ALP: Adaptive Lossless Floating-Point Compression
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.