Relational joins on graphics processors

392 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

LINQits: big data on little clients (2013, background): “, 27X speedup in [20], 3-8X speedup in [25]) on complex queries such as Joins; furthermore, these studies do not compare relative energy consumption, a first-class constraint in future systems.”
Horton Tables: Fast Hash Tables for In-Memory Data-Intensive Computing (2016, methodology): “In in-memory databases, there has been significant effort spent on optimizing hash tables due to their use in hash join algorithms on CPUs [5, 6, 9, 12, 60], coupled CPUGPU systems [28, 29, 38], and the Xeon Phi [37, 60].”
Dandelion: a compiler and runtime for heterogeneous systems (2013, neutral): “also implemented a join primitive [38, 37].”
Sort vs. Hash Revisited: Fast Join Implementation on Modern Multi-Core CPUs (2009, methodology): “To study the beneﬁt of partitioning for hash join algorithm, we join two tables of 128 million tuples with uniformly distributed keys [9, 18, 28].”
Relational query coprocessing on graphics processors (2009, methodology): “The counting step in the three-step (IRiI+ISiI) = · output scheme doubles the cost [He et al. 2008].”