
Innovative approach to optimize storage device performance by allowing software to specify latency-sensitive requests, enabling devices to calibrate interrupts and balance latency and throughput effectively.

Innovative tool for lossless log compression with fast search capabilities, outperforming existing solutions in compression ratio, search speed, and ingestion performance for petabyte-scale log management.

STORM: A web framework for building MVC applications with compile-time enforcement of security policies, reducing trusted code to under 1% and providing static security enforcement with minimal overhead.

Explores RESIN optimizer extension for SQL queries, introducing Generalized Sub-Query Fusion to eliminate redundant I/O and improve performance in big-data analytics, with significant speedups demonstrated on TPCDS benchmark.

Innovative tensor compiler approach for efficient ML model scoring, simplifying infrastructure and leveraging neural network compilers for CPU and GPU acceleration.

Explores virtualizing consensus in replicated systems, enabling dynamic protocol changes without downtime. Introduces VirtualLog and Loglets for simplified, diverse, and composable consensus implementations, showcasing benefits in the Delos database.

Optimizing DNN computation on hardware accelerators through novel abstractions and holistic scheduling, achieving significant performance improvements over existing compilers and libraries.

Innovative approach to detect logic bugs in database systems using Pivoted Query Synthesis, demonstrating high effectiveness in finding and fixing issues in major DBMSs.

Explores a novel distributed file system leveraging persistent memory modules for enhanced IO performance, rapid failover, and strong consistency, outperforming traditional remote storage models.

Explores techniques for detecting bugs in P4 compilers, presenting Gauntlet tool that found 96 new bugs across platforms, leading to fixes and P4 specification changes.