I've just finished the prototype of HVM, a beta-optimal, massively parallel, GC-free runtime for functional programming languages. It may be the key to fully harvesting the parallelism of CPUs and GPUs with no programmer action. It already beats GHC, the fastest functional compiler in the world, in many cases. On its repository, there is a description of how all it works:
https://github.com/kindelia/hvm
What do you think?
Top comments (0)