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

Test Maintainer

Michael Larabel 

Test Type

System

Average Install Time

11 Seconds

Average Run Time

5 Minutes, 24 Seconds

Accolades

5k+ Downloads

Supported Platforms


Public Result Uploads *Reported Installs **Reported Test Completions **Test Profile Page Views ***OpenBenchmarking.orgEventsTensorFlow Lite Popularity Statisticspts/tensorflow-lite2020.082020.092020.102020.112020.122021.012021.022021.032021.042021.052021.062021.072021.082021.092021.102021.112021.122K4K6K8K10K
* 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 current as of 8 December 2021.
Mobilenet Float16.5%Inception ResNet V217.6%SqueezeNet16.1%Inception V416.5%Mobilenet Quant16.1%NASNet Mobile17.2%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: Mobilenet Float

OpenBenchmarking.org metrics for this test profile configuration based on 1,245 public results since 23 August 2020 with the latest data as of 6 December 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
# Compatible Public Results
Microseconds (Average)
100th
6
26373 +/- 319
99th
4
30239 +/- 164
99th
7
30864 +/- 1680
98th
4
31253 +/- 1808
96th
8
35720 +/- 3010
95th
23
36700 +/- 4138
95th
6
37060 +/- 4302
94th
7
38031 +/- 15
92nd
23
40639 +/- 3772
91st
19
41220 +/- 1948
90th
3
41928 +/- 2673
89th
5
43626 +/- 970
88th
19
43845 +/- 858
88th
6
44023 +/- 35
86th
4
46222 +/- 952
85th
8
46568 +/- 937
85th
14
47094 +/- 68
83rd
5
48273 +/- 248
82nd
8
49480 +/- 806
82nd
8
49885 +/- 1491
79th
11
51745 +/- 1143
79th
4
52454 +/- 3422
78th
4
53571 +/- 6659
77th
8
54643 +/- 356
77th
6
56780 +/- 573
76th
15
59021 +/- 1123
Mid-Tier
75th
> 59231
75th
8
59353 +/- 255
75th
4
59655 +/- 204
73rd
6
60767 +/- 691
73rd
7
60932 +/- 362
72nd
14
61909 +/- 508
70th
46
62766 +/- 375
68th
5
66439 +/- 191
67th
9
67787 +/- 1317
67th
5
67862 +/- 13
66th
16
68764 +/- 204
64th
5
75032 +/- 1437
63rd
13
80296 +/- 120
62nd
6
80523 +/- 41
60th
38
84037 +/- 489
59th
8
84336 +/- 321
58th
6
85525 +/- 329
57th
23
86653 +/- 2196
56th
3
88079 +/- 11608
54th
6
94350 +/- 489
53rd
10
95928 +/- 635
51st
15
110298 +/- 528
Median
50th
113607
49th
30
114708 +/- 824
47th
18
117988 +/- 7671
47th
6
118677 +/- 1771
47th
5
118729 +/- 288
46th
15
122656 +/- 1532
44th
8
126175 +/- 122
44th
6
126222 +/- 688
42nd
3
133607 +/- 316
42nd
15
136510 +/- 3620
41st
3
143919 +/- 21323
40th
7
150945 +/- 10381
40th
18
152652 +/- 2586
38th
4
155102 +/- 2980
38th
10
155469 +/- 4157
36th
14
160774 +/- 188
34th
8
172864 +/- 1248
34th
3
173700 +/- 426
34th
11
174192 +/- 8585
33rd
4
176202 +/- 1008
33rd
3
176511 +/- 79
31st
3
197030 +/- 65
31st
3
197077 +/- 165
30th
4
201338 +/- 1
30th
3
202429 +/- 647
30th
15
202470 +/- 130
28th
18
214587 +/- 9331
28th
3
214780 +/- 149
28th
3
216552 +/- 17
27th
3
219691 +/- 10
27th
12
222083 +/- 1630
Low-Tier
25th
> 233898
25th
13
237035 +/- 2325
25th
6
237630 +/- 3084
24th
9
246315 +/- 59
23rd
4
255295 +/- 2341
22nd
6
259599 +/- 21
22nd
6
260486 +/- 2756
22nd
3
261083 +/- 76
21st
3
269343 +/- 13
21st
11
271246 +/- 18112
21st
3
274477 +/- 655
20th
4
275611 +/- 5565
20th
4
275865 +/- 10078
20th
3
282718 +/- 739
19th
3
304775 +/- 42
19th
4
305678 +/- 566
18th
3
319383 +/- 66
18th
3
321558 +/- 18
18th
3
325212 +/- 398
18th
3
332759 +/- 2119
17th
3
338555 +/- 68
17th
3
339406 +/- 31
16th
4
351298 +/- 146
16th
3
365322 +/- 37
15th
4
366219 +/- 709
15th
3
369899 +/- 225
14th
40
370557 +/- 18477
11th
42
382951 +/- 2612
9th
3
387869 +/- 89
8th
4
394458 +/- 5452
8th
3
394492 +/- 119
7th
15
438597 +/- 17004
7th
3
444496 +/- 5547
6th
3
451547 +/- 222
5th
3
458252 +/- 4150
5th
5
464341 +/- 33449
5th
9
466068 +/- 33410
4th
7
498786 +/- 13013
3rd
3
623521 +/- 169
3rd
3
690680 +/- 318
3rd
3
777976 +/- 47
3rd
4
827989 +/- 261
2nd
5
899236 +/- 652
2nd
3
976603 +/- 27
1st
3
1011213 +/- 373
OpenBenchmarking.orgDistribution Of Public Results - Model: Mobilenet Float1230 Results Range From 25734 To 1610230 Microseconds2573457424891141208041524941841842158742475642792543109443426343743244060144377044693945010845327745644645961546278446595346912247229147546047862948179848496748813649130549447449764341008124103981410715041103194113488411665741198264122995412616441293334132502413567141388404142009414517841483474151516415468541578544161023460120180240300

Based on OpenBenchmarking.org data, the selected test / test configuration (TensorFlow Lite 2020-08-23 - Model: Mobilenet Float) has an average run-time of 4 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-Time3691215Min: 1 / Avg: 3 / Max: 11

Based on public OpenBenchmarking.org results, the selected test / test configuration has an average standard deviation of 0.3%.

OpenBenchmarking.orgPercent, Fewer Is BetterAverage Deviation Between RunsModel: Mobilenet FloatDeviation246810Min: 0 / Avg: 0.28 / Max: 4

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.

IntelAMDOpenBenchmarking.orgRelative Core Scaling To BaseTensorFlow Lite CPU Core ScalingModel: Mobilenet Float24681216243248643691215

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: 10 May 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

7 Systems - 213 Benchmark Results

AMD Ryzen 5 5500U - LENOVO LNVNB161216 - AMD Renoir

Ubuntu 21.10 - 5.13.0-22-generic - GNOME Shell 40.5

2 Systems - 474 Benchmark Results

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

Ubuntu 21.10 - 5.13.0-22-generic - GNOME Shell 40.5

2 Systems - 169 Benchmark Results

4 Systems - 359 Benchmark Results

AMD Ryzen 5 5500U - LENOVO LNVNB161216 - AMD Renoir

Ubuntu 21.10 - 5.13.0-22-generic - GNOME Shell 40.5

1 System - 474 Benchmark Results

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

Ubuntu 21.10 - 5.13.0-22-generic - GNOME Shell 40.5

1 System - 169 Benchmark Results

3 Systems - 494 Benchmark Results

AMD Ryzen 7 4700U - LENOVO LNVNB161216 - AMD Renoir

Ubuntu 21.10 - 5.13.0-22-generic - GNOME Shell 40.5

2 Systems - 484 Benchmark Results

AMD Ryzen 5 5500U - LENOVO LNVNB161216 - AMD Renoir

Ubuntu 21.10 - 5.13.0-22-generic - GNOME Shell 40.5

1 System - 502 Benchmark Results

AMD Ryzen 5 5500U - LENOVO LNVNB161216 - AMD Renoir

Ubuntu 21.10 - 5.13.0-22-generic - GNOME Shell 40.5

1 System - 6 Benchmark Results

Intel Core i7-9750H - MSI MS-17E2 - Intel Cannon Lake PCH

Ubuntu 20.04 - 5.4.0-89-generic - Xfce 4.14

2 Systems - 48 Benchmark Results

Intel Xeon Platinum 8375C - Amazon EC2 m6i.4xlarge - Intel 440FX 82441FX PMC

Amazon Linux 2 - 5.10.75-79.358.amzn2.x86_64 - 1.0.61

1 System - 4 Benchmark Results

Intel Core i5-7440HQ - Dell 00YYJC - Intel Xeon E3-1200 v6

Debian 10 - 5.14.5 - KDE Plasma 5.14.5

1 System - 6 Benchmark Results

Intel Core i5-7440HQ - Dell 00YYJC - Intel Xeon E3-1200 v6

Debian 10 - 5.14.5 - KDE Plasma 5.14.5

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 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 - 174 Benchmark Results

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

Fedora 32 - 5.6.6-300.fc32.x86_64 - GNOME Shell 3.36.1

8 Systems - 439 Benchmark Results

Intel Core i5-10600K - Gigabyte Z490 AORUS MASTER - Intel Comet Lake PCH

Ubuntu 21.04 - 5.12.0-051200rc3daily20210315-generic - GNOME Shell 3.38.3

12 Systems - 229 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

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

2 Systems - 78 Benchmark Results

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

openSUSE 15.2 - 5.3.18-lp152.63-default - KDE Plasma 5.18.6

3 Systems - 376 Benchmark Results

2 x AMD EPYC 7F72 24-Core - Supermicro H11DSi-NT v2.00 - AMD Starship

Ubuntu 20.10 - 5.11.0-051100rc4daily20210122-generic - GNOME Shell 3.38.1

3 Systems - 406 Benchmark Results

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

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

2 Systems - 81 Benchmark Results

2 x Intel Xeon Platinum 8280 - GIGABYTE MD61-SC2-00 v01000100 - Intel Sky Lake-E DMI3 Registers

Ubuntu 20.04 - 5.8.0-44-generic - GNOME Shell 3.36.4

2 Systems - 297 Benchmark Results

AMD Ryzen Threadripper 3990X 64-Core - System76 Thelio Major - AMD Starship

Pop 20.04 - 5.4.0-7642-generic - GNOME Shell 3.36.4

2 Systems - 95 Benchmark Results

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

Ubuntu 20.10 - 5.12.0-051200rc2-generic - GNOME Shell 3.38.1

3 Systems - 191 Benchmark Results

AMD Ryzen 3 2200G - ASUS PRIME B350M-E - AMD Raven

Ubuntu 20.10 - 5.8.0-38-generic - GNOME Shell 3.38.1

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

Find More Test Results