Cache locality is not enough: high-performance nearest neighbor search with product quantization fast scan
The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Abstract
Nearest Neighbor (NN) search in high dimension is an important feature in many applications (e.g., image retrieval, multimedia databases). Product Quantization (PQ) is a widely used solution which offers high performance, i.e., low response time while preserving a high accuracy. PQ represents high-dimensional vectors (e.g., image descriptors) by compact codes. Hence, very large databases can be stored in memory, allowing NN queries without resorting to slow I/O operations. PQ computes distances to neighbors using cache-resident lookup tables, thus its performance remains limited by (i) the many cache accesses that the algorithm requires, and (ii) its inability to leverage SIMD instructions available on modern CPUs. In this paper, we advocate that cache locality is not sufficient for efficiency. To address these limitations, we design a novel algorithm, PQ Fast Scan, that transforms the cache-resident lookup tables into small tables, sized to fit SIMD registers. This transformation allows (i) in-register lookups in place of cache accesses and (ii) an efficient SIMD implementation. PQ Fast Scan has the exact same accuracy as PQ, while having 4 to 6 times lower response time (e.g., for 25 million vectors, scan time is reduced from 74ms to 13ms).
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Least squares quantization in PCM
Lloyd, S. (1982) · IEEE Transactions on Information Theory · doi:10.1109/tit.1982.1056489 · Cited by 15,836
Product Quantization for Nearest Neighbor Search
Jégou, H., Douze, M., & Schmid, C. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2010.57 · Cited by 2,956 · cited 9×
“We focus on product quantizers with 2 centroids as they offer a good tradeoff between complexity and quality for NN search [14].”
BackgroundMethodInfluentialExperiencing SAX: A novel symbolic representation of time series
Lin, J., Keogh, E., Wei, L., & Lonardi, S. (2007) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-007-0064-z · Cited by 1,618 · cited 1×
“Compression schemes, either generic [23, 12, 3, 25] or specific (e.g., SAX for time series [18]), have been widely adopted in database systems.”
Cited by
Billion-scale similarity search with GPUs
Johnson, J., Douze, M., & Jegou, H. (2021) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2019.2921572 · Cited by 4,228
Billion-scale similarity search with GPUs
Johnson, J., Douze, M., & Jégou, H. (2017) · arXiv · doi:10.48550/arxiv.1702.08734 · Cited by 4,140
“L1 cache with little eort, and L1 cache latency and bandwidth remains a limiting factor. Other similarity search components, like PQ code manipulation, tend to have greater impact on CPU performance [2]. GPU heaps. Heaps can be similarly implemented on a GPU [7]. However, a straightforward GPU heap implementation suer…”
BackgroundMethod(2021) · doi:10.1145/3448016.3457550 · Cited by 416
Fast approximate nearest neighbor search with the navigating spreading-out graph
Fu, C., Xiang, C., Wang, C., & Cai, D. (2019) · Proceedings of the VLDB Endowment · doi:10.14778/3303753.3303754 · Cited by 379
A Biresolution Spectral Framework for Product Quantization
Mukherjee, L., Peng, J., Ravi, S. N., & Singh, V. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00351 · Cited by 2
“This implies W ∗ j 2 = W∗ j for j = [1, 2].”
Background
Metadata
- Authors
- André, F., Kermarrec, A.-M., & Le Scouarnec, N.
- Venue
- Proceedings of the VLDB Endowment
- Published
- 2015-12
- Volume
- 9
- Issue
- 4
- Pages
- 288-299
- ISSN
- 2150-8097 (ISSN-L)
- OpenAlex
- W2204555070
- Cited by
- 70
- References
- 3
- FWCI
- 2.89
- Type
- journal article
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Cache locality is not enough: high-performance nearest neighbor search with product quantization fast scan. https://app.cochat.ai/papers/10.14778/2856318.2856324
- The paper
- André, F., Kermarrec, A.-M., & Le Scouarnec, N. (2015). Cache locality is not enough: high-performance nearest neighbor search with product quantization fast scan. Proceedings of the VLDB Endowment. https://doi.org/10.14778/2856318.2856324
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.