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

Test Created

18 September 2020

Last Updated

18 December 2020

Test Maintainer

Michael Larabel 

Test Type

System

Average Install Time

52 Seconds

Average Run Time

20 Minutes, 48 Seconds

Test Dependencies

CMake + C/C++ Compiler Toolchain + Vulkan

Accolades

5k+ Downloads

Supported Platforms

Public Result Uploads *Reported Installs **Reported Test Completions **Test Profile Page Views ***OpenBenchmarking.orgEventsNCNN Popularity Statisticspts/ncnn2020.092020.102020.112020.122021.012021.022021.032021.042021.052021.062K4K6K8K10K
* 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 15 June 2021.
Vulkan GPU67.7%CPU21.9%Vulkan GPU-v2-v25.2%Vulkan GPU-v3-v35.2%Target Option PopularityOpenBenchmarking.org
mnasnet6.7%efficientnet-b06.7%vgg166.7%yolov4-tiny6.7%squeezenet_ssd6.7%resnet186.7%regnety_400m6.7%shufflenet-v26.7%resnet506.7%mobilenet-v26.7%alexnet6.7%blazeface6.6%googlenet6.7%mobilenet6.7%mobilenet-v36.7%Model Option PopularityOpenBenchmarking.org

Revision History

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 20201218

Target: Vulkan GPU - Model: alexnet

OpenBenchmarking.org metrics for this test profile configuration based on 1,599 public results since 18 December 2020 with the latest data as of 2 June 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)
Gigabyte AMD Radeon 540
97th
3
9
Sapphire AMD Radeon RX 5500
88th
3
10
AMD Radeon RX 5600 OEM
82nd
13
10 +/- 1
Sapphire AMD Radeon RX 5600 OEM
82nd
59
10
Mid-Tier
75th
> 10
NVIDIA GeForce RTX 3090
68th
7
11 +/- 1
Zotac NVIDIA GeForce RTX 2080
67th
3
11
NVIDIA GeForce RTX 2060 SUPER
64th
4
11
NVIDIA GeForce RTX 2080 SUPER
64th
4
11 +/- 1
NVIDIA GeForce RTX 2070 SUPER
63rd
4
12
ASUS NVIDIA GeForce RTX 2070
63rd
3
12
XFX AMD Radeon R9 285
62nd
3
12
NVIDIA GeForce RTX 2080 Ti
62nd
5
12 +/- 1
NVIDIA GeForce RTX 3080
62nd
6
12 +/- 1
Gigabyte AMD Radeon RX 5500
62nd
5
12
NVIDIA GeForce RTX 3060 Ti
62nd
5
12 +/- 1
AMD Radeon RX 56
61st
3
12
ASUS Intel UHD 630
61st
10
12 +/- 1
Sapphire AMD Radeon RX 470
52nd
6
13 +/- 2
Zotac NVIDIA GeForce RTX 2060 SUPER
52nd
142
13
Median
50th
13
MSI Intel UHD 630
45th
3
14
MSI Intel HD 630
45th
4
15
NVIDIA Quadro RTX 5000 with Max-Q Design
44th
4
15
NVIDIA GeForce RTX 2060
41st
55
16
MSI AMD Radeon RX 470
41st
55
16 +/- 1
AMD Radeon RX 470
40th
7
16 +/- 1
Gigabyte Intel UHD 630
34th
3
17
Intel HD P630
31st
3
18
Low-Tier
25th
> 18
Intel Iris Plus G7
25th
32
18
MSI Intel HD P530
22nd
3
19
Intel 8th Gen Core Gaussian Mixture Model
22nd
3
19
Intel UHD P630
19th
3
21
Gigabyte Intel HD 530
18th
3
21
Intel HD 530
18th
3
25
Gigabyte Intel HD 4600
17th
3
25
Gigabyte Intel HD 630
17th
7
26 +/- 1
Intel UHD 620
17th
9
29 +/- 1
Intel Iris Pro 580
16th
47
31
Sapphire AMD Radeon RX 550 640SP
13th
3
32
Gigabyte AMD Radeon RX 470
10th
3
34 +/- 2
Intel HD 5500
7th
3
37
MSI NVIDIA GeForce GTX 1080 Ti
3rd
47
188
OpenBenchmarking.orgDistribution Of Public Results - Target: Vulkan GPU - Model: alexnet1599 Results Range From 8 To 189 ms82134476073869911212513815116417719030060090012001500

Based on OpenBenchmarking.org data, the selected test / test configuration (NCNN 20201218 - Target: Vulkan GPU - 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.

OpenBenchmarking.orgMinutesTime Required To Complete BenchmarkTarget: Vulkan GPU - Model: alexnetRun-Time714212835Min: 3 / Avg: 9.66 / Max: 33

Based on public OpenBenchmarking.org results, the selected test / test configuration has an average standard deviation of 3.7%.

OpenBenchmarking.orgPercent, Fewer Is BetterAverage Deviation Between RunsTarget: Vulkan GPU - Model: alexnetDeviation510152025Min: 0 / Avg: 3.72 / Max: 18

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 MOVD PSHUFD PSHUFLW MOVDQU PUNPCKLQDQ SUBSD MOVAPD MINSD MAXSD ADDSD CVTSI2SD DIVSD CVTSS2SD MULSD MULPD PSRLDQ CVTSD2SS CVTDQ2PS CVTTPS2DQ
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 VINSERTF128 VEXTRACTF128 VBROADCASTSS VPERM2F128 VMASKMOVPS VPERMILPS 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 VPERM2I128 VEXTRACTI128 VPERMQ VPBROADCASTD VPERMD VPBROADCASTB VGATHERDPS VPBROADCASTW VPBROADCASTQ
FMA (FMA)
Used by default on supported hardware.
Found on Intel processors since Haswell (2013).
Found on AMD processors since Bulldozer (2011).
 
VFMADD132PS VFMADD132SS VFMADD231SS VFMADD231PS VFNMADD231PS VFMADD213PS VFMSUB132PS VFMADD213SS VFNMADD132PS VFMSUB231PS VFMSUB132SS VFMADD231SD VFNMADD213SS VFNMADD132SS VFMADD132PD VFMADD132SD VFNMADD213PS VFMSUB213PS VFNMADD231SS
The test / benchmark does honor compiler flag changes.
Last automated analysis: 10 May 2021

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

Recent Test Results

OpenBenchmarking.org Results Compare

2 Systems - 118 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

11 Systems - 454 Benchmark Results

AMD Ryzen 7 5800X 8-Core - ASUS ROG CROSSHAIR VIII HERO - AMD Starship

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

1 System - 29 Benchmark Results

Intel Xeon E-2288G - Intel 440BX - Intel 440BX

Kali 2021.1 - 5.10.0-kali7-amd64 - Xfce 4.16

5 Systems - 190 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

4 Systems - 178 Benchmark Results

Intel Core i7-1165G7 - Dell 0GG9PT - Intel Tiger Lake-LP

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

4 Systems - 178 Benchmark Results

Intel Core i7-1065G7 - Dell 06CDVY - Intel Ice Lake-LP DRAM

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

3 Systems - 218 Benchmark Results

Intel Core i7-1165G7 - Dell 0GG9PT - Intel Tiger Lake-LP

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

2 Systems - 218 Benchmark Results

Intel Core i7-1165G7 - Dell 0GG9PT - Intel Tiger Lake-LP

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

1 System - 234 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 - 94 Benchmark Results

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

Fedora 34 - 5.11.20-300.fc34.x86_64 - GNOME Shell 40.1

5 Systems - 59 Benchmark Results

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

Ubuntu 20.04 - 5.11.0-051100-generic - GNOME Shell 3.36.4

Most Popular Test Results

OpenBenchmarking.org Results Compare

6 Systems - 143 Benchmark Results

Intel Core i7-9750H - Dell 0VYV0G - Intel Cannon Lake PCH

Ubuntu 20.10 - 5.10.13-xanmod1 - KDE Plasma 5.19.5

3 Systems - 191 Benchmark Results

AMD Ryzen 3 2200G - ASUS PRIME B350M-E - AMD Raven

Ubuntu 20.10 - 5.8.0-38-generic - GNOME Shell 3.38.1

4 Systems - 80 Benchmark Results

Intel Core i7-9750H - Notebook P95_96_97Ex Rx - Intel Cannon Lake PCH

Ubuntu 20.04 - 5.7.0-999-generic - GNOME Shell 3.36.4

4 Systems - 110 Benchmark Results

Intel Core i7-1165G7 - Dell 0GG9PT - Intel Tiger Lake-LP

Clear Linux OS 34130 - 5.9.16-1009.native - GNOME Shell 3.38.2

4 Systems - 91 Benchmark Results

AMD Ryzen 5 5600X 6-Core - ASUS TUF GAMING B550M-PLUS - AMD Starship

Ubuntu 20.10 - 5.10.4-051004-generic - GNOME Shell 3.38.1

1 System - 16 Benchmark Results

Intel Core i7-7700K - ASUS MAXIMUS IX CODE - Intel Xeon E3-1200 v6

Fedora 32 - 5.9.16-100.fc32.x86_64 - Openbox 3.6.1

4 Systems - 145 Benchmark Results

Intel Core i7-9750H - Notebook P95_96_97Ex Rx - Intel Cannon Lake PCH

Ubuntu 18.04 - 5.4.0-65-generic - KDE Plasma 5.12.9

2 Systems - 85 Benchmark Results

Intel Core i5-1135G7 - Dell 0THX8P - Intel Device a0ef

Ubuntu 20.04 - 5.6.0-1036-oem - GNOME Shell 3.36.4
Find More Test Results