BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260708T214332Z
UID:36450427-ac11-4bc7-8ed0-635852cf3cc6
DTSTART:20190502T060000Z
DTEND:20190503T130000Z
DESCRIPTION:Description\n\nThe Portable Extensible Toolkit for Scientific c
 omputing (PETSc) is a software framework for scalable numerical solution o
 f complex problems in science and engineering. It is designed primarily fo
 r typical computations connected with Partial Differential Equations (PDE)
  solution\, but is already successfully used also e.g.\, in data science. 
 PETSc provides implementations of distributed sparse/dense/unassembled mat
 rices\, linear algebra\, linear/non-linear system solvers\, time integrato
 rs\, mathematical optimization\, discretization and more. It can as well b
 e selectively extended with user's own implementations at any level. Codes
  using PETSc can be compiled on a wide range of computer architectures fro
 m iPhone to a large cluster with no code changes. PETSc is written in C bu
 t can be employed e.g.\, in C++\, Fortran and Python programs as well. The
  course will interleave theory and practice — presentations and hands-on
  exercises with individual consultations.\n\nLearning outcome\n\nAfter the
  course participants are able to:  \n\n\n	make use of the vast functional
 ity available in PETSc to write their own programs\, from mini-apps to big
 ger projects\;  \n	write their PETSc-based programs in a way allowing exp
 eriments with command-line options with no need for recompiling — for ex
 ample\, to apply different preconditioners to the same problem and compare
  their performance\;  \n	add their own functionality if needed by extendi
 ng prefabricated building blocks available in PETSc\; \n	take advantage of
  the debugging and profiling tools within PETSc\; \n	use PETSc as a "packa
 ge manager" to fetch\, compile and link various external libraries such as
  ParMETIS easily\;  \n	do something more with PETSc\, also based on their
  individual preferences.\n\n\nPrerequisites\n\nParticipants need some expe
 rience in C programming\, but expertise is not required. One should be fam
 iliar with:  \n\n\n	C syntax\; \n	Control flow (if/else\, loops\, writing
 /calling functions)\;  \n	Writing and calling functions\; \n	Compiling a 
 C program on their target platform.  \n\n\nOne also needs some conceptual
  knowledge of MPI:  \n\n\n	What is message passing about\; \n	What are MP
 I communicators.\n\n\n\nCourse Outline\n\nThursday\, May 2\n\n\n\n\n\nDay 
 1 – Linear algebra and linear system solution \n\n\n	\n	Introduction &am
 p\; Hello World\n	\n	\n	Objects\n	\n	\n	Vectors &amp\; Index Sets\n	\n	\n	
 Matrices\n	\n	\n	Linear System Solvers \n	\n\n\nFriday\, May 3 \n\nDay 2 
 – Advanced topics \n\n\n	\n	Technical Stuff (installation from source\, 
 use as package manager\, start your own project\, debug\, profile) \n	\n	\
 n	Discretization (DM) \n	\n	\n	Advanced Solvers (SNES\, TAO\, SLEPc) \n	\n
 	\n	Extras (MATLAB interface\, individual projects) \n	\n\n\n\n\n\n\n\nLec
 turers:  \n\nVaclav Hapla  (ETH)\n\nLanguage:  English\nPrice:    
       Free of charge\nhttps://events.prace-ri.eu/event/871/
SUMMARY:Scalable Parallel Computations with PETSc @ CSC
URL;VALUE=URI:https://events.prace-ri.eu/event/871/
END:VEVENT
END:VCALENDAR
