Mobile Neural Network

MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. This MNN test profile is building the OpenMP / CPU threaded version for processor benchmarking and not any GPU-accelerated test. MNN does allow making use of AVX-512 extensions.

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

Project Site

mnn.zone

Source Repository

github.com

Test Created

17 September 2020

Last Updated

31 August 2022

Test Maintainer

Michael Larabel

Test Type

System

Average Install Time

1 Minute, 43 Seconds

Average Run Time

8 Minutes, 24 Seconds

Test Dependencies

CMake + C/C++ Compiler Toolchain

Accolades

30k+ Downloads

Supported Platforms

Revision History

pts/mnn-2.1.0 [View Source] Wed, 31 Aug 2022 10:53:57 GMT
Update against MNN 2.1 upstream.

pts/mnn-2.0.0 [View Source] Sat, 13 Aug 2022 09:41:19 GMT
Update against MNN 2.0 upstream.

pts/mnn-1.3.0 [View Source] Fri, 18 Jun 2021 06:27:34 GMT
Update against new upstream MNN 1.2.0 release.

pts/mnn-1.2.0 [View Source] Fri, 12 Mar 2021 07:05:09 GMT
Update against upstream MNN 1.1.3.

pts/mnn-1.1.1 [View Source] Tue, 12 Jan 2021 16:25:37 GMT
Test builds fine on macOS.

pts/mnn-1.1.0 [View Source] Wed, 06 Jan 2021 12:46:43 GMT
Update against MNN 1.1.1 upstream.

pts/mnn-1.0.1 [View Source] Thu, 17 Sep 2020 20:25:29 GMT
Add min/max reporting to result parser.

pts/mnn-1.0.0 [View Source] Thu, 17 Sep 2020 18:57:32 GMT
Initial commit of Alibaba MNN deep learning framework benchmark.

Suites Using This Test

Machine Learning

HPC - High Performance Computing

Performance Metrics

Analyze Test Configuration:

Mobile Neural Network 2.1

Model: SqueezeNetV1.0

OpenBenchmarking.org metrics for this test profile configuration based on 314 public results since 31 August 2022 with the latest data as of 30 May 2023.

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)

AMD Ryzen 7 7700X 8-Core

99th

2.4 ^{+/- 0.2}

AMD Ryzen 7 7700 8-Core

98th

2.5 ^{+/- 0.1}

AMD Ryzen 5 7600 6-Core

98th

2.5 ^{+/- 0.1}

Intel Core i9-11900K

93rd

3.3 ^{+/- 0.4}

2 x Intel Xeon Platinum 8362

89th

3.6

AMD Ryzen 9 7900X 12-Core

89th

3.7 ^{+/- 0.1}

Intel Xeon Platinum 8380

86th

3.7

AMD Ryzen 9 7950X 16-Core

86th

3.7 ^{+/- 0.1}

Intel Xeon Gold 6342

86th

3.7 ^{+/- 0.2}

Intel Core i5-12400

82nd

3.8

AMD Ryzen 9 7900 12-Core

80th

3.8 ^{+/- 0.1}

2 x Intel Xeon Gold 6342

78th

3.9 ^{+/- 0.2}

AMD Ryzen 7 5800X 8-Core

77th

4.0 ^{+/- 0.1}

2 x Intel Xeon Platinum 8380

76th

4.0 ^{+/- 0.3}

Mid-Tier

75th

> 4.0

AMD Ryzen 7 5800X3D 8-Core

75th

4.0

Intel Core i9-12900K

75th

4.0 ^{+/- 0.3}

Intel Core i9-10900K

68th

4.3

2 x Intel Xeon Gold 6346

64th

4.5 ^{+/- 0.1}

AMD Ryzen 9 5900HX

64th

4.5 ^{+/- 0.1}

Intel Xeon Gold 6346

63rd

4.6 ^{+/- 0.2}

Intel Core i5-12600K

62nd

4.7 ^{+/- 0.5}

AMD Ryzen 7 5700G

60th

4.8 ^{+/- 0.2}

Intel Core i7-8700K

60th

4.9

Intel Core i9-10980XE

60th

4.9 ^{+/- 0.3}

Intel Xeon Gold 6226R

58th

4.9

Intel Core i9-13900K

54th

5.2

AMD Ryzen 9 5950X 16-Core

53rd

5.2 ^{+/- 0.1}

AMD Ryzen Threadripper 3970X 32-Core

51st

5.3 ^{+/- 0.1}

Median

50th

5.4

Intel Core i7-1165G7

50th

5.5 ^{+/- 0.6}

Intel Xeon E3-1275 v6

47th

5.8

Intel Core i7-1185G7

45th

6.0

2 x Intel Xeon Platinum 8280

45th

6.0 ^{+/- 0.3}

AMD Ryzen 9 3950X 16-Core

44th

6.0 ^{+/- 0.8}

AMD Ryzen Threadripper PRO 5965WX 24-Cores

44th

6.1 ^{+/- 0.2}

AMD Ryzen 7 PRO 5850U

42nd

6.3 ^{+/- 0.1}

AMD Ryzen Threadripper 3990X 64-Core

39th

6.4 ^{+/- 0.1}

Intel Xeon E3-1280 v5

39th

6.5 ^{+/- 0.2}

AMD Ryzen Threadripper 3960X 24-Core

37th

6.5

AMD Ryzen 9 3900XT 12-Core

36th

6.6 ^{+/- 0.7}

AMD Ryzen 7 PRO 6850U

34th

6.7 ^{+/- 0.3}

Intel Core i7-5960X

33rd

6.7 ^{+/- 0.3}

AMD Ryzen 5 4500U

33rd

6.8 ^{+/- 0.1}

AMD Ryzen 5 5500U

31st

6.8 ^{+/- 0.2}

AMD Ryzen 9 3900X 12-Core

30th

6.9 ^{+/- 0.1}

Apple M1

27th

7.2 ^{+/- 0.2}

Low-Tier

25th

> 7.4

2 x Intel Xeon Gold 5220R

24th

7.6

Intel Xeon E5-2609 v4

22nd

7.6

Apple M2

20th

8.3 ^{+/- 0.7}

Intel Xeon Silver 4216

20th

8.6

2 x AMD EPYC 7713 64-Core

19th

8.6 ^{+/- 0.5}

2 x AMD EPYC 9654 96-Core

18th

8.9 ^{+/- 0.3}

Intel Core i7-10700T

17th

9.1 ^{+/- 0.1}

AMD EPYC 7F32 8-Core

15th

9.6 ^{+/- 0.7}

AMD Ryzen 7 4700U

14th

10.0 ^{+/- 0.1}

AMD Ryzen 7 4800U

12th

10.4 ^{+/- 0.2}

Intel Core i7-1280P

12th

10.5 ^{+/- 0.2}

Intel Core i7-8565U

10th

11.0 ^{+/- 0.2}

AMD Ryzen Threadripper 2950X 16-Core

9th

11.8 ^{+/- 0.5}

2 x AMD EPYC 7601 32-Core

7th

15.3 ^{+/- 0.4}

AMD Ryzen 3 3200U

5th

23.1 ^{+/- 0.3}

Rockchip ARMv8 Cortex-A76 4-Core

4th

35.2 ^{+/- 5.3}

ARMv8 Cortex-A72 4-Core

2nd

60.4 ^{+/- 1.2}

Based on OpenBenchmarking.org data, the selected test / test configuration (Mobile Neural Network 2.1 - Model: SqueezeNetV1.0) has an average run-time of 19 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.

Based on public OpenBenchmarking.org results, the selected test / test configuration has an average standard deviation of 0.5%.

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.

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.

CVTSS2SD MOVAPD CVTSD2SS MOVDQU PUNPCKLQDQ MOVDQA CVTSI2SD ADDSD MULSD MOVD CVTDQ2PS ANDPD COMISD CVTTSD2SI CMPNLESD SUBSD PSHUFD PMULUDQ PSRLDQ CVTTPS2DQ PADDQ CVTDQ2PD CMPLTPD ADDPD CVTPS2PD UNPCKLPD MOVUPD MAXPD UNPCKHPD MAXSD DIVSD SHUFPD ORPD XORPD PSHUFLW DIVPD CVTPD2PS ANDNPD SQRTSD CVTPS2DQ

SSE3 (SSE3)

Used by default on supported hardware.

MOVSLDUP MOVSHDUP HADDPS

SSSE3 (SSSE3)

Used by default on supported hardware.

PSHUFB PALIGNR PHADDD

Advanced Vector Extensions (AVX)

Used by default on supported hardware.
Found on Intel processors since Sandy Bridge (2011).
Found on AMD processors since Bulldozer (2011).

VBROADCASTSS VEXTRACTF128 VZEROUPPER VZEROALL VPERM2F128 VINSERTF128 VBROADCASTF128 VPERMILPS VMASKMOVPS VBROADCASTSD

Advanced Vector Extensions 2 (AVX2)

Used by default on supported hardware.
Found on Intel processors since Haswell (2013).
Found on AMD processors since Excavator (2016).

VINSERTI128 VPBROADCASTD VPERMQ VPBROADCASTQ VEXTRACTI128 VPERM2I128 VPBROADCASTB VGATHERQPS VPGATHERQD VPERMD VPMASKMOVD VPBROADCASTW VPGATHERQQ

FMA (FMA)

Used by default on supported hardware.
Found on Intel processors since Haswell (2013).
Found on AMD processors since Bulldozer (2011).

VFMADD231PS VFMADD231SS VFMADD132SS VFMADD132PS VFNMADD231SS VFMADD231SD VFMADD132SD VFMSUB132SS VFNMADD132SS VFMSUB231SS VFMSUB132SD VFMADD213SS VFMSUB231SD VFNMADD213PS VFNMADD132PS VFNMADD213SS VFMADD213PS VFNMADD132SD VFMSUB132PS VFMADD213SD VFNMADD231PS VFMSUB213PS

Advanced Vector Extensions 512 (AVX512)

Requires passing a supported compiler/build flag (verified with targets: tigerlake, cascadelake, sapphirerapids).

(ZMM REGISTER USE)

The test / benchmark does honor compiler flag changes.

Last automated analysis: 17 January 2022

This test profile binary relies on the shared libraries libMNN.so, libc.so.6, libm.so.6, libmvec.so.1.

Tested CPU Architectures

This benchmark has been successfully tested on the below mentioned architectures. The CPU architectures listed is where successful OpenBenchmarking.org result uploads occurred, namely for helping to determine if a given test is compatible with various alternative CPU architectures.

CPU Architecture

Kernel Identifier

Verified On

Intel / AMD x86 64-bit

x86_64

(Many Processors)

ARMv8 64-bit

arm64

Apple M1

ARMv8 64-bit

aarch64

ARMv8 Cortex-A72 4-Core, ARMv8 Neoverse-N1 128-Core, Apple, Apple M1, Apple M2, Rockchip ARMv8 Cortex-A76 4-Core

ML 1 System - 253 Benchmark Results	Intel Core i7-12700H - Intel NUC12SNKi72 - Intel Alder Lake PCH Ubuntu 22.04 - 5.19.0-42-generic - GNOME Shell 42.5
Raspberry Pi 400 vs. Orange Pi 5 Benchmarks 5 Systems - 286 Benchmark Results	Rockchip ARMv8 Cortex-A76 - Orange Pi 5 - 8GB Ubuntu 22.04 - 5.10.110-rockchip-rk3588 - Xfce 4.16
mnn-i9-12900 1 System - 8 Benchmark Results	Intel Core i9-12900 - MSI PRO Z690-A - Intel Alder Lake-S PCH Clear Linux OS 38750 - 6.2.10-1295.native - GNOME Shell 44.0
Raspberry Pi 400 vs. Orange Pi 5 Benchmarks 4 Systems - 286 Benchmark Results	Rockchip ARMv8 Cortex-A76 - Orange Pi 5 - 8GB Ubuntu 22.04 - 5.10.110-rockchip-rk3588 - Xfce 4.16
Raspberry Pi 400 vs. Orange Pi 5 Benchmarks 3 Systems - 286 Benchmark Results	Rockchip ARMv8 Cortex-A76 - Orange Pi 5 - 8GB Ubuntu 22.04 - 5.10.110-rockchip-rk3588 - Xfce 4.16
pts-machine-learning 1 System - 187 Benchmark Results	2 x Intel Xeon Gold 6330 - Supermicro X12DPG-QT6 v1.00 - Intel Ice Lake IEH AlmaLinux 8.7 - 4.18.0-425.13.1.el8_7.x86_64 - X Server
RPi 2023 1 System - 222 Benchmark Results	ARMv8 Cortex-A72 - BCM2835 Raspberry Pi 400 Rev 1.0 - Broadcom BCM2711 Debian 11 - 5.15.84-v8+ - LXDE
RPi 2023 1 System - 202 Benchmark Results	ARMv8 Cortex-A72 - BCM2835 Raspberry Pi 400 Rev 1.0 - Broadcom BCM2711 Debian 11 - 5.15.84-v8+ - LXDE
ml_results 1 System - 219 Benchmark Results	AMD Ryzen 9 6900HS - ASUS GA402RJ v1.0 - AMD 17h-19h PCIe Root Complex Ubuntu 22.04 - 5.19.0-35-generic - GNOME Shell 42.5
Ryzen 9 5900X / Ryzen 9 5950X Linux Performance 13 Systems - 228 Benchmark Results	AMD Ryzen 9 5900X 12-Core - ASUS ROG CROSSHAIR VIII HERO - AMD Starship Ubuntu 20.04 - 5.9.0-050900-generic - GNOME Shell 3.36.4
sk3tchy-creator-tst 1 System - 182 Benchmark Results	2 x Intel Core i9-9900K - Intel 440BX - Intel 440BX Debian 11 - 5.10.0-21-amd64 - 1.0.2
2023-02-25-0937 1 System - 211 Benchmark Results	AMD Ryzen Threadripper PRO 3955WX 16-Cores - ASUS Pro WS WRX80E-SAGE SE WIFI - AMD Starship Ubuntu 20.04.4 LTS - 6.2.0-1275.native - OpenCL 2.1 AMD-APP
2023-02-23-1703 1 System - 10 Benchmark Results	Unknown - HPE C01_APACHE_MB - 128GB Ubuntu 22.04.1 LTS - 5.4.0-137-generic - GCC 11.2.0
2023-02-23-1455 1 System - 10 Benchmark Results	2 x AMD EPYC 7451 24-Core - Supermicro H11DSU-iN - 128GB Ubuntu 22.04.1 LTS - 5.4.0-139-generic - GCC 11.2.0
2023-02-23-1308 1 System - 10 Benchmark Results	2 x Intel Xeon Gold 6148 - Supermicro X11DDW-L v1.10 - 94GB Ubuntu 22.04.1 LTS - 5.4.0-139-generic - GCC 11.2.0

AMD Ryzen 9 7950X AVX-512 2 Systems - 226 Benchmark Results	AMD Ryzen 9 7950X 16-Core - ASUS ROG CROSSHAIR X670E HERO - AMD Device 14d8 Ubuntu 22.04 - 6.0.0-060000rc1daily20220820-generic - GNOME Shell 42.2
12600k sept 3 Systems - 311 Benchmark Results	Intel Core i5-12600K - ASUS PRIME Z690-P WIFI D4 - Intel Device 7aa7 Ubuntu 22.04 - 5.19.0-051900rc6daily20220716-generic - GNOME Shell 42.1
dd 3 Systems - 81 Benchmark Results	Intel Core i7-1165G7 - Dell 0GG9PT - Intel Tiger Lake-LP Ubuntu 21.10 - 5.13.0-52-generic - GNOME Shell 40.5
3900xt-september 4 Systems - 211 Benchmark Results	AMD Ryzen 9 3900XT 12-Core - MSI MEG X570 GODLIKE - AMD Starship Ubuntu 22.04 - 5.15.0-40-generic - GNOME Shell 42.2
3950X Sep 5 Systems - 75 Benchmark Results	AMD Ryzen 9 3950X 16-Core - ASUS ROG CROSSHAIR VII HERO - AMD Starship Ubuntu 22.04 - 5.19.0-051900daily20220813-generic - GNOME Shell 42.2
extra cpu tests 9 Systems - 113 Benchmark Results	AMD Ryzen 9 5950X 16-Core - ASUS ROG CROSSHAIR VIII HERO - AMD Starship Ubuntu 22.04 - 6.0.0-060000rc1daily20220820-generic - GNOME Shell 42.2
new new 3 Systems - 88 Benchmark Results	AMD Ryzen 7 5800X3D 8-Core - ASUS ROG CROSSHAIR VIII HERO - AMD Starship Ubuntu 22.04 - 5.17.0-1013-oem - GNOME Shell 42.2
epyc sep 4 Systems - 49 Benchmark Results	2 x AMD EPYC 7713 64-Core - AMD DAYTONA_X - AMD Starship Ubuntu 22.04 - 5.19.0-051900daily20220803-generic - GNOME Shell 42.4
12400 nnn 3 Systems - 172 Benchmark Results	Intel Core i5-12400 - MSI PRO Z690-A WIFI DDR4 - Intel Device 7aa7 Ubuntu 22.04 - 5.15.0-40-generic - GNOME Shell 42.2
icelake vino 3 Systems - 34 Benchmark Results	Intel Core i7-1065G7 - Dell 06CDVY - Intel Ice Lake-LP DRAM Ubuntu 22.04 - 5.18.8-051808-generic - GNOME Shell 42.2
cxle sep 2022 3 Systems - 49 Benchmark Results	Intel Core i9-10980XE - ASRock X299 Steel Legend - Intel Sky Lake-E DMI3 Registers Ubuntu 22.04 - 5.19.0-051900rc7-generic - GNOME Shell 42.2
New Tests 3 Systems - 221 Benchmark Results	2 x Intel Xeon Platinum 8380 - Intel M50CYP2SB2U - Intel Device 0998 Clear Linux OS 36990 - 5.19.6-1185.native - GNOME Shell 42.4
xeon 8380 2P 4 Systems - 41 Benchmark Results	2 x Intel Xeon Platinum 8380 - Intel M50CYP2SB2U - Intel Ice Lake IEH Ubuntu 22.10 - 5.19.0-15-generic - GNOME Shell
AMD EPYC 4th Gen AVX-512 Comparison 2 Systems - 135 Benchmark Results	2 x AMD EPYC 9654 96-Core - AMD Titanite_4G - AMD Device 14a4 Ubuntu 22.10 - 6.1.0-phx - GNOME Shell 43.0
3900X Seppy 3 Systems - 307 Benchmark Results	AMD Ryzen 9 3900X 12-Core - ASUS TUF GAMING X570-PLUS - AMD Starship Ubuntu 20.04 - 5.11.0-rc1-phx - GNOME Shell 3.36.4

Mobile Neural Network

Project Site

Source Repository

Test Created

Last Updated

Test Maintainer

Test Type

Average Install Time

Average Run Time

Test Dependencies

Accolades

Supported Platforms

Revision History

Suites Using This Test

Performance Metrics

Mobile Neural Network 2.1

Model: SqueezeNetV1.0

Does It Scale Well With Increasing Cores?

Notable Instruction Set Usage

Tested CPU Architectures

Recent Test Results

Most Popular Test Results