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

1 Minute, 18 Seconds

Average Run Time

20 Minutes, 48 Seconds

Test Dependencies

CMake + C/C++ Compiler Toolchain + Vulkan

Accolades

60k+ Downloads

Supported Platforms


Public Result Uploads *Reported Installs **Reported Test Completions **Test Profile Page Views ***OpenBenchmarking.orgEventsNCNN Popularity Statisticspts/ncnn2020.092020.112021.012021.032021.052021.072021.092021.112022.012022.032022.052022.072022.092022.112023.012023.032023.052023.072023.092023.112024.012024.032024.056K12K18K24K30K
* 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 23 June 2024.
CPU58.5%Vulkan GPU34.2%Vulkan GPU-v3-v3-v37.3%Target Option PopularityOpenBenchmarking.org
yolov4-tiny5.8%shufflenet-v25.9%mobilenet-v35.6%vgg165.9%efficientnet-b05.9%regnety_400m5.9%googlenet5.9%FastestDet5.8%alexnet5.9%mobilenet5.9%resnet185.9%resnet505.9%vision_transformer5.9%blazeface5.9%mobilenet-v25.9%squeezenet_ssd5.9%mnasnet5.9%Model Option PopularityOpenBenchmarking.org

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: googlenet

OpenBenchmarking.org metrics for this test profile configuration based on 274 public results since 1 August 2023 with the latest data as of 12 May 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.

OpenBenchmarking.orgDistribution Of Public Results - Target: CPU - Model: googlenet274 Results Range From 3 To 1984 ms348931381832282733183634084534985435886336787237688138589039489931038108311281173121812631308135313981443148815331578162316681713175818031848189319381983202850100150200250

Based on OpenBenchmarking.org data, the selected test / test configuration (NCNN 20230517 - Target: CPU - Model: googlenet) has an average run-time of 26 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: googlenetRun-Time60120180240300Min: 2 / Avg: 25.8 / Max: 328

Based on public OpenBenchmarking.org results, the selected test / test configuration has an average standard deviation of 1.1%.

OpenBenchmarking.orgPercent, Fewer Is BetterAverage Deviation Between RunsTarget: CPU - Model: googlenetDeviation816243240Min: 0 / Avg: 1.08 / Max: 37

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
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
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)
RISC-V 64-bit
riscv64
SiFive RISC-V, rv64imafdcvsu
ARMv7 32-bit
armv7l
ARMv7 Cortex-A72 4-Core
ARMv8 64-bit
arm64
Apple M2 Pro
ARMv8 64-bit
aarch64
ARMv8 Cortex-A72, ARMv8 Cortex-A76 4-Core, ARMv8 Neoverse-N1, ARMv8 Neoverse-N2, ARMv8 Neoverse-V1, ARMv8 Neoverse-V2, Apple M2

Recent Test Results

OpenBenchmarking.org Results Compare

2 Systems - 18 Benchmark Results

ARMv8 Cortex-A76 - Raspberry Pi 5 Model B Rev 1.0 - 4096MB

Debian 12 - 6.6.31+rpt-rpi-2712 - 4.5 Mesa 23.2.1-1~bpo12+rpt3

2 Systems - 52 Benchmark Results

Loongson-3C5000L - fill - Loongson LLC Hyper Transport Bridge

Uos 20 - 4.19.0-loongson-3-desktop - Deepin Desktop Environment

2 Systems - 71 Benchmark Results

rv64imafdcvsu - Scaleway EM-RV1-C4M16S128-A - 16GB

Ubuntu 24.04 - 5.10.113+ - GCC 13.2.0

2 Systems - 70 Benchmark Results

rv64imafdcvsu - Scaleway EM-RV1-C4M16S128-A - 16GB

Ubuntu 24.04 - 5.10.113+ - GCC 13.2.0

1 System - 17 Benchmark Results

ARMv8 Cortex-A76 - Raspberry Pi 5 Model B Rev 1.0 - 8GB

Debian 12 - 6.6.28+rpt-rpi-2712 - 4.5 Mesa 23.2.1-1~bpo12+rpt3

1 System - 17 Benchmark Results

ARMv8 Cortex-A76 - Raspberry Pi 5 Model B Rev 1.0 - 8GB

Debian 12 - 6.6.28+rpt-rpi-2712 - 4.5 Mesa 23.2.1-1~bpo12+rpt3

1 System - 34 Benchmark Results

ARMv7 Cortex-A72 - BCM2711 Raspberry Pi 4 Model B Rev 1.4 - Broadcom BCM2711

Raspbian 11 - 5.15.84-v7l+ - X Server 1.20.11

1 System - 134 Benchmark Results

AMD Ryzen 7 7700X 8-Core - MSI PRO B650-P WIFI - AMD Device 14d8

Ubuntu 23.04 - 6.2.0-39-generic - GNOME Shell 44.3

1 System - 52 Benchmark Results

ARMv7 rev 3 - BCM2711 - Broadcom and subsidiaries BCM2711

Raspbian 11 - 5.15.84-v7l+ - ext4

3 Systems - 105 Benchmark Results

2 x Intel Xeon E5-2682 v4 - Supermicro SYS-7048GR-TR X10DRG-Q v1.10 - Intel Xeon E7 v4

Ubuntu 22.04 - 5.15.0-102-generic - X Server 1.21.1.3

1 System - 214 Benchmark Results

1 System - 211 Benchmark Results

ARMv8 Neoverse-V2 - Amazon EC2 r8g.4xlarge - Amazon Device 0200

Amazon Linux 2023.4.20240401 - 6.1.82-99.168.amzn2023.aarch64 - GCC 11.4.1 20230605

1 System - 208 Benchmark Results

ARMv8 Neoverse-V2 - Amazon EC2 r8g.4xlarge - Amazon Device 0200

Amazon Linux 2023.4.20240401 - 6.1.82-99.168.amzn2023.aarch64 - GCC 11.4.1 20230605

1 System - 192 Benchmark Results

ARMv8 Neoverse-V2 - Amazon EC2 r8g.4xlarge - Amazon Device 0200

Amazon Linux 2023.4.20240401 - 6.1.82-99.168.amzn2023.aarch64 - GCC 11.4.1 20230605

Most Popular Test Results

OpenBenchmarking.org Results Compare

2 Systems - 831 Benchmark Results

AMD Ryzen 7 7840U - Framework FRANMDCP07 - AMD Device 14e8

Ubuntu 23.10 - 6.7.0-060700rc5-generic - GNOME Shell 45.1

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

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

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

4 Systems - 96 Benchmark Results

2 x Intel Xeon Platinum 8490H - Quanta Cloud S6Q-MB-MPS - Intel Device 1bce

Ubuntu 22.10 - 6.0.0-060000rc3daily20220904-generic - GNOME Shell

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

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

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

2 Systems - 191 Benchmark Results

AMD Ryzen 7 PRO 5850U - HP 8A78 - AMD Renoir

Pop 22.04 - 6.2.6-76060206-generic - GNOME Shell 42.5

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

3 Systems - 369 Benchmark Results

Intel Xeon E-2388G - ASRockRack E3C252D4U - Intel Tiger Lake-H

Ubuntu 22.04 - 6.2.0-26-generic - GNOME Shell 42.9

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

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

Find More Test Results