TNN

TNN is an open-source deep learning reasoning framework developed by Tencent.

Learn more about this test at the upstream project site: https://github.com/Tencent/TNN.

This scientific test profile is maintained by Michael Larabel. This OpenBenchmarking.org test profile was created on 24 September 2020 and last updated on 11 January 2021. To run this test with the Phoronix Test Suite, the basic command is: phoronix-test-suite benchmark tnn.

This test has an average install time of 40 seconds and an average run-time of 1 minute, 25 seconds.

Recently Updated Test Profile

Public Result UploadsReported Installs*Test Completions*OpenBenchmarking.orgEventsTNN Popularity Statisticspts/tnn2020.092020.102020.112020.122021.01400800120016002000

* 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 Sat, 16 Jan 2021 21:19:02 GMT.

SqueezeNet v1.150.0%MobileNet v250.0%Model Option PopularityOpenBenchmarking.org

Revision History

pts/tnn-1.0.1   [View Source]   Mon, 11 Jan 2021 13:15:50 GMT
Update download mirror as the GitHub URL changed its checksums...

pts/tnn-1.0.0   [View Source]   Thu, 24 Sep 2020 18:33:29 GMT
Initial commit of Tencent TNN framework.

Suites Using This Test

Machine Learning

HPC - High Performance Computing


Performance Metrics

Analyze Test Configuration:

TNN 0.2.3

Target: CPU - Model: MobileNet v2

OpenBenchmarking.org metrics for this test profile configuration based on 741 public results since 24 September 2020 with the latest data as of 16 January 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
ms (Average)
80th
7
259 +/- 1
77th
3
265 +/- 1
Mid-Tier
75th
> 268
70th
25
275 +/- 4
68th
9
278 +/- 3
66th
6
282 +/- 1
65th
9
283 +/- 3
62nd
5
286 +/- 2
62nd
3
287 +/- 3
60th
3
290 +/- 1
60th
6
291 +/- 10
58th
5
293 +/- 1
58th
6
294 +/- 2
55th
10
297 +/- 2
55th
13
297 +/- 10
54th
11
298 +/- 3
53rd
4
299 +/- 2
Median
50th
302
50th
3
302 +/- 1
50th
3
303 +/- 2
49th
3
305 +/- 14
48th
8
306 +/- 3
46th
3
313 +/- 1
45th
3
317 +/- 2
44th
18
319 +/- 56
44th
7
320 +/- 3
42nd
6
324 +/- 2
39th
3
326 +/- 1
39th
6
326 +/- 1
37th
3
331 +/- 1
32nd
6
336 +/- 3
30th
9
337 +/- 1
30th
5
338 +/- 3
29th
3
339 +/- 1
Low-Tier
25th
> 342
25th
3
344 +/- 1
25th
6
345 +/- 27
24th
7
346 +/- 10
22nd
4
354 +/- 3
17th
8
363 +/- 7
17th
10
363 +/- 15
15th
4
367 +/- 5
15th
3
368 +/- 4
13th
6
369 +/- 2
11th
3
375 +/- 1
10th
6
378 +/- 3
6th
3
424 +/- 6
5th
3
560 +/- 2
4th
4
613 +/- 3
1st
7
1475 +/- 155
OpenBenchmarking.orgDistribution Of Public Results - Target: CPU - Model: MobileNet v2741 Results Range From 210 To 3985 ms210286362438514590666742818894970104611221198127413501426150215781654173018061882195820342110218622622338241424902566264227182794287029463022309831743250332634023478355436303706378238583934401070140210280350

Based on OpenBenchmarking.org data, the selected test / test configuration (TNN 0.2.3 - Target: CPU - Model: MobileNet v2) has an average run-time of 2 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 BenchmarkTarget: CPU - Model: MobileNet v2Run-Time246810Min: 1 / Avg: 1.1 / Max: 5

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 RunsTarget: CPU - Model: MobileNet v2Deviation246810Min: 0 / Avg: 0.14 / Max: 1

Recent Test Results

Compare

1 System - 2 Benchmark Results

AMD Ryzen 9 5900X 12-Core - ASRock B550M Pro4 - AMD Starship

Clear Linux OS 34170 - 5.10.7-1014.native - GNOME Shell 3.38.2

3 Systems - 125 Benchmark Results

AMD Ryzen 9 5950X 16-Core - ASUS ROG CROSSHAIR VIII HERO - AMD Starship

Ubuntu 20.10 - 5.11.0-051100rc2daily20210108-generic - GNOME Shell 3.38.1

3 Systems - 16 Benchmark Results

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

Ubuntu 20.10 - 5.8.0-36-generic - GNOME Shell 3.38.1

4 Systems - 91 Benchmark Results

AMD Ryzen 5 5600X 6-Core - ASUS TUF GAMING B550M-PLUS - AMD Starship

Ubuntu 20.10 - 5.10.4-051004-generic - GNOME Shell 3.38.1

4 Systems - 19 Benchmark Results

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

Ubuntu 20.10 - 5.11.0-rc2-phx - GNOME Shell 3.38.1

4 Systems - 24 Benchmark Results

Intel Core i5-8400 - MSI Z370M MORTAR - Intel 8th Gen Core

Ubuntu 20.04 - 5.9.0-050900rc7daily20200929-generic - GNOME Shell 3.36.4

4 Systems - 104 Benchmark Results

AMD Ryzen 5 2400G - MSI B350M GAMING PRO - AMD Raven

Ubuntu 19.10 - 5.3.0-64-generic - GNOME Shell 3.34.1

3 Systems - 18 Benchmark Results

Intel Core i9-10980XE - ASRock X299 Steel Legend - Intel Sky Lake-E DMI3 Registers

Ubuntu 20.04 - 5.11.0-rc2-phx - GNOME Shell 3.36.4

4 Systems - 22 Benchmark Results

AMD Ryzen 7 3700X 8-Core - Gigabyte A320M-S2H-CF - AMD Starship

Ubuntu 20.04 - 5.8.1-050801-generic - GNOME Shell 3.36.4

3 Systems - 17 Benchmark Results

AMD Ryzen 7 5800X 8-Core - ASRock X570 Pro4 - AMD Starship

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

3 Systems - 24 Benchmark Results

AMD Ryzen 9 5950X 16-Core - ASUS ROG CROSSHAIR VIII HERO - AMD Starship

Ubuntu 20.10 - 5.11.0-051100rc2daily20210108-generic - GNOME Shell 3.38.1

3 Systems - 36 Benchmark Results

Intel Core i5-6500 - Gigabyte Z170M-D3H-CF - Intel Xeon E3-1200 v5

Ubuntu 20.04 - 5.9.0-050900rc7daily20200929-generic - GNOME Shell 3.36.4

Most Popular Test Results

Find More Test Results


User Comments

Post A Comment