NSDI 2023
as the organisers put it
The 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI '23) will take place April 17–19, 2023, at the Boston Marriott Long Wharf in Boston, MA, USA. NSDI focuses on the design principles, implementation, and practical evaluation of networked and distributed systems.
who it's for
cloud engineers, platform engineers, network engineers, machine learning engineers, site reliability engineers, systems researchers, embedded systems engineers
topics
RDMA NIC architecture; RNIC performance isolation; transparent GPU sharing; GPU-initiated DMA I/O; distributed GNN training; sub-RTT congestion control; in-network compute for ML; RPC as a managed service; swap and remote memory redesigns; programmable switch sketches; intercloud brokering and overlays; predictive WAN traffic engineering
| title | author | length |
|---|---|---|
| SRNIC: A Scalable Architecture for RDMA NICs | Zilong Wang, Layong Luo, Qingsong Ning, Chaoliang Zeng, Wenxue Li, Xinchen Wan, Peng Xie, Tao Feng, Ke Cheng, Xiongfei Geng, Tianhao Wang, Weicheng Ling, Kejia Huo, Pingbo An, Kui Ji, Shideng Zhang, Bin Xu, Ruiqing Feng, Tao Ding, Kai Chen, Chuanxiong Guo | 17m |
Presents SRNIC, an FPGA prototype RDMA NIC architecture that removes on‑chip structures via protocol header extensions, cache‑free QP scheduling, and… | ||
| Hostping: Diagnosing Intra-host Network Bottlenecks in RDMA Servers | Kefei Liu, Zhuo Jiang, Jiao Zhang, Haoran Wei, Xiaolong Zhong, Lizhuang Tan, Tian Pan, Tao Huang | 15m |
Hostping runs loopback tests between RNICs and endpoints to measure intra-host latency and bandwidth and uses baseline comparison plus a binary network… | ||
| Understanding RDMA Microarchitecture Resources for Performance Isolation | Xinhao Kong, Jingrong Chen, Wei Bai, Yechen Xu, Mahmoud Elhaddad, Shachar Raindel, Jitendra Padhye, Alvin R. Lebeck, Danyang Zhuo | 14m |
Presents a model tying RDMA verbs to RNIC internal resources using hardware counters, then builds the Husky test suite that creates verb pairs to target… | ||
| Empowering Azure Storage with RDMA | Wei Bai, Shanim Sainul Abdeen, Ankit Agrawal, Krishan Kumar Attre, Paramvir Bahl, Ameya Bhagat, Gowri Bhaskara, Tanya Brokhman, Lei Cao, Ahmad Cheema, Rebecca Chow, Jeff Cohen, Mahmoud Elhaddad, Vivek Ette, Igal Figlin, Daniel Firestone, Mathew George, Ilya German, Lakhmeet Ghai, Eric Green, Albert Greenberg, Manish Gupta, Randy Haagens, Matthew Hendel, Ridwan Howlader, Neetha John, Julia Johnstone, Tom Jolly, Greg Kramer, David Kruse, Ankit Kumar, Erica Lan, Ivan Lee, Avi Levy, Marina Lipshteyn, Xin Liu, Chen Liu, Guohan Lu, Yuemin Lu, Xiakun Lu, Vadim Makhervaks, Ulad Malashanka, David A. Maltz, Ilias Marinos, Rohan Mehta, Sharda Murthi, Anup Namdhari, Aaron Ogus, Jitendra Padhye, Madhav Pandya, Douglas Phillips, Adrian Power, Suraj Puri, Shachar Raindel, Jordan Rhee, Anthony Russo, Maneesh Sah, Ali Sheriff, Chris Sparacino, Ashutosh Srivastava, Weixiang Sun, Nick Swanson, Fuhou Tian, Lukasz Tomczyk, Vamsi Vadlamuri, Alec Wolman, Ying Xie, Joyce Yom, Lihua Yuan, Yanzhao Zhang, Brian Zill | 20m |
Azure replaces TCP with RoCEv2-based RDMA at regional scale, moving roughly 70% of traffic to RDMA and handling exabytes per day over 100+ Gbps links up to… | ||
| Transparent GPU Sharing in Container Clouds for Deep Learning Workloads | Bingyang Wu, Zili Zhang, Zhihao Bai, Xuanzhe Liu, Xin Jin | 15m |
Claims a kernel‑intercept OS layer called TGS that enables transparent GPU sharing under Docker/Kubernetes with ~3000 LOC, adaptive rate control and… | ||
| ARK: GPU-driven Code Execution for Distributed Deep Learning | Changho Hwang, KyoungSoo Park, Ran Shu, Xinyuan Qu, Peng Cheng, Yongqiang Xiong | 13m |
Claims a GPU-driven I/O path that lets GPU threads initiate DMA and run a single persistent GPU loop kernel so GPUs handle control and scheduling autonomously… | ||
| BGL: GPU-Efficient GNN Training by Optimizing Graph Data I/O and Preprocessing | Tianfeng Liu, Yangrui Chen, Dan Li, Chuan Wu, Yibo Zhu, Jun He, Yanghua Peng, Hongzheng Chen, Hongzhi Chen, Chuanxiong Guo | 17m |
Distributed GNN training system BGL builds a dynamic cache engine and a two-level CPU+GPU cache that together cut feature-retrieval traffic and reduce… | ||
| Zeus: Understanding and Optimizing GPU Energy Consumption of DNN Training | Jie You, Jae-Won Chung, Mosharaf Chowdhury | 15m |
Zeus is an online optimizer that jointly tunes batch size and GPU power limit to minimize energy per target accuracy, using an exploration‑exploitation… | ||
| Remote Procedure Call as a Managed System Service | Jingrong Chen, Yongji Wu, Shihan Lin, Yechen Xu, Xinhao Kong, Thomas E. Anderson, Matthew Lentz, Xiaowei Yang, Danyang Zhuo | 15m |
mRPC implements RPC as a managed system service rather than a linked library, with a shim using shared-memory queues, a schema generator that produces… | ||
| Canvas: Isolated and Adaptive Swapping for Multi-Applications on Remote Memory | Chenxi Wang, Yifan Qiao, Haoran Ma, Shi Liu, Yiying Zhang, Wenguang Chen, Ravi Netravali, Miryung Kim, Guoqing Harry Xu | 14m |
Canvas isolates per-application swap data paths and builds a replacement swap system on Linux 5.5 that gives each workload dedicated swap partition, swap… | ||
| Hermit: Low-Latency, High-Throughput, and Transparent Remote Memory... | Yifan Qiao, Chenxi Wang, Zhenyuan Ruan, Adam Belay, Qingda Lu, Yiying Zhang, Miryung Kim, Guoqing Harry Xu | 18m |
Hermit is a kernel swap redesign that implements feedback-directed asynchrony to move expensive, non-urgent work off the page-fault path, adaptively schedule… | ||
| NetRPC: Enabling In-Network Computation in Remote Procedure Calls | Bohan Zhao, Wenfei Wu, Wei Xu | 16m |
NetRPC implements an INC-enabled RPC stack that exposes protobuf/grpc interfaces and a JSON net filter to declare primitives like add on map and… | ||
| Bolt: Sub-RTT Congestion Control for Ultra-Low Latency | Serhat Arslan, Yuliang Li, Gautam Kumar, Nandita Dukkipati | 16m |
Bolt pushes congestion control to sub-RTT reaction by using programmable switches to emit immediate per‑packet feedback and by combining Sub-RTT Control (SRC)… | ||
| Understanding the impact of host networking elements on traffic bursts | Erfan Sharafzadeh, Sepehr Abdous, Soudeh Ghorbani | 15m |
Valinor combines eBPF hooks inside the host and a programmable data‑plane collector to timestamp packets from nanoseconds to seconds and attribute bursts to… | ||
| Poseidon: Efficient, Robust, and Practical Datacenter CC via Deployable INT | Weitao Wang, Masoud Moshref, Yuliang Li, Gautam Kumar, T. S. Eugene Ng, Neal Cardwell, Nandita Dukkipati | 14m |
Poseidon uses switch INT to feed a tiny maximum per-hop delay (MPD) tag back to senders and runs an adaptive rate-targeted MIMD update that decouples fairness… | ||
| Rearchitecting the TCP Stack for I/O-Offloaded Content Delivery | Taehyun Kim, Deondre Martin Ng, Junzhi Gong, Youngjin Kwon, Minlan Yu, KyoungSoo Park | 17m |
Claims a split TCP stack called IO-TCP that keeps control on the host CPU and pushes high-throughput data work to SmartNICs, using p2p PCIe DMA so the NIC… | ||
| Hydra: Serialization-Free Network Ordering for Strongly Consistent Distributed Applications | Inho Choi, Ellis Michael, Yunfan Li, Dan R. K. Ports, JIALIN LI | 16m |
Hydra implements a distributed network sequencer primitive that combines per-sequencer sequence counters with loosely synchronized physical timestamps to avoid… | ||
| The Benefit of Hindsight: Tracing Edge-Cases in Distributed Systems | Lei Zhang, Zhiqiang Xie, Vaastav Anand, Ymir Vigfusson, Jonathan Mace | 16m |
Proposes retroactive sampling and an implementation, Hindsight, that traces every request into a fixed-size buffer pool in shared memory but only ingests… | ||
| DiSh: Dynamic Shell-Script Distribution | Tammam Mustafa, Konstantinos Kallas, Pratyush Das, Nikos Vasilakis | 10m |
DiSh is a shim that analyzes and transforms existing shell scripts into a distributed dataflow graph, then schedules pieces to cluster nodes while each node… | ||
| Waverunner: An Elegant Approach to Hardware Acceleration of State Machine Replication | Mohammadreza Alimadadi, Hieu Mai, Shenghsun Cho, Michael Ferdman, Peter Milder, Shuai Mu | 16m |
Implements an FPGA SmartNIC (Xilinx U280) that moves only the common SMR data-replication path into hardware while leaving leader election and recovery to… | ||
| LeakyScatter: A Frequency-Agile Directional Backscatter Network Above 100 GHz | Atsutse Kludze, Yasaman Ghasempour | 13m |
Claims a fabricated leaky-wave backscatter node (16 mm × 54 mm) that passively steers energy back toward the source above 100 GHz using aperture reciprocity… | ||
| RF-Bouncer: A Programmable Dual-band Metasurface for Sub-6 Wireless Networks | Xinyi Li, Chao Feng, Xiaojing Wang, Yangfan Zhang, Yaxiong Xie, Xiaojiang Chen | 10m |
A compact metasurface steers both 2.4 GHz and 5 GHz signals simultaneously using slot-tuned patches and two PIN diodes per meta-atom to implement a two-bit… | ||
| Scalable Distributed Massive MIMO Baseband Processing | Junzhi Gong, Anuj Kalia, Minlan Yu | 17m |
Hydra is a distributed software BBU that cuts inter-server and inter-core communication by using FFT offload to RU and RU-configurable fronthaul packet… | ||
| DChannel: Accelerating Mobile Applications With Parallel High-bandwidth... | William Sentosa, Balakrishnan Chandrasekaran, P. Brighten Godfrey, Haitham Hassanieh, Bruce M. Maggs | 19m |
Builds a packet-steering system called DChannel that puts a client on the phone and a proxy in the 5G core to steer IP packets across parallel eMBB and URLLC… | ||
| SkyPilot: An Intercloud Broker for Sky Computing | Zongheng Yang, Zhanghao Wu, Michael Luo, Wei-Lin Chiang, Romil Bhardwaj, Woosuk Kwon, Siyuan Zhuang, Frank Sifei Luan, Gautam Mittal, Scott Shenker, Ion Stoica | 17m |
SkyPilot is an intercloud broker that automatically matches jobs to concrete zones and instance types across AWS, GCP, Azure and others, taking into account… | ||
| Unlocking unallocated cloud capacity for long, uninterruptible workloads | Anup Agarwal, Shadi Noghabi, Íñigo Goiri, Srinivasan Seshan, Anirudh Badam | 16m |
Characterization of Harvest VMs reveals high variance in interchange times; the system uses distribution-based predictions of stability plus a scheduling and a… | ||
| Invisinets: Removing Networking from Cloud Networks | Sarah McClure, Zeke Medley, Deepak Bansal, Karthick Jayaraman, Ashok Narayanan, Jitendra Padhye, Sylvia Ratnasamy, Anees Shaikh, Rishabh Tewari | 16m |
Invisinets replaces VPCs and gateways with per-endpoint parameters: every endpoint gets a public endpoint IP and optional service IPs, connectivity uses… | ||
| Bamboo: Making Preemptible Instances Resilient for Affordable Training of Large DNNs | John Thorpe, Pengzhan Zhao, Jonathan Eyolfson, Yifan Qiao, Zhihao Jia, Minjia Zhang, Ravi Netravali, Guoqing Harry Xu | 15m |
Bamboo makes preemptible (spot) instances usable for large DNN training by building a distributed system that inserts redundant computations into idle pipeline… | ||
| OneWAN is better than two: Unifying a split WAN architecture | Umesh Krishnaswamy, Rachee Singh, Paul Mattes, Paul-Andre C Bissonnette, Nikolaj Bjørner, Zahira Nasrin, Sonal Kothari, Prabhakar Reddy, John Abeln, Srikanth Kandula, Himanshu Raj, Luis Irun-Briz, Jamie Gaudette, Erica Lan | 16m |
Presents a deployed architecture that merges SWAN and CORE into ONEWAN to carry Internet and inter‑datacenter traffic under a single software‑defined… | ||
| RHINE: Robust and High-performance Internet Naming with E2E Authenticity | Huayi Duan, Rubén Fischer, Jie Lou, Si Liu, David Basin, Adrian Perrig | 15m |
RHINE replaces DNSSEC’s fragile chain with an end-entity PKI plus a novel public logging service called Delegation Transparency, formally verified in Tamarin… | ||
| Enabling Users to Control their Internet | Ammar Tahir, Radhika Mittal | 17m |
A receiver-side system called CRAB estimates downlink capacity and per-flow demand, computes max-min weighted fair rates, and throttles incoming flows on Linux… | ||
| xBGP: Faster Innovation in Routing Protocols | Thomas Wirtgen, Tom Rousseaux, Quentin De Coninck, Nicolas Rybowski, Randy Bush, Laurent Vanbever, Axel Legay, Olivier Bonaventure | 12m |
Proposes xBGP, a vendor‑neutral API plus an eBPF VM that runs BGP extension code inside existing routers, implemented in FRRouting and BIRD; demonstrates seven… | ||
| TACCL: Guiding Collective Algorithm Synthesis using Communication Sketches | Aashaka Shah, Vijay Chidambaram, Meghan Cowan, Saeed Maleki, Madan Musuvathi, Todd Mytkowicz, Jacob Nelson, Olli Saarikivi, Rachee Singh | 15m |
TACCL is a synthesizer that uses communication sketches to prune an MILP search and generate concrete ALLGATHER/ALLREDUCE/ALLTOALL algorithms tuned to DGX‑2… | ||
| Synthesizing Runtime Programmable Switch Updates | Yiming Qiu, Ryan Beckett, Ang Chen | 15m |
FlexPlan synthesizes step-by-step runtime P4 switch update plans using program synthesis and an SMT-based verifier, encoding intermediate states as version… | ||
| Practical Intent-driven Routing Configuration Synthesis | Sivaramakrishnan Ramanathan, Ying Zhang, Mohab Gawish, Yogesh Mundada, Zhaodong Wang, Sangki Yun, Eric Lippert, Walid Taha, Minlan Yu, Jelena Mirkovic | 17m |
Aura is a production routing-synthesis system that precomputes and preloads multiple base paths and switches among them via staging and labeling, using BGP… | ||
| Formal Methods for Network Performance Analysis | Mina Tahmasbi Arashloo, Ryan Beckett, Rachit Agarwal | 15m |
Formal analysis encodes queues and timed packet sequences in logic, uses Z3 and syntax-guided synthesis to produce concise constraint-based workloads (not… | ||
| Flattened Clos: Designing High-performance Deadlock-free Expander Data Center Networks... | Shizhen Zhao, Qizhou Zhang, Peirui Cao, Xiao Zhang, Xinbing Wang, Chenghu Zhou | 17m |
Proposes a topology and routing codesign that logically splits each ToR into k virtual layers, builds only adjacent-layer links, generates virtual up‑down… | ||
| Scalable Tail Latency Estimation for Data Center Networks | Kevin Zhao, Prateesh Goyal, Mohammad Alizadeh, Thomas E. Anderson | 16m |
Claims a practical estimator that cuts ns-3’s 11+ hour run for a 6,000-host, 5s trace to about a minute by decompose into independent single-link simulations… | ||
| Shockwave: Fair and Efficient Cluster Scheduling for Dynamic Adaptation in Machine Learning | Pengfei Zheng, Rui Pan, Tarannum Khan, Shivaram Venkataraman, Aditya Akella | 18m |
Shockwave is a cluster scheduler that predicts batch‑size and throughput changes using a Bayesian mixture‑of‑regimes model and expands Fisher markets into a… | ||
| Protego: Overload Control for Applications with Unpredictable Lock Contention | Inho Cho, Ahmed Saeed, Seo Jin Park, Mohammad Alizadeh, Adam Belay | 17m |
Protego implements an Active Synchronization Queue Management (ASQM) that aborts requests whose remaining lock-wait budget cannot meet SLOs, plus a… | ||
| TopoOpt: Co-optimizing Network Topology and Parallelization Strategy for Distributed... | Weiyang Wang, Moein Khazraee, Zhizhen Zhong, Manya Ghobadi, Zhihao Jia, Dheevatsa Mudigere, Ying Zhang, Anthony Kewitsch | 17m |
TopoOpt co-optimizes computation, communication, and physical network topology to speed distributed DNN training, claiming up to 3.4x faster 99th-percentile… | ||
| ModelKeeper: Accelerating DNN Training via Automated Training Warmup | Fan Lai, Yinwei Dai, Harsha V. Madhyastha, Mosharaf Chowdhury | 14m |
ModelKeeper automatically initializes new DNN training by transforming weights from previously trained models in a shared cluster, using structure-aware… | ||
| SHEPHERD: Serving DNNs in the Wild | Hong Zhang, Yupeng Tang, Anurag Khandelwal, Ion Stoica | 15m |
SHEPHERD is a model serving system that combines a two-level design planner that partitions hundreds-to-thousands of request streams into groups and an online… | ||
| Better Together: Jointly Optimizing ML Collective Scheduling and Execution Planning... | Kshiteej Mahajan, Ching-Hsiang Chu, Srinivas Sridharan, Aditya Akella | 22m |
SYNDICATE is a system that jointly optimizes scheduling and execution planning for ML collectives by introducing a motif abstraction to break collectives into… | ||
| Addax: A fast, private, and accountable ad exchange infrastructure | Ke Zhong, Yiping Ma, Yifeng Mao, Sebastian Angel | 20m |
Addax implements private bids with public auditability by extending affine aggregatable encodings (from Prio) and running auctions over two non‑colluding… | ||
| SPEEDEX: A Scalable, Parallelizable, and Economically Efficient Decentralized EXchange... | Geoffrey Ramseyer, Ashish Goel, David Mazières | 17m |
SPEEDEX implements an Arrow-Debreu exchange market inside a Layer‑1 blockchain, computing unique per-block asset valuations so all trades use the same exchange… | ||
| Boomerang: Metadata-Private Messaging under Hardware Trust | Peipei Jiang, Qian Wang, Jianhao Cheng, Cong Wang, Lei Xu, Xinyu Wang, Yihao Wu, Xiaoyuan Li, Kui Ren | 17m |
Boomerang claims cryptographic metadata privacy by running the message mixer inside secure enclaves and using label-based routing plus oblivious proactive… | ||
| Hamilton: A High-Performance Transaction Processor for Central Bank Digital Currencies | James Lovejoy, Madars Virza, Cory Fields, Kevin Karwaski, Anders Brownworth, Neha Narula | 16m |
Hamilton is a CBDC transaction processor that achieves 1.7M tps across three AWS regions by making users include input values so validation is stateless… | ||
| RECL: Responsive Resource-Efficient Continuous Learning for Video Analytics | Mehrdad Khani, Ganesh Ananthanarayanan, Kevin Hsieh, Junchen Jiang, Ravi Netravali, Yuanchao Shu, Mohammad Alizadeh, Victor Bahl | 17m |
System integrates a shared model zoo of previously adapted lightweight experts, a learned model selector that predicts per-frame accuracy and aggregates… | ||
| Boggart: Towards General-Purpose Acceleration of Retrospective Video Analytics | Neil Agarwal, Ravi Netravali | 15m |
Boggart builds a preprocessor that uses classical CV—background subtraction, morphological ops, connected components, keypoints and descriptors—to produce… | ||
| Tambur: Efficient loss recovery for videoconferencing via streaming codes | Michael Rudow, Francis Y. Yan, Abhishek Vijaya Kumar, Ganesh Ananthanarayanan, Martin Ellis, K.V. Rashmi | 20m |
Tambur applies streaming codes tuned to videoconferencing, evaluated on Microsoft Teams traces and in emulated end-to-end calls after being implemented in C++… | ||
| Gemel: Model Merging for Memory-Efficient, Real-Time Video Analytics at the Edge | Arthi Padmanabhan, Neil Agarwal, Anand Iyer, Ganesh Ananthanarayanan, Yuanchao Shu, Nikolaos Karianakis, Guoqing Harry Xu, Ravi Netravali | 16m |
Gemel is a system that jointly retrains and merges layers and weights across edge vision models so one copy of shared layers fits in GPU memory, combined with… | ||
| Fast, Approximate Vector Queries on Very Large Unstructured Datasets | Zili Zhang, Chao Jin, Linpeng Tang, Xuanzhe Liu, Xin Jin | 14m |
Auncel provides bounded query error and bounded latency for billion-item vector search by building a per-query error-latency profile that predicts how many… | ||
| Arya: Arbitrary Graph Pattern Mining with Decomposition-based Sampling | Zeying Zhu, Kan Wu, Zaoxing Liu | 15m |
Arya is an approximate graph pattern miner that uses decomposition-based sampling (fractional edge cover to split patterns into cycles and stars) and… | ||
| SECRECY: Secure collaborative analytics in untrusted clouds | John Liagouris, Vasiliki Kalavri, Muhammad Faisal, Mayank Varia | 18m |
SECRECY implements cryptographic MPC with arithmetic and Boolean secret sharing, a co‑designed query engine and physical optimizations that batch messages to… | ||
| FLASH: Towards a High-performance Hardware Acceleration Architecture for Cross-silo... | Junxue Zhang, Xiaodian Cheng, Wei Wang, Liu Yang, Jinbin Hu, Kai Chen | 18m |
Identifies nine real-world cryptographic operations that dominate cross-silo federated learning and shows they all reduce to two primitives, modular… | ||
| On Modular Learning of Distributed Systems for Predicting End-to-End Latency | Chieh-Jan Mike Liang, Zilin Fang, Yuqing Xie, Fan Yang, Zhao Lucis Li, Li Lyna Zhang, Mao Yang, Lidong Zhou | 19m |
Fluxion builds a modular performance model by packaging per-service ML models into learning assignments and wiring them into an inference graph so changes only… | ||
| SelfTune: Tuning Cluster Managers | Ajaykrishna Karthikeyan, Nagarajan Natarajan, Gagan Somashekar, Lei Zhao, Ranjita Bhagwan, Rodrigo Fonseca, Tatiana Racheva, Yogesh Bansal | 17m |
SelfTune is a lightweight API plus learning engine that plugs into cluster managers via simple calls like predict and set_reward, uses a continuous bandits… | ||
| CausalSim: A Causal Framework for Unbiased Trace-Driven Simulation | Abdullah Alomar, Pouya Hamadanian, Arash Nasr-Esfahany, Anish Agarwal, Mohammad Alizadeh, Devavrat Shah | 18m |
CausalSim provides a causal model and estimator that removes bias in trace-driven simulation by learning latent network conditions from an initial randomized… | ||
| HALP: Heuristic Aided Learned Preference Eviction Policy for YouTube Content Delivery... | Zhenyu Song, Kevin Chen, Nikhil Sarda, Deniz Altınbüken, Eugene Brevdo, Jimmy Coleman, Xiao Ju, Pawel Jurczyk, Richard Schooler, Ramki Gummadi | 16m |
HALP runs as YouTube’s DRAM eviction layer since early 2022 and claims a 9.1% average reduction in P95 byte-miss during peak with ~1.8% CPU overhead. It… | ||
| OpenLoRa: Validating LoRa Implementations through an Extensible and Open-sourced Framework | Manan Mishra, Daniel Koch, Muhammad Osama Shahid, Bhuvana Krishnaswamy, Krishna Chintalapudi, Suman Banerjee | 15m |
Built an open-source Python platform called OpenLoRa framework that unifies and reimplements four recent collision-resolving demodulators (CiC, ChoLoRa… | ||
| VeCare: Statistical Acoustic Sensing for Automotive In-Cabin Monitoring | Yi Zhang, Weiying Hou, Zheng Yang, Chenshu Wu | 14m |
System uses existing in-car speakers and a single microphone to compute correlated impulse-like channel responses and extract motion, breathing rate and speed… | ||
| SlimWiFi: Ultra-Low-Power IoT Radio Architecture Enabled by Asymmetric Communication | Renjie Zhao, Kejia Wang, Kai Zheng, Xinyu Zhang, Vincent Leung | 13m |
Claims a working radio that drops Wi‑Fi transmitter hardware to simple OOK plus open‑loop oscillator and still decodes on unmodified Wi‑Fi APs by exploiting… | ||
| SLNet: A Spectrogram Learning Neural Network for Deep Wireless Sensing | Zheng Yang, Yi Zhang, Kun Qian, Chenshu Wu | 17m |
SLNet generates super-resolution spectrograms with a learned spectrogram enhancement network (SEN) trained on synthetic 1–5 component spectra, then applies a… | ||
| A High-Speed Stateful Packet Processing Approach for Tbps Programmable Switches | Mariano Scazzariello, Tommaso Caiazzi, Hamid Ghasemirahni, Tom Barbette, Dejan Kostić, Marco Chiesa | 16m |
RIBOSOME splits packets at a Tofino ASIC, sends only headers to a FastClick NF on one 100G NIC and stores payloads on shared servers via RDMA, achieving 300… | ||
| ExoPlane: An Operating System for On-Rack Switch Resource Augmentation | Daehyeok Kim, Vyas Sekar, Srinivasan Seshan | 19m |
ExoPlane is an OS that augments a programmable switch with on-rack devices (smartNICs) and claims to let multiple stateful P4 apps share resources with low… | ||
| Sketchovsky: Enabling Ensembles of Sketches on Programmable Switches | Hun Namkung, Zaoxing Liu, Daehyeok Kim, Vyas Sekar, Peter Steenkiste | 17m |
Sketchovsky implements five cross-sketch optimizations, a heuristic strategy finder and an automatic code composer to pack multiple sketches onto a… | ||
| RingLeader: Efficiently Offloading Intra-Server Orchestration to NICs | Jiaxin Lin, Adney Cardoza, Tarannum Khan, Yeonju Ro, Brent E. Stephens, Hassan M. G. Wassel, Aditya Akella | 16m |
Claims that intra-server orchestration moves from a CPU bottleneck to the NIC by implementing a hardware load balancer and scheduler, a shallow per-core… | ||
| StarryNet: Empowering Researchers to Evaluate Futuristic Integrated Space and Terrestrial | Zeqi Lai, Hewu Li, Yangtao Deng, Qian Wu, Jun Liu, Yuanjie Li, Jihao Li, Lixin Liu, Weisen Liu, Jianping Wu | 16m |
StarryNet claims a practical, data-driven digital twin that emulates mega-constellations with 300 to 4000 satellites, uses real public orbit data plus model… | ||
| POLYCORN: Data-driven Cross-layer Multipath Networking for High-speed Railway | Yunzhe Ni, Feng Qian, Taide Liu, Yihua Cheng, Zhiyao Ma, Jing Wang, Zhongfeng Wang, Gang Huang, Xuanzhe Liu, Chenren Xu | 15m |
Collects a 1.79 TB GPS-labeled TCP-LTE dataset over 28,800 km and deploys a system on the Beijing–Shanghai HSR gateway at ~300 km/h. POLYCORN uses a robust… | ||
| Augmenting Augmented Reality with Non-Line-of-Sight Perception | Tara Boroushaki, Maisy Lam, Laura Dodds, Aline Eid, Fadel Adib | 17m |
An integrated AR headset prototype augments Hololens 2 with an AR-conformal antenna on a thin Kapton substrate, BladeRF radios and a Raspberry Pi to sense… | ||
| Acoustic Sensing and Communication Using Metasurface | Yongzhao Zhang, Yezhou Wang, Lanqing Yang, Mei Wang, Yi-Chao Chen, Lili Qiu, Yihong Liu, Guangtao Xue, Jiadi Yu | 15m |
System combines a passive 16×16 metasurface with a tiny speaker array and joint optimization of metasurface phase, speaker codebook, and geometry to steer… | ||
| Skyplane: Optimizing Transfer Cost and Throughput Using Cloud-Aware Overlays | Paras Jain, Sam Kumar, Sarah Wooders, Shishir G Patil, Joseph E. Gonzalez, Ion Stoica | 16m |
Skyplane is a system for fast, low-cost bulk transfers between cloud object stores that probes cloud network throughput, models routing with mixed-integer… | ||
| Electrode: Accelerating Distributed Protocols with eBPF | Yang Zhou, Zezhou Wang, Sowmya Dharanipragada, Minlan Yu | 16m |
Electrode implements three eBPF kernel offloads — broadcasting, fast-ack, quorum counting — using TC/XDP offloads to run common Multi-Paxos path operations… | ||
| Nu: Achieving Microsecond-Scale Resource Fungibility with Logical Processes | Zhenyuan Ruan, Seo Jin Park, Marcos K. Aguilera, Adam Belay, Malte Schwarzkopf | 18m |
A system called Nu implements logical processes that split a Unix process into many small stateful proclets and a centralized controller, and it migrates those… | ||
| Enabling High-Quality Real-Time Communications with Adaptive Frame-Rate | Zili Meng, Tingfeng Wang, Yixin Shen, Bo Wang, Mingwei Xu, Rui Han, Honghao Liu, Venkat Arun, Hongxin Hu, Xue Wei | 15m |
Adaptive Frame Rate (AFR) is a controller that coordinates frame rate with network fluctuation and decoder capacity to avoid transient decoder overloads… | ||
| LemonNFV: Consolidating Heterogeneous Network Functions at Line Speed | Hao Li, Yihan Dang, Guangda Sun, Guyue Liu, Danfeng Shan, Peng Zhang | 16m |
Consolidates five heterogeneous NFs into one process by recompiling each as shared libraries loaded at runtime, replacing packet I/O so RX/TX become… | ||
| Disaggregating Stateful Network Functions | Deepak Bansal, Gerald DeGrace, Rishabh Tewari, Michal Zygmunt, James Grantham, Silvano Gai, Mario Baldi, Krishna Doddapaneni, Arun Selvarajan, Arunkumar Arumugam, Balakrishnan Raman, Avijit Gupta, Sachin Jain, Deven Jagasia, Evan Langlais, Pranjal Srivastava, Rishiraj Hazarika, Neeraj Motwani, Soumya Tiwari, Stewart Grant, Ranveer Chandra, Srikanth Kandula | 19m |
Disaggregates stateful network functions off hosts into shared appliances that combine general‑purpose ARM cores with match‑processing ASICs, implemented as a… | ||
| Following the Data, Not the Function: Rethinking Function Orchestration in Serverless | Minchen Yu, Tingjia Cao, Wei Wang, Ruichuan Chen | 17m |
Pheromone implements a data-bucket abstraction and trigger primitives on Kubernetes (coordinator + workers) so intermediate objects themselves drive invocation… | ||
| Doing More with Less: Orchestrating Serverless Applications without an Orchestrator | David H. Liu, Amit Levy, Shadi Noghabi, Sebastian Burckhardt | 18m |
Unum implements orchestration as a library that compiles Step Functions graphs into an IR and runs inside user Lambdas using DynamoDB (and Firebase on Google… | ||
| Enhancing Global Network Monitoring with Magnifier | Tobias Bühler, Romain Jacob, Ingmar Poese, Laurent Vanbever | 16m |
Magnifier infers ingress and egress prefixes from sparse packet samples then validates those inferences by deploying negative mirroring rules on routers to… | ||
| NetPanel: Traffic Measurement of Exchange Online Service | Yu Chen, Liqun Li, Yu Kang, Boyang Zheng, Yehan Wang, More Zhou, Yuchao Dai, Zhenguo Yang, Brad Rutkowski, Jeff Mealiffe, Qingwei Lin | 15m |
NetPanel measures Exchange Online traffic at component granularity by fusing IPFIX, ETW, application logs and applying IP→location translation, port… | ||
| DOTE: Rethinking (Predictive) WAN Traffic Engineering | Yarin Perry, Felipe Vieira Frujeri, Chaim Hoch, Srikanth Kandula, Ishai Menache, Michael Schapira, Aviv Tamar | 17m |
Claims a system called DOTE that trains a deep neural network to map recent demand history to a WAN traffic engineering configuration, avoiding demand… | ||
| Dashlet: Taming Swipe Uncertainty for Robust Short Video Streaming | Zhuqi Li, Yaxiong Xie, Ravi Netravali, Kyle Jamieson | 15m |
Implements out-of-order chunk pre-buffering that schedules specific chunks of upcoming short videos based on a simple non-ML swipe model derived from two… | ||
| CellDAM: User-Space, Rootless Detection and Mitigation for 5G Data Plane | Zhaowei Tan, Jinghao Zhao, Boyan Ding, Songwu Lu | 17m |
CellDAM runs user-space and rootless on the device or a nearby security hub, captures over-the-air 5G signaling using a watermark to identify the protected… | ||
| LOCA: A Location-Oblivious Cellular Architecture | Zhihong Luo, Silvery Fu, Natacha Crooks, Shaddi Hasan, Christian Maciocco, Sylvia Ratnasamy, Scott Shenker | 16m |
LOCA claims to hide user location from operators while still delivering identity-based services by splitting duties between an MVNO-style broker and… | ||
| mmWall: A Steerable, Transflective Metamaterial Surface for NextG mmWave Networks | Kun Woo Cho, Mohammad H. Mazaheri, Jeremy Gummeson, Omid Abari, Kyle Jamieson | 17m |
A 10 cm × 20 cm steerable metamaterial panel is built (a 28 by 76 unit cell array) using varactor-split ring resonators and custom control PCBs to avoid RF… | ||
| Building Flexible, Low-Cost Wireless Access Networks With Magma | Shaddi Hasan, Amar Padmanabhan, Bruce Davie, Jennifer Rexford, Ulas Kozat, Hunter Gatewood, Shruti Sanadhya, Nick Yurchenko, Tariq Al-Khasib, Oriol Batalla, Marie Bremner, Andrei Lee, Evgeniy Makeev, Scott Moeller, Alex Rodriguez, Pravin Shelar, Karthik Subraveti, Sudarshan Kandi, Alejandro Xoconostle, Praveen Kumar Ramakrishnan, Xiaochen Tian, Anoop Tomar | 20m |
Magma refactors the cellular core by terminating RAN protocols at the edge and using a cloud orchestrator plus one access gateway per cell site to push user… | ||
| LinkLab 2.0: A Multi-tenant Programmable IoT Testbed for Experimentation with Edge-Cloud | Wei Dong, Borui Li, Haoyu Li, Hao Wu, Kaijie Gong, Wenzhao Zhang, Yi Gao | 15m |
LinkLab 2.0 is a live, multi-tenant IoT testbed that combines a tiered LinkLab Device Center (LDC), device-involved multi-tenancy, and heterogeneous container… | ||
| Push-Button Reliability Testing for Cloud-Backed Applications with Rainmaker | Yinfang Chen, Xudong Sun, Suman Nath, Ze Yang, Tianyin Xu | 18m |
A push-button SDK called Rainmaker injects faults at the REST-layer fault injection using an HTTP proxy and automatic fault policies so existing test suites… | ||
| Test Coverage for Network Configurations | Xieyang Xu, Weixin Deng, Ryan Beckett, Ratul Mahajan, David Walker | 16m |
NetCov identifies which router configuration lines a test suite actually exercises by tracing data-plane facts back to contributing config lines using an… | ||
| Norma: Towards Practical Network Load Testing | Yanqing Chen, Bingchuan Tian, Chen Tian, Li Dai, Yu Zhou, Mengjing Ma, Ming Tang, Hao Zheng, Zhewen Yang, Guihai Chen, Dennis Cai, Ennan Zhai | 15m |
Norma implements a practical network load tester on programmable switch ASICs (Tofino) with a stateful protocol abstraction mapped into the pipeline, a… | ||
| μMote: Enabling Passive Chirp De-spreading and μW-level Long-Range Downlink | Yihang Song, Li Lu, Jiliang Wang, Chong Zhang, Hui Zheng, Shen Yang, Jinsong Han, Jian Li | 17m |
Passive chirp de-spreading moves chirp generation to the RF transmitter and mixes two transmitted chirps on-device, while a resonant LC accumulates energy and… | ||
| Channel-Aware 5G RAN Slicing with Customizable Schedulers | Yongzhou Chen, Ruihao Yao, Haitham Hassanieh, Radhika Mittal | 17m |
RadioSaber implements channel-aware RAN slicing by making both inter-slice and enterprise schedulers greedy inter-slice and enterprise schedulers so the… | ||
| RF-Chord: Towards Deployable RFID Localization System for Logistic Networks | Bo Liang, Purui Wang, Renjie Zhao, Heyu Guo, Pengyu Zhang, Junchen Guo, Shunmin Zhu, Hongqiang Harry Liu, Xinyu Zhang, Chenren Xu | 17m |
Claims a deployable RFID locator that meets reliability, throughput and range by combining a digital 200 MHz wideband sniffer (using multisine carriers and… | ||
| Exploring Practical Vulnerabilities of Machine Learning-based Wireless Systems | Zikun Liu, Changming Xu, Emerson Sie, Gagandeep Singh, Deepak Vasisht | 18m |
RAFA (RAdio Frequency Attack) implements a robust wireless UAP that models channel distortion and sample misalignment to craft over-the-air perturbations. A… | ||
| nothing matches | ||