Lukas Maas

I’m a software engineer and researcher specializing in high-performance data systems.

At Microsoft Research, I shipped resource allocation mechanisms for Azure SQL Database, helped build Garnet, an open-source key-value store, and investigated GPU-accelerated query processing. I’ve also worked in research and development at Harvard, TU Dresden, Oracle Labs, and IBM’s Almaden Research Center.

Publications

  1. CoddSpeed: Hardware Accelerated Query Processing in Microsoft Fabric
    SIGMOD 2026Best Industry Paper
  2. Garnet: A Next-Generation Cache-Store for Accelerating Applications and Services
    PVLDB 2025Best Research Paper · VLDB 2026
  3. Flexible Resource Allocation for Relational Database-as-a-Service
    PVLDB 2023
More publicationsFewer publications
  1. Scalable GPU Acceleration of Scalar Functions in Analytical Databases: Compilation, Benchmarking, and Optimization
    PVLDB 2026Honorable Mention · VLDB 2026
  2. Scaling GPU-Accelerated Databases beyond GPU Memory Size
    PVLDB 2025
  3. Designing Access Methods: The RUM Conjecture
    EDBT 2016
  4. BUZZARD: a NUMA-aware in-memory indexing system
    SIGMOD 2013