Hypermultiplexed Integrated-Photonics-based Tensor Optical Processor
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909365933441024 |
|---|---|
| author | Ou, Shaoyuan Xue, Kaiwen Zhou, Lian Lee, Chun-ho Sludds, Alexander Hamerly, Ryan Zhang, Ke Feng, Hanke Kopparapu, Reshma Zhong, Eric Wang, Cheng Englund, Dirk Yu, Mengjie Chen, Zaijun |
| author_facet | Ou, Shaoyuan Xue, Kaiwen Zhou, Lian Lee, Chun-ho Sludds, Alexander Hamerly, Ryan Zhang, Ke Feng, Hanke Kopparapu, Reshma Zhong, Eric Wang, Cheng Englund, Dirk Yu, Mengjie Chen, Zaijun |
| contents | The escalating data volume and complexity resulting from the rapid expansion of artificial intelligence (AI), internet of things (IoT) and 5G/6G mobile networks is creating an urgent need for energy-efficient, scalable computing hardware. Here we demonstrate a hypermultiplexed integratedphotonics-based tensor optical processor (HITOP) that can perform trillions of operations per second (TOPS) at the energy efficiency of 40 TOPS/W. Space-time-wavelength three-dimensional (3D) optical parallelism enables O($N^{2}$) operations per clock-cycle using O($N$) modulator devices. The system is built with wafer-fabricated III/V micron-scale lasers and high-speed thin-film Lithium-Niobate electro-optics for encoding at 10s femtojoule/symbol. Lasing threshold incorporates analog inline rectifier (ReLu) nonlinearity for low-latency activation. The system scalability is verified with machine learning models of 405,000 parameters. A combination of high clockrates, energy-efficient processing and programmability unlocks the potential of light for large-scale AI accelerators in applications ranging from training of large AI models to real-time decision making in edge deployment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_18050 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Hypermultiplexed Integrated-Photonics-based Tensor Optical Processor Ou, Shaoyuan Xue, Kaiwen Zhou, Lian Lee, Chun-ho Sludds, Alexander Hamerly, Ryan Zhang, Ke Feng, Hanke Kopparapu, Reshma Zhong, Eric Wang, Cheng Englund, Dirk Yu, Mengjie Chen, Zaijun Emerging Technologies Optics The escalating data volume and complexity resulting from the rapid expansion of artificial intelligence (AI), internet of things (IoT) and 5G/6G mobile networks is creating an urgent need for energy-efficient, scalable computing hardware. Here we demonstrate a hypermultiplexed integratedphotonics-based tensor optical processor (HITOP) that can perform trillions of operations per second (TOPS) at the energy efficiency of 40 TOPS/W. Space-time-wavelength three-dimensional (3D) optical parallelism enables O($N^{2}$) operations per clock-cycle using O($N$) modulator devices. The system is built with wafer-fabricated III/V micron-scale lasers and high-speed thin-film Lithium-Niobate electro-optics for encoding at 10s femtojoule/symbol. Lasing threshold incorporates analog inline rectifier (ReLu) nonlinearity for low-latency activation. The system scalability is verified with machine learning models of 405,000 parameters. A combination of high clockrates, energy-efficient processing and programmability unlocks the potential of light for large-scale AI accelerators in applications ranging from training of large AI models to real-time decision making in edge deployment. |
| title | Hypermultiplexed Integrated-Photonics-based Tensor Optical Processor |
| topic | Emerging Technologies Optics |
| url | https://arxiv.org/abs/2401.18050 |