Accelerating range-based loops on heterogeneous systems

Range-based loop is a powerful construct due to its clear and concise syntax. The abstraction of loop index in a range-based loop implies loop-level parallelism ready to be exploited. Despite its advantage on hidden parallelism and programmability, the magnitude of performance gain by accelerating range-based loop on heterogeneous systems is still not well studied. This paper addresses this issue and make three contributions. First, the review showing the magnitude of performance gain from CUDA/OpenCL code, generated by ten exisiting auto-parallelizing compilers is presented. Second, the performance comparison between range-based and traditional loops acceleration on four workloads from the SHOC benchmark is reported. Third, the performance limitation on using directive-based compiler to accelerate range-based loop is discussed. The results show that transforming scientific workloads to exploit range-based loops is a challenge. The review results show that code generated by auto-parallelizing achieved an average of 37±23 folds speedup relative to sequential CPU, while the proposed range-based compiler achieved higher speedup than the average (44.8±22x). The evaluation against four workloads from highly-tuned benchmark shows that range-based loop acceleration achieved in average 72% of the benchmark's performance. This highlights range-based loops as a promising target for auto parallelizing compiling code on heterogeneous systems.