This blog explains how int4 quantization works in Lucene, how it lines up, and the benefits of using int4 quantization.

Introduction to Int4 quantization in Lucene

How does `Int4` quantization work in Lucene

Storing and scoring the quantized vectors

Calculating the quantization error correction

Finding the optimal bucketing for int4 quantization

Speed vs. size for quantization

Speed part 2: more SIMD in int4

The end?

Int4 provides additional compression options. It reduces the quantization space to only 16 possible values (0 through 15).

What is Int4 quantization in Lucene?

Understanding Int4 scalar quantization in Lucene

Discover how modern Java features, including vectorization and FFI/madvise, are speeding up Lucene's performance.

Foreign memory

Foreign function

Vectorization

Conclusion

Lucene & Java: How vectorization & FFI/madvise speed up Lucene

Making Lucene faster with vectorization and FFI/madvise

Explore multi-graph vector search in Lucene and discover how sharing information between segment searches enhances search speed.

The previous state of multi-graph vector search in Lucene

Speeding up multi-graph vector search by sharing information between segment searches

Impact on performance

Impact on recall

Lucene vector search: Speeding up multi-graph vector search

Speeding Up Multi-graph Vector Search

Learn how to optimize vector distance computations using the Foreign Function & Memory (FFM) API to achieve faster performance.

Current state of play: The Panama Vector API

Introducing the Foreign Function & Memory (FFM) API

FFM usage example

Going foreign

Back in Java-land

Performance improvements with FFM API

Summary

Optimizing vector distance computations with the FFM API

Optimizing vector distance computations with the Foreign Function & Memory (FFM) API

2023 has been another big year for Apache Lucene, this blog reviews major milestones of 2023

Community

Vector search

Radix sort everywhere

Faster query evaluation

Closer integration with the Java virtual machine

What happened in Lucene land in 2023?

Lucene 9.9 brings major speedups to query evaluation. Here are the performance improvements observed in nightly benchmarks & optimization resources.

Key speedup benchmarks in Lucene

Lucene optimization resources

Lucene 9.9: Optimizations, performance & benchmarks insights

Apache Lucene 9.9, the fastest Lucene release ever

Learn about MAXSCORE, block-max MAXSCORE & WAND. Improve the MAXSCORE algorithm to evaluate disjunctive queries more like a conjunctive query.

Introduction to WAND and MAXSCORE

Block-max MAXSCORE & MAXSCORE in Lucene

MAXSCORE usage example

Improving MAXSCORE to intersect terms

MAXSCORE sorts terms by increasing maximum impact score and partitions them into two groups: essential terms and non-essential terms. Non-essential terms are terms with low maximum impact scores whose sum of maximum scores is less than the minimum competitive score. Essential terms are all other terms. Essential terms are used to find candidate matches while non-essential terms are only used to compute the score of a candidate.

How does the MAXSCORE algorithm work?

WAND typically evaluates fewer hits than MAXSCORE but with a higher per-hit overhead. This makes MAXSCORE generally perform better on high k values or with many terms - when skipping hits is hard, and WAND performs better otherwise."

How do block-max MAXSCORE performance characteristics compare to WAND?

MAXSCORE & block-max MAXSCORE: Improving the algorithm

MAXSCORE & block-max MAXSCORE: More skipping with block-max MAXSCORE

Learn how to use fused multiply-add (FMA) within vector similarity computations in Lucene and discover how FMA can improve performance.

What is fused multiply-add (FMA)

FMA in Lucene: Under the hood

Performance improvements with FMA

Wrapping up

Fused multiply-add (FMA) is a single operation that performs both the multiply and add operations in one - the multiplication and addition are said to be “fused” together. FMA is typically faster than a separate multiplication and addition and produces more accurate results.

What is fused multiply-add (FMA)?

Understanding fused multiply add (FMA) in Lucene

Understanding fused multiply-add (FMA) within vector similarity computations in Lucene

Explore how Elastic introduced scalar quantization into Lucene, including automatic byte quantization, quantization per segment & performance insights.

Automatic byte quantization in Lucene

Scalar quantization 101

Exploring the architecture

Quantization per segment in Lucene

Quantization that grows with you

Quantization performance & numbers

Scalar quantization is a lossy compression technique. Some simple math gives significant space savings with little impact on recall.

What is scalar quantization?

Understanding scalar quantization in Lucene

Elasticsearch is out-of-the-box 2x–12x faster than OpenSearch for vector search

Lucene

Elasticsearch vs. OpenSearch: Vector Search Performance Comparison