Sign up for our newsletter and get the latest HPC news and analysis.

Cilk++ Multicore Course

The folks at CilkArts have announced that they will hold a two day course on programming in a multicore environment with Cilk++.  The course, Concepts in Multicore Programming, will be taught by Charles E. Leiserson and Pablo Halpern.  You might remember them from their book, Introduction to Algorithms.  A quick summary of the course outline:

  • Day 1: Understand multicore architecture trends (Moore’s law, chip multiprocessors, etc.). Exhibit the ability to compile and run basic Cilk++ programs. Display a hands-on knowledge of basic multicore-programming concepts, including nested and loop parallelism, serial semantics, race conditions. Describe performance concepts, including work, span, and parallelism. Show an understanding of the practical implications of elementary scheduling theory.
  • Day 2: Display a familiarity of advanced parallel programming concepts, such as locking, deadlock, synchronizing through memory, and reducers. Show an ability to deal with hurdles to parallelization, including insufficient parallelism, loop-carried dependences, grain size, burdened parallelism, memory bandwidth, nondeterminism, and legacy threading.

The course will be taught June 8-9 in Boston via a partnership with the MIT Professional Education program.  For more info, read all the details here.

Comments

  1. Wow this coarse really covers just about everything the days are completely filled with lots of all the stuff that we need to know with regards to this, I like the fact that in this there is a hands on approach, I like this as I find it a better way of learning, than just all the theory, as I find that this can at times be very confusing.

Resource Links: