The ever-increasing growth of data demands reliable data-base system with high-throughput and low-latency. Main memory-based column store database systems are state-of-the-art on this perspective, whereby data (values) in relational tables are organized by columns rather than by rows. In such systems, a full column scan is a fundamental key operation and thus, the optimization of the key operation is very crucial. This leads to have compact storage layout based fast column scan techniques through intra-value parallelism. For this reason, we investigated on different well-known fast column scan techniques using SIMD (Single Instruction Multiple Data) vectorization as well as using Field Programmable Gate Arrays (FPGA). Moreover, we present selective results of our exhaustive evaluation. Based on this evaluation, we find out the best column scan technique as per implementation mechanism–FPGA and SIMD. Finally, we conclude this paper via mentioning some lessons learned for our ongoing research activities.
| Identifer | oai:union.ndltd.org:DRESDEN/oai:qucosa:de:qucosa:83950 |
| Date | 23 March 2023 |
| Creators | Nusrat, Jahan Lisa, Ungethüm, Annett, Habich, Dirk, Lehner, Wolfgang, Nguyen, Duy Anh Tuan, Kumar, Akash |
| Publisher | Springer |
| Source Sets | Hochschulschriftenserver (HSSS) der SLUB Dresden |
| Language | English |
| Detected Language | English |
| Type | info:eu-repo/semantics/acceptedVersion, doc-type:conferenceObject, info:eu-repo/semantics/conferenceObject, doc-type:Text |
| Rights | info:eu-repo/semantics/openAccess |
| Relation | 978-3-030-26635-6, 978-3-030-26636-3, 10.1007/978-3-030-26636-3_6 |
Page generated in 0.0019 seconds