A Comparative Analysis of Microrings Based Incoherent Photonic GEMM Accelerators
Several microring resonator (MRR) based analog photonic architectures have been proposed to accelerate general matrix-matrix multiplications (GEMMs) in deep neural networks with exceptional throughput and energy efficiency. To implement GEMM functions, these MRR-based architectures, in general, manipulate optical signals in five different ways: (i) Splitting (copying) of multiple optical signals to achieve a certain fan-out, (ii) Aggregation (multiplexing) of multiple optical signals to achieve a certain fan-in, (iii) Modulation of optical signals to imprint input values onto analog signal amplitude, (iv) Weighting of modulated optical signals to achieve analog input-weight multiplication, (v) Summation of optical signals. The MRR-based GEMM accelerators undertake the first four ways of signal manipulation in an arbitrary order ignoring the possible impact of the order of these manipulations on their performance. In this paper, we conduct a detailed analysis of accelerator organizations with three different orders of these manipulations: (1) Modulation-Aggregation-Splitting-Weighting (MASW), (2) Aggregation-Splitting-Modulation-Weighting (ASMW), and (3) Splitting-Modulation-Weighting-Aggregation (SMWA). We show that these organizations affect the crosstalk noise and optical signal losses in different magnitudes, which renders these organizations with different levels of processing parallelism at the circuit level, and different magnitudes of throughput and energy-area efficiency at the system level. Our evaluation results for four CNN models show that SMWA organization achieves up to 4.4$\times$, 5$\times$, and 5.2$\times$ better throughput, energy efficiency, and area-energy efficiency, respectively, compared to ASMW and MASW organizations on average.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
A silicon photonics feed-forward neural network for nonlinear distortion mitigation in an optical link
We design and model a single-layer, passive, all-optical silicon photonics neural network to mitigate optical link nonlinearities. The network nodes are formed by silicon microring resonators whose transfer function has …
Signal-to-Noise Ratio of Microwave Photonic Filter With an Interferometric Structure Based on an Incoherent Broadband Optical Source
A comprehensive investigation of the signal-to-noise ratio (SNR) of the microwave photonic filter (MPF) with an interferometric structure based on an incoherent broadband optical source (IBOS) is presented from the time …
Non-negative isomorphic neural networks for photonic neuromorphic accelerators
Neuromorphic photonic accelerators are becoming increasingly popular, since they can significantly improve computation speed and energy efficiency, leading to femtojoule per MAC efficiency. However, deploying existing DL…
ChatGPT at the Speed of Light: Optical Comb-Based Monolithic Photonic-Electronic Linear-Algebra Accelerators
This paper proposes to adopt advanced monolithic silicon-photonics integrated-circuits manufacturing capabilities to achieve a system-on-chip photonic-electronic linear-algebra accelerator with the features of optical co…
A compact butterfly-style silicon photonic-electronic neural chip for hardware-efficient deep learning
The optical neural network (ONN) is a promising hardware platform for next-generation neurocomputing due to its high parallelism, low latency, and low energy consumption. Previous ONN architectures are mainly designed fo…