A Full-System Simulation Framework for CXL-Based SSD Memory System
🤖 AI Summary
The Compute Express Link (CXL) memory expansion technology remains in its infancy, with a critical lack of system-level evaluation tools. Method: This paper introduces CXL-SSD-Sim—the first open-source full-system simulation framework for CXL-based memory expansion—built upon deeply customized gem5 and SimpleSSD. It enables end-to-end modeling of CXL-interconnected SSDs as memory devices, integrating a high-fidelity SSD model, an NVMe-over-CXL kernel driver, and a configurable DRAM cache layer to mitigate CXL’s inherent latency bottlenecks. Contribution/Results: We propose a novel hierarchical storage architecture and cache-coordination policy, supporting realistic workloads (e.g., SPEC CPU, Redis). Experimental evaluation across five memory device configurations quantifies latency, bandwidth, and application-level performance, substantially bridging the early-hardware validation gap for CXL. The framework is publicly released and has been adopted by the research community.
Application Category
📝 Abstract
Compute eXpress Link (CXL) is a promising technology for memory disaggregation and expansion. Especially, CXL makes it more effectively for large-capacity storage devices such as Solid State Drive (SSD) to be deployed in the memory pool. However, CXL-based SSDs are still in early stages, necessitating the development of reliable simulation tools. In this paper, we propose CXL-SSD-Sim, the first open-source full-system simulator designed to simulate CXL-based SSD memory system. Constructed on the foundation of gem5 and SimpleSSD, CXL-SSD-Sim extends an high fidelity SSD memory expander model along with the corresponding device driver. In addition, CXL-SSD-Sim models a DRAM layer as a caching mechanism for the SSD, meticulously engineered to counteract latency issues inherent to CXL-based SSD memory access. Experiments are performed among five different memory devices with CXL-SSD-Sim in aspect of latency, bandwidth and real-world benchmark performance. These experiments serve to underscore the efficacy of our simulation tool in providing a comprehensive analysis of CXL-based SSD memory systems. The CXL-SSD-Sim simulator is available at https://github.com/WangYaohuii/CXL-SSD-Sim.
Problem
Research questions and friction points this paper is trying to address.
CXL Technology
SSD Storage System
Performance Optimization
Innovation
Methods, ideas, or system contributions that make the work stand out.
CXL-SSD-Sim
open-source simulator
CXL technology
🔎 Similar Papers
No similar papers found.
