A "device memory" enabling project encompassing tools and libraries for CXL, NVDIMMs, DAX, memory tiering and other platform memory device topics.

Pond: CXL-Based Memory Pooling Systems for Cloud Platforms (ASPLOS'23)

A full-system, cycle-level simulator based on gem5 that provides complete support for all three CXL sub-protocols and all three types of CXL devices.

A library for constructing allocators and memory pools. It also contains broadly useful abstractions and utilities for memory management. UMF allows users to manage multiple memory pools characterized by different attributes, allowing certain allocation types to be isolated from others and allocated using different hardware resources as required.

Tigon: A Distributed Database for a CXL Pod [OSDI '25]

[ACM CoNEXT22 Best Paper Award] NTSocks: An ultra-low latency and compatible PCIe interconnect for rack-scale disaggregation.

Pin based tool for simulation of rack-scale disaggregated memory systems

Tiered Memory Management Beyond Hotness (OSDI'25)

Systematic CXL Memory Characterization and Performance Analysis at Scale (ASPLOS'25)

CXL Management Interface library

Contain some materials about CXL.

STREAMer: Benchmarking remote volatile and non-volatile memory bandwidth

kernel development code for my work (ioatdma, ntb_hw_intel, idxd, PCI, and CXL related bits)

Codes for our ADMS'24 paper "Bandwidth Expansion via CXL: A Pathway to Accelerating In-Memory Analytical Processing".

[ACM CoNEXT22 Best Paper Award] Case Study: A Fast Nginx and Apache Bench Tool over NTSocks for high performance file transfer services.

A PowerShell script that converts hierarchical OPML (Outline Processor Markup Language) files into CXL concept maps compatible with CMapTools.

A PowerShell script that converts CMap Tools concept map files (CXL format) into hierarchical OPML outlines, enabling seamless import into mind mapping and outlining software.

CXL Review: Is It Worth Your Investment In 2025?

Open Source software code for use with PCIe card-based hardware AI accelerators catering to both inference and training use cases