Skip links to main content

Welcome to the Accelerated Computing Systems Lab (ACSL)!

We work on a broad range of computer systems projects spanning hardware architecture, compilers, operating systems, security and privacy, high-speed networking.  All our software is open-source and free .

A short pitch for the kind of research we are doing is here .

Feel passionate about building secure and fast computer systems of the future?! Check out how to apply!

RESEARCH

all research areas
slide for Accelerator-Centric Operating System
Accelerator-Centric Operating System
Accelerator-centric Operating System Architecture, OmniX, enables direct interaction between accelerators and I/O devices, for example, files and network sockets for GPU kernels
slide for Confidential Computing
Confidential Computing
New methods for detection and defense against side-channel attacks on software and hardware for Trusted Execution Environments.
slide for Programmable Networks
Programmable Networks
New infrastructure for programmable NICs, distributed replication in data-plane using Programmable Switches, neural-network based packet classification (OVS).
slide for GPU computing, Virtualization, Machine Learning, Distributed Systems
GPU computing, Virtualization, Machine Learning, Distributed Systems
Playground for exploring interesting topics in a search for new ideas

SELECTED PUBLICATIONS

all publications
[SYSTOR 2024] Space-efficient FTL for Mobile Storage via Tiny Neural Nets
[SIGCOMM 2024] In-Network Address Caching for Virtual Networks
[NSDI 2024] Multitenant In-Network Acceleration with SwitchVM
[MICRO 2023] NeuroLPM: Scaling Longest Prefix Match Hardware with Neural Networks
[USENIX Security 2023] AEX-Notify: Thwarting Precise Single-Stepping Attacks through Interrupt Awareness for Intel SGX Enclaves
[USENIX ATC 2023] Translation Pass-Through for Near-Native Paging Performance in VMs
[S&P 2023] Hide and Seek with Spectres: Efficient discovery of speculative information leaks with random testing
[ISMM 2022] Reconsidering OS Memory Optimizations in the Presence of Disaggregated Memory
[ATC 2022] ZNSwap: un-Block your Swap
[EuroSys 2022] Slashing the Disaggregation Tax in Heterogeneous Data Centers with FractOS
[NSDI 2022] Scaling Open vSwitch with a Computational Cache
[NSDI 2022] An edge-queued datagram service for all data-center traffic
[NSDI 2022] SwiSh: Distributed Shared State Abstractions for Programmable Switches
[ASPLOS 2022] Revizor: Testing Black-box CPUs against Speculation Contracts
[ASPLOS 2022] FlexDriver: A Network Driver for Your Accelerator
[NeurIPS 2021] Faster Neural Network Training with Approximate Tensor Operations
[ATC 2021] Fine-tuning giant neural networks on commodity hardware with automatic pipeline model parallelism
[HotNets 2020] SwiShmem: Distributed Shared State Abstractions for Programmable Switches
[EuroSys 2020] Autarky: Closing controlled channels with self-paging enclaves
[SIGCOMM 2020] A computational approach to packet classification
[USENIX Security 2020] SpecFuzz: Bringing Spectre-type vulnerabilities to the surface
[ASPLOS 2020] Lynx: a SmartNIC-driven accelerator-centric architecture for network servers
[ACM TOCS 2019] SPIN: Seamless OS integration of Peer-to-Peer DMA between SSDs and GPUs
[PACT 2019] Achieving Scalability in a k-NN Multi-GPU Network Service with Centaur
[USENIX ATC 2019] GAIA: An OS Page Cache for Heterogeneous Systems
[USENIX ATC 2019] CoSMIX: A Compiler-based System for Secure Memory Instrumentation and Execution in Enclaves
[USENIX ATC 2019] NICA: An Infrastructure for Inline Acceleration of Network Applications
[USENIX Security 2018] Foreshadow: Extracting the Keys to the Intel SGX Kingdom with Transient Out-of-Order Execution
[PETS 2018] Power to peep-all: Inference Attacks by Malicious Batteries on Mobile Devices
[USENIX ATC 2018] Varys: Protecting SGX enclaves from practical side-channel attacks
[USENIX ATC 2017] SPIN: Seamless OS integration of Peer-to-Peer DMA between SSDs and GPUs
[HotOS 2017] OmniX: an accelerator-centric OS for omni-programmable systems
[EuroSys 2017] Eleos: Exit-Less OS Services for SGX Enclaves
[GPGPU 2017] Understanding The Security of Discrete GPUs
[ACM TOCS 2016] GPUnet: networking abstractions for GPUs
[ISCA 2016] ActivePointers: A Case for Software Address Translation on GPUs
[CACM 2014] GPUfs: the case for operating system services on GPUs
[SYSTOR 2014] Lazy Means Smart: Reducing Repair Bandwidth Costs in Erasure-coded Distributed Storage
[ACM TOCS 2014] GPUfs: Integrating a file system with GPUs
Scroll Publications Up
Scroll Publications Down

NEWS & EVENTS

all news & events
29.08.2023 A bunch of cool new papers!
10.07.2022 18th International Summer School on Advanced Computer Architecture and Compilation for High-performance Embedded Systems
15.05.2022 Hosting 360 degree lab exposure event for undergrads
12.05.2022 Congrats to Shai Bergman for the acceptance of two papers to ISMM and USENIX ATC
11.12.2021 Three papers accepted to NSDI'22!
14.11.2021 Two papers accepted to ASPLOS'22! Congrats to Haggai Eran and Oleksii Oleksenko (TU Dresden)
12.10.2021 NeurIPS accepted! Congrats to Menachem Adelman
7.02.2021 Prof. Michio Honda virtual visit
30.08.2020 Lior Zeno got his HotNets'20 submission accepted!
17.05.2020 Alon Rashelbach's paper accepted to SIGCOMM 2020!
5.05.2020 Our team won the Grand Prize in IEEE SP-Cup 2020
20.04.2020 Welcome to the new website of ACS lab !
Scroll News Up
Scroll News Down