Towards Efficient Hyperdimensional Computing Using Photonics
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917794037104640 |
|---|---|
| author | Fayza, Farbin Demirkiran, Cansu Chen, Hanning Liu, Che-Kai Mohan, Avi Errahmouni, Hamza Yun, Sanggeon Imani, Mohsen Zhang, David Bunandar, Darius Joshi, Ajay |
| author_facet | Fayza, Farbin Demirkiran, Cansu Chen, Hanning Liu, Che-Kai Mohan, Avi Errahmouni, Hamza Yun, Sanggeon Imani, Mohsen Zhang, David Bunandar, Darius Joshi, Ajay |
| contents | Over the past few years, silicon photonics-based computing has emerged as a promising alternative to CMOS-based computing for Deep Neural Networks (DNN). Unfortunately, the non-linear operations and the high-precision requirements of DNNs make it extremely challenging to design efficient silicon photonics-based systems for DNN inference and training. Hyperdimensional Computing (HDC) is an emerging, brain-inspired machine learning technique that enjoys several advantages over existing DNNs, including being lightweight, requiring low-precision operands, and being robust to noise introduced by the nonidealities in the hardware. For HDC, computing in-memory (CiM) approaches have been widely used, as CiM reduces the data transfer cost if the operands can fit into the memory. However, inefficient multi-bit operations, high write latency, and low endurance make CiM ill-suited for HDC. On the other hand, the existing electro-photonic DNN accelerators are inefficient for HDC because they are specifically optimized for matrix multiplication in DNNs and consume a lot of power with high-precision data converters.
In this paper, we argue that photonic computing and HDC complement each other better than photonic computing and DNNs, or CiM and HDC. We propose PhotoHDC, the first-ever electro-photonic accelerator for HDC training and inference, supporting the basic, record-based, and graph encoding schemes. Evaluating with popular datasets, we show that our accelerator can achieve two to five orders of magnitude lower EDP than the state-of-the-art electro-photonic DNN accelerators for implementing HDC training and inference. PhotoHDC also achieves four orders of magnitude lower energy-delay product than CiM-based accelerators for both HDC training and inference. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_17801 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Towards Efficient Hyperdimensional Computing Using Photonics Fayza, Farbin Demirkiran, Cansu Chen, Hanning Liu, Che-Kai Mohan, Avi Errahmouni, Hamza Yun, Sanggeon Imani, Mohsen Zhang, David Bunandar, Darius Joshi, Ajay Emerging Technologies Hardware Architecture Machine Learning Over the past few years, silicon photonics-based computing has emerged as a promising alternative to CMOS-based computing for Deep Neural Networks (DNN). Unfortunately, the non-linear operations and the high-precision requirements of DNNs make it extremely challenging to design efficient silicon photonics-based systems for DNN inference and training. Hyperdimensional Computing (HDC) is an emerging, brain-inspired machine learning technique that enjoys several advantages over existing DNNs, including being lightweight, requiring low-precision operands, and being robust to noise introduced by the nonidealities in the hardware. For HDC, computing in-memory (CiM) approaches have been widely used, as CiM reduces the data transfer cost if the operands can fit into the memory. However, inefficient multi-bit operations, high write latency, and low endurance make CiM ill-suited for HDC. On the other hand, the existing electro-photonic DNN accelerators are inefficient for HDC because they are specifically optimized for matrix multiplication in DNNs and consume a lot of power with high-precision data converters. In this paper, we argue that photonic computing and HDC complement each other better than photonic computing and DNNs, or CiM and HDC. We propose PhotoHDC, the first-ever electro-photonic accelerator for HDC training and inference, supporting the basic, record-based, and graph encoding schemes. Evaluating with popular datasets, we show that our accelerator can achieve two to five orders of magnitude lower EDP than the state-of-the-art electro-photonic DNN accelerators for implementing HDC training and inference. PhotoHDC also achieves four orders of magnitude lower energy-delay product than CiM-based accelerators for both HDC training and inference. |
| title | Towards Efficient Hyperdimensional Computing Using Photonics |
| topic | Emerging Technologies Hardware Architecture Machine Learning |
| url | https://arxiv.org/abs/2311.17801 |