TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. 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

Test Created

23 August 2020

Last Updated

23 August 2020

Test Maintainer

Michael Larabel 

Test Type

System

Average Install Time

9 Seconds

Average Run Time

4 Minutes, 44 Seconds

Supported Platforms


Public Result UploadsReported Installs*Test Completions*OpenBenchmarking.orgEventsTensorFlow Lite Popularity Statisticspts/tensorflow-lite2020.082020.092020.102020.112020.122021.012021.0211002200330044005500
* 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 Fri, 26 Feb 2021 12:49:57 GMT.
Mobilenet Float16.6%Inception ResNet V216.8%SqueezeNet16.5%Inception V417.0%Mobilenet Quant16.8%NASNet Mobile16.4%Model Option PopularityOpenBenchmarking.org

Revision History

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 2020-08-23

Model: Inception V4

OpenBenchmarking.org metrics for this test profile configuration based on 862 public results since 23 August 2020 with the latest data as of 24 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.

Component
Percentile Rank
# Matching Public Results
Microseconds (Average)
100th
12
642483 +/- 93685
95th
18
837153 +/- 26938
95th
7
843892 +/- 97728
92nd
38
928155 +/- 81159
92nd
5
939558 +/- 123052
91st
5
953713 +/- 5861
90th
7
964418 +/- 17575
87th
13
1012771 +/- 4208
87th
7
1016970 +/- 26056
84th
5
1062883 +/- 9744
84th
7
1078691 +/- 30279
83rd
3
1091599 +/- 32213
83rd
10
1091624 +/- 74485
80th
7
1267651 +/- 3250
79th
4
1301404 +/- 1089
79th
15
1323553 +/- 16184
78th
6
1337462 +/- 11159
Mid-Tier
75th
> 1346957
75th
36
1349681 +/- 8115
72nd
13
1394181 +/- 33012
71st
8
1450834 +/- 20299
69th
16
1501519 +/- 3477
68th
5
1513658 +/- 9274
68th
4
1553774 +/- 19410
66th
12
1744999 +/- 5566
65th
6
1760707 +/- 423
63rd
36
1788370 +/- 6831
60th
7
1818832 +/- 903
59th
16
1853381 +/- 4345
58th
6
1859435 +/- 323
55th
13
1993321 +/- 120555
54th
6
2007173 +/- 8923
52nd
24
2375080 +/- 2802
Median
50th
2379217
50th
6
2478724 +/- 67692
50th
5
2522157 +/- 25935
48th
15
2642372 +/- 33013
47th
8
2661069 +/- 1826
45th
3
2833567 +/- 2924
44th
11
2926770 +/- 61822
44th
5
2945565 +/- 425896
41st
7
3276896 +/- 257101
41st
10
3294265 +/- 28269
41st
10
3300646 +/- 87576
40th
4
3336966 +/- 60324
39th
13
3474556 +/- 6813
37th
3
3622617 +/- 2512
36th
3
3661980
35th
3
3755293 +/- 15369
35th
11
3781791 +/- 225796
34th
4
3826542 +/- 9266
33rd
3
4177253 +/- 958
32nd
3
4180822 +/- 3737
31st
4
4293005 +/- 83
30th
11
4351155 +/- 3520
29th
3
4382592 +/- 18386
29th
3
4508289 +/- 101
29th
15
4609940 +/- 213154
29th
3
4614180 +/- 249
27th
6
4891576 +/- 670870
26th
10
5162842 +/- 37359
Low-Tier
25th
> 5203603
25th
9
5278125 +/- 1884
23rd
4
5442567 +/- 32231
23rd
6
5522806 +/- 31927
22nd
6
5573186 +/- 1449
22nd
9
5653801 +/- 292314
22nd
3
5748968 +/- 566
21st
3
5758377 +/- 384
21st
3
5785801 +/- 15088
20th
4
5956926 +/- 108509
20th
3
5972134 +/- 13379
19th
3
6420592 +/- 84632
19th
3
6467311 +/- 629
18th
4
6490153 +/- 11453
18th
3
6832660 +/- 679
17th
3
6894610 +/- 1092
17th
3
6924027 +/- 10096
17th
3
7025878 +/- 25406
16th
3
7167092 +/- 714
16th
3
7203782 +/- 760
15th
4
7346190 +/- 2925
15th
3
7780924 +/- 7562
15th
3
7807922 +/- 893
14th
4
7820482 +/- 12835
13th
3
7994576 +/- 8535
12th
28
8101477 +/- 364988
11th
3
8293764 +/- 3127
10th
3
8372534 +/- 1682
9th
4
8575365 +/- 28108
7th
3
9377187 +/- 336
7th
12
9442529 +/- 379360
7th
3
9554590 +/- 2649
6th
3
10007035 +/- 85830
6th
5
10027546 +/- 724872
5th
7
10339239 +/- 631305
4th
3
13230678 +/- 805
4th
3
14680022 +/- 88498
3rd
3
16580844 +/- 6996
2nd
4
17609975 +/- 5034
2nd
5
17668280 +/- 497696
2nd
5
19554807 +/- 24764
1st
3
20841444 +/- 11702
1st
3
21619078 +/- 8720
OpenBenchmarking.orgDistribution Of Public Results - Model: Inception V4858 Results Range From 552858 To 28134967 Microseconds55285811045011656144220778727594303311073386271644143594966002551764560692886620931717257477242178275860882750393791469930789104824321103407511585718121373611268900413240647137922901434393314895576154472191599886216550505171021481765379118205434187570771930872019860363204120062096364921515292220669352261857823170221237218642427350724825150253767932592843626480079270317222758336528135008306090120150

Based on OpenBenchmarking.org data, the selected test / test configuration (TensorFlow Lite 2020-08-23 - Model: Inception V4) has an average run-time of 6 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: Inception V4Run-Time48121620Min: 1 / Avg: 6.04 / Max: 14

Based on public OpenBenchmarking.org results, the selected test / test configuration has an average standard deviation of 0.1%.

OpenBenchmarking.orgPercent, Fewer Is BetterAverage Deviation Between RunsModel: Inception V4Deviation246810Min: 0 / Avg: 0.1 / Max: 2

Does It Scale Well With Increasing Cores?

Yes, based on the automated analysis of the collected public benchmark data, this test / test settings does 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.

AMDIntelOpenBenchmarking.orgRelative Core Scaling To BaseTensorFlow Lite CPU Core ScalingModel: Inception V44681216243248643691215

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
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: 31 January 2021

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

Recent Test Results

OpenBenchmarking.org Results Compare

2 Systems - 95 Benchmark Results

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

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

10 Systems - 47 Benchmark Results

Intel Core i7-1165G7 - LENOVO LNVNB161216 - Intel Tiger Lake-LP

ManjaroLinux 20.2.1 - 5.11.1-1-MANJARO - GNOME Shell 3.38.3

9 Systems - 47 Benchmark Results

Intel Core i7-1165G7 - Dell 0GG9PT - Intel Tiger Lake-LP

Ubuntu 20.10 - 5.8.0-31-generic - GNOME Shell 3.38.1

2 Systems - 243 Benchmark Results

Intel Core i9-10885H - HP 8736 - Intel Comet Lake PCH

Ubuntu 20.10 - 5.8.0-43-generic - GNOME Shell 3.38.2

1 System - 238 Benchmark Results

Intel Core i9-10885H - HP 8736 - Intel Comet Lake PCH

Ubuntu 20.10 - 5.8.0-43-generic - GNOME Shell 3.38.2

3 Systems - 108 Benchmark Results

Intel Core i7-10700T - Logic Supply RXM-181 - Intel Comet Lake PCH

Ubuntu 20.10 - 5.8.0-43-generic - GNOME Shell 3.38.2

2 Systems - 86 Benchmark Results

Intel Core i7-10700T - Logic Supply RXM-181 - Intel Comet Lake PCH

Ubuntu 20.10 - 5.8.0-43-generic - GNOME Shell 3.38.2

1 System - 2 Benchmark Results

AMD EPYC 7542 32-Core - UpCloud Cloud Server - Intel 440FX 82441FX PMC

Ubuntu 20.04 - 5.4.0-58-generic - bochs-drmdrmfb

5 Systems - 118 Benchmark Results

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

Fedora 33 - 5.10.13-200.fc33.x86_64 - GNOME Shell 3.38.3

4 Systems - 114 Benchmark Results

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

Clear Linux OS 34220 - 5.10.10-1017.native - GNOME Shell 3.38.3

3 Systems - 113 Benchmark Results

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

salientos rolling - 5.10.14-arch1-1 - Xfce 4.16

2 Systems - 113 Benchmark Results

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

salientos rolling - 5.10.14-arch1-1 - Xfce 4.16

Most Popular Test Results

OpenBenchmarking.org Results Compare

3 Systems - 268 Benchmark Results

Intel Core i5-2520M - HP 161C - Intel 2nd Generation Core DRAM

Ubuntu 18.04 - 4.18.0-20-generic - GNOME Shell 3.28.3

2 Systems - 535 Benchmark Results

AMD Ryzen 5 4500U - LENOVO LNVNB161216 - AMD Renoir Root Complex

Ubuntu 20.04 - 5.9.0-050900rc7daily20201002-generic - GNOME Shell 3.36.4

11 Systems - 217 Benchmark Results

AMD Ryzen 5 3600X 6-Core - ASUS ROG CROSSHAIR VIII HERO - AMD Starship

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

3 Systems - 174 Benchmark Results

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

Fedora 32 - 5.8.11-200.fc32.x86_64 - GNOME Shell 3.36.6

2 Systems - 403 Benchmark Results

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

Ubuntu 20.10 - 5.8.0-22-generic - GNOME Shell 3.38.0

3 Systems - 11 Benchmark Results

AMD Ryzen 7 3800XT 8-Core - ASRock X570 Pro4 - AMD Starship

Ubuntu 20.04 - 5.4.0-42-generic - GNOME Shell 3.36.1

3 Systems - 406 Benchmark Results

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

Ubuntu 20.04 - 5.4.0-48-generic - GNOME Shell 3.36.4

4 Systems - 6 Benchmark Results

Intel Core i7-1065G7 - Dell 06CDVY - Intel Device 34ef

Ubuntu 20.04 - 5.9.0-050900rc1daily20200819-generic - GNOME Shell 3.36.4

12 Systems - 229 Benchmark Results

AMD Ryzen 5 2600 Six-Core - ASUS ROG CROSSHAIR VIII HERO - AMD 17h

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

Find More Test Results

OpenBenchmarking.org Community User Comments

Post A Comment