USENIX Courses

The nanoPU - A Nanosecond Network Stack for Datacenters

Innovative NIC-CPU co-design accelerating datacenter applications with μs-scale RPCs. Features fast network-to-CPU path, hardware-supported transport and load balancing, achieving 69ns wire-to-wire response time and improved performance.

• YouTube
• 15 minutes
• Self-Paced
• Conference Talk

Privacy Budget Scheduling

Explores privacy budget scheduling in machine learning, introducing PrivateKube for managing differential privacy as a resource. Presents DPF algorithm for fair allocation of non-replenishable privacy budgets in ML workloads.

• YouTube
• 14 minutes
• Self-Paced
• Conference Talk

Pollux - Co-adaptive Cluster Scheduling for Goodput-Optimized Deep Learning

Innovative deep learning cluster scheduler optimizing resource allocation and job performance through adaptive co-optimization, resulting in reduced completion times and improved fairness among competing jobs.

• YouTube
• 14 minutes
• Self-Paced
• Conference Talk

Finding Consensus Bugs in Ethereum via Multi-transaction Differential Fuzzing

Explore multi-transaction differential fuzzing for detecting Ethereum consensus bugs, improving security and reliability in blockchain networks.

• YouTube
• 15 minutes
• Self-Paced
• Conference Talk

Distributed Deep Graph Learning at Scale

Explores a novel system for scaling Graph Neural Network training to large real-world graphs, introducing pipelined push-pull parallelism for faster and more efficient distributed processing.

• YouTube
• 14 minutes
• Self-Paced
• Conference Talk

ASAP - Fast Mobile Application Switch via Adaptive Prepaging

Innovative mobile OS technique reducing app switch time by up to 35.7% through adaptive prepaging, enhancing user experience and resource utilization on memory-constrained devices.

• YouTube
• 15 minutes
• Self-Paced
• Conference Talk

MigrOS - Transparent Live-Migration Support for Containerised RDMA Applications

Transparent live-migration architecture for containerized RDMA applications, enabling OS control over active connections without compromising performance or requiring application changes.

• YouTube
• 15 minutes
• Self-Paced
• Conference Talk

Proactive Energy-Aware Adaptive Video Streaming on Mobile Devices

Explore proactive energy-aware adaptation for mobile video streaming, improving battery life and user experience. Learn about implementation, performance tradeoffs, and QoE enhancements for power-hungry apps.

• YouTube
• 15 minutes
• Self-Paced
• Conference Talk

One-Sided RDMA-Conscious Extendible Hashing for Disaggregated Memory

Explore efficient indexing for disaggregated memory with RACE hashing, featuring lock-free remote concurrency control and optimized resizing for improved performance in distributed systems.

• YouTube
• 15 minutes
• Self-Paced
• Conference Talk

Dorylus - Affordable, Scalable, and Accurate GNN Training with Distributed CPU Servers and Serverless Threads

Distributed system for training Graph Neural Networks using serverless computing, offering affordable scalability for billion-edge graphs with improved performance-per-dollar compared to GPU servers.

• YouTube
• 15 minutes
• Self-Paced
• Conference Talk

GoJournal - A Verified, Concurrent, Crash-Safe Journaling System

Explore GoJournal, a verified concurrent journaling system for storage applications. Learn about its implementation, performance, and the challenges overcome in its development and verification process.

• YouTube
• 14 minutes
• Self-Paced
• Conference Talk

SANRAZOR - Reducing Redundant Sanitizer Checks in C-C++ Programs

Optimizing sanitizer performance in C/C++ programs by identifying and removing redundant checks, reducing runtime overhead while maintaining bug detection capabilities.

• YouTube
• 14 minutes
• Self-Paced
• Conference Talk

Prediction-Based Power Oversubscription in Cloud Platforms

Explore power oversubscription in cloud platforms using prediction-based techniques to optimize datacenter resources, increase efficiency, and minimize impact on critical workloads.

• YouTube
• 16 minutes
• Self-Paced
• Conference Talk

Zeph - Cryptographic Enforcement of End-to-End Data Privacy

Cryptographic system for enforcing user-defined privacy policies in real-time data analytics, ensuring compliance and protection against breaches while maintaining scalability and low latency.

• YouTube
• 15 minutes
• Self-Paced
• Conference Talk

Refurbish Your Training Data - Reusing Partially Augmented Samples for Faster Deep Neural Network Training

Innovative data refurbishing technique accelerates deep neural network training while maintaining model generalization by reusing partially augmented samples and optimizing CPU-GPU overlap.

• YouTube
• 15 minutes
• Self-Paced
• Conference Talk