TAFFO: Tuning Assistant for Floating to Fixed Point Optimization

Cherubin, Stefano; Cattaneo, Daniele; Chiari, Michele; Bello, Antonio Di; Agosta, Giovanni

Abstract

While many approximate computing methods are quite application-dependent, reducing the size of the data representation used in the computation has a more general applicability. We present a tuning assistant for floating to fixed point optimization (TAFFO), an LLVM-based framework designed to assist programmers in the precision tuning of software. We discuss the framework architecture and we provide guidelines to effectively tradeoff precision to improve the time-to-solution. We evaluate our framework on a well-known approximate computing benchmark suite, AXBENCH, achieving a speedup on 5 out of 6 benchmarks (up to 366%) with only a limited loss in precision (

Citation

Cherubin, S., Cattaneo, D., Chiari, M., Bello, A. D., & Agosta, G. (2020). TAFFO: Tuning Assistant for Floating to Fixed Point Optimization. IEEE Embedded Systems Letters, 12(1), 5-8. https://doi.org/10.1109/les.2019.2913774

• Journal Article Type: Article
• Acceptance Date: Apr 22, 2019
• Online Publication Date: Apr 29, 2019
• Publication Date: 2020-03
• Deposit Date: Mar 11, 2021
• Journal: IEEE Embedded Systems Letters
• Print ISSN: 1943-0663
• Publisher: Institute of Electrical and Electronics Engineers (IEEE)
• Peer Reviewed: Peer Reviewed
• Volume: 12
• Issue: 1
• Pages: 5-8
• DOI: https://doi.org/10.1109/les.2019.2913774
• Public URL: http://researchrepository.napier.ac.uk/Output/2749993