collaborators

6 papers

cs.DB2026

Over the Memory Wall, Into the Instruction Wall: The New Bottleneck in GPU Data Processing

Sven Hepkema, Bowen Wu, Christos Kozyrakis +2

Datacenter GPUs have seen an order-of-magnitude increase in memory bandwidth with the adoption of newer generations of HBM. Meanwhile, GPU database systems are gaining traction, ma…

cs.DB2026

Oasis: Hiding the Cost of Querying Parquet Files in the Datapath

Jonas Dann, Luca Tagliavini, Gustavo Alonso

Cloud-native database systems disaggregate compute and storage resources to improve cost efficiency over traditional monolithic architectures through elasticity and resource poolin…

cs.DB2026

Eiger: An Efficient Library for GPU-based Data Analytics

Bowen Wu, Marko Kabić, Sven Hepkema +3

GPUs have become an increasingly attractive platform for accelerating analytical workloads due to their massive parallelism and high memory bandwidth. Recent studies show that in s…

cs.DB2026

To GPU or Not to GPU: Vector Search in Relational Engines

Vasilis Mageirakos, Joel André, Marko Kabić +3

Vector search (VS) is now available in most database engines. However, while vector search is a common feature in AI/ML/LLMs where the dominant computing platforms are GPUs, existi…

cs.DB2026

Should I Hide My Duck in the Lake?

Jonas Dann, Gustavo Alonso

Data lakes spend a significant fraction of query execution time on scanning data from remote, disaggregated storage. Decoding alone accounts for 46% of runtime when running TPC-H d…

cs.DB2025

Cracking Vector Search Indexes

Vasilis Mageirakos, Bowen Wu, Gustavo Alonso

Retrieval Augmented Generation (RAG) uses vector databases to expand the expertise of an LLM model without having to retrain it. The idea can be applied over data lakes, leading to…