Clove: Object-Level CXL Memory Management in Managed Runtimes

2026-05-19

AI Summary

This work addresses the mismatch between conventional page-based CXL heterogeneous memory management and the object-level memory access patterns inherent to managed language runtimes, which often leads to suboptimal performance and inefficient resource utilization. To bridge this gap, the paper introduces the first object-level CXL memory management system integrated into the JVM runtime. By leveraging the JVM’s built-in optimization infrastructure, the approach employs performance-profile-guided hot object tracking, lightweight object relocation, and a tailored migration policy to enable fine-grained tiered memory management. Evaluation of the prototype demonstrates that, compared to traditional page-level schemes, the proposed method reduces application slowdown by 22%–84%, substantially improves fast-tier memory utilization, and effectively contains runtime overhead.

Abstract

Object-level management of tiered memory has been studied to address the inefficiencies in page-based systems. However, object-level management for CXL-tiered memory remains underexplored due to CXL's tight performance budget and load/store interface. As a result, existing approaches remain limited in scope, primarily targeting unmanaged-language applications with bespoke runtimes or compiler support. This paper identifies and explores a new design point for object-level CXL management: managed languages and their runtimes. The key observation is that existing managed runtimes already provide highly optimized mechanisms for problems closely related to object-level management, including object relocation and dynamic code generation. However, they still lack the features needed for tiered memory management, such as hotness tracking and relocation policies, and thus must be carefully extended to fully realize this direction. We present Clove, a system that extends existing managed runtimes to support object-level CXL management for managed-language applications. Clove combines profile-guided object hotness tracking with object relocation techniques and policies. Our JVM prototype demonstrates that this extension enables high utilization of fast-tier memory while bounding runtime overhead, reducing application slowdown by 22-84% compared to page-based systems.

Problem

• CXL memory
• object-level management
• managed runtimes
• tiered memory
• memory management

Innovation

• CXL memory
• object-level management
• managed runtime
• hotness tracking
• memory tiering