NCNN Benchmark - OpenBenchmarking.org

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.

* 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 4 January 2025.

Revision History

pts/ncnn-1.6.0 [View Source] Sun, 29 Dec 2024 10:47:25 GMT
Update against NCNN 20241226.

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.

Performance Metrics

NCNN 20241226

Target: CPU - Model: alexnet

OpenBenchmarking.org metrics for this test profile configuration based on 49 public results since 29 December 2024 with the latest data as of 30 December 2024.

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 9 9950X 16-Core

96th

3.3 ^{+/- 0.1}

AMD Ryzen Threadripper 7980X 64-Cores

80th

4.5 ^{+/- 0.2}

AMD Ryzen AI 9 HX 370

80th

4.6 ^{+/- 0.2}

Mid-Tier

75th

> 4.8

AMD Ryzen AI 9 365

66th

5.3 ^{+/- 0.4}

AMD Ryzen 7 7840HS

64th

5.3 ^{+/- 0.2}

Intel Core i7-1280P

58th

5.7 ^{+/- 0.1}

Median

50th

6.1

Intel Core Ultra 7 155H

45th

6.4 ^{+/- 0.1}

2 x AMD EPYC 9654 96-Core

31st

10.9 ^{+/- 0.4}

2 x AMD EPYC 9684X 96-Core

31st

11.2 ^{+/- 0.9}

Low-Tier

25th

> 11.6

Intel Core Ultra 9 285K

15th

18.2 ^{+/- 0.5}

ARMv8 Neoverse-N1 128-Core

5th

37.8 ^{+/- 0.2}

Based on OpenBenchmarking.org data, the selected test / test configuration (NCNN 20241226 - Target: CPU - Model: alexnet) has an average run-time of 10 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.

Recent Test Results

Compare

ncnn llama 4 Systems - 48 Benchmark Results	Intel Core Ultra 7 256V - ASUS Zenbook S 14 UX5406SA_UX5406SA UX5406SA v1.0 - Intel Device a87f Ubuntu 24.10 - 6.12.0-rc6-phx-drm-next - GNOME Shell 47.0
ncnn llama 4 Systems - 48 Benchmark Results	AMD Ryzen Threadripper 7980X 64-Cores - System76 Thelio Major - AMD Device 14a4 Ubuntu 24.04 - 6.12.3-061203-generic - GNOME Shell 46.0
9654 llama ncnn 2 Systems - 30 Benchmark Results	2 x AMD EPYC 9654 96-Core - AMD Titanite_4G - AMD Device 14a4 Ubuntu 24.10 - 6.11.0-13-generic - GNOME Shell 47.0
ncnn llama 4 Systems - 48 Benchmark Results	Intel Core Ultra 9 285K - ASUS ROG MAXIMUS Z890 HERO - Intel Device ae7f Ubuntu 24.10 - 6.11.0-13-generic - GNOME Shell 47.0
ncnn llama ryzen 3 Systems - 48 Benchmark Results	AMD Ryzen 7 7840HS - Framework Laptop 16 - AMD Device 14e8 Ubuntu 24.04 - 6.8.0-49-generic - GNOME Shell 46.0
llama ncnn 9950X 4 Systems - 48 Benchmark Results	AMD Ryzen 9 9950X 16-Core - ASRock X870E Taichi - AMD Device 14d8 Ubuntu 24.04 - 6.12.3-061203-generic - GNOME Shell 46.0
9654 llama ncnn 2 Systems - 30 Benchmark Results	2 x AMD EPYC 9654 96-Core - AMD Titanite_4G - AMD Device 14a4 Ubuntu 24.10 - 6.11.0-13-generic - GNOME Shell 47.0

ncnn llama 4 Systems - 48 Benchmark Results	Intel Core Ultra 9 285K - ASUS ROG MAXIMUS Z890 HERO - Intel Device ae7f Ubuntu 24.10 - 6.11.0-13-generic - GNOME Shell 47.0
llama ncnn 9950X 4 Systems - 48 Benchmark Results	AMD Ryzen 9 9950X 16-Core - ASRock X870E Taichi - AMD Device 14d8 Ubuntu 24.04 - 6.12.3-061203-generic - GNOME Shell 46.0
ncnn llama ryzen 3 Systems - 48 Benchmark Results	AMD Ryzen 7 7840HS - Framework Laptop 16 - AMD Device 14e8 Ubuntu 24.04 - 6.8.0-49-generic - GNOME Shell 46.0
ncnn llama 4 Systems - 48 Benchmark Results	Intel Core Ultra 7 256V - ASUS Zenbook S 14 UX5406SA_UX5406SA UX5406SA v1.0 - Intel Device a87f Ubuntu 24.10 - 6.12.0-rc6-phx-drm-next - GNOME Shell 47.0
ncnn llama 4 Systems - 48 Benchmark Results	AMD Ryzen Threadripper 7980X 64-Cores - System76 Thelio Major - AMD Device 14a4 Ubuntu 24.04 - 6.12.3-061203-generic - GNOME Shell 46.0
9654 llama ncnn 2 Systems - 30 Benchmark Results	2 x AMD EPYC 9654 96-Core - AMD Titanite_4G - AMD Device 14a4 Ubuntu 24.10 - 6.11.0-13-generic - GNOME Shell 47.0
vulk-com2 1 System - 18 Benchmark Results	AMD Ryzen 9 5900X 12-Core - ASRock X570 Steel Legend - AMD Starship Ubuntu 24.10 - 6.11.0-13-generic - X Server
hurricane-server 1 System - 322 Benchmark Results	AMD Eng Sample 100-000000897-03 - Supermicro Super Server H13SSL-N v2.00 - AMD Device 14a4 Ubuntu 24.04 - 6.8.0-50-generic - GNOME Shell 46.0
hurricane-server 1 System - 322 Benchmark Results
RTX 4070 SUPER 6 Systems - 199 Benchmark Results	Intel Core i5-10300H - CML Stonic_CMS - Intel Comet Lake PCH Ubuntu 24.04 - 6.8.0-49-generic - GNOME Shell 46.0
RTX 4070 SUPER 5 Systems - 211 Benchmark Results	Intel Core Ultra 9 285K - MSI MEG Z890 UNIFY-X - Intel Device ae7f Ubuntu 24.10 - 6.12.1-061201-generic - GNOME Shell 47.0
Benchmark Intel 1 System - 39 Benchmark Results	Intel Core Ultra 9 285K - MSI MEG Z890 UNIFY-X - Intel Device ae7f Ubuntu 24.10 - 6.12.1-061201-generic - GNOME Shell 47.0
testgpu 1 System - 44 Benchmark Results	AMD Ryzen Threadripper PRO 7965WX 24-Cores - ASUS Pro WS WRX90E-SAGE SE - AMD Genoa Debian - 6.11.10-amd64 - KDE Plasma 6.2.3
test Featured Processor Comparison	2 x Intel Xeon E5-2680 v4
test Featured Processor Comparison	2 x Intel Xeon E5-2680 v4

NCNN

Project Site

Source Repository

Test Created

Last Updated

Test Maintainer

Test Type

Average Install Time

Average Run Time

Test Dependencies

Accolades

Supported Platforms