├── .gitignore └── README.md /.gitignore: -------------------------------------------------------------------------------- 1 | .DS_Store 2 | *.bak 3 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # EN.601.814: Selected Topics in Computer Networks 2 | 3 | ## Logistics 4 | 5 | - Instructor: [Xin Jin](http://www.cs.jhu.edu/~xinjin/) 6 | - Time: Wednesday, 4-5pm 7 | - Location: Malone 235 8 | 9 | ## Course Description 10 | 11 | In this course we will read, discuss and present classic papers and current research in computer networks. The topic coverage will vary each semester. 12 | 13 | ## Course Syllabus 14 | 15 | For fall 2020 semester, we will focus on programmable networks, streaming algorithms, sketches, machine learning systems, and the intersection of AI and networking. Time: Wednesday, 4-5pm. 16 | 17 | | Date | Topics | Presenter | 18 | | :------ | :------ | :------ | 19 | | Wed 09/02 | Understanding PCIe performance for end host networking ([pdf](https://dl.acm.org/doi/pdf/10.1145/3230543.3230560)) | Hang Zhu | 20 | | Wed 09/09 | Serving DNNs like Clockwork: Performance Predictability from the Bottom Up ([pdf](https://link.zhihu.com/?target=https%3A//arxiv.org/pdf/2006.02464.pdf))| Zhihao Bai | 21 | | Wed 09/16 | Probabilistic Verification of Network Configurations ([pdf](https://dl.acm.org/doi/pdf/10.1145/3387514.3405900))| Zhuolong Yu | 22 | | Wed 09/30 | Heterogeneity-Aware Cluster Scheduling Policies for Deep Learning Workloads ([pdf](https://arxiv.org/pdf/2008.09213.pdf))| Zhen Zhang | 23 | | Wed 10/07 | RackSched: A Microsecond-Scale Scheduler for Rack-Scale Computers ([pdf](https://www.usenix.org/conference/osdi20/presentation/zhu))| Hang Zhu | 24 | | Wed 10/28 | Correctness and Performance for Stateful Chained Network Functions ([pdf](https://www.usenix.org/system/files/nsdi19-khalid.pdf))| Zhuolong Yu | 25 | | Wed 11/11 | A Unified Architecture for Accelerating Distributed DNN Training in Heterogeneous GPU/CPU Clusters| Zhen Zhang | 26 | | Wed 11/18 | Swift: Delay is Simple and Effective for Congestion Control in the Datacenter ([pdf](https://dl.acm.org/doi/pdf/10.1145/3387514.3406591))| Hang Zhu | 27 | | Wed 12/10 | Information-Agnostic Flow Scheduling for Commodity Data Centers ([pdf](https://www.usenix.org/system/files/conference/nsdi15/nsdi15-paper-bai.pdf))| Zhuolong Yu | 28 | | Wed 12/17 | AntMan: Dynamic Scaling on GPU Clusters for Deep Learning ([pdf](https://www.usenix.org/system/files/osdi20-xiao.pdf))| Zhihao Bai | 29 | 30 | For spring 2020 semester, we will focus on programmable networks, streaming algorithms, sketches, machine learning systems, and the intersection of AI and networking. Time: Tuesday, 4-5pm. 31 | 32 | | Date | Topics | Presenter | 33 | | :------ | :------ | :------ | 34 | | Tue 02/25 | Programmable Calendar Queues for High-speed Packet Scheduling ([pdf](https://www.usenix.org/system/files/nsdi20-paper-sharma.pdf)) | Zhuolong Yu | 35 | | Tue 03/03 | TCP ≈ RDMA : CPU-efficient Remote Storage Access with i10 ([pdf](https://www.usenix.org/system/files/nsdi20-paper-hwang.pdf) [slides](https://www.usenix.org/sites/default/files/conference/protected-files/nsdi20_slides_hwang.pdf) )| Zhen Zhang | 36 | | Tue 03/10 | IronFleet: Proving Practical Distributed Systems Correct ([pdf](https://www.microsoft.com/en-us/research/wp-content/uploads/2015/10/ironfleet.pdf)) | Hang Zhu | 37 | | Tue 03/17 | Sol: Fast Distributed Computation Over Slow Networks ([pdf](https://www.usenix.org/system/files/nsdi20-paper-lai.pdf)) | Zhihao Bai | 38 | | Tue 03/24 | 2DFQ: Two-Dimensional Fair Queuing for Multi-Tenant Cloud Services ([pdf](https://cs.brown.edu/~jcmace/papers/mace162dfq.pdf)) | Zhuolong Yu | 39 | | Tue 03/31 | THEMIS: Fair and Efficient GPU Cluster Scheduling ([pdf](https://www.usenix.org/system/files/nsdi20-paper-mahajan.pdf)) | Zhen Zhang | 40 | | Tue 04/06 | Enabling Programmable Transport Protocols in High-Speed NICs ([pdf](https://www.usenix.org/system/files/nsdi20-paper-arashloo.pdf)) | Hang Zhu | 41 | | Tue 04/14 | Privacy Accounting and Quality Control in the Sage Differentially Private ML Platform ([pdf](https://dl.acm.org/authorize?N695026)) | Zhihao Bai | 42 | | Tue 04/21 | Multi-Resource Fair Queueing for Packet Processing ([pdf](https://users.ece.cmu.edu/~vsekar/papers/sigcomm12_drfq.pdf)) | Zhuolong Yu | 43 | | Tue 04/28 | Cliffhanger: Scaling Performance Cliffs in Web Memory Caches ([pdf](https://www.usenix.org/conference/nsdi16/technical-sessions/presentation/cidon)) | Zhen Zhang | 44 | | Tue 05/05 | FileMR: Rethinking RDMA Networking for Scalable Persistent Memory ([pdf](https://www.usenix.org/conference/nsdi20/presentation/yang)) | Hang Zhu | 45 | | Tue 05/12 | Firecracker: Lightweight Virtualization for Serverless Applications ([pdf](https://www.usenix.org/conference/nsdi20/presentation/agache)) | Zhihao Bai | 46 | | Tue 05/19 | Optimizing Data-Intensive Computations in Existing Libraries with Split Annotations ([pdf](https://cs.stanford.edu/~matei/papers/2019/sosp_split_annotations.pdf)) | Zhuolong Yu | 47 | | Tue 06/08 | PLINK: DISCOVERING AND EXPLOITING DATACENTER NETWORK LOCALITY FOR EFFICIENT CLOUD-BASED DISTRIBUTED TRAINING ([pdf](https://homes.cs.washington.edu/~arvind/papers/plink.pdf)) | Zhen Zhang | 48 | | Tue 06/16 | Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation ([pdf](http://papers.nips.cc/paper/7877-graph-convolutional-policy-network-for-goal-directed-molecular-graph-generation.pdf)) | Hang Zhu | 49 | | Tue 06/23 | DeepRecSys: A System for Optimizing End-to-End At-Scale Neural Recommendation Inference ([pdf](http://vlsiarch.eecs.harvard.edu/wp-content/uploads/2020/05/DeepRecSys_Gupta_ISCA2020.pdf)) | Zhihao Bai | 50 | | Tue 06/30 | Designing Distributed Tree-based Index Structures for Fast RDMA-capable Networks ([pdf](https://readingxtra.github.io/docs/RMDA/icmd19-ziegler.pdf)) | Zhuolong Yu | 51 | | Tue 07/07 | Capuchin: Tensor-based GPU Memory Management for Deep Learning ([website](https://dl.acm.org/doi/abs/10.1145/3373376.3378505)) | Zhen Zhang | 52 | | Tue 07/14 | Harmonia: Near-Linear Scalability for Replicated Storage with In-Network Conflict Detection ([pdf](https://www.cs.jhu.edu/~xinjin/files/VLDB19_Harmonia.pdf)) | Hang Zhu | 53 | | Tue 07/21 | NetLock: Fast, Centralized Lock Management Using Programmable Switches ([pdf](http://cs.jhu.edu/~zhuolong/papers/sigcomm20netlock.pdf))| Zhuolong Yu | 54 | | Tue 07/28 | Is Network the Bottleneck of Distributed Training? ([pdf](https://arxiv.org/pdf/2006.10103.pdf))| Zhen Zhang | 55 | | Tue 08/04 | Harmonia: Near-Linear Scalability for Replicated Storage with In-Network Conflict Detection ([pdf](https://www.cs.jhu.edu/~xinjin/files/VLDB19_Harmonia.pdf)) | Hang Zhu | 56 | | Tue 08/11 | RecNMP: Accelerating Personalized Recommendation with Near-Memory Processing ([pdf](https://conferences.computer.org/isca/pdfs/ISCA2020-4QlDegUf3fKiwUXfV0KdCm/466100a790/466100a790.pdf))| Zhihao Bai | 57 | | Tue 08/18 | Caching with Delayed Hits ([pdf](https://dl.acm.org/doi/pdf/10.1145/3387514.3405883))| Zhuolong Yu | 58 | | Tue 08/25 | Zero Downtime Release: Disruption-free Load Balancing of a Multi-Billion User Website ([pdf](https://dl.acm.org/doi/abs/10.1145/3387514.3405885))| Zhen Zhang | 59 | 60 | For fall 2019 semester, we will focus on programmable networks, streaming algorithms, sketches, and the intersection of AI and networking. Time: Wednesday, 4-5pm. 61 | 62 | | Date | Topics | Presenter | 63 | | :------ | :------ | :------ | 64 | | Wed 09/04 | Scaling Distributed Machine Learning with In-Network Aggregation ([pdf](https://arxiv.org/abs/1903.06701)) | Zhuolong | 65 | | Wed 09/11 | Gandiva: Introspective Cluster Scheduling for Deep Learning ([pdf](https://www.usenix.org/system/files/osdi18-xiao.pdf)) | Zhihao | 66 | | Wed 09/25 | Packet Transactions: High-Level Programming for Line-Rate Switches ([pdf](https://cs.nyu.edu/~anirudh/domino-sigcomm.pdf)) | Hang | 67 | | Wed 10/02 | A Generic Communication Scheduler for Distributed DNN Training Acceleration ([pdf](https://i.cs.hku.hk/~cwu/papers/yhpeng-sosp19.pdf)) | Zhihao | 68 | | Wed 10/08 | Floem: A Programming System for NIC-Accelerated Network Applications ([pdf](https://www.usenix.org/conference/osdi18/presentation/phothilimthana)) | Hang | 69 | | Wed 10/16 | Making Sense of Performance in Data Analytics Frameworks ([pdf](https://www.usenix.org/system/files/conference/nsdi15/nsdi15-paper-ousterhout.pdf)) | Zhen | 70 | | Wed 10/23 | Offloading Distributed Applications onto SmartNICs using iPipe ([pdf](https://homes.cs.washington.edu/~arvind/papers/ipipe.pdf)) | Zhuolong | 71 | | Wed 10/30 | SP-PIFO: Approximating Push-In First-Out Behaviors using Strict-Priority Queues ([pdf](https://nsg.ee.ethz.ch/fileadmin/user_upload/SP-PIFO.pdf)) | Zhihao | 72 | | Wed 11/06 | My current project | Hang | 73 | | Wed 11/13 | QPipe: Quantiles Sketch Fully in the Data Plane ([pdf](http://cs.jhu.edu/~zhuolong/papers/conext19qpipe.pdf)) | Zhuolong | 74 | | Wed 11/20 | Beyond fat-trees without antennae, mirrors, and disco-balls ([pdf](https://www.cse.huji.ac.il/~mestrebisli/pubs/2017/fatfree.pdf)) | Zhen | 75 | | Wed 11/27 | Accelerated Service Chaining on a Single Switch ASIC ([pdf](https://www.cs.rice.edu/~eugeneng/papers/HotNets19.pdf)) | Hang | 76 | | Wed 12/4 | Architecting Programmable Data Plane Defenses into the Network with FastFlex([pdf](https://dl.acm.org/authorize.cfm?key=N698892)) | Zhihao | 77 | --------------------------------------------------------------------------------