Faiss

Faiss is developed by Meta/Facebook. Faiss is a library for efficient similarity search and clustering of dense vectors.

To run this test with the Phoronix Test Suite, the basic command is: phoronix-test-suite benchmark faiss.

Project Site

faiss.ai

Source Repository

github.com

Test Created

28 April 2023

Test Maintainer

Michael Larabel 

Test Type

System

Test Dependencies

Python + C/C++ Compiler Toolchain + Fortran

Accolades

20k+ Downloads

Supported Platforms


Public Result Uploads *Reported Installs **Reported Test Completions **Test Profile Page ViewsOpenBenchmarking.orgEventsFaiss Popularity Statisticspts/faiss2023.042023.052023.062023.072023.082023.092023.102023.112023.122024.012024.022024.032024.042024.052024.062024.072024.082024.092024.102024.1111002200330044005500
* Uploading of benchmark result data to OpenBenchmarking.org is always optional (opt-in) via the Phoronix Test Suite for users wishing to share their results publicly.
** Data based on those opting to upload their test results to OpenBenchmarking.org and users enabling the opt-in anonymous statistics reporting while running benchmarks from an Internet-connected platform.
Data updated weekly as of 19 November 2024.
bench_polysemous_sift1m94.3%demo_sift1M5.7%Test Option PopularityOpenBenchmarking.org

Revision History

pts/faiss-1.0.1   [View Source]   Fri, 28 Apr 2023 08:50:48 GMT
Update dependencies.

pts/faiss-1.0.0   [View Source]   Fri, 28 Apr 2023 08:35:53 GMT
Initial commit of FAISS


Performance Metrics

Analyze Test Configuration:

Faiss 1.7.4

Test: bench_polysemous_sift1m - Polysemous 64

OpenBenchmarking.org metrics for this test profile configuration based on 42 public results since 28 April 2023 with the latest data as of 8 January 2024.

Below is an overview of the generalized performance for components where there is sufficient statistically significant data based upon user-uploaded results. It is important to keep in mind particularly in the Linux/open-source space there can be vastly different OS configurations, with this overview intended to offer just general guidance as to the performance expectations.

Component
Percentile Rank
# Compatible Public Results
ms per query (Average)
98th
3
4.11 +/- 0.02
89th
4
4.30 +/- 0.19
Mid-Tier
75th
> 6.08
65th
9
6.11 +/- 0.02
Median
50th
6.62
46th
3
6.67 +/- 0.08
Low-Tier
25th
> 7.39
3rd
3
14.48 +/- 0.14
OpenBenchmarking.orgDistribution Of Public Results - Test: bench_polysemous_sift1m - Polysemous 6442 Results Range From 4 To 15 ms per query44.9175.8346.7517.6688.5859.50210.41911.33612.25313.1714.08715.00448121620

Based on OpenBenchmarking.org data, the selected test / test configuration (Faiss 1.7.4 - Test: bench_polysemous_sift1m - Polysemous 64) has an average run-time of 15 minutes. By default this test profile is set to run at least 3 times but may increase if the standard deviation exceeds pre-defined defaults or other calculations deem additional runs necessary for greater statistical accuracy of the result.

OpenBenchmarking.orgMinutesTime Required To Complete BenchmarkTest: bench_polysemous_sift1m - Polysemous 64Run-Time612182430Min: 9 / Avg: 14.27 / Max: 29

Tested CPU Architectures

This benchmark has been successfully tested on the below mentioned architectures. The CPU architectures listed is where successful OpenBenchmarking.org result uploads occurred, namely for helping to determine if a given test is compatible with various alternative CPU architectures.

CPU Architecture
Kernel Identifier
Verified On
Intel / AMD x86 64-bit
x86_64
(Many Processors)