Parallelizing code is usually done only under requirements to increase performance and/or efficiency. It is just too hard to write parallel code all the time and even if one manages to write correct parallel code the improvement over the initial code is often underwhelming.
This talk will be a whirlwind tour through the different dimensions of parallelization, the problems and pitfalls with the hardware, the techniques available, hardware and software, and a general outlook onto the direction the hard- and software industries move now and will be moving in the near future.
// Ulrich Drepper
worked on free software projects, mostly in the Linux environment, for 20+ years. He maintained the C/C++ runtime environment for Linux for 15 years and still contributes to all kinds of OS projects and programming language implementations.