TY - GEN
T1 - Bitwise Neural Network Acceleration Using Silicon Photonics
AU - Shiflett, Kyle
AU - Karanth, Avinash
AU - Louri, Ahmed
AU - Bunescu, Razvan
N1 - Publisher Copyright:
© 2021 ACM.
PY - 2021/6/22
Y1 - 2021/6/22
N2 - Hardware accelerators provide significant speedup and improve energy efficiency for several demanding deep neural network (DNN) applications. DNNs have several hidden layers that perform concurrent matrix-vector multiplications (MVMs) between the network weights and input features. As MVMs are critical to the performance of DNNs, previous research has optimized the performance and energy efficiency of MVMs at both the architecture and algorithm levels. In this paper, we propose to use emerging silicon photonics technology to improve parallelism, speed and overall efficiency with the goal of providing real-time inference and fast training of neural nets. We use microring resonators (MRRs) and Mach-Zehnder interferometers (MZIs) to design two versions (all-optical and partial-optical) of hybrid matrix multiplications for DNNs. Our results indicate that our partial optical design gave the best performance in both energy efficiency and latency, with a reduction of 33.1% for energy-delay product (EDP) with conservative estimates and a 76.4% reduction for EDP with aggressive estimates.
AB - Hardware accelerators provide significant speedup and improve energy efficiency for several demanding deep neural network (DNN) applications. DNNs have several hidden layers that perform concurrent matrix-vector multiplications (MVMs) between the network weights and input features. As MVMs are critical to the performance of DNNs, previous research has optimized the performance and energy efficiency of MVMs at both the architecture and algorithm levels. In this paper, we propose to use emerging silicon photonics technology to improve parallelism, speed and overall efficiency with the goal of providing real-time inference and fast training of neural nets. We use microring resonators (MRRs) and Mach-Zehnder interferometers (MZIs) to design two versions (all-optical and partial-optical) of hybrid matrix multiplications for DNNs. Our results indicate that our partial optical design gave the best performance in both energy efficiency and latency, with a reduction of 33.1% for energy-delay product (EDP) with conservative estimates and a 76.4% reduction for EDP with aggressive estimates.
KW - deep neural networks
KW - optical signal processing
KW - silicon photonics
UR - http://www.scopus.com/inward/record.url?scp=85109210183&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85109210183&partnerID=8YFLogxK
U2 - 10.1145/3453688.3461515
DO - 10.1145/3453688.3461515
M3 - Conference contribution
AN - SCOPUS:85109210183
T3 - Proceedings of the ACM Great Lakes Symposium on VLSI, GLSVLSI
SP - 9
EP - 14
BT - GLSVLSI 2021 - Proceedings of the 2021 Great Lakes Symposium on VLSI
PB - Association for Computing Machinery
T2 - 31st Great Lakes Symposium on VLSI, GLSVLSI 2021
Y2 - 22 June 2021 through 25 June 2021
ER -