To Overlay or to Customize? Revisiting Architectural Choices in Heterogeneous Systems

2026-05-22

AI Summary

This study addresses the challenges of frequent model switching, energy efficiency, and reconfiguration overhead in autonomous driving scenarios by systematically comparing the deployment trade-offs between overlay architectures and custom accelerators. Through real workload-driven architectural simulations and multidimensional evaluation metrics—including reconfiguration latency, energy efficiency, and flexibility—the work provides the first quantitative assessment of these two architectural paradigms under realistic deployment conditions. The findings reveal that current overlay architectures are better suited for high-frequency switching scenarios; however, as reconfiguration overheads of custom accelerators decrease or the capabilities of overlay systems improve, the optimal deployment strategy may shift. These insights offer critical guidance for future heterogeneous hardware design targeting dynamic autonomous driving workloads.

Abstract

In this work, we present a systematic study of this trade-off from a deployment-centric perspective, focusing on an autonomous driving scenario. Instead of treating overlay and customized acceleration as isolated design points, we analyze when each approach is preferable under practical conditions, including workload variation, architectural design, reconfiguration latency, and switching frequency. Our analysis shows that overlay-based architecture is more suitable for highly frequent model switching under the state-of-the-art architecture. However, as bitstream reload overhead continues to reduce, customized architectures may become increasingly attractive, especially for workloads with efficiency requirements. Conversely, if overlay architectures become more capable and flexible, they may further expand their advantage over customized architectures. These observations provide design insights for future architectural design, and the optimal deployment strategy will be flipped according to the technique development.

Problem

• overlay architecture
• customized acceleration
• heterogeneous systems
• model switching
• deployment strategy

Innovation

• overlay architecture
• customized acceleration
• heterogeneous systems
• deployment-centric design
• reconfiguration latency