PISim: A Unified Simulator for Photonic Neural Inference Design-Space Exploration
Researchers present PISim, a simulator that couples pretrained deep neural network execution with physics-based models of photonic accelerator architectures, modulator technologies, optical source organizations, and readout schemes. It embeds stage-resolved impairment operators for quantization, extinction ratio, shot noise, relative-intensity noise, thermal drift, propagation loss, and crosstalk, plus an analytical cycle-level interface timing model. In simulated MNIST MLP benchmarks, PISim identifies 6-bit optimal precision for Mach-Zehnder and microring modulators under multi-impairment stress and quantifies a 52.5-percentage-point accuracy gap between VCSEL-array and parallel-fanout laser architectures under the modeled conditions. It also models interface-limited throughput scaling across emitter-array widths from 32 to 128 channels.
It offers a reproducible pre-fabrication framework for evaluating accuracy, precision, and interface bottlenecks in photonic neural accelerators.
Comments & Questions (0)
No comments yet
Be the first to comment!