FlexDriver: A Network Driver for Your Accelerator
Authors:
- Haggai EranHEHaggai Eran
- Dimitris SyrivelisDSDimitris Syrivelis
- Maxim FudimMFMaxim Fudim
- Gabi MalkaGMGabi Malka
- Gal ShalomGSGal Shalom
- Noam CohenNCNoam Cohen
- Amit HermonyAHAmit Hermony
- Dotan LeviDLDotan Levi
- Liran LissLLLiran Liss
- Paraskevas BakopoulosPBParaskevas Bakopoulos
- Elad MentovichEMElad Mentovich
- Mark SilbersteinMSMark Silberstein
Open Access
- 24 June 2026
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computer Systems
- Vol. 44 (3) , 1-35
Abstract
We propose a new system design for connecting hardware and FPGA accelerators to the network, allowing them to directly control commodity ASIC NICs without using the CPU. This solves the key challenge of leveraging existing NIC hardware offloads such as RDMA and virtualization for hardware disaggregation and accelerator networking. Our approach supports a diverse set of use cases, from direct network access for disaggregated accelerators to inline acceleration of the network stack and disaggregation of main system memory, all without implementing complex networking logic. To demonstrate this approach, we build FlexDriver (FLD) , a hardware module that implements a NIC data-plane driver. Our main technical contribution is compressing NIC control structures by 5 ×, allowing FLD to achieve high scalability with low die area and no memory bandwidth interference. We build two prototypes – FLD core on NVIDIA Innova-2 FPGA SmartNICs and FLD with a load/store interface on IBM OpenCAPI FPGA deployment with ConnectX-6 Dx. We demonstrate four different use cases: a disaggregated LTE cipher, an IP-reassembly inline accelerator, an IoT cryptographic-token authentication offload, and a fine-grained memory disaggregation datapath over RDMA. These leverage the ASIC NIC for RDMA processing, VXLAN tunneling, and traffic shaping, without CPU involvement.Keywords
Funding Information
- Israel Science Foundation (1027/18, and 1998/22)
- Israel Innovation Authority
- Israel National Cyber Directorate
- Technion Hiroshi Fujiwara Cyber Security Research Center
This publication has 70 references indexed in Scilit:
- Feasibility of FPGA accelerated IPsec on cloudMicroprocessors and Microsystems, 2019
- Providing Multi-tenant Services with FPGAs: Case Study on a Key-Value Store2018
- GPUDirect Async: Exploring GPU synchronous communication techniques for InfiniBand clustersJournal of Parallel and Distributed Computing, 2018
- GPU-Centric Communication on NVIDIA GPU Clusters with InfiniBand: A Case Study with OpenSHMEM2017
- IBM Power9 Processor ArchitectureIEEE Micro, 2017
- Low-latency TCP/IP stack for data center applications2016
- Recent Advances in Cloud Radio Access Networks: System Architectures, Key Techniques, and Open IssuesIEEE Communications Surveys & Tutorials, 2016
- NetFPGA SUME: Toward 100 Gbps as Research CommodityIEEE Micro, 2014
- Shared receive queue based scalable MPI design for InfiniBand clusters2006
- Cuckoo hashingJournal of Algorithms, 2004