OpenMP Towards Approximation: Loop Perforation and Multithreading

• João B. Oliveira UTFPR
• Rogério A. Gonçalves UTFPR
• João Fabrício Filho UTFPR

DOI: https://doi.org/10.5753/eradsp.2024.239866

Abstract

This study investigates the integration of loop perforation into OpenMP to enhance the performance of applications on systems with limited computational resources. Four perforation techniques – init, fini, large, and small – were implemented, with experimental results demonstrating significant performance gains across various test configurations. The results indicate performance improvements up to 43.33% with the proposed techniques.

References

Che, S., Boyer, M., Meng, J., Tarjan, D., Sheaffer, J. W., Lee, S.-H., and Skadron, K. (2009). Rodinia: A benchmark suite for heterogeneous computing. In 2009 IEEE International Symposium on Workload Characterization (IISWC), pages 44–54.

Parasyris, K., Georgakoudis, G., Menon, H., Diffenderfer, J., Laguna, I., Osei-Kuffuor, D., and Schordan, M. (2021). HPAC: evaluating approximate computing techniques on HPC OpenMP applications. In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pages 1–14, St. Louis Missouri. ACM.

Que, H.-H., Jin, Y., Wang, T., Liu, M.-K., Yang, X.-H., and Qiao, F. (2023). A Survey of Approximate Computing: From Arithmetic Units Design to HighLevel Applications. Journal of Computer Science and Technology, 38(2):251–272.