DSLs for high performance computing

[Peter Alexander via Digitalmars-d]

On Wednesday, 18 June 2014 at 19:00:26 UTC, Andrei Alexandrescu 
wrote:
> The work on such DSLs (reminiscent of Don's work on optimizing 
> matrix operations years ago) seems be on the rise.

Is it?

It would be good for D if it is, since D has a great offering in 
that arena, but I haven't seen much, if any, new DSL work 
recently. Maybe I'm not looking in the right places.