Orca - Server-assisted Multicast for Datacenter Networks
Innovative multicast architecture for datacenter networks, reducing switch state and communication overhead while improving scalability and efficiency for large-scale group communications.
Saiyan - Design and Implementation of a Low-power Demodulator for LoRa Backscatter Systems
Ultra-low-power demodulator for long-range LoRa backscatter systems, enabling feedback demodulation, packet retransmission, rate adaptation, and channel hopping with improved range and efficiency.
PowerTCP - Pushing the Performance Limits of Datacenter Networks
Explore PowerTCP, a novel congestion control algorithm for datacenter networks that adapts to bandwidth-window product, offering faster reaction times and improved performance in dynamic environments.
FlexTOE - Flexible TCP Offload with Fine-Grained Parallelism
Explore FlexTOE, a high-performance TCP offload engine for SmartNICs. Learn about its flexible design, fine-grained parallelism, and performance benefits in various network scenarios and hardware architectures.
Configanator - A Data-driven Approach to Improving CDN Performance
Explore a data-driven approach to optimize CDN performance by dynamically configuring web server parameters based on network and device characteristics, improving tail web performance by 32-67%.
Packet Order Matters! Improving Application Performance by Deliberately Delaying Packets
Explores improving application performance by deliberately delaying and reordering network packets to increase traffic locality, enhancing cache efficiency in high-speed network interfaces.
An Edge-Queued Datagram Service for All Datacenter Traffic
Edge-queued datagram service for datacenters moves queuing to sending hosts, enabling multiple protocols to coexist, improving performance, and facilitating future enhancements without modifying higher-layer stacks.
Aquila - A Unified, Low-Latency Fabric for Datacenter Networks
Introducing Aquila: A revolutionary datacenter network fabric designed for ultra-low latency communication, supporting resource disaggregation and emerging programming models while maintaining compatibility with traditional traffic.
Tiara - A Scalable and Efficient Hardware Acceleration Architecture for Stateful Layer-4 Load Balancing
Scalable hardware acceleration architecture for stateful layer-4 load balancing, supporting high traffic rates, large concurrent flows, and numerous new connections without traffic pattern assumptions.
Closed-Loop Network Performance Monitoring and Diagnosis with SpiderMon
Innovative closed-loop network monitoring system using programmable switches for efficient performance diagnosis in data centers, leveraging "wait-for" relations to balance coverage and overhead.
SwarmMap - Scaling Up Real-time Collaborative Visual SLAM at the Edge
Scaling up real-time collaborative visual SLAM for edge-based multi-agent systems, addressing data explosion and improving performance with innovative modules for synchronization, scheduling, and map representation.
CISP - A Speed-of-Light Internet Service Provider
Explore the design of ultra-low latency wide-area networks using free-space microwave wireless connectivity, addressing practical challenges and demonstrating economic viability.
Scaling Open vSwitch with a Computational Cache
Innovative approach to scale Open vSwitch using NuevoMatch algorithm, improving packet classification performance and rule update speed for enhanced network virtualization efficiency.
Backdraft - A Lossless Virtual Switch that Prevents the Slow Receiver Problem
Innovative virtual switch solution preventing packet loss and improving network performance through dynamic queuing, doorbell queues, and overlay network techniques for enhanced application responsiveness.
Passive DSSS - Empowering the Downlink Communication for Backscatter Systems
Innovative technique to enhance downlink communication in backscatter systems using passive DSSS, improving SINR by 16.5 dB and extending effective range while maintaining ultra-low power consumption.
Backpressure Flow Control
Explores Backpressure Flow Control, a novel congestion control architecture for data center networks, offering improved throughput and latency compared to end-to-end schemes.
The Pandemic and The Classroom - Enabling Education for Millions
Explore how Microsoft Teams adapted to enable remote education for millions during COVID-19, discussing challenges, solutions, and engineering strategies for large-scale online learning.
A Fresh Look at Operational Debt
Explore a new model of operational debt in SRE, focusing on process gaps and risk. Learn to prioritize and address issues for improved service reliability and team collaboration.
DeepSketch - A New Machine Learning-Based Reference Search Technique for Post-Deduplication Delta Compression
Explores DeepSketch, a machine learning-based technique for post-deduplication delta compression in storage systems, improving data reduction efficiency through enhanced reference search accuracy.
Operational Characteristics of SSDs in Enterprise Storage Systems - A Large-Scale Field Study
Comprehensive field study analyzing operational characteristics of SSDs in enterprise storage systems, covering performance, lifespan, write amplification, and NAND usage rates across nearly 2 million drives.
Removing Double-Logging with Passive Data Persistence in LSM-tree Based Relational Databases
Explores a novel solution to remove double-logging in LSM-tree based relational databases, improving performance and efficiency while maintaining data reliability and fast recovery.