Tutorial: Efficient and safe approaches to mutation in data parallelism

By the way, I’m by no means an expert on CPU hardware and have very little understanding of how the coherence protocol actually works. In particular, I don’t know how on earth certain false sharing does not happen in Intel and IBM CPUs. So, I appreciate if the experts comment on/fact check the false sharing part.

(Of course, comments on other points are also welcome too :slight_smile: )

2 Likes