Scaling Photonic Tensor Cores with Unary and Homodyne Designs
arXiv:2604.1466416.3h-index: 15
AI Analysis
For researchers in photonic computing, this work identifies design choices that improve scalability of tensor cores.
The paper analyzes five photonic microring tensor core designs using a common optical power model, finding that unary encoding and homodyne accumulation offer the strongest path to higher parallelism.
We analyze five photonic microring tensor core designs with a common optical power model. The results show that circuit ordering, unary encoding, and homodyne accumulation shape scalability, with the last two offering the strongest path to higher parallelism.