I stumbled across this paper describing a language that aims to do that. For some reason I was not that excited by the matrix multiplication use case, mainly because that is not the kind of application I'm interested in. I'd like to see examples of stuff a lot of cycles are burnt on in "web" data centers.

But I would like to see more work along these lines -- pointers appreciated.

http://sequoia.stanford.edu/

http://scholar.google.com/scholar?cluster=170564211168157303...

Modula-2 back in 1978.

Async is provided via co-routines and is as cache friendly as C.

That would break the point of it being 'low-level' unless you're saying the standard library and kernel were both designed to function like that.