Conferences · eligible papers
OSDI
2022–2026 LIVE
Operating & Distributed Systems
2026 · 136 papers
このEditionに反映済みのmain full research papersのみ掲載しています。著者リンクは日本の大学への著者別所属根拠がある場合に限ります。
- A Compilation-Based Under-Constrained Execution Engine
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- ADAngel: Accelerating Arbitrary-Precision Quantized LLMs with Adaptive Computing Mapping
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Accelerating Confidential Databases with Crypto-Free Mappings
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Achieving Cloud-Grade SLOs for Local Mixture-of-Experts Inference through CPU–GPU Hybrid Design
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Acumen: A Platform for Encrypted and Accountable Collaborative Editing
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Aletheia: Automated Detection of Data Integrity Violations in Microservices
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- All Along the Watchtower: Achieving the Trinity of Observability in Cloud with DiTing
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Ambulance: Saving BFT through Racing
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Arctic: A Practical Lock-Free Adaptive Radix Tree
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- BatchGen: An Architecture for Scalable and Efficient Batch Inference
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Blowfish: Elastic Virtual Machine Memory for Disaggregated Memory
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Bodega: Localized Linearizable Reads at Anywhere Anytime via Roster Leases
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Break On Through to the Other Side: Pooling Memory Elastically with RamRyder
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- CoPilotIO: CPU as a Co-Pilot for GPU I/O to Free GPU Compute
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Cocoon: A System Architecture for Differentially Private Training with Correlated Noises
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Compaction-Free Memory Defragmentation for Virtualization via Infinite Guest Physical Address Space
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Continuation-Centric Computing with Arca
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Controlling Opaque-Component Effects with Semisolates and Try
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- DPA-Store: An Ordered Network Data Path Key-Value Store
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- DVLA: Dynamic VM Lifetime Aware Scheduling for Drifting Lifetime Distributions and Long-Lived VM Placement Debt (Operational Systems)
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- DeLFS: A Decentralized Log-Structured File System for Manycores
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Diagnosing Performance Issues in Application-Defined Resources
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Disentangling Graph Dependencies for Efficient Billion-Scale GPU Vector Search
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Distributed Speculative Execution for Resilient Cloud Applications
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Drs.NAS: Ultra-Efficient Neural Architecture Search for Recommendation Systems
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Duhu: Shared Disaggregated Memory for Distributed Data Processing Frameworks
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- DynaRL: Flexible and Dynamic Scheduling of Large-Scale Reinforcement Learning Training
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- ECHO: Efficient KV Cache Offloading with Lossless Prefetching for Serving Native Sparse Attention LLMs
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- ECO: An AI-Driven Code Efficiency Optimizer for Warehouse Scale Computers (Operational Systems)
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Efficient GPU-Centric Evolving Graph Processing at Scale
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Efficient LLM Serving on Commodity GPU Clusters with Data-Reduced Cross-Instance Orchestration
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Efficient and Scalable Synchronization via Generalized Cache Coherence
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Equal Opportunity: A Correctness Condition for Ordered Consensus
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Espresso: Constructing Cost-Efficient CXL JBOF via Inter-SSD Computing Resource Sharing
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Extracting Database Access-Control Policies from Web Applications
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- FARLock: Asymmetric RDMA Locking Made Fair
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- FORGE: Mitigating Synchronization Amplification for Memory-Disaggregated Caching Systems
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Finding NEMO: Nimble and Expressive Memory Observability
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- GraCE: Unlocking CUDA Graphs with Compiler Support for ML Workloads
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Hardware Lifecycle-Aware Power Planning in Commercial Hyperscale Datacenters (Operational Systems)
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Harvesting Sub-Microsecond CXL Memory Stalls with LiteSwitch
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Heterogeneity at Hyperscale: Characterization and Scheduling of Large Production AI Clusters at Alibaba (Operational Systems)
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Hetu v2: A General and Scalable Deep Learning System with Hierarchical and Heterogeneous Single Program Multiple Data Annotations
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- High Fidelity Models for Large Scale Stateful Services (Operational Systems)
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Ichnaea: A Framework for Precise Tracking of Memory Objects
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Incr: Faster Re-Execution via Bolt-On Incrementalization
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Inference in the Shadows: Taming Memory Bandwidth Contention in Mobile LLM Inference with Sereno
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Inside Out: A Paradigm Shift in VM Introspection
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- JANUS: Cross-World, Cooperative Nested Virtualization for Secure Containers
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Jetpack: Consensus Made Generally Fast
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Kairox: Adaptive GPU-CPU Hybrid LLM Inference via Online Neuron Balancing
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Kareus: Joint Reduction of Dynamic and Static Energy in Large Model Training
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Learning-Augmented Heuristics: Simple Yet Smart, Robust and Interpretable Cache Eviction
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- LifeLine: An Object-Page Lifetime Alignment GC Enabling Minimal Memory Copying for Mobile Devices
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- M3U: Scalable Kernel Memory Management for Efficient Post-Copy Live Migration of High-End Virtual Machines
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- MAC: Metadata Acceleration for Sustainable Performance in Big-Data Systems with CXL DRAM
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- MDK: Rethinking the Data Center Memory Reclamation Problem
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- MEGALON: Efficient Data Sharing for Partly Coherent CXL Memory
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- MPK: A Compiler and Runtime for Mega-Kernelizing Tensor Programs
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Merlin: An Efficient Adaptive Cache Eviction Algorithm via Fine-Grained Characterization
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Mimesys: Generating Realistic Executable Testing Environments from Resource Usage Traces
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Mohabi: Disaggregating and Sandboxing the Firefox JavaScript Engine
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- MoonBright: A GPU Memory Allocator with Device-Side Page Table Materialization and Deferred TLB Coherence
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Murakkab: Resource-Efficient Agentic Workflow Orchestration in Cloud Platforms
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Nested SEV: Secure and Generic SEV Support for Nested Virtualization
Operating & Distributed Systems
日本大学: 九州工業大学
- Neuro-Symbolic Proof Generation for Scaling Systems Software Verification
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Nixie: Efficient, Transparent Temporal Multiplexing for Consumer GPUs
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- No Buffer, No Bottleneck: Efficient Zero-Copy KV Cache Offloading for Long-Context LLMs
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- OBASE: Object-Based Address-Space Engineering to Improve Memory Tiering
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- OpGuard: Bitwise Alignment for Precise and General Debugging of Production LLM Training
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- OpenTela: Unifying Decentralized Computing Resources for Heterogeneous LLM Serving (Operational Systems)
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Optimal Software Pipelining and Warp Specialization for Tensor Core GPUs
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Osprey: Transparent and Efficient Virtual Memory for Secure Computation
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Oxbow: A Coordinated Architecture for Multi-Component File Systems
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- PIMS: Fleet-Wide Datacenter Maintenance with Minimal Capacity Buffer and Predictable Latency (Operational Systems)
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- PeeR: First-Class Scheduling for Latency-Critical eBPF Applications
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Pluto: High-Performance, Memory-Efficient Distributed Graph Analytics through Advanced Mirroring
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Prism: Cost-Efficient Multi-LLM Serving via GPU Memory Ballooning
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Quota Marketplace: Dynamic Pricing for Efficient Allocation of ML Training Resources
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- RLinf: Flexible and Efficient Large-Scale Reinforcement Learning via Macro-to-Micro Flow Transformation
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- RT: Regular Types for the Streaming Shell
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Rakaia: Scalable In-Kernel Scheduling for TCP-Based RPCs
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Rethinking Process Snapshots for Near-Warm Serverless Cold Starts
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Revisiting Pipeline Parallelism for LLM Serving
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- RoCE BALBOA: Service-Enhanced RDMA Offload Engine for Data Center SmartNICs
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- RobustRL: Role-Based Fault Tolerance System for RL Post-Training
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- RollArt: Disaggregated Multi-Task Agentic RL Training at Scale
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- SBB: Eliminating Centralized Bottlenecks in Userspace Network Runtime
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- SDCs in the Wild: Characterizing and Diagnosing SDC-Defective GPUs in Production LLM Training (Operational Systems)
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- SMARTTalk: Teaching SMART Logs to Talk to LLMs
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- SPADE: Signal-Aware DAG Scheduling and Dynamic Provisioning for Data Processing Clusters
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Safeguarding LLM Training at Scale: Online SDC Detection and Insights from 35 Million GPU Hours
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Scaling the IO Wall with Declarative IO
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Seer: Online Context Learning for Fast Synchronous LLM Reinforcement Learning
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Shaving the Peaks: Taming Tail Latency for Managed Workloads via Disaggregated Garbage Collection
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Simple Is Better: Multiplication May Be All You Need for LLM Request Scheduling
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Spain: Succinct Proofs for Numerical Computations
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Stop Pretending to Be Busy: A Case for Serverless Paradigms in Co-Located Batch Workloads (Operational Systems)
Operating & Distributed Systems
日本大学: 関与なし（対象大学）
- Strata: Hierarchical Context Caching for Long Context Language Model Serving
Operating & Distributed Systems
日本大学: 関与なし（対象大学）