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

18 June 2021

Test Maintainer

Michael Larabel 

Test Type

System

Average Install Time

1 Minute, 3 Seconds

Average Run Time

1 Minute, 29 Seconds

Test Dependencies

CMake + C/C++ Compiler Toolchain

Accolades

5k+ Downloads

Supported Platforms


Public Result Uploads *Reported Installs **Reported Test Completions **Test Profile Page Views ***OpenBenchmarking.orgEventsTNN Popularity Statisticspts/tnn2020.092020.102020.112020.122021.012021.022021.032021.042021.052021.062021.072021.082021.092021.1010002000300040005000
* 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 17 October 2021.
MobileNet v225.3%SqueezeNet v1.124.9%DenseNet25.6%SqueezeNet v224.3%Model Option PopularityOpenBenchmarking.org

Revision History

pts/tnn-1.1.0   [View Source]   Fri, 18 Jun 2021 07:29:44 GMT
Update against TNN 0.3 upstream release.

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 0.3

Target: CPU - Model: DenseNet

OpenBenchmarking.org metrics for this test profile configuration based on 354 public results since 18 June 2021 with the latest data as of 16 October 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
ms (Average)
95th
34
2421 +/- 19
83rd
12
2602 +/- 31
83rd
5
2615 +/- 39
79th
11
2714 +/- 22
78th
6
2722 +/- 3
Mid-Tier
75th
> 2730
73rd
3
2814 +/- 52
71st
4
2836 +/- 5
70th
3
2868 +/- 15
70th
4
2871 +/- 243
65th
16
2984 +/- 94
62nd
3
3005 +/- 13
58th
6
3058 +/- 1
54th
3
3137 +/- 14
53rd
4
3152 +/- 6
52nd
4
3277 +/- 19
Median
50th
3321
49th
3
3380 +/- 15
46th
11
3455 +/- 24
44th
3
3475 +/- 12
44th
8
3490 +/- 35
37th
3
3674 +/- 4
36th
3
3728 +/- 9
34th
3
3793 +/- 3
31st
3
3956 +/- 1
30th
3
4026 +/- 9
28th
6
4081 +/- 12
Low-Tier
25th
> 4207
25th
3
4253 +/- 142
25th
3
4255 +/- 36
25th
3
4257 +/- 5
24th
7
4264 +/- 182
23rd
3
4290 +/- 7
19th
3
4463 +/- 117
18th
4
4467 +/- 26
17th
3
4523 +/- 5
16th
4
4544 +/- 24
15th
3
4565 +/- 5
13th
3
4738 +/- 8
12th
3
4873 +/- 44
12th
3
4878 +/- 1
10th
3
4999 +/- 7
9th
4
5056 +/- 96
9th
5
5280 +/- 195
7th
3
5822 +/- 11
6th
3
6188 +/- 41
3rd
4
8548 +/- 10
1st
4
21542 +/- 42
OpenBenchmarking.orgDistribution Of Public Results - Target: CPU - Model: DenseNet354 Results Range From 2347 To 129572 ms2347489274379982125271507217617201622270725252277973034232887354323797740522430674561248157507025324755792583376088263427659726851771062736077615278697812428378786332888779142293967965129905710160210414710669210923711178211432711687211941712196212450712705212959770140210280350

Based on OpenBenchmarking.org data, the selected test / test configuration (TNN 0.3 - Target: CPU - Model: DenseNet) has an average run-time of 11 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: DenseNetRun-Time1020304050Min: 3 / Avg: 10.7 / Max: 52

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 BaseTNN CPU Core ScalingTarget: CPU - Model: DenseNet2468162432640.43960.87921.31881.75842.198

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

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

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

 
VFMADD231SS VFMADD132SS VFNMADD132SS VFMADD213SS VFNMADD132PD VFMADD132PD VFNMADD132SD VFMADD132SD VFNMADD132PS VFMADD132PS VFMADD213PS VFMADD231PS VFNMADD231SD VFMADD231PD VFMADD231SD VFMSUB213SS VFMSUB231SD VFNMSUB231SD VFNMSUB132SD VFMADD213SD
The test / benchmark does honor compiler flag changes.
Last automated analysis: 10 May 2021

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

Recent Test Results

OpenBenchmarking.org Results Compare

8 Systems - 364 Benchmark Results

2 x AMD EPYC 7742 64-Core - Supermicro H11DSi-NT v2.00 - AMD Starship

Ubuntu 21.10 - 5.13.0-19-generic - GNOME Shell 40.5

1 System - 495 Benchmark Results

AMD EPYC 75F3 32-Core - ASRockRack ROME2D16-2T - AMD Starship

Ubuntu 21.10 - 5.13.0-19-generic - GNOME Shell 40.5

3 Systems - 326 Benchmark Results

AMD EPYC 7742 64-Core - Supermicro H11DSi-NT v2.00 - AMD Starship

Ubuntu 21.10 - 5.13.0-19-generic - GNOME Shell 40.5

4 Systems - 318 Benchmark Results

AMD EPYC 7F52 16-Core - Supermicro H11DSi-NT v2.00 - AMD Starship

Ubuntu 21.10 - 5.13.0-19-generic - GNOME Shell 40.5

3 Systems - 210 Benchmark Results

AMD EPYC 74F3 24-Core - ASRockRack ROME2D16-2T - AMD Starship

Ubuntu 21.04 - 5.11.0-37-generic - X Server

3 Systems - 185 Benchmark Results

2 x AMD EPYC 7601 32-Core - Dell 02MJ3T - AMD 17h

Ubuntu 19.10 - 5.9.0-050900rc6daily20200922-generic - GNOME Shell 3.34.1

2 Systems - 149 Benchmark Results

AMD Ryzen 5 3600XT 6-Core - MSI X470 GAMING M7 AC - AMD Starship

Ubuntu 20.10 - 5.8.0-55-generic - GNOME Shell 3.38.1

3 Systems - 126 Benchmark Results

AMD Ryzen 3 3300X 4-Core - MSI B350M GAMING PRO - AMD Starship

Ubuntu 20.04 - 5.9.0-rc5-14sep-patch - GNOME Shell 3.36.4

8 Systems - 111 Benchmark Results

2 x Intel Xeon Platinum 8380 - Intel M50CYP2SB2U - Intel Device 0998

CentOS Stream 8 - 4.18.0-338.el8.x86_64 - GNOME Shell 3.32.2

7 Systems - 110 Benchmark Results

2 x Intel Xeon Platinum 8380 - Intel M50CYP2SB2U - Intel Device 0998

Arch Linux - 5.14.9-arch2-1 - GCC 11.1.0

6 Systems - 186 Benchmark Results

2 x Intel Xeon Platinum 8380 - Intel M50CYP2SB2U - Intel Device 0998

Arch Linux - 5.14.9-arch2-1 - GCC 11.1.0

1 System - 130 Benchmark Results

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

Ubuntu 21.04 - 5.11.0-37-generic - GNOME Shell 3.38.4

5 Systems - 186 Benchmark Results

2 x Intel Xeon Platinum 8380 - Intel M50CYP2SB2U - Intel Device 0998

Debian 11 - 5.10.0-8-amd64 - 1.0.2

4 Systems - 186 Benchmark Results

2 x Intel Xeon Platinum 8380 - Intel M50CYP2SB2U - Intel Device 0998

Ubuntu 21.10 - 5.13.0-16-generic - GNOME Shell 40.5

Most Popular Test Results

OpenBenchmarking.org Results Compare

4 Systems - 42 Benchmark Results

AMD Ryzen 9 5950X 16-Core - 32GB - 466GB

Ubuntu 20.04 - 4.4.0-19041-Microsoft - GCC 9.3.0

2 Systems - 354 Benchmark Results

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

Pop 20.04 - 5.11.0-7620-generic - GNOME Shell 3.36.7

4 Systems - 78 Benchmark Results

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

Fedora 34 - 5.13.4-200.fc34.x86_64 - GNOME Shell 40.3

2 Systems - 75 Benchmark Results

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

Arch Linux - 5.13.4-arch1-1 - GNOME Shell 40.3

3 Systems - 78 Benchmark Results

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

Clear Linux OS 34860 - 5.12.16-1054.native - GNOME Shell 40.3

2 Systems - 115 Benchmark Results

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

Ubuntu 21.04 - 5.11.0-31-generic - GNOME Shell 3.38.4

3 Systems - 34 Benchmark Results

Intel Xeon E-2288G - Compulab SBC-ATCFL v1.2 - Intel Cannon Lake PCH

Ubuntu 20.10 - 5.8.0-41-generic - GNOME Shell 3.38.2

3 Systems - 89 Benchmark Results

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

Ubuntu 20.04 - 5.9.0-050900daily20201012-generic - GNOME Shell 3.36.4

3 Systems - 41 Benchmark Results

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

Ubuntu 21.04 - 5.11.0-17-generic - GNOME Shell 3.38.4

3 Systems - 45 Benchmark Results

AMD Ryzen Threadripper 3970X 32-Core - ASUS ROG ZENITH II EXTREME - AMD Starship

Ubuntu 20.10 - 5.11.0-rc6-phx - GNOME Shell 3.38.1

2 Systems - 237 Benchmark Results

AMD Ryzen 7 5700G - ASUS TUF GAMING B550M-PLUS - AMD Renoir Root Complex

Ubuntu 21.04 - 5.11.0-25-generic - GNOME Shell 3.38.4

3 Systems - 24 Benchmark Results

2 x Intel Xeon Platinum 8259CL - Amazon EC2 m5.24xlarge - Intel 440FX 82441FX PMC

Ubuntu 20.04 - 5.4.0-1045-aws - 1.0.2

2 Systems - 69 Benchmark Results

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

Fedora 34 - 5.12.9-300.fc34.x86_64 - GNOME Shell 40.1

3 Systems - 100 Benchmark Results

Intel Core i7-3770K - ECS Z77H2-A2X v1.0 - Intel Xeon E3-1200 v2

Ubuntu 20.04 - 5.8.0-55-generic - GNOME Shell 3.36.9

Find More Test Results