las3_pub / predictable_parallel_patterns

Basic profiling works. Next steps are to 'refine' the interface, i.e. allow to disable parts of the profiling and better output for some stats. Maybe look at storing/loading the DAG's with stats to/from disk.

Add key-points required to capture an execution DAG. Currently all data is in-memory and printed out. In future work it would be good to store the DAG's and/or process them further.

Remove easy profiler for now. It might be useful for later on to get a grasp of general behaviour, but because of its issues with coroutines it is not worth profiling code with it right now.

Merge continuation-style into master branch

See merge request !13

Our benchmarks require isolation from other system effects. Additionally,
we would like to have a system with 'very symmetric cores' (no hyperthreading,
no different memory connections, ....) that falls more into  the embedded
class of devices than desktop processors do. The notes describe how to setup
an banana pi m3 with a linux distri with rt preemt patch to achieve this.

Tsan needs the fix for not leaking fibers on the server to work properly.
Disable the tests until we can somehow easily get a build of it on the CI server.

I am not sure if this is appropriate, but it works and is no focus of this project.

Make sure that the guard page leads to sigsegv as expected.

It is now possible to use a memory mapped stack that throws a SIGSEV if thes coroutine stacks are exhausted.

Remove the strict static memory allocation scheme in favour of placing objects on the heap at startup. This still keeps the requirements posed for modern, high performance embedded systems, but makes APIs a lot cleaner.

The cas size could exceed an unsigned long, so we use the correct cas_integer type for the traded_cas_field representations.

We fixed the bug in tsan causing it to crash after creating/deleting many fibers, because of that there is no need for this cache mechanism (you have to use the most recent clang build with the patch for it to work thought).

We yield after num_thread failed steals in a row. This parameter can be tuned for better performance, but we stick to a sensible default just to prevent massive spinning.