Schedule

This is a tentative schedule subject to change.

Note: all times here are displayed in Pacific time.

Wednesday, November 19, 2025

8:00 AM 8:15 AM	Opening remarks
8:15 AM 9:15 AM	Keynote Toward Sustainable Data Centers for Artificial Intelligence Benjamin C. Lee (University of Pennsylvania)
9:15 AM 10:35 AM	Serverless Towards a Lightweight Sidecar-based Service Mesh for Serverless Lazar Cvetković, Ana Klimovic (ETH Zurich) Serverless Elasticsearch: the Architecture Transformation from Stateful to Stateless Iraklis Psaroudakis, Pooya Salehi, Jason Bryan, Francisco Fernández Castaño, Brendan Cully, Ankita Kumar, Henning Andersen, Thomas Repantis (Elastic) ALAP: Intent-Based Serverless Computing via Delayed Decision-Making Prasoon Sinha (The University of Texas at Austin); Kostis Kaffes (Columbia University); Neeraja J. Yadwadkar (The University of Texas at Austin) Hydra: Virtualized Multi-Language Runtime for High-Density Serverless Platforms Serhii Ivanenko, Vasyl Lanko (INESC-ID, Instituto Superior Técnico, University of Lisbon); Rudi Horn, Vojin Jovanovic (Oracle Labs); Rodrigo Bruno (INESC-ID, Instituto Superior Técnico, University of Lisbon)
10:35 AM 11:35 AM	Memory Rethinking Tiered Memory Management in Cloud Data Centers Tong Xing, Jiaxun Yang (The University of Edinburgh); Javier Picorel (Huawei Technologies); Antonio Barbalace (The University of Edinburgh) Cost-Efficient Cloud Infrastructure with Hugepage-aware Memory Deduplication Ruizhe Huang, Xinyu Wang, Zhida An, Hanwen Lei (Peking University); Peng Jiang (Southeast University); Ziqi Zhang, Ding Li, Yao Guo, Xiangqun Chen (Peking University); Yuntao Liu, Kang Zhou, Yuxin Ren, Ning Jia, Xinwei Hu (Huawei Technologies) [Honorable Mention] Memory Matters: Load-Time Deduplication for Unikernels Gaulthier Gain, Benoît Knott, Cyril Soldani, Laurent Mathy (University of Liège)
11:35 AM 12:45 PM	Break
12:45 PM 2:45 PM	Schedulers Balancing Fairness and Performance in Multi-User Spark Workloads with Dynamic Scheduling Davis Kazemaks (Delft University of Technology); Laurens Versluis (ASML); Burcu Kulahcioglu Ozkan, Jérémie Decouchant (Delft University of Technology) CPU-Limits kill Performance: Time to rethink Resource Control Chirag C Shetty, Sarthak Chakraborty (UIUC); Hubertus Franke, Larisa Shwartz, Chandra Narayanaswami (IBM Research); Indranil Gupta (UIUC); Saurabh Jha (IBM Research) Metis: A Non-Clairvoyant, Workflow-Aware OS Scheduler for Serverless Applications Wenda Tang, Yanan Yang (Cloud Computing Research Institute, China Telecom); Jie Wu (Cloud Computing Research Institute, China Telecom; Department of Computer and Information Sciences, Temple University) From Bottleneck to Breakthrough: Optimizing Scheduling for Hyperscale Containerized Clusters Bing Li (ByteDance); Yuquan Ren (Bytedance); Xinyi Song, Zhilei Liu (ByteDance); Cong Xu (Bytedance); Jingyuan Zhang (ByteDance); Caixue Lin (Bytedance); Wu Xiang (ByteDance); Rui Shi (Bytedance) CoRe: Collaborative Replica Scheduling for Large-Scale Cloud Database Services Hongyu Lei, Shiyu Di, Chunhua Li, Ke Zhou (Huazhong University of Science and Technology); Ming Xie, Fenqiang Yang, Jianping Zhu, Xiang Li, Kezhou Yan (Tencent Inc.) Scheduling Cloud VMs on Variable Capacity Datacenters Rajini Wijayawardana (University of Chicago); Andrew A. Chien (University of Chicago and Argonne National Laboratory)
2:45 PM 3:00 PM	Break
3:00 PM 4:20 PM	Green Computing Water Footprint of Datacenter Applications: Methodological Implications of Manufacturing, Operational, and Decommissioning Phases Amit Samanta (University of Utah); Yankai Jiang (Northeastern University); Ryan Stutsman, Rohan Basu Roy (University of Utah) Middlebox: Unlocking Datacenter Growth and Grid Decarbonization Liuzixuan Lin (University of Chicago); Andrew A Chien (University of Chicago and Argonne National Laboratory) GridGreen: Integrating Serverless Computing in HPC Systems for Performance and Sustainability Amit Samanta, Ryan Stutsman, Rohan Basu Roy (University of Utah) REEF: Energy-Efficient, Application-QoS-Aware Thread Processing in Oversubscribed Server Environments Ning Li, Hong Jiang, Hao Che, Zhijun Wang (Department of Computer Science and Engineering, The University of Texas at Arlington)
4:20 PM 5:20 PM	Privacy Confidential Analytics with Scylla Shamiek Mangipudi (Università della Svizzera italiana); Pavel Chuprikov (Télécom Paris, Institut Polytechnique de Paris); Gerald Prendi, Patrick Eugster (Università della Svizzera italiana) FedDance: Efficient Participant Selection for Federated Learning in Highly Dynamic Environments Yuanhang Chen, Xiaosong Chen, Wenyan Chen, Huanle Xu (University of Macau) FedLTA: A Federated Long-Tail Alignment Framework via Global Class Anchors Yuzi Li, Zhigang Wang, Qinghua Zhang, Junfeng Zhao (Inner Mongolia University)
5:20 PM	End of Day 1

Thursday, November 20, 2025

8:30 AM 10:50 AM	LLM Serving Oneiros: KV Cache Optimization through Parameter Remapping for Multi-tenant LLM Serving Ruihao Li, Shagnik Pal, Vineeth Narayan Pullu, Prasoon Sinha (The University of Texas at Austin); Jeeho Ryoo (Fairleigh Dickinson University); Lizy K. John, Neeraja J. Yadwadkar (The University of Texas at Austin) Symbiosis: Multi-Adapter Inference and Fine-Tuning Saransh Gupta, Umesh Deshpande, Travis Janssen, Swaminathan Sundararaman (IBM Research) AdaSpec: Adaptive Speculative Decoding for Fast, SLO-Aware Large Language Model Serving Kaiyu Huang (Tongji University and Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong, Shenzhen); Hao Wu (HUST); Zhubo Shi, Han Zou (Tongji University); Minchen Yu (School of Data Science, The Chinese University of Hong Kong, Shenzhen and Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong, Shenzhen); Qingjiang Shi (Tongji University and Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong, Shenzhen) DyOrc: Efficient Serving of Dynamic Machine Learning Workflows Shiwei Zhang (The University of Hong Kong); Lansong Diao (Alibaba Group); Zisheng Meng (The University of Hong Kong); Siyu Wang, Wei Lin (Alibaba Group); Chuan Wu (The University of Hong Kong) Multiplexed Heterogeneous LLM Serving via Stage-Aligned Parallelism Tao Luo, Kelvin K.W. Ng, Zhen Ping Khor, Sidharth Sankhe, Boon Thau Loo, Vincent Liu (University of Pennsylvania) ModServe: Modality- and Stage-Aware Resource Disaggregation for Scalable Multimodal Model Serving Haoran Qiu, Anish Biswas (Microsoft); Zihan Zhao (University of Virginia); Jayashree Mohan, Alind Khare, Esha Choukse, Íñigo Goiri (Microsoft); Zeyu Zhang, Haiying Shen (University of Virginia); Chetan Bansal, Ram Ramjee, Rodrigo Fonseca (Microsoft) Cauchy: A Cost-Efficient LLM Serving System through Adaptive Heterogeneous Deployment Yihui Zhang (Beihang University); Han Shen (Kuaishou Inc.); Renyu Yang (Beihang University); Di Tian (Kuaishou Inc.); Yuxi Luo, Menghao Zhang, Li Li, Chunming Hu, Tianyu Wo (Beihang University); Chengru Song, Jin Ouyang (Kuaishou Inc.)
10:50 AM 11:00 AM	Break
11:00 AM 12:20 PM	Network PnM: Efficient Intra-Datacenter Calls Packing for Large Conferencing Services Rohan Gandhi (Microsoft Research, India); Ankur Mallick (Microsoft) PerfMon: Performance Monitoring of Host Network Stack Ranjitha K, Ankit Sarma, Malsawmsanga Sailo, Arun Siddardha, Amrit Kumar, Praveen Tammana (Indian Institute of Technology Hyderabad); Pravein Govindan Kannan, Priyanka Naik (IBM Research) FLASH: Fast Linked AF_XDP Sockets for High Performance Network Function Chains Debojeet Das, Kevin Prafull Baua, Aditya Kansara, Arghyadip Chakraborty, Dheeraj Kurukunda (Indian Institute of Technology Bombay); Mythili Vutukuru (Indian Institute of Technology, Bombay); Purushottam Kulkarni (Indian Institute of Technology Bombay) Rethinking Web Cache Design for the AI Era Yazhuo Zhang, Jinqing Cai (ETH Zurich); Avani Wildani (Cloudflare); Ana Klimovic (ETH Zurich)
12:20 PM 1:30 PM	Break
1:30 PM 3:50 PM	Consistency The case for synchronous distributed protocols in public clouds Nenad Milošević (Università della Svizzera italiana (USI)); Robert Soulé (Yale University); Fernando Pedone (Università della Svizzera italiana (USI)) DFUSE: Strongly Consistent Write-Back Kernel Caching for Distributed Userspace File Systems Haoyu Li, Jingkai Fu (Columbia University); Qing Li, Windsor Hsu (Alibaba Cloud); Asaf Cidon (Columbia University) ParaLog: Consistent Host-side Logging for Parallel Checkpoints Steven W. D. Chien (University of Edinburgh); Kento Sato (RIKEN R-CCS); Artur Podobas, Niclas Jansson, Stefano Markidis (KTH Royal Institute of Technology); Michio Honda (University of Edinburgh) VLCs: Managing Parallelism with Virtualized Libraries Yineng Yan, William Ruys, Hochan Lee, Ian Henriksen, Arthur Peters, Sean Stephens, Bozhi You, Henrique Fingler (University of Texas at Austin); Martin Burtscher (Texas State University); Milos Gligoric, Keshav Pingali, Mattan Erez, George Biros, Christopher J. Rossbach (University of Texas at Austin) Revisiting State Machine Replication in Practice: Lessons from Building an etcd-inspired System Lucas Lebow, Mason Dunkle (Unaffiliated); Christopher Siems (Clark University); Jonathan Zarnstorff (BoreDM); Lewis Tseng (UMass Lowell) Orcas: A DAG-based Consensus Approach with Linear Communication Overhead Yi Hua, Xiulong Liu, Hao Xu, Chenyu Zhang, Gaowei Shi, Keqiu Li (Tianjin University); Muhammad Shahzad (Department of Computer Science, North Carolina State University, Raleigh, NC, USA); Guyue (Grace) Liu (Peking University) Nano-consensus: Ultra-fast, Quorum-less Coordination on the Wire Davide Rovelli (Università della Svizzera Italiana, SAP SE); Christian Faerber, Graham McKenzie (Altera); Ali Pahlevan (SAP SE); Sina Darabi (Università della Svizzera italiana); Patrick Jahnke (turbalance); Patrick Eugster (Università della Svizzera italiana)
3:50 PM 4:00 PM	Break
4:00 PM 5:40 PM	Co-processors Funky: Cloud-Native FPGA Virtualization and Orchestration Atsushi Koshiba, Charalampos Mainas, Pramod Bhatotia (Technical University of Munich) Understanding GPU Resource Interference One Level Deeper Paul Elvinger, Foteini Strati (ETH Zurich); Natalie Enright Jerger (University of Toronto); Ana Klimovic (ETH Zurich) Spatio-Temporal Resource Control for Cloud-Native GPU Provisioning Hyeon-Jun Jang, Sang-Jae Kim (Konkuk University); Weikuan Yu (Florida State University); Hyun-Wook Jin (Konkuk University) ZipBatch: Multi-Tenant GPU Batching with Dual-Resource Regulation Haoxuan Yu, Sheng Yao, Wei Wang (Hong Kong University of Science and Technology) Snap & Replay: A new way to analyze uarch-scale performance bottlenecks for ML accelerators Ioannis Zarkadas (Columbia University); Amanda Tomlinson (University of California, San Diego); Asaf Cidon (Columbia University); Baris Kasikci (University of Washington); Ofir Weisse (Google)
5:40 PM	End of Day 2

Friday, November 21, 2025

8:30 AM 10:30 AM	Cloud-for-ML CoMPI: Coordinated Model Merging and Parallel Inference at Edge Shuang Zeng, Haitao Zhang, Zezhong Yan (Beijing University of Posts and Telecommunications) FaaSGNN: Enabling Memory Efficient and Low Latency GNN Inference Services with Serverless Computing Yuzhuo Yang, Kaihua Fu, Quan Chen (Shanghai Jiao Tong University); Deze Zeng (China University of Geosciences); Shuo Quan (Cloud Computing Research Institute, China Telecom); Jie Wu (Temple University); Minyi Guo (Shanghai Jiao Tong University) CIS: Checkpointed Inference for Data Drift-Resilient Model Serving at Edge Servers Sudipta Saha Shubha, Haiying Shen (University of Virginia); Ganesh Ananthanarayanan (Microsoft) Understanding Diffusion Model Serving in Production: A Top-Down Analysis of Workload, Scheduling, and Resource Efficiency Yanying Lin (University of Chinese Academy of Sciences); Shuaipeng Wu (Chinese Academy of Sciences, Alibaba Group); Shutian Luo (University of Virginia); Hong Xu (The Chinese University of Hong Kong); Haiying Shen (University of Virginia); Chong Ma, Min Shen, Le Chen (AIOS Team, Alibaba Group Inc); Chengzhong Xu (University of Macau); Lin Qu (AIOS Team, Alibaba Group Inc); Kejiang Ye (Chinese Academy of Sciences) SneakPeek: Data-Aware Model Selection and Scheduling for Inference Serving on the Edge Joel Wolfrath, Daniel Frink, Abhishek Chandra (University of Minnesota) FailLite: Failure-Resilient Model Serving for Resource-Constrained Edge Environments Li Wu, Walid Hanafy (University of Massachusetts Amherst); Tarek Abdelzaher (UIUC); David Irwin (University of Massachusetts Amherst); Jesse Milzman (Army Research Laboratory); Prashant Shenoy (University of Massachusetts Amherst)
10:30 AM 10:45 AM	Break
10:45 AM 12:25 PM	Training Cuckoo: Deadline-Aware Job Packing on Heterogeneous GPUs for DL Model Training Yuzheng Zhang, Renyu Yang, Junhong Liu, Weihan Jiang, Tianyu Ye (Beihang University); Yiqiao Liao, Penghao Zhang, Tiezi Zhang, Kun Shang (Kuaishou Inc.); Tianyu Wo, Chunming Hu (Beihang University); Chengru Song, Jin Ouyang (Kuaishou Inc.) THORN-ML: Transparent Hardware Offloaded Resilient Networks for RDMA based Distributed ML Workloads Maziyar Nazari (University of Colorado Boulder); Daniel Noland (Unaffiliated); Giulio Sidoretti, Erika Hunhoff, Tamara Silbergleit Lehman (University of Colorado Boulder); Eric Keller (University of Colorado, Boulder) Multi-Agent Reinforcement Learning with Serverless Computing Rui Wei, Hanfei Yu (Stevens Institute of Technology); Xikang Song (University of Chicago); Jian Li (Stony Brook University); Devesh Tiwari (Northeastern University); Ying Mao (Fordham University); Hao Wang (Stevens Institute of Technology) PowerTrip: Exploiting Federated Heterogeneous Datacenter Power for Distributed ML Training Talha Mehboob (University of Massachusetts Amherst); Luanzheng Guo, Nathan R. Tallent (Pacific Northwest National Laboratory); Michael Zink, David Irwin (University of Massachusetts Amherst) 10Cache: Heterogeneous Resource-Aware Tensor Caching and Migration for LLM Training Sabiha Afroz, Redwan Ibne Seraj Khan (Virginia Tech); Hadeel Albahar (Kuwait University); Jingoo Han, Ali R. Butt (Virginia Tech)
12:25 PM 1:30 PM	Break
1:30 PM 3:10 PM	ML-for-Cloud Cloud-Native Digital Twin Orchestration for Real-Time Decision Optimization Using Fuzzy Constraints and Reinforcement Learning David Li (Yeshiva University); Angela Li (Stony Brook University) DRAM Failure Prediction with Correctable Error Spatial Patterns: A Hybrid Learning Approach Lei Liu (Inspur Cloud Information Technology Co.,Ltd.); Yinling Zhang (JINAN THERMAL POWER GROUP CO..LTD) Defragmentation Scheduling with Deep Reinforcement Learning in Shared GPU Clusters Qingfu Wu, Pengfei Chen, Yilun Wang (Sun Yat-sen University) A Bootstrapping Technique for Reducing the Costs of Machine Learning Models for Predicting Execution Times in IaaS Clouds Romolo Marotta, Gabriele Russo Russo, Francesco Quaglia (University of Rome Tor Vergata); Pierangelo Di Sanzo (Roma Tre University) Hybrid Learning and Optimization-Based Dynamic Scheduling for DL Workloads on Heterogeneous GPU Clusters Shruti Dongare, Redwan Ibne Seraj Khan (Virginia Tech); Hadeel Albahar (Kuwait University); Nannan Zhao (Northwestern Polytechnical University, China); Diego Meléndez-Maita, Ali R. Butt (Virginia Tech)
3:10 PM 4:10 PM	Infrastructure Offloading Cloud-Native Infrastructure with XpuPod Bicheng Yang, Jingkai He, Dong Du, Yubin Xia, Haibo Chen (Shanghai Jiao Tong University) DuoAdmit: Dual-Layer Cache Admission for Load-Balancing Hybrid-Redundancy Block Storage Xiaojun Guo, Guangjie Xing, Hua Wang, Ke Zhou (Huazhong University of Science an Technology); Ming Xie, Fenqiang Yang, Min Fu, Bin Xu, Jianying Hu, Guangchao Yang (Tencent Technology Co., Ltd.) [Honorable Mention] WDP: Mitigating Interference in CPU Sharing Through Wake-up Delay Driven Preemption for QoS-aware Co-location Yaoxuan Li, Pu Pang, Yecheng Yang, Quan Chen, Zhengxuan Yan (Shanghai Jiao Tong University); Guoyao Xu, Guodong Yang, Liping Zhang (Alibaba Group); Minyi Guo (Shanghai Jiao Tong University)
4:10 PM 5:50 PM	Storage A Fast, Efficient, and Strongly-Consistent Object Store Shuwen Sun, Isaac Khor, Ji-Yong Shin, Peter Desnoyers (Northeastern University) BLAFS: A Bloat-Aware Container File System Huaifeng Zhang (Chalmers University of Technology and University of Gothenburg); Mohannad Alhanahnah (University of Wisconsin-Madison); Philipp Leitner, Ahmed Ali-Eldin (Chalmers University of Technology and University of Gothenburg) [Best Paper] Valet: Efficient Data Placement on Modern SSDs Devashish R. Purandare, Peter Alvaro (University of California, Santa Cruz); Avani Wildani (Emory University and Cloudflare); Darrell D. E. Long (University of California, Santa Cruz); Ethan L. Miller (Pure Storage / University of California, Santa Cruz) Accelerating Distributed Filesystem Metadata Service via Decoupling Directory Semantics from Metadata Indexing Wenhao Lv, Hao Guo, Qing Wang, Youyou Lu, Jiwu Shu (Tsinghua University) Scalable and Fault-Tolerant Storage and File System Services with Non-Blocking Synchronization for Private Clouds Mincheol Sung (Virginia Tech); Ruslan Nikolaev (The Pennsylvania State University); Binoy Ravindran (Virginia Tech)
5:50 PM 6:00 PM	Closing remarks
6:00 PM	End of SoCC '25!