GitLab

this gets rid of the non-fatal build error 'No names found, cannot describe anything'

Simply installs vanilla simics under sims/external/simics. Because of licensing
restrictions we cannot automatically download simics from the intel page.
Instead the makefile will prompt the user to download to files and add them to
the simics directory.

This commit does not include any simbricks integration at all yet.
Co-authored-by: Antoine Kaufmann <antoinek@mpi-sws.org>

The newer linux drivers now use 16b instead of 32b descriptors. So far
this leads to an abort. This adds proper support for 16b descriptors.

Depending on the order some of the constructors get executed, instances of the
logger can end up with a null pointer for the runner. This led to a segfault
when calling TimePs() on that nullptr.

Here we fix this in two steps: first the logger takes a device pointer, which
in turn contains a pointer to the runner that will eventually be initialized.
Also fix up the logger to simply use 0 as a timestamp for log events before the
runner is there.

P4 implementation of memory steering and address translation with the tofino
simulator.

Basic switch simulator that can steer network memory requests to different
network attached memory modules based on a configured address mapping. The
switch also performs address translation.
Co-authored-by: GAO Bin <bingao.cs@gmail.com>

Basic behavioral simulator for a memory controller to access  network attached
memory accessed via a simple UDP protocol.
Co-authored-by: Hejing Li <hajeongee@gmail.com>
Co-authored-by: Antoine Kaufmann <antoinek@mpi-sws.org>

Basic behavioral simulator for a network attached memory accessed via a simple
UDP protocol.
Co-authored-by: Hejing Li <hajeongee@gmail.com>
Co-authored-by: Antoine Kaufmann <antoinek@mpi-sws.org>

A very simple UDP-based protocol for accessing network-attached memories.

Basic behavioral memory simulator that implements the new memory protocol.
Co-authored-by: Antoine Kaufmann <antoinek@mpi-sws.org>
Co-authored-by: Jonas Kaufmann <jokau03@gmail.com>

make lint should pass again now

Empty structs are not standard C and sizeof for them in gcc is zero but for c++
is 1.

(uses SimBricksBaseIfEstablish)

As the python scripts pass the same arguments to both. We had dropped the sync
mode here but not in nicbm. For now just make it consistent

Currently sequence number is printed signed, while gem5 prints it unsigned as
it should be.

Previously we were calling completions etc. directly, but then the
prioritization does not match what gem5 does. This is slightly slower, but we
want to match gem5 exactly here.