AGON: Automated Design Framework for Customizing Processors from ISA Documents

TL;DR

AGON is a novel framework that leverages large language models and a new IR to automate the design of customized out-of-order processors, achieving significant speedups with minimal human effort.

Contribution

The paper introduces AGON, a new LLM-based framework with a nano-operator IR that automates out-of-order processor design while ensuring correctness and enabling PPA optimization.

Findings

Achieves 2.35× speedup over BOOM processors.

Reduces human effort in processor design.

Provides correctness guarantees and PPA optimization.

Abstract

Customized processors are attractive solutions for vast domain-specific applications due to their high energy efficiency. However, designing a processor in traditional flows is time-consuming and expensive. To address this, researchers have explored methods including the use of agile development tools like Chisel or SpinalHDL, high-level synthesis (HLS) from programming languages like C or SystemC, and more recently, leveraging large language models (LLMs) to generate hardware description language (HDL) code from natural language descriptions. However, each method has limitations in terms of expressiveness, correctness, and performance, leading to a persistent contradiction between the level of automation and the effectiveness of the design. Overall, how to automatically design highly efficient and practical processors with minimal human effort remains a challenge. In this paper, we propose AGON, a novel framework designed to leverage LLMs for the efficient design of out-of-order (OoO) customized processors with minimal human effort. Central to AGON is the nano-operator function (nOP function) based Intermediate Representation (IR), which bridges high-level descriptions and hardware implementations while decoupling functionality from performance optimization, thereby providing an automatic design framework that is expressive and efficient, has correctness guarantees, and enables PPA (Power, Performance, and Area) optimization. Experimental results show that superior to previous LLM-assisted automatic design flows, AGON facilitates designing a series of customized OoO processors that achieve on average 2.35 $\times$ speedup compared with BOOM, a general-purpose CPU designed by experts, with minimal design effort.