Benchmarking End-To-End Performance of AI-Based Chip Placement Algorithms

TL;DR

This paper introduces ChiPBench, a comprehensive benchmark for evaluating AI-based chip placement algorithms based on their impact on final design PPA, addressing the gap between intermediate metrics and end-to-end performance.

Contribution

The paper presents ChiPBench, a new benchmark with 20 diverse circuits to evaluate AI chip placement algorithms on actual final PPA metrics, bridging the evaluation gap.

Findings

AI algorithms often optimize intermediate metrics but not final PPA.

Experimental results show discrepancies between intermediate and final PPA outcomes.

Benchmark facilitates realistic assessment of AI-based chip placement methods.

Abstract

The increasing complexity of modern very-large-scale integration (VLSI) design highlights the significance of Electronic Design Automation (EDA) technologies. Chip placement is a critical step in the EDA workflow, which positions chip modules on the canvas with the goal of optimizing performance, power, and area (PPA) metrics of final chip designs. Recent advances have demonstrated the great potential of AI-based algorithms in enhancing chip placement. However, due to the lengthy workflow of chip design, the evaluations of these algorithms often focus on intermediate surrogate metrics, which are easy to compute but frequently reveal a substantial misalignment with the end-to-end performance (i.e., the final design PPA). To address this challenge, we introduce ChiPBench, which can effectively facilitate research in chip placement within the AI community. ChiPBench is a comprehensive benchmark specifically designed to evaluate the effectiveness of existing AI-based chip placement algorithms in improving final design PPA metrics. Specifically, we have gathered 20 circuits from various domains (e.g., CPU, GPU, and microcontrollers). These designs are compiled by executing the workflow from the verilog source code, which preserves necessary physical implementation kits, enabling evaluations for the placement algorithms on their impacts on the final design PPA. We executed six state-of-the-art AI-based chip placement algorithms on these designs and plugged the results of each single-point algorithm into the physical implementation workflow to obtain the final PPA results. Experimental results show that even if intermediate metric of a single-point algorithm is dominant, while the final PPA results are unsatisfactory. We believe that our benchmark will serve as an effective evaluation framework to bridge the gap between academia and industry.