Proceedings of the 2016 International Conference on Management of Data 2016
DOI: 10.1145/2882903.2915224
|View full text |Cite
|
Sign up to set email alerts
|

GPL

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
21
0
1

Year Published

2017
2017
2019
2019

Publication Types

Select...
5
1

Relationship

1
5

Authors

Journals

citations
Cited by 63 publications
(22 citation statements)
references
References 37 publications
0
21
0
1
Order By: Relevance
“…The study found that column store layouts are uniquely suitable for GPUs due to its ability to 1) ensure more coalesced data access, 2) achieve better compression ratios and 3) minimize the amount of data that needs to be moved to the GPUs. Later studies [11,119] arrived at a similar conclusion and hence modern GPU database systems [4,9] have almost exclusively adopted column store layout.…”
Section: Data Storage and Data Accessmentioning
confidence: 92%
See 4 more Smart Citations
“…The study found that column store layouts are uniquely suitable for GPUs due to its ability to 1) ensure more coalesced data access, 2) achieve better compression ratios and 3) minimize the amount of data that needs to be moved to the GPUs. Later studies [11,119] arrived at a similar conclusion and hence modern GPU database systems [4,9] have almost exclusively adopted column store layout.…”
Section: Data Storage and Data Accessmentioning
confidence: 92%
“…Weaver [31] proposed a design where the final gather operation is not performed when the filter kernel is fused with other operator kernels. Later, GPL [4] adopted a similar pipelined design where the gather stage is skipped. Now, most early GPU filter implementations [9,44], made use of branching if statements while checking the filter criteria.…”
Section: Selection/filtermentioning
confidence: 99%
See 3 more Smart Citations