Fully reconfigurable coherent optical vector–matrix multiplication
Полностью перенастраиваемое когерентное оптическое умножение вектор–матрица
2020-09-14
SCID: 54.1/ebuf8k3d
Discuss with AI
coherent optical vector–matrix multiplicationoptical neural networksparallel vector-vector multiplicationreconfigurable free-space optical multiplierspatial light modulators
Figures from the paper
Abstract (AI)
Optics is a promising platform in which to help realize the next generation of fast, parallel, and energy-efficient computation. We demonstrate a reconfigurable free-space optical multiplier that is capable of over 3000 computations in parallel, using spatial light modulators with a pixel resolution of only 340×340. This enables vector-matrix multiplication and parallel vector-vector multiplication with vector size of up to 56. Our design is, to the best of our knowledge, the first to simultaneously support optical implementation of reconfigurable, large-sized, and real-valued linear algebraic operations. Such an optical multiplier can serve as a building block of special-purpose optical processors such as optical neural networks and optical Ising machines.
Key Findings
1
Demonstrated a reconfigurable free-space optical multiplier capable of performing over 3000 computations in parallel
2
Enabled vector-matrix multiplication and parallel vector-vector multiplication with vector size up to 56
3
First reported design to simultaneously support optical implementation of reconfigurable, large-sized, real-valued linear algebraic operations
4
Proposed optical multiplier as a building block for special-purpose optical processors (optical neural networks and optical Ising machines)
5
Used spatial light modulators with pixel resolution 340×340 to enable the system
Research Object
Reconfigurable free-space coherent optical multiplier using spatial light modulators (340×340 pixels) for vector–matrix and parallel vector–vector multiplication
Research Subject
Optical implementation and performance of reconfigurable, large-sized, real-valued linear algebra operations (vector–matrix and parallel vector–vector multiplication) with up to 3000 parallel computations and vector size up to 56
Publication Details
Publication Date
2020-09-14
Journal
Publisher
ISSN
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest