Logo des Repositoriums
 

Speculative Dynamic Reconfiguration and Table Prefetching Using Query Look-Ahead in the ReProVide Near-Data-Processing System

dc.contributor.authorBeena Gopalakrishnan, Lekshmi
dc.contributor.authorBecher, Andreas
dc.contributor.authorWildermann, Stefan
dc.contributor.authorMeyer-Wegener, Klaus
dc.contributor.authorTeich, Jürgen
dc.date.accessioned2021-05-04T09:39:20Z
dc.date.available2021-05-04T09:39:20Z
dc.date.issued2021
dc.description.abstractFPGAs are promising target architectures for hardware acceleration of database query processing, as they combine the performance of hardware with the programmability of software. In particular, they are partially reconfigurable at runtime, which allows for the runtime adaptation to a variety of queries. However, reconfiguration costs some time, and a region of the FPGA is not available for computations during its reconfiguration. Techniques to avoid or at least hide the reconfiguration latencies can improve the overall performance. This paper presents optimizations based on query look-ahead, which follows the idea of exploiting knowledge about subsequent queries for scheduling the reconfigurations such that their overhead is minimized. We evaluate our optimizations with a calibrated model for various parameter settings. Improvements in execution time can be “calculated” even if only being able to look one query ahead.de
dc.identifier.doi10.1007/s13222-020-00363-7
dc.identifier.pissn1610-1995
dc.identifier.urihttp://dx.doi.org/10.1007/s13222-020-00363-7
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/36414
dc.publisherSpringer
dc.relation.ispartofDatenbank-Spektrum: Vol. 21, No. 1
dc.relation.ispartofseriesDatenbank-Spektrum
dc.subjectFPGAs
dc.subjectHardware acceleration
dc.subjectQuery optimization
dc.subjectReconfiguration
dc.titleSpeculative Dynamic Reconfiguration and Table Prefetching Using Query Look-Ahead in the ReProVide Near-Data-Processing Systemde
dc.typeText/Journal Article
gi.citation.endPage64
gi.citation.startPage55

Dateien