ABSTRACT
We present a hybrid optical-electrical analog deep learning (DL) accelerator, the first work to use incoherent optical signals for DL workloads. Incoherent optical designs are more attractive than coherent ones as the former can be more easily realized in practice. However, a significant challenge in analog DL accelerators, where multiply-accumulate operations are dominant, is that there is no known solution to perform accumulation using incoherent optical signals. We overcome this challenge by devising a hybrid approach: accumulation is done in the electrical domain, while multiplication is performed in the optical domain. The key technology enabler of our design is the transistor laser, which performs electrical-to-optical and optical-to-electrical conversions efficiently to tightly integrate electrical and optical devices into compact circuits. As such, our design fully realizes the ultra high-speed and high-energy-efficiency advantages of analog and optical computing. Our evaluation results using the MNIST benchmark show that our design achieves 2214× and 65× improvements in latency and energy, respectively, compared to a state-of-the-art memristor-based analog design.
- A. Arbabi et al. 2011. Realization of a narrowband single wavelength microring mirror. Applied Physics Letters 99, 9 (2011).Google ScholarCross Ref
- Rajeev Balasubramonian et al. 2017. CACTI 7: New Tools for Interconnect Exploration in Innovative Off-Chip Memories. ACM Trans. Archit. Code Optim. 14, 2 (2017).Google Scholar
- D. J. Blumenthal et al. 2018. Silicon Nitride in Silicon Photonics. Proc. IEEE 106, 12 (Dec 2018), 2209--2231.Google ScholarCross Ref
- Julian Bueno et al. 2018. Reinforcement learning in a large-scale photonic recurrent neural network. Optica 5, 6 (2018), 756--760.Google ScholarCross Ref
- John Carlson et al. 2019. Epitaxial Bonding and Transfer Processes for Large-Scale Heterogeneously Integrated Electronic-Photonic Circuitry. J. Electrochem. Soc. 166, D3158 (2019).Google Scholar
- Julie Chang et al. 2018. Hybrid optical-electronic convolutional neural networks with optimized diffractive optics for image classification. Scientific reports 8, 1 (2018), 12324.Google Scholar
- Milton Feng et al. 2017. Resonance-free optical response of a vertical cavity transistor laser. Applied Physics Letters 111, 12 (2017).Google Scholar
- Tyler W Hughes et al. 2018. Training of photonic neural networks through in situ back propagation and gradient measurement. Optica (2018).Google Scholar
- M. R. Jokar et al. 2019. Direct-modulated optical networks for interposer systems. In Proceedings of the 13th IEEE/ACM International Symposium on Networks-on-Chip.Google ScholarDigital Library
- M. R. Jokar et al. 2020. Baldur: A Power-Efficient and Scalable Network Using All-Optical Switches. In 2020 IEEE International Symposium on High Performance Computer Architecture (HPCA). 153--166.Google Scholar
- Haibo Liang et al. 2015. Electro-optical phase-change 2x2 switching using threeand four-waveguide directional couplers. Appl. Opt. (Jul 2015).Google Scholar
- I. Palit et al. 2019. A Uniform Modeling Methodology for Benchmarking DNN Accelerators. In 2019 IEEE/ACM International Conference on Computer-Aided Design (ICCAD). 1--7.Google ScholarCross Ref
- A. Shafiee et al. 2016. ISAAC: A Convolutional Neural Network Accelerator with In-Situ Analog Arithmetic in Crossbars. In ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA).Google Scholar
- Yichen Shen et al. 2017. Deep learning with coherent nanophotonic circuits. Nature Photonics 11, 7 (2017), 441.Google ScholarCross Ref
- P. R. Stanfield et al. 2019. CMOS-compatible, piezo-optomechanically tunable photonics for visible wavelengths and cryogenic temperatures. Opt. Express 27, 20 (Sep 2019), 28588--28605.Google ScholarCross Ref
- Han Wui Then, Milton Feng, and Nick Holonyak. 2013. The transistor laser: Theory and experiment. Proc. IEEE 101, 10 (2013), 2271--2298.Google ScholarCross Ref
- M. Zhao et al. 2017. Investigation of statistical retention of filamentary analog RRAM for neuromophic computing. In 2017 IEEE International Electron Devices Meeting (IEDM). 39.4.1--39.4.4.Google ScholarCross Ref
Index Terms
- A Hybrid Optical-Electrical Analog Deep Learning Accelerator Using Incoherent Optical Signals
Recommendations
A Hybrid Optical-Electrical Analog Deep Learning Accelerator Using Incoherent Optical Signals
Optical deep learning (DL) accelerators have attracted significant interests due to their latency and power advantages. In this article, we focus on incoherent optical designs. A significant challenge is that there is no known solution to perform single-...
DNNARA: A Deep Neural Network Accelerator using Residue Arithmetic and Integrated Photonics
ICPP '20: Proceedings of the 49th International Conference on Parallel ProcessingDeep Neural Networks (DNNs) are currently used in many fields, including critical real-time applications. Due to its compute-intensive nature, speeding up DNNs has become an important topic in current research. We propose a hybrid opto-electronic ...
A Deep Neural Network Accelerator using Residue Arithmetic in a Hybrid Optoelectronic System
The acceleration of Deep Neural Networks (DNNs) has attracted much attention in research. Many critical real-time applications benefit from DNN accelerators but are limited by their compute-intensive nature. This work introduces an accelerator for ...
Comments