HERO-ML is an array language, on very high level, which is intended for specifying data parallel algorithms in a concise and platform-independent way where all the inherent data parallelism is easy to identify. The goal is to support the software development for heterogeneous systems with different kinds of parallel numerical accelerators, where programs tend to be very platform-specific and difficult to develop.
HERO-ML was originally concieved within the HERO project. Results so far include a detailed language specification, and a proof-of-concept implementation. Any further development of HERO-ML will take place within this spinoff project.
The current implementation of HERO-ML (an interpreter written in F#) can be downloaded from https://hero-ml-language.github.io/.