Table of Contents

• Empowering WebAssembly with Thin Kernel InterfacesArjun Ramesh, Tianshu Huang, Ben L. Titzer, Anthony Rowe 0001. 1-20 [doi]
• Revealing the Unstable Foundations of eBPF-Based Kernel ExtensionsShawn Wanxiang Zhong, Jing Liu, Andrea C. Arpaci-Dusseau, Remzi H. Arpaci-Dusseau. 21-41 [doi]
• eNetSTL: Towards an In-kernel Library for High-Performance eBPF-based Network FunctionsBin Yang 0027, Dian Shen, Junxue Zhang 0001, Hanlin Yang, Lunqi Zhao, Beilun Wang, Guyue Liu, Kai Chen 0005. 42-58 [doi]
• CRAVE: Analyzing Cross-Resource Interaction to Improve Energy Efficiency in Systems-on-ChipDipayan Mukherjee, Sam Hachem, Jeremy Bao, Curtis Madsen, Tian Ma, Saugata Ghose, Gul Agha. 59-75 [doi]
• Efeu: generating efficient, verified, hybrid hardware/software drivers for I2C devicesDaniel Schwyn, Zikai Liu, Timothy Roscoe. 76-93 [doi]
• CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge FusionJiayi Yao, Hanchen Li, Yuhan Liu, Siddhant Ray, Yihua Cheng, Qizheng Zhang, Kuntai Du, Shan Lu 0001, Junchen Jiang. 94-109 [doi]
• DeltaZip: Efficient Serving of Multiple Full-Model-Tuned LLMsXiaozhe Yao, Qinghao Hu, Ana Klimovic. 110-127 [doi]
• Fast State Restoration in LLM Serving with HCacheShiwei Gao, Youmin Chen, Jiwu Shu. 128-143 [doi]
• Stateful Large Language Model Serving with PensieveLingfan Yu, Jinkun Lin, Jinyang Li 0001. 144-158 [doi]
• SkyServe: Serving AI Models across Regions and Clouds with Spot InstancesZiming Mao, Tian Xia, Zhanghao Wu, Wei-Lin Chiang, Tyler Griggs, Romil Bhardwaj, Zongheng Yang, Scott Shenker, Ion Stoica. 159-175 [doi]
• RoboRebound: Multi-Robot System Defense with Bounded-Time InteractionNeeraj Gandhi, Yifan Cai, Andreas Haeberlen, Linh Thi Xuan Phan. 176-192 [doi]
• Achilles: Efficient TEE-Assisted BFT Consensus via Rollback Resilient RecoveryJianyu Niu, Xiaoqing Wen, Guanlong Wu, Shengqi Liu, Jiangshan Yu, Yinqian Zhang. 193-210 [doi]
• ParallelEVM: Operation-Level Concurrent Transaction Execution for EVM-Compatible BlockchainsHaoran Lin, Hang Feng, Yajin Zhou, Lei Wu 0012. 211-225 [doi]
• Ladon: High-Performance Multi-BFT Consensus via Dynamic Global OrderingHanzheng Lyu, Shaokang Xie, Jianyu Niu, Chen Feng 0001, Yinqian Zhang, Ivan Beschastnikh. 226-242 [doi]
• SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUsRuibo Fan, Xiangrui Yu, Peijie Dong, ZeYu Li, Gu Gong, Qiang Wang 0022, Wei Wang 0030, Xiaowen Chu 0001. 243-260 [doi]
• Empower Vision Applications with LoRA LMMLiang Mi, Weijun Wang, Wenming Tu, Qingfeng He, Rui Kong, XinYu Fang, Yazhu Dong, Yikang Zhang, Yuanchun Li, Meng Li 0010, Haipeng Dai 0001, Guihai Chen, Yunxin Liu. 261-277 [doi]
• T-MAC: CPU Renaissance via Table Lookup for Low-Bit LLM Deployment on EdgeJianyu Wei, Shijie Cao, Ting Cao, Lingxiao Ma, Lei Wang, Yanyong Zhang, Mao Yang. 278-292 [doi]
• Samoyeds: Accelerating MoE Models with Structured Sparsity Leveraging Sparse Tensor CoresChenpeng Wu, Qiqi Gu, Heng Shi, Jianguo Yao, Haibing Guan. 293-310 [doi]
• Collaborative Text Editing with Eg-walker: Better, Faster, SmallerJoseph Gentle, Martin Kleppmann. 311-328 [doi]
• Themis: Finding Imbalance Failures in Distributed File Systems via a Load Variance ModelYuanliang Chen, Fuchen Ma, Yuanhang Zhou, Zhen Yan, Qing Liao 0001, Yu Jiang 0001. 329-344 [doi]
• Moko: Marrying Python with Big Data SystemsKe Meng, Tao He, Sijie Shen, Lei Wang 0004, Wenyuan Yu, Jingren Zhou 0001. 345-359 [doi]
• Pegasus: Transparent and Unified Kernel-Bypass Networking for Fast Local and Remote CommunicationDinglan Peng, Congyu Liu, Tapti Palit, Anjo Vahldiek-Oberwagner, Mona Vij, Pedro Fonseca 0001. 360-378 [doi]
• Multi-Grained Specifications for Distributed System Model Checking and VerificationLingzhi Ouyang, Xudong Sun 0013, Ruize Tang, Yu Huang 0002, Madhav Jivrajani, Xiaoxing Ma, Tianyin Xu. 379-395 [doi]
• Enabling Virtual Priority in Data Center Congestion ControlZhaochen Zhang, Feiyang Xue, Keqiang He, Zhimeng Yin, Gianni Antichi, Jiaqi Gao, Yizhi Wang, Rui Ning, Haixin Nan, Xu Zhang 0006, Peirui Cao, Xiaoliang Wang 0001, Wanchun Dou, Guihai Chen, Chen Tian 0001. 396-412 [doi]
• Achieving Fairness Generalizability for Learning-based Congestion Control with JuryHan Tian, Xudong Liao, Decang Sun, Chaoliang Zeng, Yilun Jin, Junxue Zhang 0001, Xinchen Wan, Zilong Wang 0007, Yong Wang 0011, Kai Chen 0005. 413-427 [doi]
• Introspective Congestion Control for Consistent High PerformanceWanchun Jiang, Haoyang Li, Jia Wu 0001, Kai Wang, Fengyuan Ren, Jianxin Wang 0001. 428-445 [doi]
• Fork: A Dual Congestion Control Loop for Small and Large Flows in DatacentersYuan Liu, Wenxin Li 0001, Yulong Li, Lide Suo, Xuan Gao, Xin Xie 0001, Sheng Chen 0008, Ziqi Fan, Wenyu Qu, Guyue Liu. 446-459 [doi]
• Marlin: Enabling High-Throughput Congestion Control Testing in Large-Scale NetworksYanqing Chen, Li Wang, Jingzhi Wang, Songyue Liu, Keqiang He, Jian Wang 0038, Xiaoliang Wang 0001, Wanchun Dou, Guihai Chen, Chen Tian 0001. 460-474 [doi]
• LOFT: A Lock-free and Adaptive Learned Index with High Scalability for Dynamic WorkloadsYuxuan Mo, Yu Hua 0001. 475-491 [doi]
• MetaHG: Enhancing HGNN Systems Leveraging Advanced Metapath Graph AbstractionHaiheng He, Haifeng Liu 0003, Long Zheng 0003, Yu Huang 0013, Xinyang Shen, Wenkan Huang, Shuaihu Cao, Xiaofei Liao, Hai Jin 0001, Jingling Xue. 492-506 [doi]
• Flex: Fast, Accurate DNN Inference on Low-Cost Edges Using Heterogeneous Accelerator ExecutionTanmoy Sen, Haiying Shen, Anand Padmanabha Iyer. 507-523 [doi]
• A House United Within Itself: SLO-Awareness for On-Premises Containerized ML Inference Clusters via FaroBeomyeol Jeon, Chen Wang 0039, Diana Arroyo, Alaa Youssef, Indranil Gupta. 524-540 [doi]
• Comprehensive Deadlock Prevention for GPU Collective CommunicationLichen Pan, Juncheng Liu, Yongquan Fu, Jinhui Yuan, Rongkai Zhang 0005, Pengze Li, Zhen Xiao. 541-557 [doi]
• Jupiter: Pushing Speed and Scalability Limitations for Subgraph Matching on Multi-GPUsZhiheng Lin, Ke Meng, Changjie Xu, Weichen Cao 0002, Guangming Tan. 558-572 [doi]
• Improving GPU Sharing Performance through Adaptive Bubbleless Spatial-Temporal SharingShulai Zhang, Quan Chen 0002, Weihao Cui, Han Zhao 00005, Chunyu Xue, Zhen Zheng, Wei Lin 0016, Minyi Guo. 573-588 [doi]
• Multiplexing Dynamic Deep Learning Workloads with SLO-awareness in GPU ClustersWenyan Chen 0001, Chengzhi Lu, Huanle Xu, Kejiang Ye, Chengzhong Xu 0001. 589-604 [doi]
• Bingo: Radix-based Bias Factorization for Random Walk on Dynamic GraphsPinhuan Wang, Chengying Huan, Zhibin Wang, Chen Tian 0001, Yuede Ji, Hang Liu 0001. 605-620 [doi]
• OHMiner: An Overlap-centric System for Efficient Hypergraph Pattern MiningHao Qi 0004, Kang Luo, Ligang He, Yu Zhang 0027, Minzhi Cai, Jingxin Dai, Bingsheng He, Hai Jin 0001, Zhan Zhang, Jin Zhao 0003, Hengshan Yue, Hui Yu, Xiaofei Liao. 621-636 [doi]
• Impeller: Stream Processing on Shared LogsZhiting Zhu, Zhipeng Jia, Newton Ni, Dixin Tang, Emmett Witchel. 637-653 [doi]
• CAPSys: Contention-aware task placement for data stream processingYuanli Wang, Lei Huang, Zikun Wang, Vasiliki Kalavri, Ibrahim Matta. 654-670 [doi]
• NeuStream: Bridging Deep Learning Serving and Stream ProcessingHaochen Yuan, Yuanqing Wang, Wenhao Xie, Yu Cheng, Ziming Miao, Lingxiao Ma, Jilong Xue, Zhi Yang. 671-685 [doi]
• Towards VM Rescheduling Optimization Through Deep Reinforcement LearningXianzhong Ding, Yunkai Zhang 0002, Binbin Chen, Donghao Ying, Tieying Zhang, Jianjun Chen 0001, Lei Zhang, Alberto Cerpa, Wan Du. 686-701 [doi]
• HyperAlloc: Efficient VM Memory De/Inflation via Hypervisor-Shared Page-Frame AllocatorsLars Wrenger, Kenny Albes, Marco Wurps, Christian Dietrich 0001, Daniel Lohmann. 702-719 [doi]
• FastIOV: Fast Startup of Passthrough Network I/O Virtualization for Secure ContainersYunzhuo Liu, Junchen Guo, Bo Jiang 0003, Yang Song 0022, Pengyu Zhang, Rong Wen, Biao Lyu, Shunmin Zhu, Xinbing Wang. 720-735 [doi]
• Hey Hey, My My, Skewness Is Here to Stay: Challenges and Opportunities in Cloud Block Store TrafficHaonan Wu, Erci Xu, Ligang Wang, Yuandong Hong, Changsheng Niu, Bo Shi, Lingjun Zhu, Jinnian He, Dong Wu, Weidong Zhang, Qiuping Wang, Changhong Wang, Xinqi Chen, Guangtao Xue, Yi-Chao Chen 0001, Dian Ding. 736-752 [doi]
• Optimizing Task Scheduling in Cloud VMs with Accurate vCPU AbstractionEdward Guo, Weiwei Jia 0001, Xiaoning Ding, Jianchen Shan. 753-768 [doi]
• JABAS: Joint Adaptive Batching and Automatic Scaling for DNN Training on Heterogeneous GPUsGyeongchan Yun, Junesoo Kang, HyunJoon Jeong, Sanghyeon Eom, Minsung Jang, Young-ri Choi. 769-786 [doi]
• SpaceFusion: Advanced Deep Learning Operator Fusion via Space-Mapping GraphLiang Zhu, Jianguo Yao, Haibing Guan. 787-802 [doi]
• Groot: Graph-Centric Row Reordering with Tree for Sparse Matrix Multiplications on Tensor CoresYuang Chen, Jiadong Xie 0002, Siyi Teng, Wenqi Zeng, Jeffrey Xu Yu. 803-817 [doi]
• SuperFE: A Scalable and Flexible Feature Extractor for ML-based Traffic Analysis ApplicationsMenghao Zhang 0001, Guanyu Li, Cheng Guo, Renyu Yang, Shicheng Wang, Han Bao 0011, Xiao Li, Mingwei Xu, Tianyu Wo, Chunming Hu. 818-834 [doi]
• Chrono: Meticulous Hotness Measurement and Flexible Page Migration for Memory TieringZhenlin Qi, Shengan Zheng, Ying Huang, Yifeng Hui, Bowen Zhang 0012, Linpeng Huang, Hong Mei 0001. 835-853 [doi]
• PET: Proactive Demotion for Efficient Tiered Memory ManagementWanju Doh, Yaebin Moon, Seoyoung Ko, Seunghwan Chung, Kwanhee Kyung, Eojin Lee, Jung Ho Ahn. 854-869 [doi]
• Adios to Busy-Waiting for Microsecond-scale Memory DisaggregationWonsup Yoon, Jisu Ok, Sue Moon, Youngjin Kwon. 870-885 [doi]
• Deft: A Scalable Tree Index for Disaggregated MemoryJing Wang, Qing Wang 0031, Yuhao Zhang 0006, Jiwu Shu. 886-901 [doi]
• SeBS-Flow: Benchmarking Serverless Cloud Function WorkflowsLarissa Schmid, Marcin Copik, Alexandru Calotoiu, Laurin Brandner, Anne Koziolek, Torsten Hoefler. 902-920 [doi]
• AlloyStack: A Library Operating System for Serverless Workflow ApplicationsJianing You, Kang Chen, Laiping Zhao, Yiming Li, Yichi Chen, Yuxuan Du, Yanjie Wang, Luhang Wen, Keyang Hu, Keqiu Li. 921-937 [doi]
• Serverless Cold Starts and Where to Find ThemArtjom Joosen, Ahmed Hassan, Martin Asenov, Rajkarn Singh, Luke Nicholas Darlow, Jianfeng Wang, Qiwen Deng, Adam Barker. 938-953 [doi]
• TUNA: Tuning Unstable and Noisy Cloud ApplicationsJohannes Freischuetz, Konstantinos Kanellis, Brian Kroth, Shivaram Venkataraman. 954-973 [doi]
• Solid State Drive Targeted Memory-Efficient Indexing for Universal I/O Patterns and Fragmentation DegreesJunsu Im, Jeonggyun Kim, Seonggyun Oh, Jinhyung Koo, Juhyung Park, Hoon Sung Chwa, Sam H. Noh, Sungjin Lee 0001. 974-990 [doi]
• Daredevil: Rescue Your Flash Storage from Inflexible Kernel Storage StackJunzhe Li, Ran Shu 0001, Jiayi Lin 0007, Qingyu Zhang, Ziyue Yang, Jie Zhang 0048, Yongqiang Xiong, Chenxiong Qian. 991-1008 [doi]
• Overcoming the Last Mile between Log-Structured File Systems and Persistent Memory via Scatter LoggingYifeng Zhang, Yanqi Pan, Hao Huang, Yuchen Shan, Wen Xia. 1009-1025 [doi]
• Garbage Collection Does Not Only Collect Garbage: Piggybacking-Style Defragmentation for Deduplicated Backup StorageDingbang Liu, Xiangyu Zou, Tao Lu, Philip Shilane, Wen Xia, Wenxuan Huang, Yanqi Pan, Hao Huang. 1026-1043 [doi]
• Understanding the Linux Kernel, VisuallyHanzhi Liu, Yanyan Jiang 0001, Chang Xu 0001. 1044-1060 [doi]
• Understanding and Detecting SQL Function Bugs: Using Simple Boundary Arguments to Trigger Hundreds of DBMS BugsJingzhou Fu, Jie Liang 0006, Zhiyong Wu 0010, Yanyang Zhao, Shanshan Li, Yu Jiang 0001. 1061-1076 [doi]
• BESA: Extending Bugs Triggered by Runtime Testing via Static AnalysisJia-Ju Bai. 1077-1091 [doi]
• HawkSet: Automatic, Application-Agnostic, and Efficient Concurrent PM Bug DetectionJoão Oliveira, João Gonçalves, Miguel Matos. 1092-1108 [doi]
• Heimdall: Optimizing Storage I/O Admission with Extensive Machine Learning PipelineDaniar Heri Kurniawan, Rani Ayu Putri, Peiran Qin, Kahfi S. Zulkifli, Ray A. O. Sinurat, Janki Bhimani, Sandeep Madireddy, Achmad Imam Kistijantoro, Haryadi S. Gunawi. 1109-1125 [doi]
• Cheetah: Metadata Aggregation for Fast Object Storage without Distributed OrderingYiming Zhang, Li Wang, Shengyun Liu, Shun Gai, Haonan Wang, Xin Yao, Meiling Wang, Kai Chen, Dongsheng Li, Jiwu Shu. 1126-1141 [doi]
• Towards Efficient Flash Caches with Emerging NVMe Flexible Data Placement SSDsMichael Allison, Arun George, Javier González 0006, Dan Helmick, Vikash Kumar, Roshan R. Nair, Vivek Shah 0001. 1142-1160 [doi]
• Pre-Stores: Proactive Software-guided Movement of Data Down the Memory HierarchyXiaoxiang Wu, Baptiste Lepers, Willy Zwaenepoel. 1161-1176 [doi]
• Rakis: Secure Fast I/O Primitives Across Trust Boundaries on Intel SGXMansour Alharthi, Fan Sang, Dmitrii Kuvaiskii, Mona Vij, Taesoo Kim. 1177-1193 [doi]
• DPack: Efficiency-Oriented Privacy Budget SchedulingPierre Tholoniat, Kelly Kostopoulou, Mosharaf Chowdhury, Asaf Cidon, Roxana Geambasu, Mathias Lécuyer, Junfeng Yang. 1194-1209 [doi]
• Erebor: A Drop-In Sandbox Solution for Private Data Processing in Untrusted Confidential Virtual MachinesChuqi Zhang, Rahul Priolkar, Yuancheng Jiang, Yuan Xiao, Mona Vij, Zhenkai Liang, Adil Ahmad. 1210-1228 [doi]
• A Hardware-Software Co-Design for Efficient Secure ContainersJiacheng Shi, Yang Yu, Jinyu Gu 0001, Yubin Xia. 1229-1245 [doi]
• Seal: Towards Diverse Specification Inference for Linux Interfaces from Security PatchesWei Chen, Bowen Zhang, Chengpeng Wang, Wensheng Tang, Charles Zhang 0001. 1246-1262 [doi]
• MEPipe: Democratizing LLM Training with Memory-Efficient Slice-Level Pipeline Scheduling on Cost-Effective AcceleratorsZhenbo Sun, Shengqi Chen 0001, Yuanwei Wang, Jian Sha, Guanyu Feng, Wenguang Chen. 1263-1278 [doi]
• HybridFlow: A Flexible and Efficient RLHF FrameworkGuangming Sheng, Chi Zhang, Zilingfeng Ye, Xibin Wu, Wang Zhang, Ru Zhang, Yanghua Peng, Haibin Lin, Chuan Wu 0001. 1279-1297 [doi]
• Mist: Efficient Distributed Training of Large Language Models via Memory-Parallelism Co-OptimizationZhanda Zhu, Christina Giannoula, Muralidhar Andoorveedu, Qidong Su, Karttikeya Mangalam, Bojian Zheng, Gennady Pekhimenko. 1298-1316 [doi]
• Hourglass: Enabling Efficient Split Federated Learning with Data ParallelismQiang He 0001, Kaibin Wang, Zeqian Dong, Liang Yuan, Feifei Chen 0001, Hai Jin 0001, Yun Yang 0001. 1317-1333 [doi]
• FlowCheck: Decoupling Checkpointing and Training of Large-Scale ModelsZimeng Huang, Hao Nie, Haonan Jia, Bo Jiang 0003, Junchen Guo, Jianyuan Lu, Rong Wen, Biao Lyu, Shunmin Zhu, Xinbing Wang. 1334-1349 [doi]
• Atlas: Towards Real-Time Verification in Large-Scale Networks via a Native Distributed ArchitectureMingxiao Ma, Yuehan Zhang, Jingyu Wang, Bo He 0003, Chenyang Zhao, Qi Qi 0001, Zirui Zhuang, Haifeng Sun 0001, Lingqi Guo, Yuebin Guo, Gong Zhang, Jianxin Liao. 1350-1364 [doi]
• Occamy: A Preemptive Buffer Management for On-chip Shared-memory SwitchesDanfeng Shan, Yunguang Li, Jinchao Ma, Zhenxing Zhang, Zeyu Liang, Xinyu Wen, Hao Li 0011, Wanchun Jiang, Nan Li, Fengyuan Ren. 1365-1382 [doi]
• Phantom: Virtualizing Switch Register Resources for Accurate Sketch-based Network MeasurementXiang Chen 0017, Hongyan Liu 0001, Zhengyan Zhou, Xi Sun, Wenbin Zhang 0002, Hongyang Du, Dong Zhang 0010, Xuan Liu 0006, Haifeng Zhou, Dusit Niyato, Qun Huang 0001, Chunming Wu 0001, Kui Ren 0001. 1383-1398 [doi]
• Eva: Cost-Efficient Cloud-Based Cluster SchedulingTzu-Tao Chang, Shivaram Venkataraman. 1399-1416 [doi]
• Byte vSwitch: A High-Performance Virtual Switch for Cloud NetworkingXin Wang, Deguo Li, Zhihong Wang, Lidong Jiang, Shubo Wen, Daxiang Kang, Engin Arslan, Peng He, Xinyu Qian, Bin Niu, Jianwen Pi, Xiaoning Ding, Ke Lin, Hao Luo. 1417-1432 [doi]