NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent.

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

Project Site

github.com

Source Repository

github.com

Test Created

18 September 2020

Last Updated

1 August 2023

Test Maintainer

Michael Larabel

Test Type

System

Average Install Time

55 Seconds

Average Run Time

20 Minutes, 48 Seconds

Test Dependencies

CMake + C/C++ Compiler Toolchain + Vulkan

Accolades

40k+ Downloads

Supported Platforms

* 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 updated weekly as of 28 November 2023.

Revision History

pts/ncnn-1.5.0 [View Source] Tue, 01 Aug 2023 11:49:36 GMT
Update against latest upstream.

pts/ncnn-1.4.0 [View Source] Sat, 13 Aug 2022 09:59:41 GMT
Update against NCNN 20220729 upstream.

pts/ncnn-1.3.0 [View Source] Tue, 27 Jul 2021 16:34:42 GMT
Update against NCNN 2021-07-20 upstream, fix possible Vulkan build issue by including glslang source tree.

pts/ncnn-1.2.0 [View Source] Fri, 18 Jun 2021 08:11:33 GMT
Update against NCNN 20210525 release.

pts/ncnn-1.1.0 [View Source] Fri, 18 Dec 2020 08:06:41 GMT
Update against new upstream NCNN 20201218.

pts/ncnn-1.0.3 [View Source] Fri, 25 Sep 2020 06:36:39 GMT
Drop int8 tests per https://github.com/phoronix-test-suite/test-profiles/pull/167

pts/ncnn-1.0.2 [View Source] Thu, 24 Sep 2020 12:52:47 GMT
Expose Vulkan GPU support.

pts/ncnn-1.0.1 [View Source] Fri, 18 Sep 2020 12:28:10 GMT
Increase the run count.

pts/ncnn-1.0.0 [View Source] Fri, 18 Sep 2020 11:58:15 GMT
Initial commit of Tencent NCNN.

Suites Using This Test

Machine Learning

HPC - High Performance Computing

NVIDIA GPU Compute

Vulkan Compute

Performance Metrics

Analyze Test Configuration:

NCNN 20230517

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.org metrics for this test profile configuration based on 213 public results since 1 August 2023 with the latest data as of 14 November 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)

Intel Core i9-13900K

99th

Apple M2

95th

AMD Ryzen 9 7950X 16-Core

84th

14 ^{+/- 1}

Mid-Tier

75th

> 16

AMD Ryzen Z1 Extreme

75th

Intel Core i5-12600K

71st

17 ^{+/- 1}

AMD EPYC 7763 64-Core

65th

Intel Core i7-5960X

64th

Intel Xeon W-11865MRE

62nd

22 ^{+/- 3}

Intel Core i9-10980XE

62nd

AMD Ryzen 7 PRO 6850U

58th

2 x Intel Xeon Platinum 8490H

58th

22 ^{+/- 1}

AMD Ryzen Threadripper 3970X 32-Core

56th

AMD Ryzen 7 3800XT 8-Core

54th

Intel Xeon E-2388G

51st

Median

50th

AMD Ryzen 9 3900XT 12-Core

48th

2 x Intel Xeon Platinum 8380

47th

AMD Ryzen 7 PRO 5850U

43rd

AMD EPYC 9384X 32-Core

39th

Intel Xeon E-2336

39th

Intel Core i7-1165G7

31st

AMD Ryzen 9 5900HX

29th

31 ^{+/- 2}

Intel Core i7-1065G7

29th

31 ^{+/- 1}

AMD EPYC 9754 128-Core

26th

Low-Tier

25th

> 32

AMD EPYC 7F32 8-Core

24th

2 x AMD EPYC 9124 16-Core

18th

37 ^{+/- 2}

AMD Ryzen 7 7840U

18th

AMD Ryzen Threadripper 3990X 64-Core

17th

AMD Ryzen 7 4700U

15th

Intel Core i7-8565U

14th

39 ^{+/- 1}

2 x AMD EPYC 9334 32-Core

13th

39 ^{+/- 5}

AMD Ryzen 5 4500U

9th

2 x AMD EPYC 9754 128-Core

6th

49 ^{+/- 1}

Based on OpenBenchmarking.org data, the selected test / test configuration (NCNN 20230517 - Target: CPU - Model: yolov4-tiny) has an average run-time of 9 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 0.4%.

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.

MOVD PSHUFD PSHUFLW MOVDQU MOVDQA SUBSD MOVAPD MINSD MAXSD ADDSD CVTSI2SD DIVSD PUNPCKLQDQ CVTSS2SD MULSD MULPD PSRLDQ CVTSD2SS CVTTPS2DQ CVTDQ2PS PUNPCKHQDQ PMULUDQ PADDQ SHUFPD COMISD PSHUFHW

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).

VZEROUPPER VBROADCASTSS VPERM2F128 VINSERTF128 VEXTRACTF128 VPERMILPS VMASKMOVPS VBROADCASTF128 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).

VPBROADCASTD VINSERTI128 VPERMD VEXTRACTI128 VPERMQ VPERM2I128 VPBROADCASTW VPBROADCASTB VPBROADCASTQ VGATHERDPS VPGATHERQQ VPSRLVQ

Advanced Vector Extensions 512 (AVX512)

Used by default on supported hardware.

(ZMM REGISTER USE)

FMA (FMA)

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

VFMADD132PS VFMADD132SS VFNMADD231PS VFMADD231PS VFMADD213PS VFNMADD132PS VFNMADD132SS VFNMADD213SS VFMSUB132SS VFNMADD231SS VFMADD231SS VFMSUB132PS VFMSUB231SS VFMADD213SS VFMADD132PD VFMADD132SD VFNMSUB132SS VFNMSUB231SS

AVX Vector Neural Network Instructions (AVX-VNNI)

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

VPDPWSSD

The test / benchmark does honor compiler flag changes.

Last automated analysis: 18 September 2023

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

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

aarch64

ARMv8 Cortex-A72, ARMv8 Neoverse-N1, ARMv8 Neoverse-V1, Apple M2

kontronpts/ncnn-1.5.0 1 System - 17 Benchmark Results	Intel Xeon W-11865MRE - Kontron Europe COMe-bTL6 E2 v1.0.0 - Intel Device 43ef Ubuntu 20.04 - 5.4.0-144-generic - 1.1.182
tgls Featured Kernel Comparison	5.19.0-46-generic - 6.2.0-36-generic
ptsncnn-150test 2 Systems - 17 Benchmark Results	Intel Xeon W-11865MRE - (1060V111 BIOS) - Intel Device 43ef Ubuntu 20.04 - 5.15.0-88-generic - 1.1.182
pts/ncnn-1.5.0_test 1 System - 17 Benchmark Results	Intel Xeon W-11865MRE - (1060V111 BIOS) - Intel Device 43ef Ubuntu 20.04 - 5.15.0-88-generic - 1.1.182
h510-g6405-1 1 System - 264 Benchmark Results	Intel Pentium Gold G6405 - ASRock H510M-HDV/M.2 SE - Intel Comet Lake PCH Ubuntu 20.04 - 5.15.0-88-generic - GNOME Shell 3.36.9
TestRunNewCMake 1 System - 264 Benchmark Results	Intel Pentium Gold G6400 - ASRock H510M-HDV/M.2 SE - Intel Comet Lake PCH Ubuntu 20.04 - 5.15.0-86-generic - GNOME Shell 3.36.9
FirstRun 1 System - 83 Benchmark Results	2 x AMD EPYC 7763 64-Core - Supermicro H12DSG-O-CPU - AMD Starship Ubuntu 22.04 - 5.15.0-88-generic - X Server
okt 2 Systems - 358 Benchmark Results	AMD Ryzen 9 3900XT 12-Core - MSI MEG X570 GODLIKE - AMD Starship Ubuntu 22.04 - 6.2.0-35-generic - GNOME Shell 42.2
i7-12700hrtx3060 Featured Disk Comparison	128GB HFM128GDJTNG-8310A + 1024GB SAMSUNG MZVL21T0HCLR-00B07 - 1024GB SAMSUNG MZVL21T0HCLR-00B07 + 128GB HFM128GDJTNG-8310A
oktoberfest 2 Systems - 246 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
icelake 2023 2 Systems - 101 Benchmark Results	Intel Core i7-1065G7 - Dell 06CDVY - Intel Ice Lake-LP DRAM Ubuntu 23.04 - 6.2.0-24-generic - GNOME Shell 44.0
octty 3 Systems - 26 Benchmark Results	Apple M2 - Apple MacBook Air - Apple Silicon Arch rolling - 6.3.0-asahi-13-1-ARCH - KDE Plasma 5.27.6
wxl2pay-h510-ml 1 System - 279 Benchmark Results	Intel Core i3-10105 - ASRock H510M-HDV/M.2 SE - Intel Comet Lake PCH Ubuntu 20.04 - 5.15.0-83-generic - GNOME Shell 3.36.9
ss Featured Compiler Comparison	GCC 12.2.0 - GCC 12.3.0
Latitude System 1/5 Test 1 System - 168 Benchmark Results	2 x AMD EPYC 9354 32-Core - Supermicro H13DSG-O-CPU v1.10 - AMD Device 14a4 Ubuntu 22.04 - 6.2.0-34-generic - GNOME Shell 42.9

auggy Featured Graphics Comparison	AMD Ryzen 5 4500U - LENOVO LNVNB161216 - AMD Renoir Pop 22.04 - 5.17.5-76051705-generic - GNOME Shell 42.1
7763 2204 3 Systems - 122 Benchmark Results	AMD EPYC 7763 64-Core - AMD DAYTONA_X - AMD Starship Ubuntu 22.04 - 6.2.0-phx - GNOME Shell 42.5
new t 2 Systems - 131 Benchmark Results	AMD Ryzen 7 7840U - PHX Ray_PEU - AMD Device 14e8 Ubuntu 22.04 - 6.4.0-060400-generic - KDE Plasma 5.24.7
extra tests 4 Systems - 193 Benchmark Results	2 x AMD EPYC 9124 16-Core - Supermicro H13DSH - 24 x 32 GB DDR5-4800MT AlmaLinux 9.2 - 5.14.0-284.25.1.el9_2.x86_64 - GCC 11.3.1 20221121
bergamo extra 2 Systems - 147 Benchmark Results	AMD EPYC 9384X 32-Core - AMD Titanite_4G - AMD Device 14a4 Ubuntu 22.04 - 5.15.0-47-generic - GNOME Shell 42.4
new-new 4 Systems - 96 Benchmark Results	Intel Xeon Platinum 8471N - Quanta Cloud S6Q-MB-MPS - Intel Device 1bce Ubuntu 22.10 - 6.0.0-060000rc3daily20220904-generic - GNOME Shell
extra tests 5 Systems - 200 Benchmark Results	2 x AMD EPYC 9754 128-Core - Supermicro H13DSH - 23 x 32 GB DDR5-4800MT AlmaLinux 9.2 - 5.14.0-284.25.1.el9_2.x86_64 - GCC 11.3.1 20221121
ryzen z1 extreme vulkan compute 3 Systems - 53 Benchmark Results	AMD Ryzen Z1 Extreme - ASUS RC71L v1.0 - AMD Device 14e8 Ubuntu 23.04 - 6.2.0-24-generic - GNOME Shell 44.2
xeon auggy 2 Systems - 150 Benchmark Results	2 x Intel Xeon Platinum 8380 - Intel M50CYP2SB2U - Intel Ice Lake IEH Ubuntu 22.10 - 6.2.0-rc5-phx-dodt - GNOME Shell 43.0
dddxxx Featured Compiler Comparison	Intel Core i7-8565U - Dell 0KTW76 - Intel Cannon Point-LP Ubuntu 22.04 - 5.19.0-rc6-phx-retbleed - GNOME Shell 42.2
newnew 3 Systems - 83 Benchmark Results	Intel Core i7-1165G7 - Dell 0GG9PT - Intel Tiger Lake-LP Ubuntu 23.04 - 6.2.0-24-generic - GNOME Shell 44.0
vulkan 6800XT 2 Systems - 53 Benchmark Results	Intel Core i9-13900K - ASUS PRIME Z790-P WIFI - Intel Device 7a27 Ubuntu 22.04 - 5.19.0-50-generic - GNOME Shell 42.9
vulkan tests 3 Systems - 53 Benchmark Results	AMD Ryzen Threadripper 3990X 64-Core - Gigabyte TRX40 AORUS PRO WIFI - AMD Starship Ubuntu 23.04 - 6.2.0-26-generic - GNOME Shell 44.0
vulkan-benchmarks 20 Systems - 173 Benchmark Results	AMD Ryzen 9 7950X 16-Core - ASUS ROG STRIX X670E-E GAMING WIFI - AMD Device 14d8 Ubuntu 23.04 - 6.4.6-060406-generic - GNOME Shell 44.2
vulkan benchmarks 3 Systems - 87 Benchmark Results	AMD Ryzen 9 7950X 16-Core - ASUS ROG STRIX X670E-E GAMING WIFI - AMD Device 14d8 Ubuntu 23.04 - 6.4.6-060406-generic - GNOME Shell 44.2