TNN

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

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

Project Site

github.com

Test Created

24 September 2020

Last Updated

11 January 2021

Test Maintainer

Michael Larabel 

Test Type

System

Average Install Time

39 Seconds

Average Run Time

1 Minute, 25 Seconds

Test Dependencies

CMake + C/C++ Compiler Toolchain

Supported Platforms


Public Result UploadsReported Installs*Test Completions*OpenBenchmarking.orgEventsTNN Popularity Statisticspts/tnn2020.092020.102020.112020.122021.012021.022021.032021.04400800120016002000
* 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, 09 Apr 2021 23:06:00 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 1,050 public results since 24 September 2020 with the latest data as of 10 April 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)
82nd
14
255 +/- 4
79th
9
260 +/- 6
Mid-Tier
75th
> 265
75th
6
265 +/- 1
74th
4
270 +/- 4
71st
29
274 +/- 4
70th
10
275 +/- 4
69th
10
279 +/- 4
68th
3
280 +/- 1
66th
6
282 +/- 1
65th
10
283 +/- 3
63rd
5
286 +/- 2
63rd
7
286 +/- 7
63rd
7
287 +/- 2
60th
6
291 +/- 1
58th
5
293 +/- 1
58th
6
294 +/- 2
57th
10
295 +/- 9
57th
13
296 +/- 3
56th
13
297 +/- 10
55th
11
298 +/- 3
54th
7
299 +/- 1
51st
4
302 +/- 14
51st
6
302 +/- 1
51st
6
302 +/- 2
Median
50th
304
49th
8
306 +/- 3
48th
6
311 +/- 3
48th
6
312 +/- 2
45th
6
319 +/- 3
45th
7
320 +/- 3
43rd
9
323 +/- 2
41st
5
325 +/- 5
40th
6
326 +/- 1
40th
12
327 +/- 5
39th
6
331 +/- 1
35th
6
334 +/- 5
35th
6
335 +/- 6
35th
6
335 +/- 8
34th
6
336 +/- 3
33rd
5
338 +/- 3
33rd
4
338 +/- 6
32nd
12
339 +/- 4
32nd
6
339 +/- 1
31st
6
340 +/- 1
29th
6
341 +/- 1
28th
6
342 +/- 1
28th
6
345 +/- 27
26th
11
349 +/- 12
Low-Tier
25th
> 351
25th
5
351 +/- 8
21st
6
357 +/- 1
21st
8
358 +/- 4
20th
8
361 +/- 3
19th
6
362 +/- 1
19th
9
362 +/- 7
19th
10
363 +/- 15
17th
7
366 +/- 4
17th
6
366 +/- 4
16th
4
367 +/- 5
15th
13
368 +/- 2
14th
6
369 +/- 3
14th
6
369 +/- 1
12th
6
370 +/- 2
11th
3
375 +/- 1
10th
6
378 +/- 3
9th
6
386 +/- 47
7th
6
424 +/- 4
4th
3
560 +/- 2
4th
4
613 +/- 3
1st
10
1445 +/- 136
OpenBenchmarking.orgDistribution Of Public Results - Target: CPU - Model: MobileNet v21050 Results Range From 206 To 3985 ms2062823584345105866627388148909661042111811941270134614221498157416501726180218781954203021062182225823342410248625622638271427902866294230183094317032463322339834743550362637023778385439304006100200300400500

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: 1.09 / Max: 4

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: 0.13 / Max: 1

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.

AMDIntelOpenBenchmarking.orgRelative Core Scaling To BaseTNN CPU Core ScalingTarget: CPU - Model: MobileNet v24681216243248640.44380.88761.33141.77522.219

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.
 
PUNPCKLQDQ MOVDQA MOVDQU PSRLDQ CVTSS2SD MOVD CVTSI2SD ANDPD COMISD MOVAPD UNPCKLPD CVTPD2PS UCOMISD ADDSD PSHUFD PMULUDQ CVTSD2SS CVTDQ2PS DIVSD CVTTSD2SI MOVUPD MAXSD XORPD SUBSD CVTDQ2PD CVTPS2PD MULSD SUBPD ADDPD DIVPD SQRTSD MULPD CVTTPS2DQ UNPCKHPD SHUFPD MOVHPD MOVLPD CMPLEPD ANDNPD ORPD CVTTPD2DQ
Requires passing a supported compiler/build flag (verified with targets: sandybridge, skylake, tigerlake, cascadelake, sapphirerapids, alderlake, znver2, znver3).
Found on Intel processors since Sandy Bridge (2011).
Found on AMD processors since Bulldozer (2011).

 
VZEROUPPER VEXTRACTF128 VINSERTF128 VPERMILPS VPERM2F128 VBROADCASTSS VMASKMOVPS VBROADCASTSD
Requires passing a supported compiler/build flag (verified with targets: skylake, tigerlake, cascadelake, sapphirerapids, alderlake, znver2, znver3).
Found on Intel processors since Haswell (2013).
Found on AMD processors since Excavator (2016).

 
VEXTRACTI128 VPERMD VPBROADCASTD VPERMQ VINSERTI128 VPBROADCASTW VPERM2I128 VPBROADCASTQ VPBROADCASTB
FMA (FMA)
Requires passing a supported compiler/build flag (verified with targets: skylake, tigerlake, cascadelake, sapphirerapids, alderlake, znver2, znver3).
Found on Intel processors since Haswell (2013).
Found on AMD processors since Bulldozer (2011).

 
VFMADD132PS VFNMADD132SS VFMADD231SS VFNMADD132PS VFMADD132SS VFMADD132PD VFNMADD132PD VFMADD213PS VFMADD213SS VFMADD231PS VFNMADD231SD VFNMADD132SD VFMADD231PD VFMADD132SD VFMSUB132SS VFMSUB231SD VFNMSUB231SD VFNMSUB132SD VFMADD213SD
The test / benchmark does honor compiler flag changes.
Last automated analysis: 31 January 2021

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

Recent Test Results

OpenBenchmarking.org Results Compare

9 Systems - 442 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

1 System - 92 Benchmark Results

AMD Ryzen 5 5600X 6-Core - ASRock X570 Phantom Gaming-ITX/TB3 - AMD Device 1480

Ubuntu 18.04 - 5.4.0-70-generic - GNOME Shell 3.28.4

1 System - 323 Benchmark Results

Intel Core i9-11900K - ASUS ROG MAXIMUS XIII HERO - Intel Tiger Lake-H

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

8 Systems - 439 Benchmark Results

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

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

2 Systems - 95 Benchmark Results

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

Ubuntu 21.04 - 5.11.0-11-generic - GNOME Shell 3.38.3

1 System - 94 Benchmark Results

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

Clear Linux OS 34420 - 5.10.19-1032.native - GNOME Shell 3.38.4

26 Systems - 62 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

26 Systems - 62 Benchmark Results

AMD Ryzen 5 5600X 6-Core - ASUS TUF GAMING X570-PLUS - AMD Starship

Arch rolling - 5.11.6-138-tkg-cfs - X Server 1.20.10

25 Systems - 62 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

24 Systems - 62 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

2 Systems - 255 Benchmark Results

AMD EPYC 75F3 32-Core - AMD DAYTONA_X - AMD Starship

Ubuntu 20.04 - 5.11.6-051106-generic - GNOME Shell 3.36.4

1 System - 255 Benchmark Results

2 x AMD EPYC 7763 64-Core - AMD DAYTONA_X - AMD Starship

Ubuntu 20.04 - 5.11.6-051106-generic - GNOME Shell 3.36.4

Most Popular Test Results

Find More Test Results