Elasticity of compute and storage is crucial for analytical cloud database systems. All cloud
vendors provide disaggregated object stores, which can be used as storage backend for …

Today's clouds are inefficient: their utilization of resources like CPUs, GPUs, memory, and
storage is low. This inefficiency occurs because applications consume resources at variable …

Data-intensive systems are the backbone of today's computing and are responsible for
sha** data centers. Over the years, cloud providers have relied on three principles to …

This thesis addresses the optimal strategies for elevating Azure data warehouses,
emphasizing adopting practical solutions to enhance data storage and management …

The shift to cloud database systems, driven by independent scaling of compute and storage,
demands architectural changes. This thesis presents new concepts to improve query …

We present User-Defined Operators as a concept to include custom algorithms in modern
query engines. Users can write idiomatic code in the programming language of their choice …

This thesis introduces three ways to adapt relational database systems to advancements in
modern storage technology. First, we propose Mosaic, a storage engine optimized for …

This thesis develops a comprehensive architectural blueprint for a high-performance flash-
based HTAP database system. In particular, we devise novel approaches for low-overhead …

摘要随着云计算和大数据的发展, 传统的本地数据仓库面临着扩容困难, 数据处理效率低下的
问题, 由此云边架构的数据仓库应运而生. 该架构的数据仓库分布在云中心和边缘端 …

Efficient data processing is one of the core techniques that enables modern data driven
computer systems. Database systems are uniquely positioned to use increasing hardware …