Trackable Island-model Genetic Algorithms at Wafer Scale

TL;DR

This paper introduces a tracking-enabled island-model genetic algorithm framework optimized for wafer-scale hardware, enabling high-speed evolutionary simulations and phylogenetic analysis at unprecedented scales.

Contribution

It presents a novel scalable GA framework for wafer-scale hardware that allows real-time tracking and phylogenetic inference of evolutionary processes.

Findings

Achieves over 1 million generations per minute on large populations.

Supports quadrillions of evaluations per day.

Enables extraction of phylogenetic signals to infer evolutionary conditions.

Abstract

Emerging ML/AI hardware accelerators, like the 850,000 processor Cerebras Wafer-Scale Engine (WSE), hold great promise to scale up the capabilities of evolutionary computation. However, challenges remain in maintaining visibility into underlying evolutionary processes while efficiently utilizing these platforms' large processor counts. Here, we focus on the problem of extracting phylogenetic information from digital evolution on the WSE platform. We present a tracking-enabled asynchronous island-based genetic algorithm (GA) framework for WSE hardware. Emulated and on-hardware GA benchmarks with a simple tracking-enabled agent model clock upwards of 1 million generations a minute for population sizes reaching 16 million. This pace enables quadrillions of evaluations a day. We validate phylogenetic reconstructions from these trials and demonstrate their suitability for inference of underlying evolutionary conditions. In particular, we demonstrate extraction of clear phylometric signals that differentiate wafer-scale runs with adaptive dynamics enabled versus disabled. Together, these benchmark and validation trials reflect strong potential for highly scalable evolutionary computation that is both efficient and observable. Kernel code implementing the island-model GA supports drop-in customization to support any fixed-length genome content and fitness criteria, allowing it to be leveraged to advance research interests across the community.