USENIX Courses

AIFM - High-Performance, Application-Integrated Far Memory

Explore AIFM, a high-performance system enabling efficient use of remote memory in datacenters. Learn about its API, runtime, and benefits for applications facing memory constraints.

• YouTube
• 20 minutes
• On-Demand
• Conference Talk

Ansor - Generating High-Performance Tensor Programs for Deep Learning

Ansor: A framework for generating high-performance tensor programs in deep learning, improving execution speed across various hardware platforms through innovative search strategies and optimization techniques.

• YouTube
• 20 minutes
• On-Demand
• Conference Talk

Tolerating Slowdowns in Replicated State Machines Using Copilots

Innovative consensus protocol for replicated state machines that maintains normal latency despite slowdown of any single replica, using pilot and copilot for redundancy and fast takeovers.

• YouTube
• 20 minutes
• On-Demand
• Conference Talk

LinnOS - Predictability on Unpredictable Flash Storage with a Light Neural Network

Explore LinnOS, an OS using neural networks to predict SSD performance, enhancing storage application efficiency and outperforming industrial mechanisms with minimal overhead.

• YouTube
• 20 minutes
• On-Demand
• Conference Talk

Performance-Optimal Read-Only Transactions

Explores performance-optimal read-only transactions in distributed storage systems, introducing PORT design with version clocks for improved consistency and efficiency in applications like Scylla-PORT and Eiger-PORT.

• YouTube
• 20 minutes
• On-Demand
• Conference Talk

Overload Control for µs-scale RPCs with Breakwater

Overload control scheme for microsecond-scale RPCs, using server-driven admission control with credits based on queueing delay. Employs demand speculation and piggybacking to optimize performance.

• YouTube
• 20 minutes
• On-Demand
• Conference Talk

Serving DNNs like Clockwork - Performance Predictability from the Bottom Up

Explore a novel approach to machine learning inference systems that achieves predictable end-to-end performance, supporting thousands of models while meeting strict latency targets and request-level SLOs.

• YouTube
• 20 minutes
• On-Demand
• Conference Talk

Efficiently Mitigating Transient Execution Attacks Using the Unmapped Speculation Contract

Explores efficient mitigation of transient execution attacks using the unmapped speculation contract, presenting Ward kernel design for improved performance without compromising security.

• YouTube
• 20 minutes
• On-Demand
• Conference Talk

Heterogeneity-Aware Cluster Scheduling Policies for Deep Learning Workloads

Explores heterogeneity-aware scheduling for deep learning workloads, introducing Gavel to optimize resource allocation in clusters with diverse accelerators, improving efficiency and performance.

• YouTube
• 20 minutes
• On-Demand
• Conference Talk

A Differentially Private Data Analytics API at Scale

LinkedIn's privacy system uses differential privacy to protect member data while providing audience engagement insights, enabling marketing analytics with user-level privacy guarantees and strict budget management.

• YouTube
• 21 minutes
• On-Demand
• Conference Talk

How to -In-Effectively Convey Privacy Choices with Icons and Link Text

Explore effective privacy communication through icons and text, examining research methods, findings, and lessons learned for clear, concise privacy choice conveyance.

• YouTube
• 20 minutes
• On-Demand
• Conference Talk

AFL++ - Combining Incremental Steps of Fuzzing Research

AFL++: A community-driven fuzzing tool combining state-of-the-art research, offering novel features like Custom Mutator API. Enhances fuzzing process, enables quick testing of new techniques, and evaluates effectiveness individually and in combination.

• YouTube
• 20 minutes
• On-Demand
• Conference Talk

Unearthing the TrustedCore - A Critical Review on Huawei’s Trusted Execution Environment

Unveils critical security flaws in Huawei's TrustedCore, exposing vulnerabilities in trusted execution environments and demonstrating weaknesses in hardware-backed cryptography on mobile devices.

• YouTube
• 22 minutes
• On-Demand
• Conference Talk

Confessions of a Systems Engineer - Learning from My 20+ Years of Failure

Insights from a seasoned systems engineer on designing and running large-scale online services, drawing from 20+ years of failures and lessons learned in the tech industry.

• YouTube
• 39 minutes
• On-Demand
• Conference Talk

Faasm - Lightweight Isolation for Efficient Stateful Serverless Computing

Lightweight isolation technique for serverless computing, enabling efficient stateful processing and memory sharing between functions, resulting in improved performance and reduced resource usage.

• YouTube
• 23 minutes
• On-Demand
• Conference Talk