Performance analysis and optimization on HPX Rotate algorithm

HPX is a C++ Standard Library for Parallelism and Concurrency, which implements parallel versions of all C++ Standard algorithms. 

This poster presents the optimization of the HPX parallel rotate algorithm. The original implementation failed to effectively distribute work among CPU cores and caused un-needed overhead due to redundant usage of a hpx::future. The optimization consists of introducing core partitioning functionality and removing unnecessary overhead.

The results show significant performance gain, averaging a 2x improvement for input sizes smaller than 2^22 compared to the original implementation.