Back to AI News
arxiv

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.

AI Brief

It offers a reproducible pre-fabrication framework for evaluating accuracy, precision, and interface bottlenecks in photonic neural accelerators.

arXiv:2611.16522v1 Announce Type: cross Abstract: Photonic neural accelerators offer ultra-low latency linear algebra, yet their usable numerical precision, sustainable throughput, and application accuracy remain tightly bounded by surrounding electro-optical interfaces and physical non-idealities. Pre-fabrication design-space exploration (DSE) requires a cross-layer electronic design automation (EDA) framework capable of evaluating disparate optical topologies under identical neural workloads and physical assumptions. We present \textbf{PISim}, a unified Photonic Inference Simulator that couples pretrained deep neural network execution with physics-based models of six accelerator architecture families, six electro-optic modulator technologies, four optical source organizations, and direct or coherent readout schemes. PISim embeds stage-resolved impairment operators---covering control and analog-to-digital quantization, finite extinction ratio, shot noise, correlated relative-intensity noise (RIN), thermal drift, propagation loss, and channel crosstalk---alongside an analytical cycle-level interface timing model to expose electronic-optical bottlenecks. Using simulated MNIST multilayer perceptron (MLP) benchmarks, we demonstrate how PISim identifies optimal precision operating points under multi-impairment stress (peaking at 6 bits for Mach--Zehnder and microring modulators), quantifies a 52.5 percentage-point accuracy gap between VCSEL-array and parallel-fanout laser architectures arising, under the modeled conditions, from power partitioning and correlated source noise, and models interface-limited throughput scaling across emitter-array widths from 32 to 128 channels. This comprehensive framework establishes an extensible, reproducible foundation for accuracy-constrained Pareto optimization prior to photonic tape-out.
Be the first to rate this article.

Comments & Questions (0)

Captcha
Please be respectful — let's keep the conversation friendly.

No comments yet

Be the first to comment!