Platform Research

About

About Us

The Systems Platform Research Group was established by Prof. Jian Huang at UIUC in 2018. Our group consists of students from both CS and ECE departments. We enjoy building both hardware and software systems, with a focus on the software/hardware co-design. Our research interests lie in the areas of computer systems and architecture, including memory and storage systems, AI platform and infrastructure, distributed systems, systems security, and especially the intersections of them.

Our research contributions have been published at top-tier systems, architecture, and security conferences, such as ISCA, OSDI, SOSP, ASPLOS, MICRO, PLDI, FAST, and CCS. Some of them are being transferred into products, and have been featured by CACM, the Register, PCWorld, ZDNet, and many other media agencies.

Our research is partially sponsored by NSF, DoE, Army Research, IBM-Illinois Discovery Accelerator Institute, Western Digital, Google, Intel, NetApp, and IBM.

Research

Active Research Projects

Learning-Based Storage Systems

Develop systems and architecture techniques to build a learning-based storage ecosystem.

Network/Storage Co-design

Bridge the gaps between network and storage to achieve improved end-to-end systems performance and resource efficiency.

Storage-Class Memory

Break the memory wall with new and emerging memory and storage technologies, such as flash memory and non-volatile memory.

Software-Defined and Intelligent Cloud Infrastructure

Develop next-generation intelligent cloud infrastructure for facilitating the development and deployment of AI-driven applications.

Accelerator-Centric Storage

Build memory/storage systems and architecture for hardware accelerators and AI systems.

Secure Storage Systems

Rethink the design and implementation of the entire storage stack with a cross-layer approach for enhanced data security.

Join Us

We usually have a few Ph.D. openings every year. We welcome master and undergraduate students to join us, and encourage them to drive projects in our group. We also have research internship openings for undergraduate students every summer. Interested in joining us? Please contact Prof. Jian Huang with your CV and research interests.

Projects

Recent Research Highlights

LeaFTL

A Learning-Based Flash Translation Layer for Modern SSDs

BlockFlex

Enabling Learning-Based Storage Harvesting in Cloud Platforms

IceClave

A TEE for In-Storage Computing

ParaCrash

Identify Crash-Consistency Bugs in HPC Storage Stack

UniHeap

Managed runtimes for NVM

iSwitch

Accelerate Distributed RL with In-Switch Computing

FlatFlash

Systems and Architecture Support for Byte-Addressable SSDs

TimeSSD

Secure Storage Systems

HOOP

Reduce Memory Persistency Overheads with Architectural Support

Papers

Recent Publications

Learning to Drive Software-Defined Solid-State Drives

Daixuan Li, Jinghan Sun, Jian Huang. MICRO 2023.
G10: Enabling An Efficient Unified GPU Memory and Storage Architecture with Smart Tensor Migrations

Haoyang Zhang, Yirui Eric Zhou, Yuqi Xue, Yiqi Liu, Jian Huang. MICRO 2023.
RackBlox: A Software-Defined Rack-Scale Storage System with Network-Storage Co-Design

Benjamin Reidys, Yuqi Xue, Daixuan Li, Bharat Sukhwani, Wen-mei Hwu, Deming Chen, Sameh Asaad, Jian Huang. SOSP 2023.
System Virtualization for Neural Processing Units

Yuqi Xue, Yiqi Liu, Jian Huang. HotOS 2023.
The Security War in File Systems: An Empirical Study from A Vulnerability-Centric Perspective

Jinghan Sun, Shaobo Li, Jun Xu, Jian Huang. TOS 2023.
V10: Hardware-Assisted NPU Multi-tenancy for Improved Resource Utilization and Fairness

Yuqi Xue, Yiqi Liu, Lifeng Nai, Jian Huang. ISCA 2023.
LeaFTL: A Learning-Based Flash Translation Layer for Solid-State Drives

Jinghan Sun, Shaobo Li, Yunxin Sun, Chao Sun, Dejan Vucinic, Jian Huang. ASPLOS 2023.
Learning to Drive Software-Defined Storage

Jian Huang, Daixuan Li, Jinghan Sun. MLSys@NIPS'22.
BlockFlex: Enabling Storage Harvesting with Software-Defined Flash in Modern Cloud Platforms

Benjamin Reidys*, Jinghan Sun*, Anirudh Badam, Shadi Noghabi, Jian Huang. OSDI 2022.

*Co-primary authors.
RSSD: Defend Against Ransomware with Hardware-Isolated Network-Storage Codesign and Post-Attack Analysis

Benjamin Reidys, Peng Liu, Jian Huang. ASPLOS 2022.
Understanding and Detecting Deep Memory Persistency Bugs in NVM Programs with DeepMC

Benjamin Reidys, Jian Huang. PPoPP 2022.
IceClave: A Trusted Execution Environment for In-Storage Computing

Luyi Kang*, Yuqi Xue*, Weiwei Jia*, Xiaohao Wang, Jongryool Kim, Changhwan Youn, Myeong Joon Kang, Jin Lim, Bruce Jacob, Jian Huang. MICRO 2021.

*Co-primary authors.
Distributed Data Persistency

Apostolos Kokolis, Antonis Psistakis, Benjamin Reidys, Jian Huang, Josep Torrellas. MICRO 2021.
Pinpointing Crash-Consistency Bugs in the HPC I/O Stack: A Cross-Layer Approach

Jinghan Sun, Jian Huang, and Marc Snir. SC 2021.
UniHeap: Managing Persistent Objects Across Managed Runtimes for Non-Volatile Memory

Daixuan Li, Benjamin Reidys, Jinghan Sun, Thomas Shull, Josep Torrellas, Jian Huang. SYSTOR 2021.
Hoop: Efficient Hardware-Assisted Out-of-Place Update for Non-Volatile Memory

Miao Cai, Chance C. Coats, Jian Huang. ISCA 2020.