Schedule

Proceedings of SoCC 2023 with free and open access to all papers is available via ACM DL

Note: all times here are displayed in PDT

Monday, October 30th

7:30 AM
8:00 AM

Breakfast

8:00 AM
8:30 AM

Opening

8:30 AM
9:30 AM

Keynote 1

Chairs: Fatma Ozcan (Systems Research@Google)

  • Sky Computing

    Ion Stoica (UC Berkeley)


9:30 AM
10:00 AM

Break

10:00 AM
12:00 PM

Session 1 (Cloud Machine Learning)

Chairs: Thaleia Dimitra Doudali (IMDEA Software Institute)

  • OneAdapt: Fast Adaptation for Deep Learning Applications via Backpropagation

    Kuntai Du, Yuhan Liu, Yitian Hao (University of Chicago); Qizheng Zhang (Stanford University); Haodong Wang (The University of Chicago); Yuyang Huang (University of Chicago); Ganesh Ananthanarayanan (Microsoft); Junchen Jiang (University of Chicago)


  • tf.data service: A Case for Disaggregating ML Input Data Processing (industry)

    Andrew Audibert, Yang Chen (Google); Dan Graur, Ana Klimovic (ETH Zurich); Jiri Simsa, Chandramohan A. Thekkath (Google)


  • Anticipatory Resource Allocation for ML Training Clusters

    Tapan Chugh (Microsoft Research, University of Washington), Srikanth Kandula (Microsoft Research), Arvind Krishnmamurhy (University of Washington), Ratul Mahajan (University of Washington), Ishai Menache (Microsoft Research)


  • Towards GPU Memory Efficiency for Distributed Training at Scale (industry)

    Runxiang Cheng (University of Illinois Urbana-Champaign); Chris Cai, Selman Yilmaz, Rahul Mitra, Malay Bag, Mrinmoy Ghosh (Meta Platforms, Inc.); Tianyin Xu (University of Illinois Urbana-Champaign)


  • AsyFunc: A High-Performance and Resource-Efficient Serverless Inference System via Asymmetric Functions

    Qiangyu Pei, Yongjie Yuan, Haichuan Hu (School of Computer Science and Technology, Huazhong University of Science and Technology); Qiong Chen (Huawei); Fangming Liu (Peng Cheng Laboratory & Huazhong University of Science and Technology)


  • A Comparison of End-to-End Decision Forest Inference Pipelines

    Hong Guan, Saif Masood, Mahidhar Reddy Dwarampudi, Venkatesh Gunda (Arizona State University); Hong Min (IBM T. J. Watson Research Center); Lei Yu (Rensselaer Polytechnic Institut); Soham Nag, Jia Zou (Arizona State University)


12:00 PM
1:30 PM

Lunch + DEI mentoring lunch

1:30 PM
2:30 PM

Keynote 2

Chairs: Peter Pietzuch (Imperial College London)

  • Cloud computing research in the era of machine learning

    Christos Kozyrakis (Stanford)


2:30 PM
3:00 PM

Break

3:00 PM
5:00 PM

Session 2 (Trustworthy Cloud)

Chairs: Peter Pietzuch (Imperial College London)

  • Auxo: Efficient Federated Learning via Scalable Client Clustering

    Jiachen Liu (University of Michigan); Fan Lai (University of Illinois Urbana-Champaign); Yinwei Dai (Princeton University); Aditya Akella (UT Austin); Harsha V. Madhyastha (University of Southern California); Mosharaf Chowdhury (University of Michigan)


  • KVSEV: A Secure In-Memory Key-Value Store with Secure Encrypted Virtualization

    Junseung You, Kyeongryong Lee (Seoul National University); Hyungon Moon (UNIST (Ulsan National Institute of Science and Technology)); Yeongpil Cho (Hanyang University); Yunheung Paek (Seoul National University)


  • Building GPU TEEs using CPU Secure Enclaves with GEVisor

    Xiaolong Wu, Dave (Jing) Tian (Purdue University); Chung Hwan Kim (University of Texas at Dallas)


  • Cryonics: Trustworthy Function-as-a-Service using Snapshot-based Enclaves

    Seong-Joong Kim (The Affiliated Institute of ETRI, KAIST); Myoungsung You (KAIST); Byung Joon Kim (The Affiliated Institute of ETRI); Seungwon Shin (KAIST)


  • Oblivious Paxos: Privacy-Preserving Consensus Over Secret-Shares

    Fadhil I. Kurnia, Arun Venkataramani (University of Massachusetts Amherst)


  • HELIOS: Hardware-assisted High-performance Security Extension for Cloud Networking

    Myoungsung You (KAIST); Jaehyun Nam (Dankook University); Minjae Seo, Seungwon Shin (KAIST)


5:00 PM
6:00 PM

Poster session

  • Anticipatory Resource Allocation for ML Training Clusters

    Tapan Chugh (Microsoft Research, University of Washington), Srikanth Kandula (Microsoft Research), Arvind Krishnmamurhy (University of Washington), Ratul Mahajan (University of Washington), Ishai Menache (Microsoft Research)


  • Towards GPU Memory Efficiency for Distributed Training at Scale (industry)

    Runxiang Cheng (University of Illinois Urbana-Champaign); Chris Cai, Selman Yilmaz, Rahul Mitra, Malay Bag, Mrinmoy Ghosh (Meta Platforms, Inc.); Tianyin Xu (University of Illinois Urbana-Champaign)


  • AsyFunc: A High-Performance and Resource-Efficient Serverless Inference System via Asymmetric Functions

    Qiangyu Pei, Yongjie Yuan, Haichuan Hu (School of Computer Science and Technology, Huazhong University of Science and Technology); Qiong Chen (Huawei); Fangming Liu (Peng Cheng Laboratory & Huazhong University of Science and Technology)


  • A Comparison of End-to-End Decision Forest Inference Pipelines

    Hong Guan, Saif Masood, Mahidhar Reddy Dwarampudi, Venkatesh Gunda (Arizona State University); Hong Min (IBM T. J. Watson Research Center); Lei Yu (Rensselaer Polytechnic Institut); Soham Nag, Jia Zou (Arizona State University)


  • KVSEV: A Secure In-Memory Key-Value Store with Secure Encrypted Virtualization

    Junseung You, Kyeongryong Lee (Seoul National University); Hyungon Moon (UNIST (Ulsan National Institute of Science and Technology)); Yeongpil Cho (Hanyang University); Yunheung Paek (Seoul National University)


  • Carbon Containers: A System-level Facility for Managing Application-level Carbon Emissions

    John Thiede, Noman Bashir (University of Massachusetts Amherst); David Irwin (University of Massachusetts, Amherst); Prashant Shenoy (University of Massachusetts Amherst)


  • Not All Resources are Visible: Exploiting Fragmented Shadow Resources in Shared-State Scheduler Architecture

    Xinkai Wang, Hao He, Yuancheng Li, Chao Li, Xiaofeng Hou, Jing Wang, Quan Chen, Jingwen Leng, Minyi Guo (Shanghai Jiao Tong University); Leibo Wang (Huawei Technologies Co., Ltd.)


  • Godel: Unified Large-Scale Resource Management and Scheduling at ByteDance (industry)

    Wu Xiang (Bytedance); Yakun Li (ByteDance); Yuquan Ren (Bytedance); Fan Jiang, Chaohui Xin, Varun Gupta, Chao Xiang (ByteDance); Xinyi Song (Bytedance); Meng Liu, Bing Li, Kaiyang Shao, Chen Xu, Wei Shao (ByteDance); Yuqi Fu (University of Virginia); Wilson Wang, Cong Xu (Bytedance); Wei Xu (ByteDance); Caixue Lin, Rui Shi (Bytedance); Yuming Liang (ByteDance)


  • Plexus: Optimizing Join Approximation for Geo-Distributed Data Analytics

    Joel Wolfrath, Abhishek Chandra (University of Minnesota)


  • Optimized Storage for Seamless Multi-cloud Systems

    Yunhao Mao, Yuqiu Zhang, Hans-Arno Jacobsen (University of Toronto)


  • Decentralized Real-time Model Serving on the Edge

    Ted Shaowang, Sanjay Krishnan (University of Chicago)


  • Towards a Memory-Adaptive Hybrid Hash Join Design

    Shiva Jahangiri, Giulliano Silva Zanotti Siviero (Santa Clara University)


  • Towards Resource Adaptive Machine Learning

    Abdullah Bin Faisal, Swaminathan Lamelas, Fahad R. Dogar (Tufts University)


6:00 PM
8:00 PM

Dinner

Tuesday, October 31st

7:30 AM
8:30 AM

Breakfast

8:30 AM
9:30 AM

Keynote 3

Chairs: Peter Alvaro (UC Santa Cruz)

  • So Many Loops: The Dynamic Behavior of Distributed Systems

    Marc Brooker (AWS)


9:30 AM
10:00 AM

Break

10:00 AM
12:00 PM

Session 3 (Serverless Cloud)

Chairs: Abhishek Chandra (University of Minnesota)

  • The Gap Between Serverless Research and Real-world Systems

    Qingyuan Liu, Dong Du, Yubin Xia (Shanghai Jiao Tong University); Ping Zhang (Huawei Cloud); Haibo Chen (Shanghai Jiao Tong University)


  • Function as a Function

    Tom Kuchler, Michael Giardino, Timothy Roscoe, Ana Klimovic (ETH Zurich)


  • How Does It Function? Characterizing Long-term Trends in Production Serverless Workloads (industry)

    Artjom Joosen, Ahmed Hassan, Luke Darlow, Martin Asenov, Wang Jianfeng, Rajkarn Singh (Huawei); Adam Barker (Huawei / University of St Andrews)


  • Chitu: Accelerating Serverless Workflows with Asynchronous State Replication Pipelines

    Zhengyu Lei (Institute of Computing Technology, Chinese Academy of Sciences; University of Chinese Academy of Sciences; Zhongguancun Laboratory); Xiao Shi (Institute of Computing Technology, Chinese Academy of Sciences; Nanjing Institute of InforSuperBahn); Cunchi Lv (Institute of Computing Technology, Chinese Academy of Sciences; University of Chinese Academy of Sciences; Zhongguancun Laboratory); Xiaobing Yu (Institute of Computing Technology, Chinese Academy of Sciences; University of Chinese Academy of Sciences); Xiaofang Zhao (Institute of Computing Technology, Chinese Academy of Sciences; University of Chinese Academy of Sciences; Zhongguancun Laboratory; Institute of Intelligent Computing Technology, Suzhou, CAS; University of Chinese Academy of Sciences, Nanjing)


  • Suyi Li, Wei Wang (Hong Kong University of Science and Technology); Jun Yang, Guangzhen Chen, Daohe Lu (WeBank)


  • Parrotfish: Parametric Regression for Optimizing Serverless Functions

    Arshia Moghimi (University of British Columbia); Joe Hattori (The University of Tokyo); Alexander Li (University of British Columbia); Mehdi BEN CHIKHA (National Institute of Applied Sciences and Technology (INSAT)); Mohammad Shahrad (University of British Columbia)


12:00 PM
1:30 PM

Lunch

1:30 PM
3:00 PM

Session 4 (Cloud Performance)

Chairs: Shungeng Zhang (Augusta University)

  • Dissecting Overheads of Service Mesh Sidecars

    Xiangfeng Zhu (University of Washington); Guozhen She (Duke university); Bowen Xue (University of Washington); Yu Zhang, Yongsu Zhang, Xuan Kelvin Zou, XiongChun Duan, Peng He (ByteDance Inc.); Arvind Krishnamurthy (University of Washington); Matthew Lentz (Duke University and VMware Research); Danyang Zhuo (Duke University); Ratul Mahajan (University of Washington, Amazon)


  • LatenSeer: Causal Modeling of End-to-End Latency Distribution by Harnessing Distributed Tracing

    Yazhuo Zhang (Emory University); Rebecca Isaacs (Amazon Web Services); Yao Yue (IOP Systems); Juncheng Yang (Carnegie Mellon University); Lei Zhang (Princeton University); Ymir Vigfusson (Emory University & Keystrike)


  • CAMEO: A Causal Transfer Learning Approach for Performance Optimization of Configurable Computer Systems

    Md Shahriar Iqbal (University of South Carolina); Ziyuan Zhong (Columbia University); Iftakhar Ahmad (University of South Carolina); Baishakhi Ray (Columbia University); Pooyan Jamshidi (University of South Carolina)


  • μConAdapter: Reinforcement Learning-based Fast Concurrency Adaptation for Microservices in Cloud

    Jianshu Liu (Louisiana State University); Shungeng Zhang (Augusta University); Qingyang Wang (Louisiana State University)


  • Multivariate Anomaly Detection with Domain Clustering (work-in-progress)

    Frederic Boesel, Livio Schläpfer (IBM Research Zurich Research Lab); H. Pozidis (IBM Research GmbH, Switzerland); Mitch Gusat (IBM Research Zurich Research Lab)


3:00 PM
3:30 PM

Break

3:30 PM
5:00 PM

Session 5 (Cloud Applications)

Chairs: Yuanyuan Tian (Gray Systems Lab, Microsoft)

  • Metaverse as a Service: Megascale Social 3D on the Cloud (vision)

    Andreas Haeberlen, Linh Thi Xuan Phan (Roblox / University of Pennsylvania); Morgan McGuire (Roblox)


  • Maximizing the Utilization of GPUs Used by Cloud Gaming through Adaptive Co-location with Combo

    Binghao Chen, Han Zhao, Weihao Cui, Yifu He, Shulai Zhang, Quan Chen, Zijun Li, Minyi Guo (Shanghai Jiao Tong University)


  • Sustainable Supercomputing for AI: GPU Power Capping at HPC Scale (vision)

    Dan Zhao (MIT); Siddharth Samsi, Joseph McDonald (MIT Lincoln Laboratory); Baolin Li (Northeastern University); David Bestor, Michael Jones (MIT Lincoln Laboratory); Devesh Tiwari (Northeastern University); Vijay Gadepally (MIT Lincoln Laboratory)


  • Flame: Simplifying Topology Extension in Federated Learning

    Harshit Daga (Georgia Institute of Technology); Jaemin Shin (KAIST); Dhruv Garg, Ada Gavrilovska (Georgia Institute of Technology); Myungjin Lee, Ramana Rao Kompella (Cisco Research)


  • Online Profiling and Adaptation of Quality Sensitivity for Internet Video (work-in-progress)

    Yihua Cheng (University of Chicago); Hui Zhang (CONVIVA); Junchen Jiang (University of Chicago)


5:00 PM
6:00 PM

Poster session

  • The Gap Between Serverless Research and Real-world Systems (vision)

    Qingyuan Liu, Dong Du, Yubin Xia (Shanghai Jiao Tong University); Ping Zhang (Huawei Cloud); Haibo Chen (Shanghai Jiao Tong University)


  • Function as a Function (vision)

    Tom Kuchler, Michael Giardino, Timothy Roscoe, Ana Klimovic (ETH Zurich)


  • How Does It Function? Characterizing Long-term Trends in Production Serverless Workloads (industry)

    Artjom Joosen, Ahmed Hassan, Luke Darlow, Martin Asenov, Wang Jianfeng, Rajkarn Singh (Huawei); Adam Barker (Huawei / University of St Andrews)


  • Chitu: Accelerating Serverless Workflows with Asynchronous State Replication Pipelines

    Zhengyu Lei (Institute of Computing Technology, Chinese Academy of Sciences; University of Chinese Academy of Sciences; Zhongguancun Laboratory); Xiao Shi (Institute of Computing Technology, Chinese Academy of Sciences; Nanjing Institute of InforSuperBahn); Cunchi Lv (Institute of Computing Technology, Chinese Academy of Sciences; University of Chinese Academy of Sciences; Zhongguancun Laboratory); Xiaobing Yu (Institute of Computing Technology, Chinese Academy of Sciences; University of Chinese Academy of Sciences); Xiaofang Zhao (Institute of Computing Technology, Chinese Academy of Sciences; University of Chinese Academy of Sciences; Zhongguancun Laboratory; Institute of Intelligent Computing Technology, Suzhou, CAS; University of Chinese Academy of Sciences, Nanjing)


  • LatenSeer: Causal Modeling of End-to-End Latency Distribution by Harnessing Distributed Tracing

    Yazhuo Zhang (Emory University); Rebecca Isaacs (Amazon Web Services); Yao Yue (IOP Systems); Juncheng Yang (Carnegie Mellon University); Lei Zhang (Princeton University); Ymir Vigfusson (Emory University & Keystrike)


  • CAMEO: A Causal Transfer Learning Approach for Performance Optimization of Configurable Computer Systems

    Md Shahriar Iqbal (University of South Carolina); Ziyuan Zhong (Columbia University); Iftakhar Ahmad (University of South Carolina); Baishakhi Ray (Columbia University); Pooyan Jamshidi (University of South Carolina)


  • Metaverse as a Service: Megascale Social 3D on the Cloud (vision)

    Andreas Haeberlen, Linh Thi Xuan Phan (Roblox / University of Pennsylvania); Morgan McGuire (Roblox)


  • Flame: Simplifying Topology Extension in Federated Learning

    Harshit Daga (Georgia Institute of Technology); Jaemin Shin (KAIST); Dhruv Garg, Ada Gavrilovska (Georgia Institute of Technology); Myungjin Lee, Ramana Rao Kompella (Cisco Research)


  • User Disengagement-Oriented Target Enforcement for Multi-Tenant Database Systems

    Ning Li (Dept. of Computer Science and Engineering, University of Texas at Arlington, USA); Hong Jiang (UT Arlington); Hao Che (Department of Computer Science and Engineering, The University of Texas at Arlington); Zhijun Wang (University of Texas at Arlington); Minh Q. Nguyen (Faculty of IT, Ho Chi Minh City University of Transport, Vietnam); Stoddard Rosenkrantz (The University of Texas at Arlington)


  • Maximizing VMs IO Performance on Overcommitted CPUs with Fairness

    Tong Xing, Cong Xiong (The University of Edinburgh); Chuan Ye, Qi Wei, Javier Picorel (Huawei Cloud); Antonio Barbalace (The University of Edinburgh)


  • Quantizing Diffusion Models for Unconditional Image Generation off the Cloud

    Jayneel Vora


  • Sybill - Gpu-Free DL Workload Profiling

    Srihas Yarlagadda, Amey Agrawal, Alexey Tumanov


  • Bridging the Gap Between Distributed Tracing and System Monitoring for Cloud Troubleshooting (vision)

    Isu Kim, Seehwan Yoo, Jaehyun Nam


  • Is Machine Learning Necessary for Cloud Resource Usage Forecasting? (vision)

    Georgia Christofidi, Konstantinos Papaioannou, Thaleia Dimitra Doudali (IMDEA Software Institute)


6:00 PM
8:00 PM

Dinner

Wednesday, November 1st

7:30 AM
8:30 AM

Breakfast

8:30 AM
9:30 AM

Keynote 4

Chairs: Yuanyuan Tian (Gray Systems Lab, Microsoft)

  • Querying Unstructured and Structured Data with Large Language Models

    Wang-Chiew Tan (Facebook AI)


9:30 AM
10:00 AM

Break

10:00 AM
12:00 PM

Session 6 (Cloud Resource Management)

Chairs: Shiva Jahangiri (Santa Clara University)

  • Is Machine Learning Necessary for Cloud Resource Usage Forecasting? (vision)

    Georgia Christofidi, Konstantinos Papaioannou, Thaleia Dimitra Doudali (IMDEA Software Institute)


  • Carbon Containers: A System-level Facility for Managing Application-level Carbon Emissions

    John Thiede, Noman Bashir (University of Massachusetts Amherst); David Irwin (University of Massachusetts, Amherst); Prashant Shenoy (University of Massachusetts Amherst)


  • Lifting the Fog of Uncertainties: Dynamic Resource Orchestration for the Containerized Cloud

    Yuqiu Zhang, Tongkun Zhang, Gengrui Zhang, Hans-Arno Jacobsen (University of Toronto)


  • Not All Resources are Visible: Exploiting Fragmented Shadow Resources in Shared-State Scheduler Architecture

    Xinkai Wang, Hao He, Yuancheng Li, Chao Li, Xiaofeng Hou, Jing Wang, Quan Chen, Jingwen Leng, Minyi Guo (Shanghai Jiao Tong University); Leibo Wang (Huawei Technologies Co., Ltd.)


  • Godel: Unified Large-Scale Resource Management and Scheduling at ByteDance (industry)

    Wu Xiang (Bytedance); Yakun Li (ByteDance); Yuquan Ren (Bytedance); Fan Jiang, Chaohui Xin, Varun Gupta, Chao Xiang (ByteDance); Xinyi Song (Bytedance); Meng Liu, Bing Li, Kaiyang Shao, Chen Xu, Wei Shao (ByteDance); Yuqi Fu (University of Virginia); Wilson Wang, Cong Xu (Bytedance); Wei Xu (ByteDance); Caixue Lin, Rui Shi (Bytedance); Yuming Liang (ByteDance)


  • TMC: Near-Optimal Resource Allocation for Tiered-Memory Systems

    Yuanjiang Ni (Alibaba Group); Pankaj Mehra (Elephance Memory, Inc.); Ethan Miller (Pure Storage / University of California, Santa Cruz); Heiner Litz (University of California, Santa Cruz)


12:00 PM
1:30 PM

Lunch

1:30 PM
2:30 PM

Session 7 (Cloud Data Management)

Chairs: Heiner Litz (UC Santa Cruz)

  • Plexus: Optimizing Join Approximation for Geo-Distributed Data Analytics

    Joel Wolfrath, Abhishek Chandra (University of Minnesota)


  • User Disengagement-Oriented Target Enforcement for Multi-Tenant Database Systems

    Ning Li (Dept. of Computer Science and Engineering, University of Texas at Arlington, USA); Hong Jiang (UT Arlington); Hao Che (Department of Computer Science and Engineering, The University of Texas at Arlington); Zhijun Wang (University of Texas at Arlington); Minh Q. Nguyen (Faculty of IT, Ho Chi Minh City University of Transport, Vietnam); Stoddard Rosenkrantz (The University of Texas at Arlington)


  • FileScale: Fast and Elastic Metadata Management for Distributed File Systems

    Gang Liao (ByteDance Infrastructure System Lab); Daniel Abadi (University of Maryland, College Park)


2:30 PM
3:00 PM

Break

3:00 PM
4:00 PM

Session 8 (Cloud Infrastructure)

Chairs: Kostis Kaffes (Columbia University)

  • Maximizing VMs IO Performance on Overcommitted CPUs with Fairness

    Tong Xing, Cong Xiong (The University of Edinburgh); Chuan Ye, Qi Wei, Javier Picorel (Huawei Cloud); Antonio Barbalace (The University of Edinburgh)


  • Enabling Multi-tenancy on SSDs with Accurate IO Interference Modeling

    Lokesh N. Jaliminche (University of California, Santa Cruz, USA); Chandranil (Nil) Chakraborttii (Trinity College, Hartford, USA); Changho Choi (Samsung Semiconductor, Inc, USA); Heiner Litz (University of California, Santa Cruz, USA)


  • Yama: Providing Performance Isolation for Black-Box Offloads

    Tao Ji, Divyanshu Saxena (The University of Texas at Austin); Brent E. Stephens (University of Utah); Aditya Akella (The University of Texas at Austin)


4:00 PM
4:30 PM

Closing