Back to Search Start Over

A transprecision floating-point cluster for efficient near-sensor data analytics

Authors :
Montagna, Fabio
Mach, Stefan
Benatti, Simone
Garofalo, Angelo
Ottavi, Gianmarco
Benini, Luca
Rossi, Davide
Tagliavini, Giuseppe
Publication Year :
2020

Abstract

Recent applications in the domain of near-sensor computing require the adoption of floating-point arithmetic to reconcile high precision results with a wide dynamic range. In this paper, we propose a multi-core computing cluster that leverages the fined-grained tunable principles of transprecision computing to provide support to near-sensor applications at a minimum power budget. Our design - based on the open-source RISC-V architecture - combines parallelization and sub-word vectorization with near-threshold operation, leading to a highly scalable and versatile system. We perform an exhaustive exploration of the design space of the transprecision cluster on a cycle-accurate FPGA emulator, with the aim to identify the most efficient configurations in terms of performance, energy efficiency, and area efficiency. We also provide a full-fledged software stack support, including a parallel runtime and a compilation toolchain, to enable the development of end-to-end applications. We perform an experimental assessment of our design on a set of benchmarks representative of the near-sensor processing domain, complementing the timing results with a post place-&-route analysis of the power consumption. Finally, a comparison with the state-of-the-art shows that our solution outperforms the competitors in energy efficiency, reaching a peak of 97 Gflop/s/W on single-precision scalars and 162 Gflop/s/W on half-precision vectors.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2008.12243
Document Type :
Working Paper
Full Text :
https://doi.org/10.1109/TPDS.2021.3101764