TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation focused on TensorFlow machine learning for mobile, IoT, edge, and other cases. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time.

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

Project Site

tensorflow.org

Source Repository

github.com

Test Created

23 August 2020

Last Updated

19 May 2022

Test Maintainer

Michael Larabel 

Test Type

System

Average Install Time

8 Seconds

Average Run Time

4 Minutes, 31 Seconds

Accolades

10k+ Downloads

Supported Platforms


Public Result Uploads *Reported Installs **Reported Test Completions **Test Profile Page Views ***OpenBenchmarking.orgEventsTensorFlow Lite Popularity Statisticspts/tensorflow-lite2020.082020.102020.122021.022021.042021.062021.082021.102021.122022.022022.042022.062022.082022.102022.122023.022023.042023.062023.082023.102023.122024.022024.042024.062024.082024.105K10K15K20K25K
* 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.
*** Test profile page view reporting began March 2021.
Data updated weekly as of 3 October 2024.
Mobilenet Float21.4%NASNet Mobile13.2%Mobilenet Quant16.9%SqueezeNet16.9%Inception ResNet V214.9%Inception V416.7%Model Option PopularityOpenBenchmarking.org

Revision History

pts/tensorflow-lite-1.1.0   [View Source]   Thu, 19 May 2022 09:57:39 GMT
Update against latest upstream nightly.

pts/tensorflow-lite-1.0.0   [View Source]   Sun, 23 Aug 2020 14:13:10 GMT
TensorFlow Lite initial commit.

Suites Using This Test

Machine Learning

HPC - High Performance Computing


Performance Metrics

Analyze Test Configuration:

TensorFlow Lite 2022-05-18

Model: Mobilenet Float

OpenBenchmarking.org metrics for this test profile configuration based on 792 public results since 19 May 2022 with the latest data as of 10 September 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
Microseconds (Average)
98th
10
1017 +/- 8
97th
10
1076 +/- 49
93rd
4
1297 +/- 2
90th
9
1406 +/- 30
89th
7
1434 +/- 13
87th
3
1518 +/- 6
87th
3
1527 +/- 5
85th
3
1606 +/- 113
82nd
10
1706 +/- 70
80th
4
1796 +/- 6
78th
4
1818 +/- 10
78th
7
1823 +/- 142
Mid-Tier
75th
> 1891
75th
3
1901 +/- 39
71st
9
2171 +/- 81
70th
4
2216 +/- 18
68th
3
2339 +/- 38
68th
6
2345 +/- 7
67th
12
2396 +/- 38
63rd
4
2482 +/- 108
62nd
3
2542 +/- 10
60th
4
2655 +/- 12
60th
3
2692 +/- 53
59th
6
2759 +/- 23
58th
3
2788 +/- 12
57th
22
2814 +/- 136
54th
5
2972 +/- 278
53rd
5
3033 +/- 59
52nd
4
3156 +/- 77
51st
7
3246 +/- 65
Median
50th
3296
47th
6
3445 +/- 258
46th
16
3526 +/- 522
37th
65
3939 +/- 15
35th
4
3953 +/- 15
35th
11
3954 +/- 64
33rd
11
3999 +/- 166
33rd
8
4017 +/- 257
32nd
3
4091 +/- 50
32nd
3
4110 +/- 99
29th
3
4257 +/- 8
27th
8
4470 +/- 366
27th
9
4541 +/- 219
27th
5
4547 +/- 675
Low-Tier
25th
> 4655
25th
3
4660 +/- 5
23rd
3
4909 +/- 23
22nd
17
4963 +/- 450
22nd
4
4965 +/- 398
21st
4
5387 +/- 53
21st
3
5606 +/- 173
18th
5
5955 +/- 4
17th
3
6049 +/- 99
17th
7
6147 +/- 270
16th
5
6857 +/- 528
15th
3
6917 +/- 5
15th
6
6974 +/- 145
14th
4
7159 +/- 10
13th
13
7316 +/- 37
11th
4
8069 +/- 17
11th
4
8393 +/- 520
9th
4
9975 +/- 7
5th
3
23400 +/- 1608
4th
3
27422 +/- 55
2nd
5
68651 +/- 3119
1st
4
277617 +/- 152
OpenBenchmarking.orgDistribution Of Public Results - Model: Mobilenet Float792 Results Range From 940 To 345091 Microseconds940782414708215922847635360422444912856012628966978076664835489043297316104200111084117968124852131736138620145504152388159272166156173040179924186808193692200576207460214344221228228112234996241880248764255648262532269416276300283184290068296952303836310720317604324488331372338256345140150300450600750

Based on OpenBenchmarking.org data, the selected test / test configuration (TensorFlow Lite 2022-05-18 - Model: Mobilenet Float) has an average run-time of 5 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 BenchmarkModel: Mobilenet FloatRun-Time48121620Min: 3 / Avg: 4.78 / Max: 15

Based on public OpenBenchmarking.org results, the selected test / test configuration has an average standard deviation of 0.8%.

OpenBenchmarking.orgPercent, Fewer Is BetterAverage Deviation Between RunsModel: Mobilenet FloatDeviation48121620Min: 0 / Avg: 0.78 / Max: 15

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 BaseTensorFlow Lite CPU Core ScalingModel: Mobilenet Float246810121416641.40212.80424.20635.60847.0105

Notable Instruction Set Usage

Notable instruction set extensions supported by this test, based on an automatic analysis by the Phoronix Test Suite / OpenBenchmarking.org analytics engine.

Instruction Set
Support
Instructions Detected
SSE2 (SSE2)
Used by default on supported hardware.
 
MOVDQA PMULUDQ PSHUFD PSRLDQ MOVD CVTSI2SD ADDSD MULSD SUBSD DIVSD MOVAPD CVTSS2SD CVTTSD2SI SQRTSD UCOMISD XORPD CVTSD2SS CVTTPS2DQ CVTDQ2PS PADDQ MOVDQU PUNPCKLQDQ UNPCKLPD CVTDQ2PD MULPD CVTPD2PS ANDPD MAXSD PSUBQ CVTPS2PD MINSD MOVUPD UNPCKHPD ADDPD PUNPCKHQDQ CVTPS2DQ
Used by default on supported hardware.
Found on Intel processors since Sandy Bridge (2011).
Found on AMD processors since Bulldozer (2011).

 
VBROADCASTF128 VZEROUPPER VMASKMOVPS VEXTRACTF128 VBROADCASTSS VINSERTF128 VPERMILPS
Advanced Vector Extensions 512 (AVX512)
Used by default on supported hardware.
 
(ZMM REGISTER USE)
FMA (FMA)
Used by default on supported hardware.
Found on Intel processors since Haswell (2013).
Found on AMD processors since Bulldozer (2011).

 
VFMADD132PS VFMADD231PS VFMADD213PS
Last automated analysis: 18 January 2022

This test profile binary relies on the shared libraries libm.so.6, libpthread.so.0, libdl.so.2, librt.so.1, libc.so.6.

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)
ARMv8 64-bit
aarch64
ARMv8 9-Core, ARMv8 Cortex-A53 2-Core, ARMv8 Cortex-A53 4-Core, ARMv8 Cortex-A72, ARMv8 Cortex-A72 4-Core, ARMv8 Cortex-A76 4-Core, ARMv8 Cortex-A78E 12-Core, ARMv8 Cortex-A78E 6-Core, ARMv8 Cortex-A78E 8-Core, ARMv8 Neoverse-N1, ARMv8 Neoverse-V1, Ampere ARMv8 Neoverse-N1 160-Core, AmpereOne 192-Core, Apple, Apple M1, Apple M2, Qualcomm

Recent Test Results

OpenBenchmarking.org Results Compare

1 System - 6 Benchmark Results

ARMv8 Cortex-A78E - NVIDIA Jetson Orin NX Engineering Developer Kit - 16GB

Ubuntu 22.04 - 5.15.136-tegra - GNOME Shell 42.9

1 System - 6 Benchmark Results

ARMv8 Cortex-A78E - NVIDIA Jetson Orin Nano Developer Kit - 8GB

Ubuntu 22.04 - 5.15.136-tegra - GNOME Shell 42.9

1 System - 6 Benchmark Results

ARMv8 Cortex-A78E - NVIDIA Jetson AGX Orin Developer Kit - 30GB

Ubuntu 22.04 - 5.15.136-tegra - GNOME Shell 42.9

1 System - 6 Benchmark Results

ARMv8 Cortex-A78E - NVIDIA Jetson Orin NX Engineering Developer Kit - 16GB

Ubuntu 22.04 - 5.15.136-tegra - GNOME Shell 42.9

1 System - 4 Benchmark Results

Intel Core i7-1185G7E - Rockwell Automation/Allen-Bradley 6300B-JB1 MB1561 v1.1 - Intel Tiger Lake-LP

Debian 12 - 6.1.0-23-amd64 - KDE Plasma 5.27.5

1 System - 7 Benchmark Results

Intel Core i7-1185G7E - Rockwell Automation/Allen-Bradley 6300B-JB1 MB1561 v1.1 - Intel Tiger Lake-LP

Debian 12 - 6.1.0-23-amd64 - KDE Plasma 5.27.5

1 System - 3 Benchmark Results

Intel Core i7-1185G7E - Rockwell Automation/Allen-Bradley 6300B-JB1 MB1561 v1.1 - Intel Tiger Lake-LP

Debian 12 - 6.1.0-23-amd64 - KDE Plasma 5.27.5

1 System - 5 Benchmark Results

Intel Core i7-1185G7E - Rockwell Automation/Allen-Bradley 6300B-JB1 MB1561 v1.1 - Intel Tiger Lake-LP

Debian 12 - 6.1.0-23-amd64 - KDE Plasma 5.27.5

1 System - 8 Benchmark Results

Intel Core i7-1185G7E - Rockwell Automation/Allen-Bradley 6300B-JB1 MB1561 v1.1 - Intel Tiger Lake-LP

Debian 12 - 6.1.0-23-amd64 - KDE Plasma 5.27.5

1 System - 6 Benchmark Results

Intel Core i7-1185G7E - Rockwell Automation/Allen-Bradley 6300B-JB1 MB1561 v1.1 - Intel Tiger Lake-LP

Debian 12 - 6.1.0-23-amd64 - KDE Plasma 5.27.5

1 System - 9 Benchmark Results

Intel Core i7-1185G7E - Rockwell Automation/Allen-Bradley 6300B-JB1 MB1561 v1.1 - Intel Tiger Lake-LP

Debian 12 - 6.1.0-23-amd64 - KDE Plasma 5.27.5

1 System - 8 Benchmark Results

Intel Core i7-1185G7E - Rockwell Automation/Allen-Bradley 6300B-JB1 MB1561 v1.1 - Intel Tiger Lake-LP

Debian 12 - 6.1.0-23-amd64 - KDE Plasma 5.27.5

1 System - 7 Benchmark Results

Intel Core i7-1185G7E - Rockwell Automation/Allen-Bradley 6300B-JB1 MB1561 v1.1 - Intel Tiger Lake-LP

Debian 12 - 6.1.0-23-amd64 - KDE Plasma 5.27.5

1 System - 8 Benchmark Results

Intel Core i7-1185G7E - Rockwell Automation/Allen-Bradley 6300B-JB1 MB1561 v1.1 - Intel Tiger Lake-LP

Debian 12 - 6.1.0-23-amd64 - KDE Plasma 5.27.5

1 System - 5 Benchmark Results

Intel Core i7-1185G7E - Rockwell Automation/Allen-Bradley 6300B-JB1 MB1561 v1.1 - Intel Tiger Lake-LP

Debian 12 - 6.1.0-23-amd64 - KDE Plasma 5.27.5

Most Popular Test Results

OpenBenchmarking.org Results Compare

16 Systems - 333 Benchmark Results

Intel Core i9-13900K - ASUS PRIME Z790-P WIFI - Intel Device 7a27

Ubuntu 22.04 - 6.0.0-060000rc1daily20220820-generic - GNOME Shell 42.2

13 Systems - 333 Benchmark Results

AMD Ryzen 9 7900X 12-Core - ASUS ROG CROSSHAIR X670E HERO - AMD Device 14d8

Ubuntu 22.04 - 6.0.0-060000rc1daily20220820-generic - GNOME Shell 42.2

5 Systems - 396 Benchmark Results

Intel Core i9-13900K - ASUS PRIME Z790-P WIFI - Intel Device 7a27

Ubuntu 23.04 - 6.2.0-060200rc8daily20230213-generic - GNOME Shell 43.2

7 Systems - 293 Benchmark Results

AMD Ryzen 5 4500U - LENOVO LNVNB161216 - AMD Renoir

Pop 22.04 - 5.17.5-76051705-generic - GNOME Shell 42.1

5 Systems - 94 Benchmark Results

ARMv8 Neoverse-N1 - Amazon EC2 c6g.4xlarge - Amazon Device 0200

Ubuntu 22.04 - 5.15.0-1004-aws - GCC 11.2.0

3 Systems - 18 Benchmark Results

AMD Ryzen Threadripper 3990X 64-Core - Gigabyte TRX40 AORUS PRO WIFI - AMD Starship

Pop 22.04 - 5.17.5-76051705-generic - GNOME Shell 42.0

11 Systems - 408 Benchmark Results

AMD Ryzen 7 PRO 5850U - HP 8A78 - AMD Renoir

Ubuntu 22.04 - 5.18.8-051808-generic - GNOME Shell 42.2

2 Systems - 86 Benchmark Results

Intel Xeon Silver 4216 - TYAN S7100AG2NR - Intel Sky Lake-E DMI3 Registers

Debian 11 - 5.10.0-10-amd64 - X Server

2 Systems - 218 Benchmark Results

Apple M1 - Apple Mac mini - 8GB

Arch Linux ARM - 5.19.0-rc7-asahi-2-1-ARCH - KDE Plasma 5.25.4

2 Systems - 219 Benchmark Results

AMD Ryzen 9 5900HX - ASUS G513QY v1.0 - AMD Renoir

Arch rolling - 5.18.16-arch1-1 - KDE Plasma 5.25.4

Find More Test Results