Processing-In-Memory of Data Filter On Compressed Data

  • Tiago R. Kepe UFPR / IFPR
  • Francis B. Moreira UFPR
  • Marco A. Z. Alves UFPR


The data filter is essential in data-centric applications, but it requires moving large data sets to the processing units. One approach to tackle such a hassle is data compression by using lightweight compression methods such as dictionary encoding. In this paper, we exploit the idea of Processing-In-Memory (PIM) data filters directly over compressed data. The initial experiments show noticeable speed-ups of over 2x against the AVX512 architecture.


Abadi, D. J., Madden, S., and Ferreira, M. (2006). Integrating compression and execution in column-oriented database systems. SIGMOD, pages 671–682.

Cordeiro, A. S. and et al. (2021). Machine learning migration for efficient near-data processing. In Euromicro International Conference on Parallel, Distributed and Network-Based Processing, pages 212–219.

Feng, Z., Lo, E., Kao, B., and Xu, W. (2015). Byteslice: Pushing the envelop of main memory data processing with a new storage layout. SIGMOD, pages 31–46.

Li, Y. and Patel, J. M. (2013). Bitweaving: fast scans for main memory data processing. SIGMOD, pages 289–300.
Como Citar

Selecione um Formato
KEPE, Tiago R.; MOREIRA, Francis B.; ALVES, Marco A. Z.. Processing-In-Memory of Data Filter On Compressed Data. In: ESCOLA REGIONAL DE ALTO DESEMPENHO DA REGIÃO SUL (ERAD-RS), 22. , 2022, Curitiba. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2022 . p. 101-102. ISSN 2595-4164. DOI: