continue practicals or bring your own code\nCourse Materials\n\nh
 ttps://www.archer.ac.uk/training/course-material/2017/10/KNL_Camb/index.ph
 p\n\n\nhttps://events.prace-ri.eu/event/671/
SUMMARY:Programming the Manycore Knights Landing Processor @ EPCC at Cambri
 dge
URL;VALUE=URI:https://events.prace-ri.eu/event/671/
END:VEVENT
END:VCALENDAR