We already have software archaeology today. People who are into software preservation track down old media, original creators, and dig through clues to restore pixel-perfect copies of abandonware. It's only going to get bigger / more important with time if we don't concentrate on open standards and open source everywhere.
And it's sad that many archivists have to break the law in order to secure the longevity of important cultural works.
Our abusive relationship with modern commercialism has disintegrated the value of art, folklore and tools, both in the eyes of consumers and producers, and we no longer as a society seek to preserve the greatest works of today's most cutting-edge mediums. It's quite a sad state of affairs, which will only be mourned with increasing intensity as time marches on and curious researchers try to piece together the early days of the internet and personal computing.
I'd say game emulation is currently the most prevalent heavyweight archaeology.
In the more common case, it's simply archiving -- we still have hardware it can run on (e.g. x86).
The GPGPU and ML stuff is likely going to age poorer, although at least we had the sense to funnel most high level code through standardized APIs and libraries.
Seems quite possible that the the present will seem to future archeologists like an illiterate dark ages, between civilisations from which paper records, that last long enough for them to find, are preserved.
It seems impossible that, given current economic trajectories, there won't be software archaeology in the future.