Photonic systolic array for all-optical matrix-matrix multiplication
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911287837982720 |
|---|---|
| author | Kim, Jungmin Zhou, Qingyi Yu, Zongfu |
| author_facet | Kim, Jungmin Zhou, Qingyi Yu, Zongfu |
| contents | Systolic arrays have proven to be highly efficient for parallelized matrix-matrix multiplication (MMM), utilizing synchronized, heartbeat-like data flows across an array of processing elements. While optical structures such as waveguide crossbar arrays and Mach-Zehnder interferometer-based meshes serve as photonic equivalents to the systolic arrays, the disparity between the two input matrices for multiplication -- one using optical signals and the other with system-defined parameters -- gives rise to a bottleneck in modern machine-learning tasks, such as evaluating attention scores in large language models. Here, we propose a photonic systolic array that performs MMM entirely with optical signals, utilizing homodyne detection at each array cell. Adjoint-based design of compact on-chip freeform optical modules enables precise control of light flow without bulky waveguide coupling schemes. The operation of a $4\times4$ photonic systolic array is numerically verified, achieving a theoretical computation density of $6.2~\mathrm{PMACs}/\mathrm{mm}^2/\mathrm{s}$. This design marks a significant step toward practical photonic computing hardware for modern AI workloads. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_21671 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Photonic systolic array for all-optical matrix-matrix multiplication Kim, Jungmin Zhou, Qingyi Yu, Zongfu Optics Systolic arrays have proven to be highly efficient for parallelized matrix-matrix multiplication (MMM), utilizing synchronized, heartbeat-like data flows across an array of processing elements. While optical structures such as waveguide crossbar arrays and Mach-Zehnder interferometer-based meshes serve as photonic equivalents to the systolic arrays, the disparity between the two input matrices for multiplication -- one using optical signals and the other with system-defined parameters -- gives rise to a bottleneck in modern machine-learning tasks, such as evaluating attention scores in large language models. Here, we propose a photonic systolic array that performs MMM entirely with optical signals, utilizing homodyne detection at each array cell. Adjoint-based design of compact on-chip freeform optical modules enables precise control of light flow without bulky waveguide coupling schemes. The operation of a $4\times4$ photonic systolic array is numerically verified, achieving a theoretical computation density of $6.2~\mathrm{PMACs}/\mathrm{mm}^2/\mathrm{s}$. This design marks a significant step toward practical photonic computing hardware for modern AI workloads. |
| title | Photonic systolic array for all-optical matrix-matrix multiplication |
| topic | Optics |
| url | https://arxiv.org/abs/2410.21671 |