Dynamic Precision Autotuning with TAFFO

Cherubin, Stefano; Cattaneo, Daniele; Chiari, Michele; Agosta, Giovanni

Abstract

Many classes of applications, both in the embedded and high performance domains, can trade off the accuracy of the computed results for computation performance. One way to achieve such a trade-off is precision tuning—that is, to modify the data types used for the computation by reducing the bit width, or by changing the representation from floating point to fixed point. We present a methodology for high-accuracy dynamic precision tuning based on the identification of input classes (i.e., classes of input datasets that benefit from similar optimizations). When a new input region is detected, the application kernels are re-compiled on the fly with the appropriate selection of parameters. In this way, we obtain a continuous optimization approach that enables the exploitation of the reduced precision computation while progressively exploring the solution space, thus reducing the time required by compilation overheads. We provide tools to support the automation of the runtime part of the solution, leaving to the user only the task of identifying the input classes. Our approach provides a significant performance boost (up to 320%) on the typical approximate computing benchmarks, without meaningfully affecting the accuracy of the result, since the error remains always below 3%.

Citation

Cherubin, S., Cattaneo, D., Chiari, M., & Agosta, G. (2020). Dynamic Precision Autotuning with TAFFO. ACM transactions on architecture and code optimization, 17(2), Article 10. https://doi.org/10.1145/3388785

• Journal Article Type: Article
• Acceptance Date: Mar 1, 2020
• Online Publication Date: May 29, 2020
• Publication Date: 2020
• Deposit Date: Feb 2, 2022
• Journal: ACM Transactions on Architecture and Code Optimization
• Print ISSN: 1544-3566
• Electronic ISSN: 1544-3973
• Publisher: Association for Computing Machinery (ACM)
• Peer Reviewed: Peer Reviewed
• Volume: 17
• Issue: 2
• Article Number: 10
• DOI: https://doi.org/10.1145/3388785
• Public URL: http://researchrepository.napier.ac.uk/Output/2839670