Numenta Anomaly Benchmark

Numenta Anomaly Benchmark (NAB) is a benchmark for evaluating algorithms for anomaly detection in streaming, real-time applications. It is comprised of over 50 labeled real-world and artificial timeseries data files plus a novel scoring mechanism designed for real-time applications. This test profile currently measures the time to run various detectors.

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

Project Site

github.com

Test Created

9 November 2018

Last Updated

28 February 2020

Test Maintainer

Michael Larabel 

Test Type

System

Average Install Time

4 Minutes, 16 Seconds

Average Run Time

18 Minutes, 30 Seconds

Test Dependencies

Python

Accolades

20k+ Downloads

Supported Platforms


Public Result UploadsReported Installs*Test Completions*OpenBenchmarking.orgEventsNumenta Anomaly Benchmark Popularity Statisticspts/numenta-nab2018.112018.122019.012019.022019.032019.042019.052019.062019.072019.082019.092019.102019.112019.122020.012020.022020.032020.042020.052020.062020.072020.082020.092020.102020.112020.122021.012021.022021.035001000150020002500
* 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 current as of Mon, 08 Mar 2021 06:00:16 GMT.
Windowed Gaussian21.6%EXPoSE14.2%Relative Entropy21.7%Earthgecko Skyline20.6%Bayesian Changepoint21.9%Detector Option PopularityOpenBenchmarking.org

Revision History

pts/numenta-nab-1.1.0   [View Source]   Fri, 28 Feb 2020 12:04:17 GMT
Update against NAB 1.1 upstream for Python 3 compatibility.

pts/numenta-nab-1.0.0   [View Source]   Fri, 09 Nov 2018 11:55:56 GMT
Initial commit of Numenta Anomaly Benchmark

Suites Using This Test

Machine Learning

CPU Massive

Server CPU Tests

Python

HPC - High Performance Computing


Performance Metrics

Analyze Test Configuration:

Numenta Anomaly Benchmark 1.1

Detector: Bayesian Changepoint

OpenBenchmarking.org metrics for this test profile configuration based on 626 public results since 28 February 2020 with the latest data as of 26 February 2021.

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.

OpenBenchmarking.orgDistribution Of Public Results - Detector: Bayesian Changepoint626 Results Range From 21 To 1732 Seconds2162103144185226267308349390431472513554595636677718759800841882923964100510461087112811691210125112921333137414151456149715381579162016611702174380160240320400

Based on OpenBenchmarking.org data, the selected test / test configuration (Numenta Anomaly Benchmark 1.1 - Detector: Bayesian Changepoint) has an average run-time of 3 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 BenchmarkDetector: Bayesian ChangepointRun-Time510152025Min: 1 / Avg: 2.87 / Max: 23

Based on public OpenBenchmarking.org results, the selected test / test configuration has an average standard deviation of 1%.

OpenBenchmarking.orgPercent, Fewer Is BetterAverage Deviation Between RunsDetector: Bayesian ChangepointDeviation246810Min: 0 / Avg: 1.01 / Max: 4

Does It Scale Well With Increasing Cores?

No, based on the automated analysis of the collected public benchmark data, this test / test settings does not generally scale well with increasing CPU core counts. Data based on publicly available results for this test / test settings, separated by vendor, result divided by the reference CPU clock speed, grouped by matching physical CPU core count, and normalized against the smallest core count tested from each vendor for each CPU having a sufficient number of test samples and statistically significant data.

IntelAMDOpenBenchmarking.orgRelative Core Scaling To BaseNumenta Anomaly Benchmark CPU Core ScalingDetector: Bayesian Changepoint481216320.46670.93341.40011.86682.3335

Recent Test Results

OpenBenchmarking.org Results Compare

1 System - 358 Benchmark Results

Ampere Altra ARMv8 Neoverse-N1 - WIWYNN Mt.Jade - Ampere Computing LLC Device e100

Ubuntu 20.04 - 5.11.0-051100-generic-64k - GNOME Shell 3.36.4

1 System - 111 Benchmark Results

2 x Intel Xeon E5-2678 v3 - HUANANZHI X99-T8D - Intel Xeon E7 v3

Debian 10 - 4.19.0-13-amd64 - GCC 8.3.0

1 System - 84 Benchmark Results

2 x Intel Xeon E5-2667 v2 - Intel S2600CP - Intel Xeon E7 v2

Debian 10 - 4.19.0-14-amd64 - GCC 8.3.0

1 System - 241 Benchmark Results

AMD Ryzen 7 3700X 8-Core - ASRock X570 Phantom Gaming-ITX/TB3 - AMD Starship

Ubuntu 20.10 - 5.8.0-41-lowlatency - X Server 1.20.9

1 System - 23 Benchmark Results

AMD Ryzen 5 4600H - HUAWEI HLYL-WXX9-PCB - AMD Renoir Root Complex

Ubuntu 20.10 - 5.8.0-25-generic - Budgie

2 Systems - 6 Benchmark Results

AMD Ryzen 9 5900X 12-Core - ASUS ROG CROSSHAIR VIII HERO - AMD Starship

Ubuntu 20.10 - 5.11.0-051100rc2daily20210105-generic - GNOME Shell 3.38.1

1 System - 6 Benchmark Results

AMD Ryzen 9 3900XT 12-Core - MSI MEG X570 GODLIKE - AMD Starship

Ubuntu 20.10 - 5.11.0-rc1-phx - GNOME Shell 3.38.1

4 Systems - 210 Benchmark Results

POWER9 - PowerNV T2P9D01 REV 1.01 - 64GB

Ubuntu 20.10 - 5.9.10-050910-generic - X Server

1 System - 219 Benchmark Results

AMD EPYC 7302P 16-Core - Supermicro H11SSL-i v2.00 - AMD Starship

Ubuntu 20.04 - 5.4.0-42-generic - GNOME Shell 3.36.4

3 Systems - 313 Benchmark Results

Intel Core i7-5960X - ASRock X99 Extreme3 - Intel Xeon E7 v3

Ubuntu 20.04 - 5.4.0-58-generic - GNOME Shell 3.36.4

2 Systems - 85 Benchmark Results

Intel Core i5-1135G7 - Dell 0THX8P - Intel Device a0ef

Ubuntu 20.04 - 5.6.0-1036-oem - GNOME Shell 3.36.4

1 System - 83 Benchmark Results

Intel Core i5-1135G7 - Dell 0THX8P - Intel Device a0ef

Ubuntu 20.04 - 5.6.0-1036-oem - GNOME Shell 3.36.4

Most Popular Test Results

OpenBenchmarking.org Results Compare

12 Systems - 593 Benchmark Results

Intel Core i9-10900K - Gigabyte Z490 AORUS MASTER - Intel Comet Lake PCH

Ubuntu 20.04 - 5.8.0-050800daily20200622-generic - GNOME Shell 3.36.2

11 Systems - 217 Benchmark Results

AMD Ryzen 9 3950X 16-Core - ASUS ROG CROSSHAIR VIII HERO - AMD Starship

Ubuntu 20.04 - 5.9.0-050900-generic - GNOME Shell 3.36.4

3 Systems - 301 Benchmark Results

Intel Core i5-7600K - Gigabyte Z270M-D3H-CF - Intel Xeon E3-1200 v6

Ubuntu 20.04 - 5.4.0-40-generic - GNOME Shell 3.36.3

12 Systems - 229 Benchmark Results

AMD Ryzen 5 5600X 6-Core - ASUS ROG CROSSHAIR VIII HERO - AMD Starship

Ubuntu 20.04 - 5.9.0-050900-generic - GNOME Shell 3.36.4

2 Systems - 475 Benchmark Results

AMD Ryzen Threadripper 3970X 32-Core - ASUS ROG ZENITH II EXTREME - AMD Starship

Ubuntu 19.10 - 5.3.0-18-generic - GNOME Shell 3.34.1

6 Systems - 733 Benchmark Results

AMD Ryzen 9 3900X 12-Core - ASUS TUF GAMING X570-PLUS - AMD Starship

Ubuntu 20.04 - 5.8.0-050800daily20200622-generic - GNOME Shell 3.36.2

3 Systems - 777 Benchmark Results

Intel Core i3-10100 - ASUS PRIME Z490M-PLUS - Intel Comet Lake PCH

Ubuntu 20.04 - 5.7.0-rc6-amd-energy - GNOME Shell 3.36.2

2 Systems - 1708 Benchmark Results

Intel Core i3-10100 - ASUS PRIME Z490M-PLUS - Intel Comet Lake PCH

Ubuntu 20.04 - 5.7.0-rc6-amd-energy - GNOME Shell 3.36.2

3 Systems - 171 Benchmark Results

Intel Xeon E3-1270 v5 - ASUS E3 PRO GAMING V5 - Intel Xeon E3-1200 v5

Clear Linux OS 31470 - 5.3.8-854.native - GNOME Shell 3.34.1

Find More Test Results