DEVELOPING AN OPTIMIZED UPC COMPILER FOR FUTURE ARCHITECTURES

UPC, or Unified Parallel C, has been gaining rising attention as a promising productive parallel programming language that can lead to shorter time-to-solution. UPC enables application developers to exploit both parallelism and data locality, while enjoying a simple and easy to use syntax. This paper examines some of the early compilers that have been developed for UPC on many different platforms. Using these developments and previous experiments, the paper abstracts a number of considerations that must be observed in new UPC compiler developments, such as for the future IBM PERCS 1 architecture, in order to achieve high-performance without affecting the ease-of-use. In addition to those general considerations, the paper also examines some of the interesting features of the future architectures that can be exploited for running UPC more efficiently