Accepted Papers
The following papers have been accepted to appear at the 30th ACM SIGOPS Symposium on Operating Systems Principles (SOSP), conditional on the approval of each paper's shepherd:
- Aceso: Achieving Efficient Fault Tolerance in Memory-Disaggregated Key-Value Stores
Zhisheng Hu (The Chinese University of Hong Kong), Pengfei Zuo (Huawei Cloud), Yizou Chen (The Chinese University of Hong Kong), Chao Wang (The Chinese University of Hong Kong), Junliang Hu (The Chinese University of Hong Kong), Ming-Chang Yang (The Chinese University of Hong Kong (CUHK)) - Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving
Yinwei Dai (Princeton University), Rui Pan (Princeton University), Anand Iyer (Georgia Tech), Kai Li (Princeton University), Ravi Netravali (Princeton University) - Autobahn: Seamless high speed BFT
Florian Suri-Payer (Cornell University), Neil Giridharan (UC Berkeley), Natacha Crooks (University of California Berkeley & Azure Systems Research), Lorenzo Alvisi (Cornell University), Ittai Abraham (Intel) - BIZA: Design of Self-Governing Block-Interface ZNS AFA for Endurance and Performance Shushu Yi (Peking University), Shaocong Sun (Peking University), Li Peng (Peking University), Yingbo Sun (Peking University), Ming-Chang Yang (The Chinese University of Hong Kong (CUHK)), Zhichao Cao (ASU), Qiao Li (Xiamen University), Myoungsoo Jung (KAIST and Panmnesia), Ke Zhou (Wuhan National Laboratory for Optoelectronics (WNLO) of Huazhong University of Science and Technology (HUST)), Jie Zhang (Peking University)
- CHIME: A Cache-Efficient and High-Performance Hybrid Index on Disaggregated Memory
Xuchuan Luo (Fudan University), Jiacheng Shen (The Chinese University of Hong Kong), Pengfei Zuo (Huawei Cloud), Xin Wang (Fudan University), Michael R. Lyu (The Chinese University of Hong Kong), Yangfan Zhou (Fudan University) - Caribou: Fine-Grained Geospatial Shifting of Serverless Applications for Sustainability
Viktor Gsteiger (ETH Zurich), Pin Hong (Daniel) Long (University of British Columbia), Yiran (Jerry) Sun (University of British Columbia), Parshan Javanrood (University of British Columbia), Mohammad Shahrad (University of British Columbia) - Cookie Monster: Efficient On-Device Budgeting for Differentially-Private Ad-Measurement Systems
Pierre Tholoniat (Columbia University), Kelly Kostopoulou (Columbia University), Peter McNeely (Columbia University), Prabhpreet Singh Sodhi (Columbia University), Anirudh Varanasi (Columbia University), Benjamin Case (Meta Inc.), Asaf Cidon (Columbia University), Mathias Lécuyer (University of British Columbia), Roxana Geambasu (Columbia University) - DNS Congestion Control in Adversarial Settings
Huayi Duan (ETH Zurich), Jihye Kim (ETH Zurich), Marc Wyss (ETH Zurich), Adrian Perrig (ETH Zurich) - Dirigent: Lightweight Serverless Orchestration
Lazar Cvetković (ETH Zurich), François Costa (ETH Zurich), Mihajlo Djokic (IBM Research Europe), Michal Friedman (ETH Zurich), Ana Klimovic (ETH Zurich) - Efficient Reproduction of Fault-Induced Failures in Distributed Systems with Feedback-Driven Fault Injection
Jia Pan (Johns Hopkins University), Haoze Wu (Johns Hopkins University), Tanakorn Leesatapornwongsa (Microsoft Research), Suman Nath (Microsoft Research), Peng Huang (University of Michigan) - Efficient file-lifetime redundancy management for cluster file systems
Tim Kim (Carnegie Mellon University), Sanjith Athlur (Carnegie Mellon University), Saurabh Kadekodi (Google), Francisco Maturana (Carnegie Mellon University), Dax Vandevoore (Carnegie Mellon University), Arif Merchant (Google), Greg Ganger (Carnegie Mellon University), Rashmi Vinayak (Carnegie Mellon University) - Enabling Parallelism Hot Switching for Efficient Training of Large Language Models
Hao Ge (Peking University), Fangcheng Fu (Peking University), Haoyang Li (Peking University), Xuanyu Wang (Peking University), Sheng Lin (Peking University), Yujie Wang (Peking University), Xiaonan Nie (Peking University), Hailin Zhang (Peking University), Xupeng Miao (Carnegie Mellon University), Bin Cui (Peking University) - FBDetect: Catching Tiny Performance Regressions at Hyperscale through In-Production Monitoring
Dong Young Yoon (Meta Platforms), Yang Wang (Meta Platforms and the Ohio State University), Miao Yu (Meta Platforms and the Ohio State University), Xu Huang (Meta Platforms), Juan Ignacio Jones (Meta Platforms), Abhinay Kukkadapu (Meta Platforms), Osman Kocas (Meta Platforms), Jonathan Wiepert (Meta Platforms), Kapil Goenka (Meta Platforms), Sherry Chen (Meta Platforms), Yanjun Lin (Meta Platforms), Zhihui Huang (Meta Platforms), Jocelyn Kong (Meta Platforms), Michael Chow (Meta Platforms), Chunqiang Tang (Meta Platforms) - Fast & Safe IO Memory Protection
Benny Rubin (Cornell University), Saksham Agarwal (Cornell University), Qizhe Cai (Cornell University), Rachit Agarwal (Cornell University) - Fast Core Scheduling with Userspace Process Abstraction
Jiazhen Lin (Tsinghua University), Youmin Chen (Tsinghua University), Shiwei Gao (Tsinghua University), Youyou Lu (Tsinghua University) - Fast, Flexible, and Practical Kernel Extensions
Kumar Kartikeya Dwivedi (EPFL), Rishabh Iyer (UC Berkeley), Sanidhya Kashyap (EPFL) - Icarus: Trustworthy Just-In-Time Compilers with Symbolic Meta-Execution
Michael Smith (UC San Diego), Abhishek Sharma (University of Texas at Austin), Hovav Shacham (University of Texas at Austin), Ranjit Jhala (UC San Diego), Deian Stefan (UC San Diego) - If At First You Don’t Succeed, Try, Try, Again...? Insights and LLM-informed Tooling for Detecting Retry Bugs in Software Systems
Bogdan Alexandru Stoica (University of Chicago), Utsav Sethi (University of Chicago), Yiming Su (University of Chicago), Cyrus Zhou (University of Chicago), Shan Lu (Microsoft Research), Jonathan Mace (Microsoft Research), Madan Musuvathi (Microsoft Research), Suman Nath (Microsoft Research) - Improving DNN Inference Throughput Using Practical, Per-Input Compute Adaptation
Anand Iyer (Georgia Tech), Swapnil Gandhi (Stanford University), Mingyu Guan (Georgia Tech), Yinwei Dai (Princeton University), Rui Pan (Princeton University), Ravi Netravali (Princeton University) - LazyLog: A New Shared Log Abstraction for Low-Latency Applications
Xuhao Luo (University of Illinois Urbana-Champaign), Shreesha G Bhat (University of Illinois Urbana-Champaign), Jiyu Hu (University of Illinois Urbana-Champaign), Ramnatthan Alagappan (University of Illinois Urbana-Champaign and VMware Research), Aishwarya Ganesan (University of Illinois Urbana-Champaign and VMware Research) - LoongServe: Efficiently Serving Long-Context Large Language Models with Elastic Sequence Parallelism
Bingyang Wu (Peking University), Shengyu Liu (Peking University), Yinmin Zhong (Peking University), Peng Sun (Shanghai AI Lab), Xuanzhe Liu (Peking University), Xin Jin (Peking University) - Modular Verification of Secure and Leakage-Free Systems: From Application Specification to Circuit-Level Implementation
Anish Athalye (Massachusetts Institute of Technology), Henry Corrigan-Gibbs (MIT), Frans Kaashoek (MIT), Joseph Tassarotti (New York University), Nickolai Zeldovich (Massachusetts Institute of Technology) - NOPE: Strengthening domain authentication with zero-knowledge proofs
Zachary DeStefano (NYU), Jeff J. Ma (NYU), Joseph Bonneau (NYU), Michael Walfish (NYU) - OZZ: Identifying Kernel Out-of-Order Concurrency Bugs with In-Vivo Memory Access Reordering
Dae R. Jeong (Georgia Tech), Yewon Choi (KAIST), Byoungyoung Lee (Seoul National University), Insik Shin (KAIST), Youngjin Kwon (KAIST) - PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU
Yixin Song (Shanghai Jiao Tong University), Zeyu Mi (Shanghai Jiao Tong University), Haotong Xie (Shanghai Jiao Tong University), Haibo Chen (Shanghai Jiao Tong University) - Practical Verification of System-Software Components Written in Standard C
Can Cebeci (EPFL), Yonghao Zou (EPFL), Diyu Zhou (EPFL), George Candea (EPFL), Clément Pit-Claudel (EPFL) - ReCycle: Pipeline Adaptation for the Resilient Distributed Training of Large DNNs
Swapnil Gandhi (Stanford University), Mark Zhao (Stanford University), Athinagoras Skiadopoulos (Stanford University), Christos Kozyrakis (Stanford University) - Reducing Energy Bloat in Large Model Training
Jae-Won Chung (University of Michigan), Yile Gu (University of Washington), Insu Jang (University of Michigan), Luoxi Meng (University of California, San Diego), Nikhil Bansal (University of Michigan), Mosharaf Chowdhury (University of Michigan) - Reducing cross-cloud/region costs with the auto-configuring MACARON cache
Hojin Park (Carnegie Mellon University), Ziyue Qiu (Carnegie Mellon University), Gregory R. Ganger (Carnegie Mellon University), George Amvrosiadis (Carnegie Mellon University) - SWARM: Replicating Shared Disaggregated-Memory Data in No Time
Antoine Murat (EPFL), Clément Burgelin (EPFL), Athanasios Xygkis (Oracle Labs), Igor Zablotchi (Mysten Labs), Marcos K. Aguilera (VMware Research Group), Rachid Guerraoui (EPFL) - Tenplex: Dynamic Parallelism for Deep Learning using Parallelizable Tensor Collections
Marcel Wagenländer (Imperial College London), Guo Li (Imperial College London), Bo Zhao (Aalto University), Luo Mai (University of Edinburgh), Peter Pietzuch (Imperial College London) - Scaling Deep Learning Computation over the Inter-Core Connected Intelligence Processor with T10
Yiqi Liu (University of Illinois Urbana-Champaign), Yuqi Xue (University of Illinois Urbana-Champaign), Yu Cheng (Microsoft Research), Lingxiao Ma (Microsoft Research), Ziming Miao (Microsoft Research), Jilong Xue (Microsoft Research), Jian Huang (University of Illinois Urbana-Champaign) - Sesame: Practical End-to-End Privacy Compliance with Policy Containers and Privacy Regions
Kinan Dak Albab (Brown University), Artem Agvanian (Brown University), Allen Aby (Brown University), Corinn Tiffany (Brown University), Alexander Portland (Brown University), Sarah Ridley (Brown University), Malte Schwarzkopf (Brown University) - SilvanForge: A Schedule-Guided Retargetable Compiler for Decision Tree Inference
Ashwin Prasad (Indian Institute of Science), Sampath Rajendra (Microsoft Research), Kaushik Rajan (Microsoft Research), R Govindarajan (Indian Institute of Science, Bangalore, India), Uday Bondhugula (Indian Institute of Science and PolyMage Labs) - Skyloft: A General High-Efficient Scheduling Framework in User Space
Yuekai Jia (Tsinghua University), Kaifu Tian (Tsinghua University), Yuyang You (Tsinghua University), Yu Chen (Tsinghua University), Kang Chen (Tsinghua University) - Tiered Memory Management: Access Latency is the Key!
Midhul Vuppalapati (Cornell University), Rachit Agarwal (Cornell University) - TrEnv: Transparently Share Serverless Execution Environments Across Different Functions and Nodes
Jialiang Huang (Tsinghua University, Alibaba Group), MingXing Zhang (Tsinghua University), Teng Ma (Alibaba Group), Zheng Liu (Zhejiang University, Alibaba Group), Sixing Lin (Tsinghua University, Wuhan University), Kang Chen (Tsinghua University), Jinlei Jiang (Tsinghua University), Xia Liao (Tsinghua University), Yingdi Shan (Tsinghua University), Ning Zhang (Alibaba Group), Mengting Lu (Alibaba Group), Tao Ma (Alibaba Group), Haifeng Gong (Intel), YongWei Wu (Tsinghua University) - Uncovering Nested Data Parallelism and Data Reuse in DNN Computation with FractalTensor
Siran Liu (Peking University), Chengxiang Qi (University of Chinese Academy of Sciences), Ying Cao (Microsoft Research Asia), Chao Yang (Peking University), Weifang Hu (Huazhong University of Science and Technology), Xuanhua Shi (Huazhong University of Science and Technology), Fan Yang (Microsoft Research Asia), Mao Yang (Microsoft Research Asia) - Unearthing Semantic Checks for Cloud Infrastructure-as-Code Programs
Yiming Qiu (University of Michigan), Patrick Tser Jern Kon (University of Michigan), Ryan Beckett (Microsoft), Ang Chen (University of Michigan) - Unifying serverless and microservice workloads with SigmaOS
Ariel Szekely (MIT), Adam Belay (MIT), Robert Morris (MIT), Frans Kaashoek (MIT) - VPRI: Optimized I/O Page Fault in Public IaaS
Kaijie Guo (Alibaba Cloud), Dingji Li (Shanghai Jiaotong University), Ben Luo (Alibaba Cloud), Yibin Shen (Alibaba Cloud), Kaihuan Peng (Alibaba Cloud), Ning Luo (Alibaba Cloud), Shengdong Dai (Alibaba Cloud), Chen Liang (Alibaba Cloud), Jianming Song (Alibaba Cloud), Hang Yang (Alibaba Cloud), Xiantao Zhang (Alibaba Cloud), Zeyu Mi (Shanghai Jiaotong University) - Verus: A Practical Foundation for Systems Verification
Andrea Lattuada (MPI-SWS), Travis Hance (Carnegie Mellon University), Jay Bosamiya (Microsoft Research), Matthias Brun (ETH Zurich), Chanhee Cho (Carnegie Mellon University), Hayley LeBlanc (University of Texas at Austin), Pranav Srinivasan (University of Michigan), Reto Achermann (University of British Columbia), Tej Chajed (University of Wisconsin-Madison), Chris Hawblitzel (Microsoft Research), Jon Howell (VMware Research), Jacob R. Lorch (Microsoft Research), Oded Padon (Weizmann Institute of Science), Bryan Parno (Carnegie Mellon University) - vSoC: Efficient Virtual System-on-Chip on Heterogeneous Hardware
Jiaxing Qiu (Tsinghua University), Zijie Zhou (Tsinghua University), Yang Li (Tsinghua University), Zhenhua Li (Tsinghua University), Feng Qian (University of Southern California), Hao Lin (Tsinghua University and University of Illinois Urbana-Champaign), Di Gao (Tsinghua University), Haitao Su (Tsinghua University), Xin Miao (Tsinghua University), Yunhao Liu (Tsinghua University), Tianyin Xu (University of Illinois Urbana-Champaign)