Data stream processing via code annotations

Abstract

Time-to-solution is an important metric when parallelizing existing code. The REPARA approach provides a systematic way to instantiate stream and data parallel patterns by annotating the sequential source code with $${\mathtt {C}}$$ ++ $${\mathtt {11}}$$ attributes. Annotations are automatically transformed in a target parallel code that uses existing libraries for parallel programming (e.g., FastFlow). In this paper, we apply this approach for the parallelization of a data stream processing application. The description shows the effectiveness of the approach in easily and quickly prototyping several parallel variants of the sequential code by obtaining good overall performance in terms of both throughput and latency.