A New Benchmark for the Appropriate Evaluation of RTL Code Optimization

TL;DR

This paper introduces RTL-OPT, a comprehensive benchmark with diverse RTL designs and an evaluation framework to assess the ability of language models to optimize hardware code in terms of power, performance, and area.

Contribution

It presents RTL-OPT, the first benchmark specifically designed to evaluate LLMs on RTL optimization quality, including functional correctness and PPA improvements.

Findings

Provides a diverse set of 36 RTL design tasks.

Includes an automated framework for functional and PPA evaluation.

Enables standardized assessment of LLMs in hardware optimization.

Abstract

The rapid progress of artificial intelligence increasingly relies on efficient integrated circuit (IC) design. Recent studies have explored the use of large language models (LLMs) for generating Register Transfer Level (RTL) code, but existing benchmarks mainly evaluate syntactic correctness rather than optimization quality in terms of power, performance, and area (PPA). This work introduces RTL-OPT, a benchmark for assessing the capability of LLMs in RTL optimization. RTL-OPT contains 36 handcrafted digital designs that cover diverse implementation categories including combinational logic, pipelined datapaths, finite state machines, and memory interfaces. Each task provides a pair of RTL codes, a suboptimal version and a human-optimized reference that reflects industry-proven optimization patterns not captured by conventional synthesis tools. Furthermore, RTL-OPT integrates an automated evaluation framework to verify functional correctness and quantify PPA improvements, enabling standardized and meaningful assessment of generative models for hardware design optimization.