Explore a 29-minute research talk that delves into ALP, an innovative approach to adaptive lossless floating-point compression. Learn how this new compression scheme significantly improves upon existing methods like Gorilla, Chimp, and PseudoDecimals in both speed and compression ratio. Discover how ALP leverages vectorized execution to enhance performance and creates compression opportunities through in-vector commonalities. Understand the two-stage compression algorithm that efficiently handles doubles originating from decimals using an enhanced PseudoDecimals version, while employing vectorized compression for front bits in other cases. The presentation, delivered at the Dutch Seminar on Data Systems Design by Leonardo Kuffó from CWI, addresses the challenges of handling floating-point data in data science applications and offers practical solutions for improved data compression in database systems.
ALP: Adaptive Lossless Floating-Point Compression
DSDSD - Dutch Seminar on Data Systems Design via YouTube
Overview
Syllabus
We hold bi-weekly talks on Fridays from PM to 5 PM CET for and by researchers and practitioners designing and implementing data systems. The objective is to establish a new forum for the Dutch Data Systems community to come together, foster collaborations between its members, and bring in high-quality international speakers. We would like to invite all researchers, especially also Ph.D. students, who are working on related topics to join the events. It is an excellent opportunity to receive feedback early on from researchers in your field.
Taught by
DSDSD - Dutch Seminar on Data Systems Design
Related Courses
-
C3: Compressing Correlated Columns - A Framework for Multi-Column Data Compression
-
Shredding Deeply Nested JSON for Efficient Analytics in DuckDB
-
LingoDB: An Open Compilation and Optimization Framework for Sustainable Data Processing
-
Decoupling Compute and Storage for Stream Processing Systems
-
Provenance Research in Data Management Systems at Microsoft
-
Leveraging Generative AI for Data Processing and Database Management
