Recent applications in low-power (1-20 mW) near-sensor computing require the adoption of floating-point arithmetic to reconcile high precision results with a wide dynamic range. In this article, we propose a low-power 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 solution - based on the open-source RISC-V architecture - combines parallelization and sub-word vectorization with a dedicated interconnect design capable of sharing floating-point units (FPUs) among the cores. On top of this architecture, we provide a full-fledged software stack support, including a parallel low-level runtime, a compilation toolchain, and a high-level programming model, with the aim to support the development of end-to-end applications. We performed an exhaustive exploration of the design space of the transprecision cluster on a cycle-accurate FPGA emulator, varying the number of cores and FPUs to maximize performance. Orthogonally, we performed a vertical exploration to identify the most efficient solutions in terms of non-functional requirements (operating frequency, power, and area). We conducted an experimental assessment 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. 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. Finally, a real-life use case demonstrates the effectiveness of our approach in fulfilling accuracy constraints.

Montagna F., Mach S., Benatti S., Garofalo A., Ottavi G., Benini L., et al. (2022). A Low-Power Transprecision Floating-Point Cluster for Efficient Near-Sensor Data Analytics. IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 33(5), 1038-1053 [10.1109/TPDS.2021.3101764].

A Low-Power Transprecision Floating-Point Cluster for Efficient Near-Sensor Data Analytics

Montagna F.;Benatti S.;Garofalo A.;Ottavi G.;Benini L.;Rossi D.;Tagliavini G.
2022

Abstract

Recent applications in low-power (1-20 mW) near-sensor computing require the adoption of floating-point arithmetic to reconcile high precision results with a wide dynamic range. In this article, we propose a low-power 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 solution - based on the open-source RISC-V architecture - combines parallelization and sub-word vectorization with a dedicated interconnect design capable of sharing floating-point units (FPUs) among the cores. On top of this architecture, we provide a full-fledged software stack support, including a parallel low-level runtime, a compilation toolchain, and a high-level programming model, with the aim to support the development of end-to-end applications. We performed an exhaustive exploration of the design space of the transprecision cluster on a cycle-accurate FPGA emulator, varying the number of cores and FPUs to maximize performance. Orthogonally, we performed a vertical exploration to identify the most efficient solutions in terms of non-functional requirements (operating frequency, power, and area). We conducted an experimental assessment 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. 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. Finally, a real-life use case demonstrates the effectiveness of our approach in fulfilling accuracy constraints.
2022
Montagna F., Mach S., Benatti S., Garofalo A., Ottavi G., Benini L., et al. (2022). A Low-Power Transprecision Floating-Point Cluster for Efficient Near-Sensor Data Analytics. IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 33(5), 1038-1053 [10.1109/TPDS.2021.3101764].
Montagna F.; Mach S.; Benatti S.; Garofalo A.; Ottavi G.; Benini L.; Rossi D.; Tagliavini G.
File in questo prodotto:
File Dimensione Formato  
Low-Power_Transprecision_Cluster_pp.pdf

accesso aperto

Tipo: Postprint
Licenza: Licenza per accesso libero gratuito
Dimensione 1.05 MB
Formato Adobe PDF
1.05 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/870155
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 13
  • ???jsp.display-item.citation.isi??? 10
social impact