USENIX Courses

WingFuzz: Implementing Continuous Fuzzing for Database Management Systems

Continuous fuzzing technique for enterprise-level DBMSs, addressing challenges in SQL grammar, codebase evolution, and anomaly analysis. Discovered 236 bugs across 12 major DBMSs.

• YouTube
• 13 minutes
• On-Demand
• Free Video

Metis - Fast Automatic Distributed Training on Heterogeneous GPUs

Efficient distributed training system for heterogeneous GPUs. Optimizes parallelism plans, improves resource utilization, and achieves significant speed-ups for large deep learning models.

• YouTube
• 20 minutes
• On-Demand
• Free Video

FBMM: Making Memory Management Extensible With Filesystems

Innovative approach using filesystems for extensible memory management, enabling diverse memory configurations and policies with minimal code and competitive performance.

• YouTube
• 18 minutes
• On-Demand
• Free Video

ALPS: An Adaptive Learning, Priority OS Scheduler for Serverless Functions

Innovative OS scheduler for serverless functions, combining SRPT and proportional-share scheduling to optimize performance of short-lived tasks while preventing starvation of longer functions.

• YouTube
• 18 minutes
• On-Demand
• Free Video

Quant-LLM: Accelerating Large Language Model Serving via FP6-Centric Algorithm-System Co-Design

Innovative GPU kernel design enables efficient 6-bit quantization for large language models, significantly improving inference speed while maintaining quality across various applications.

• YouTube
• 19 minutes
• On-Demand
• Free Video

OSMOSIS - Enabling Multi-Tenancy in Datacenter SmartNICs

Explores OSMOSIS, a resource manager enabling multi-tenancy in SmartNICs. Demonstrates dynamic hardware resource multiplexing for on-path packet processing, supporting broader adoption in datacenters with low overhead.

• YouTube
• 17 minutes
• On-Demand
• Free Video

StreamBox - A Lightweight GPU Sandbox for Serverless Inference Workflow

Innovative GPU sandbox for serverless inference, reducing memory footprint and improving throughput. Enhances DNN inference serving with efficient memory management and intra-GPU communication.

• YouTube
• 15 minutes
• On-Demand
• Free Video

Taming Hot Bloat Under Virtualization with HUGESCOPE

Innovative solution for addressing hot bloat in virtualization, improving performance and memory efficiency. HugeScope offers lightweight, effective framework for page tracking, splitting, and coalescing on commodity hardware.

• YouTube
• 17 minutes
• On-Demand
• Free Video

UniMem - Redesigning Disaggregated Memory within a Unified Local-Remote Memory Hierarchy

Explores UniMem, a novel disaggregated memory system that optimizes remote memory access, local cache utilization, and page migration for improved performance in large-scale computing environments.

• YouTube
• 20 minutes
• On-Demand
• Free Video

A Difference World: High-performance, NVM-invariant, Software-only Intermittent Computation

Explores innovative approach to intermittent computation for energy harvesting devices, introducing Camel system for efficient state management and improved performance on Flash-based platforms.

• YouTube
• 17 minutes
• On-Demand
• Free Video

SlimArchive - A Lightweight Architecture for Ethereum Archive Nodes

Innovative approach to optimize Ethereum archive nodes, reducing storage by 98.1% and improving performance through compacted, flattened, and fine-grained historical state maintenance.

• YouTube
• 20 minutes
• On-Demand
• Free Video

HydraRPC - Efficient RPC System Using CXL-Attached HDM

Explores HydraRPC, utilizing CXL-attached HDM for efficient data transmission, eliminating network rounds and memory copying. Evaluates performance on real CXL hardware, showcasing potential for building efficient RPC systems.

• YouTube
• 18 minutes
• On-Demand
• Free Video

Starburst - A Cost-aware Scheduler for Hybrid Cloud

Innovative hybrid cloud scheduler maximizing cluster utilization, reducing cloud costs by 54-91% while minimizing job completion time impact through dynamic waiting time control and configurable resource management.

• YouTube
• 19 minutes
• On-Demand
• Free Video

Every Mapping Counts in Large Amounts - Folio Accounting

Innovative folio accounting technique for Linux enhances memory management, improving performance in fork and unmap operations. Demonstrates significant speedup in fork-intensive workloads like Redis.

• YouTube
• 12 minutes
• On-Demand
• Free Video

SuperBench - Improving Cloud AI Infrastructure Reliability with Proactive Validation

Proactive validation system enhancing cloud AI infrastructure reliability by mitigating hidden degradation, featuring comprehensive benchmarks and intelligent component evaluation for optimal performance.

• YouTube
• 18 minutes
• On-Demand
• Free Video