Faster Set Intersection with SIMD instructions by Reducing Branch Mispredictions
Summary: Introduces a branch-misprediction-resilient SIMD algorithm for intersecting sorted arrays, comparing blocks of elements and advancing pointers multiple positions. It requires no preprocessing and beats gcc’s std::set_intersection by up to 5.2× on Xeon/POWER7+. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Hiroshi Inoue (IBM)
- 2. Moriyoshi Ohara (IBM)
- 3. Kenjiro Taura (University of Tokyo)
BibTeX Citation
@article{inoue_vldb15,
title = {{Faster Set Intersection with SIMD instructions by Reducing Branch Mispredictions}},
author = {Inoue, Hiroshi and Ohara, Moriyoshi and Taura, Kenjiro},
journal = {PVLDB},
series = {{VLDB} '15},
volume = {8},
number = {3},
pages = {293--304},
doi = {10.14778/2735508.2735516},
url = {https://doi.org/10.14778/2735508.2735516},
year = {2015}
}Incoming Citations (Sorted by Pagerank)
Showing 9 of 9 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 211 | EmptyHeaded: A Relational Engine for Graph Processing | 2016 | SIGMOD | 0.00024797217 |
| 2,112 | Speeding Up Set Intersections in Graph Algorithms using SIMD Instructions | 2018 | SIGMOD | 9.1514258e-05 |
| 3,821 | Distributed Subgraph Matching on Timely Dataflow | 2019 | VLDB | 7.0933895e-05 |
| 4,177 | SIMD- and Cache-Friendly Algorithm for Sorting an Array of Structures | 2015 | VLDB | 6.8499317e-05 |
| 7,842 | Processing and Optimizing Main Memory Spatial-Keyword Queries | 2016 | VLDB | 5.5333985e-05 |
| 8,201 | List Intersection for Web Search: Algorithms, Cost Models, and Optimizations | 2019 | VLDB | 5.467444e-05 |
| 8,238 | Interleaved Multi-Vectorizing | 2020 | VLDB | 5.4599422e-05 |
| 9,176 | HERO: A Hierarchical Set Partitioning and Join Framework for Speeding up the Set Intersection Over Graphs | 2024 | SIGMOD | 5.3081996e-05 |
| 11,579 | Origami: A High-Performance Mergesort Framework | 2022 | VLDB | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 5 of 5 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 293 | Implementing Database Operations Using SIMD Instructions | 2002 | SIGMOD | 0.00022259273 |
| 712 | Efficient Implementation of Sorting on Multi-Core SIMD CPU Architecture | 2008 | VLDB | 0.0001468812 |
| 1,655 | Efficient Parallel Lists Intersection and Index Compression Algorithms using Graphics Processing Units | 2011 | VLDB | 0.00010103504 |
| 1,717 | Improving the Performance of List Intersection | 2009 | VLDB | 9.9327227e-05 |
| 2,245 | Fast Set Intersection in Memory | 2011 | VLDB | 8.8734284e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 8,238 | Interleaved Multi-Vectorizing | 2020 | VLDB |
| 2 | 8,201 | List Intersection for Web Search: Algorithms, Cost Models, and Optimizations | 2019 | VLDB |
| 3 | 200 | Efficient set joins on similarity predicates | 2004 | SIGMOD |
| 4 | 634 | Rethinking SIMD Vectorization for In-Memory Databases | 2015 | SIGMOD |
| 5 | 4,177 | SIMD- and Cache-Friendly Algorithm for Sorting an Array of Structures | 2015 | VLDB |
| 6 | 712 | Efficient Implementation of Sorting on Multi-Core SIMD CPU Architecture | 2008 | VLDB |
| 7 | 1,717 | Improving the Performance of List Intersection | 2009 | VLDB |
| 8 | 293 | Implementing Database Operations Using SIMD Instructions | 2002 | SIGMOD |
| 9 | 2,245 | Fast Set Intersection in Memory | 2011 | VLDB |
| 10 | 2,112 | Speeding Up Set Intersections in Graph Algorithms using SIMD Instructions | 2018 | SIGMOD |