-
CSOPESY: A C++ OS Emulator for Teaching Multi-Core Scheduling and Demand Paging
Neil Patrick Del Gallego, Emerico Aguilar (De La Salle University)
-
Towards High-Performance eBPF-based OS Scheduling for Serverless Functions
Saman Akbari (TU Berlin); Manfred Hauswirth (Fraunhofer Institute for Open Communication Systems, TU Berlin)
-
FunPilot: Runtime Performance Diagnosis and Remediation for Serverless Applications with LLMs
Changyuan Lin (University of British Columbia); Yawen Wang (Google); Mohammad Shahrad (University of British Columbia)
-
SpongeFS: A Criticality-Aware File System for Dependency-Safe Space Reclamation
Shuyun Gui, Yifan Zhao, Mingkai Dong (Shanghai Jiao Tong University)
-
A Policy-Driven Runtime Layer for Agentic LLM Serving
Rui Zhang, Chaeeun Kim, Cheng-Wei Ching, Yi Zhong, Liting Hu (University of California, Santa Cruz)
-
Congestion-Aware Serving of LLM Applications
Mouheb Ben Nasr, Muhammad Bilal, Alessandro Cornacchia (KAUST); Boris Radovic (KAUST and University of Ljubljana); Marco Canini (KAUST)
-
MCSched: Memory-Controller-Aware Scheduling for Embodied LLM Workloads on NVIDIA Jetson
Teng Mei, Chengxuan Pei (The Chinese University of Hong Kong, Shenzhen); Marco Canini (KAUST); Yunming Xiao (The Chinese University of Hong Kong, Shenzhen)
-
SSR: Synchronous State Machine Replication with a Split Architecture
Yuke Ma (Max Planck Institute for Informatics); Paolo Costa (Microsoft Research); Yiting Xia (Max Planck Institute for Informatics)
-
BigBFT: Scaling BFT without Compromising Fault Tolerance via State Sharding
Guangda Sun, Jialin Li (National University of Singapore)
-
Ossim: OS-Driven Live Simulation for Cluster-Scale Full-Stack Evaluation
Yiliang Wan, Haifeng Sun, Yihan Yang (National University of Singapore); Jonas Kaufmann, Antoine Kaufmann (Max Planck Institute for Software Systems); Jialin Li (National University of Singapore)
-
Can Software-based Transport Perform Like RDMA?
Yonghwan Chung (Seoul National University); Yihan Dang (Xi'an Jiaotong University); Kyoungsoo Park (Seoul National University)
-
PDUMint: A Case for PDU-Aware, In-network Packet Layout Translation
Jongki Park, Junghan Yoon, SeungYeon Shin, Jonghyeon Park, KyoungSoo Park (Seoul National University)
-
NetLoom: Accelerating the Construction for Large-Scale Network Emulation on a Single Host
Minuo Jiang (Computer Network Information Center, CAS and University of Chinese Academy of Sciences); Xian Yu (Computer Network Information Center, CAS); Kaifei Peng (Computer Network Information Center, CAS and University of Chinese Academy of Sciences); Dongbiao He (Southeast University); Yanbiao Li (Computer Network Information Center, CAS and University of Chinese Academy of Sciences)
-
Tuning Optical Modulation at Floating-Point Bit Granularity for Approximate MPI Communication
Shoichi Hirasawa, Michihiro Koibuchi (National Institute of Informatics)
-
XTLS: Scalable TLS Offloading through Host-SmartNIC Stack Co-Design
Seongjong Bae, Junghan Yoon, KyoungSoo Park (Seoul National University)
-
BACKPAC: Breaking ARM’s Pointer Authentication Sidechannel Mitigation in Apple M2
Yongjun Han, Dae R. Jeong (Seoul National University)
-
Unlocking Software-defined GPU Fabric Scheduling in the LLM Era
Danyang Chen (The Chinese University of Hong Kong, Shenzhen); Yufeng Gu, Yibo Huang (University of Michigan); Chengxuan Pei, Peichun Hua (The Chinese University of Hong Kong, Shenzhen); Yang Zhou (UC Davis); Yunming Xiao (The Chinese University of Hong Kong, Shenzhen)
-
LiveResize: Runtime Dynamic GPU Reallocation for LLM Post-Training
Hanlin Du, Zhiyuan Yan, Yungang Bao, Sa Wang (Institute of Computing Technology, CAS)
-
FaultSense: Fault Localization in Large-Scale Mixture-of-Experts Model Serving Infrastructure
Harish S A, Vignesh S (Indian Institute of Technology Hyderabad); Ashwin Kurella, Rohan Gandhi (Microsoft Research, India); Praveen Tammana (Indian Institute of Technology Hyderabad)
