GitLab

Currently --repo, which is used to find simulators etc., defaults to '..',
which only works when executing in the 'experiments' directory in the simbricks
repo. Instead we make this relative to the run.py-file's path.

So far, simulator instances not connected to any other instances were
skipped accidentally when creating the graph.

Currently, when a checkpoint is created in gem5 using the KVM CPU, the
simulated tick when the checkpoint is taken will end up in the few
seconds or more when the KVM CPU is slow. When the checkpoint is
afterwards restored, gem5 will continue the simulation at this tick.
This means that other, synchronized simulators first have to catch up,
essentially just synchronizing without performing any useful work.
Depending on their speed, this can take a lot of time and is especially
costly with a RTL simulator in the loop. To avoid this we now, by
default, edit the to be restored gem5 checkpoint to start at tick 0
instead.

There are now no more inline functions and a proper main function
instead of top-level code. Functionality-wise, nothing was changed. Code
was only rearranged and some comments added.

Starting with Python3.11, asyncio.wait() doesn't accept coroutines anymore. Instead, we have to wrap every coroutine in a tasks.

These all do the same thing except with different hosts or NICs. Combine them
in one script running all configurations.
- gem5_i40e_pair
- qemu_i40e_pair
- qemu_e1000_pair

Helps quickly determine available CPU features in host simulators.

Currently we invoke m5 checksum for gem5 but nothing at all for other
simulators. This just adds an echo "ready for checkpoint". We use this in
simics to generate a checkpoint, but it is also sane default for simulators not
supporting checkpoints, as at least the logs will show what's going on.

Previously the default was m5 exit with a special case for QEMU. Here we flip
this in anticipation of Simics support.

Instead of first converting to strings. Should reduce memory consumption when
dealing with large logs.

drastically speeds up simulation performance in the presence of a lot of output