USENIX Courses

Avocado - A Secure In-Memory Distributed Storage System

Explore Avocado, a secure in-memory distributed storage system for untrusted cloud environments, offering strong security, fault-tolerance, consistency, and performance through innovative design and implementation.

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

INFaaS - Automated Model-less Inference Serving

Automated system for distributed inference serving, optimizing model selection and resource allocation to meet performance and accuracy requirements while reducing costs and complexity for developers.

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

DART - A Scalable and Adaptive Edge Stream Processing Engine

Scalable, adaptive edge stream processing engine for IoT applications, enabling fast processing of concurrent queries in dynamic environments through dynamic dataflow abstraction and P2P overlay networks.

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

Addra - Metadata-Private Voice Communication Over Fully Untrusted Infrastructure

Innovative system for metadata-private voice communication, scaling to 32K users with low latency. Utilizes untrusted infrastructure and novel mailbox assignment, improving on existing solutions for secure communication.

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

Beyond Malloc Efficiency to Fleet Efficiency - A Hugepage-Aware Memory Allocator

Explore TEMERAIRE, a hugepage-aware memory allocator enhancing TCMALLOC to reduce CPU overheads, improve application performance, and optimize fleet efficiency in warehouse-scale computing.

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

Oort - Efficient Federated Learning via Guided Participant Selection

Efficient federated learning system that improves model training and testing by intelligently selecting participants based on data utility and device capabilities, enhancing accuracy and performance.

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

PET - Optimizing Tensor Programs with Partially Equivalent Transformations and Automated Corrections

Optimizing tensor programs with partially equivalent transformations, improving DNN efficiency by up to 2.5×. Introduces PET framework for automated corrections and theoretical foundations for equivalence examination.

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

Rearchitecting Linux Storage Stack for µs Latency and High Throughput

Explore a novel Linux kernel storage stack architecture achieving microsecond-scale latency and high throughput, adapting network switch techniques for improved performance without application modifications.

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

Scalable Memory Protection in the PENGLAI Enclave

Innovative hardware-software design for scalable, dynamic secure memory in enclaves, featuring Guarded Page Tables and Mountable Merkle Trees to enhance protection, performance, and resource utilization.

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

MAGE - Nearly Zero-Cost Virtual Memory for Secure Computation

MAGE: An execution engine for secure computation, enabling efficient processing of large-scale encrypted data by leveraging oblivious memory access patterns to optimize virtual memory management.

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

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