ArchAgent: Agentic AI-driven Computer Architecture Discovery

TL;DR

ArchAgent leverages agentic AI to autonomously discover and optimize cache replacement policies, achieving state-of-the-art performance improvements in a fraction of the time required by human experts.

Contribution

This paper introduces ArchAgent, an AI-driven system that automates computer architecture design, specifically discovering new cache policies faster and more effectively than traditional human-led methods.

Findings

Achieved 5.3% IPC speedup over SoTA in two days on multi-core workloads.

Generated a new cache policy in 18 days with 0.9% IPC improvement on SPEC06 workloads.

Enabled workload-specific tuning, resulting in an additional 2.4% IPC speedup.

Abstract

Agile hardware design flows are a critically needed force multiplier to meet the exploding demand for compute. Recently, agentic generative AI systems have demonstrated significant advances in algorithm design, improving code efficiency, and enabling discovery across scientific domains. Bridging these worlds, we present ArchAgent, an automated computer architecture discovery system built on AlphaEvolve. We show ArchAgent's ability to automatically design/implement state-of-the-art (SoTA) cache replacement policies (architecting new mechanisms/logic, not only changing parameters), broadly within the confines of an established cache replacement policy design competition. In two days without human intervention, ArchAgent generated a policy achieving a 5.3% IPC speedup improvement over the prior SoTA on public multi-core Google Workload Traces. On the heavily-explored single-core SPEC06 workloads, it generated a policy in just 18 days showing a 0.9% IPC speedup improvement over the existing SoTA (a similar "winning margin" as reported by the existing SoTA). ArchAgent achieved these gains 3-5x faster than prior human-developed SoTA policies. Agentic flows also enable "post-silicon hyperspecialization" where agents tune runtime-configurable parameters exposed in hardware policies to further align the policies with a specific workload (mix). Exploiting this, we demonstrate a 2.4% IPC speedup improvement over prior SoTA on SPEC06 workloads. Finally, we outline broader implications for computer architecture research in the era of agentic AI. For example, we demonstrate the phenomenon of "simulator escapes", where the agentic AI flow discovered and exploited a loophole in a popular microarchitectural simulator - a consequence of the fact that these research tools were designed for a (now past) world where they were exclusively operated by humans acting in good-faith.