C$ (CBucks). Another CPU to GPU calculation engine.
This about sums it up.
C$ language, while concentrating on solving computationally intensive problems, also aims at solving system problems and easing integration of high-performance code into user-friendly applications, which becomes crucial as parallelism becomes widely available even on commodity PCs. In order to solve system problems, one needs object-oriented programming support in the language. For high-performance programming, however, one needs some means of parallelization. As the language is supposed to be highly portable, no assumptions can be made about the underlying architecture (GPU, SMP etc.). Therefore, some kind of array programming seems a good choice here.
C$ Project Home Page
The aim of this project is creating a unified language and system for seamless parallel programming on modern GPU's and CPU's. In future, it is planned to be extended to other processors.