Raspberry Pi 4 October

ARMv7 Cortex-A72 testing with a BCM2711 Raspberry Pi 4 Model B Rev 1.1 and V3D 4.2 2GB on Raspbian 10 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2010074-FI-RASPBERRY04
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results

Limit displaying results to tests within:

C/C++ Compiler Tests 2 Tests
CPU Massive 4 Tests
Creator Workloads 2 Tests
Fortran Tests 3 Tests
HPC - High Performance Computing 6 Tests
Machine Learning 3 Tests
Molecular Dynamics 2 Tests
Multi-Core 2 Tests
Python Tests 2 Tests
Scientific Computing 3 Tests
Single-Threaded 2 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
RPi 4 Model B
October 05 2020
  11 Hours, 50 Minutes
Raspberry Pi 4
October 06 2020
  11 Hours, 29 Minutes
Invert Hiding All Results Option
  11 Hours, 40 Minutes
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):

RPi 4 Model B

Kernel Notes: snd_bcm2835.enable_compat_alsa=0 snd_bcm2835.enable_hdmi=1 snd_bcm2835.enable_headphones=1
Compiler Notes: --build=arm-linux-gnueabihf --disable-libitm --disable-libquadmath --disable-libquadmath-support --disable-sjlj-exceptions --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++ --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-objc-gc=auto --enable-plugin --enable-shared --enable-threads=posix --host=arm-linux-gnueabihf --program-prefix=arm-linux-gnueabihf- --target=arm-linux-gnueabihf --with-arch=armv6 --with-default-libstdcxx-abi=new --with-float=hard --with-fpu=vfp --with-gcc-major-version-only --with-target-system-zlib -v
Processor Notes: Scaling Governor: cpufreq-dt ondemand
Python Notes: Python 2.7.16 + Python 3.7.3

Raspberry Pi 4

Processor: ARMv7 Cortex-A72 @ 1.50GHz (4 Cores), Motherboard: BCM2711 Raspberry Pi 4 Model B Rev 1.1, Memory: 2048MB, Disk: 32GB SC32G, Graphics: V3D 4.2 2GB, Monitor: VA2431

OS: Raspbian 10, Kernel: 5.4.51-v7l+ (armv7l), Desktop: LXDE 0.10.0, Display Server: X Server 1.20.4, Display Driver: modesetting 1.20.4, OpenGL: 2.1 Mesa 19.3.2, Compiler: GCC 8.3.0, File-System: ext4, Screen Resolution: 1920x1080

Raspberry Pi 4 OctoberOpenBenchmarking.orgPhoronix Test SuiteARMv7 Cortex-A72 @ 1.50GHz (4 Cores)BCM2711 Raspberry Pi 4 Model B Rev 1.12048MB32GB SC32GV3D 4.2 2GBVA2431Raspbian 105.4.51-v7l+ (armv7l)LXDE 0.10.0X Server 1.20.4modesetting 1.20.42.1 Mesa 19.3.2GCC 8.3.0ext41920x1080ProcessorMotherboardMemoryDiskGraphicsMonitorOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionRaspberry Pi 4 October BenchmarksSystem Logs- snd_bcm2835.enable_compat_alsa=0 snd_bcm2835.enable_hdmi=1 snd_bcm2835.enable_headphones=1 - --build=arm-linux-gnueabihf --disable-libitm --disable-libquadmath --disable-libquadmath-support --disable-sjlj-exceptions --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++ --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-objc-gc=auto --enable-plugin --enable-shared --enable-threads=posix --host=arm-linux-gnueabihf --program-prefix=arm-linux-gnueabihf- --target=arm-linux-gnueabihf --with-arch=armv6 --with-default-libstdcxx-abi=new --with-float=hard --with-fpu=vfp --with-gcc-major-version-only --with-target-system-zlib -v - Scaling Governor: cpufreq-dt ondemand- Python 2.7.16 + Python 3.7.3

RPi 4 Model B vs. Raspberry Pi 4 ComparisonPhoronix Test SuiteBaseline+8.2%+8.2%+16.4%+16.4%+24.6%+24.6%+32.8%+32.8%22.5%20.2%16.4%16.3%16.1%14.5%12.7%11.7%9.8%8.8%8%6.7%5.6%3.7%2.6%2.5%GoogleNet - CPU - 10032.8%3SqueezeNetV1.0MobileNetV2_224Rhodopsin ProteinN.2.3.C.F.R19resnet-v2-50AlexNet - CPU - 100mobilenet-v1-1.0inception-v31280 x 10241024 x 768CPU - SqueezeNet v1.1C.F.DT.T.S.S2.9%Q.1.L.H.CQ.1.LCaffeZstd CompressionMobile Neural NetworkMobile Neural NetworkLAMMPS Molecular Dynamics SimulatorFFTEZstd CompressionMobile Neural NetworkCaffeMobile Neural NetworkMobile Neural NetworkGLmark2GLmark2TNNDolfyneSpeak-NG Speech EngineWebP Image EncodeWebP Image EncodeRPi 4 Model BRaspberry Pi 4

Raspberry Pi 4 Octoberdolfyn: Computational Fluid Dynamicsffte: N=256, 3D Complex FFT Routinelammps: Rhodopsin Proteinwebp: Defaultwebp: Quality 100webp: Quality 100, Losslesswebp: Quality 100, Highest Compressionwebp: Quality 100, Lossless, Highest Compressioncompress-zstd: 3compress-zstd: 19espeak: Text-To-Speech Synthesismpv: Big Buck Bunny Sunflower 1080p - Software Onlycaffe: AlexNet - CPU - 100caffe: GoogleNet - CPU - 100mnn: SqueezeNetV1.0mnn: resnet-v2-50mnn: MobileNetV2_224mnn: mobilenet-v1-1.0mnn: inception-v3tnn: CPU - MobileNet v2tnn: CPU - SqueezeNet v1.1hint: FLOATglmark2: 1024 x 768glmark2: 1280 x 1024glmark2: 1920 x 1080RPi 4 Model BRaspberry Pi 4128.0991964.380.4239.14812.319101.05236.635226.93384.92.14178.12347.06568436173460383.088381.59545.40573.897520.1341199.7641091.80992144528.548676895035123.4902280.650.4929.13012.28198.55336.595221.1641042.45183.28446.69508908230370269.125338.59439.00867.276477.9661203.9431033.42292186428.720173955435OpenBenchmarking.org

Dolfyn

Dolfyn is a Computational Fluid Dynamics (CFD) code of modern numerical simulation techniques. The Dolfyn test profile measures the execution time of the bundled computational fluid dynamics demos that are bundled with Dolfyn. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDolfyn 0.527Computational Fluid DynamicsRPi 4 Model BRaspberry Pi 4306090120150SE +/- 0.24, N = 3SE +/- 0.29, N = 3128.10123.49
OpenBenchmarking.orgSeconds, Fewer Is BetterDolfyn 0.527Computational Fluid DynamicsRPi 4 Model BRaspberry Pi 420406080100Min: 127.66 / Avg: 128.1 / Max: 128.49Min: 123.17 / Avg: 123.49 / Max: 124.06

FFTE

FFTE is a package by Daisuke Takahashi to compute Discrete Fourier Transforms of 1-, 2- and 3- dimensional sequences of length (2^p)*(3^q)*(5^r). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMFLOPS, More Is BetterFFTE 7.0N=256, 3D Complex FFT RoutineRPi 4 Model BRaspberry Pi 45001000150020002500SE +/- 17.65, N = 3SE +/- 35.71, N = 31964.382280.651. (F9X) gfortran options: -O3 -fomit-frame-pointer -fopenmp
OpenBenchmarking.orgMFLOPS, More Is BetterFFTE 7.0N=256, 3D Complex FFT RoutineRPi 4 Model BRaspberry Pi 4400800120016002000Min: 1929.54 / Avg: 1964.38 / Max: 1986.7Min: 2230.84 / Avg: 2280.65 / Max: 2349.881. (F9X) gfortran options: -O3 -fomit-frame-pointer -fopenmp

LAMMPS Molecular Dynamics Simulator

LAMMPS is a classical molecular dynamics code, and an acronym for Large-scale Atomic/Molecular Massively Parallel Simulator. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 24Aug2020Model: Rhodopsin ProteinRPi 4 Model BRaspberry Pi 40.11070.22140.33210.44280.5535SE +/- 0.001, N = 3SE +/- 0.003, N = 30.4230.4921. (CXX) g++ options: -O3 -pthread -lm
OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 24Aug2020Model: Rhodopsin ProteinRPi 4 Model BRaspberry Pi 4246810Min: 0.42 / Avg: 0.42 / Max: 0.42Min: 0.49 / Avg: 0.49 / Max: 0.51. (CXX) g++ options: -O3 -pthread -lm

WebP Image Encode

This is a test of Google's libwebp with the cwebp image encode utility and using a sample 6000x4000 pixel JPEG image as the input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: DefaultRPi 4 Model BRaspberry Pi 43691215SE +/- 0.007, N = 3SE +/- 0.001, N = 39.1489.1301. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: DefaultRPi 4 Model BRaspberry Pi 43691215Min: 9.13 / Avg: 9.15 / Max: 9.16Min: 9.13 / Avg: 9.13 / Max: 9.131. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100RPi 4 Model BRaspberry Pi 43691215SE +/- 0.04, N = 3SE +/- 0.04, N = 312.3212.281. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100RPi 4 Model BRaspberry Pi 448121620Min: 12.27 / Avg: 12.32 / Max: 12.4Min: 12.23 / Avg: 12.28 / Max: 12.351. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, LosslessRPi 4 Model BRaspberry Pi 420406080100SE +/- 0.42, N = 3SE +/- 1.60, N = 3101.0598.551. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, LosslessRPi 4 Model BRaspberry Pi 420406080100Min: 100.21 / Avg: 101.05 / Max: 101.54Min: 96.85 / Avg: 98.55 / Max: 101.761. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Highest CompressionRPi 4 Model BRaspberry Pi 4816243240SE +/- 0.02, N = 3SE +/- 0.09, N = 336.6436.601. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Highest CompressionRPi 4 Model BRaspberry Pi 4816243240Min: 36.59 / Avg: 36.63 / Max: 36.66Min: 36.51 / Avg: 36.6 / Max: 36.771. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Lossless, Highest CompressionRPi 4 Model BRaspberry Pi 450100150200250SE +/- 0.23, N = 3SE +/- 0.33, N = 3226.93221.161. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Lossless, Highest CompressionRPi 4 Model BRaspberry Pi 44080120160200Min: 226.51 / Avg: 226.93 / Max: 227.3Min: 220.77 / Avg: 221.16 / Max: 221.811. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

Zstd Compression

This test measures the time needed to compress a sample file (an Ubuntu ISO) using Zstd compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.5Compression Level: 3RPi 4 Model BRaspberry Pi 420406080100SE +/- 0.32, N = 384.9104.01. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.5Compression Level: 3RPi 4 Model BRaspberry Pi 420406080100Min: 84.4 / Avg: 84.93 / Max: 85.51. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.5Compression Level: 19RPi 4 Model BRaspberry Pi 40.55131.10261.65392.20522.7565SE +/- 0.01, N = 2SE +/- 0.00, N = 32.142.451. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.5Compression Level: 19RPi 4 Model BRaspberry Pi 4246810Min: 2.13 / Avg: 2.14 / Max: 2.14Min: 2.45 / Avg: 2.45 / Max: 2.451. (CC) gcc options: -O3 -pthread -lz -llzma

eSpeak-NG Speech Engine

This test times how long it takes the eSpeak speech synthesizer to read Project Gutenberg's The Outline of Science and output to a WAV file. This test profile is now tracking the eSpeak-NG version of eSpeak. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BettereSpeak-NG Speech Engine 20200907Text-To-Speech SynthesisRPi 4 Model BRaspberry Pi 44080120160200SE +/- 2.40, N = 16SE +/- 2.31, N = 4178.12183.281. (CC) gcc options: -O2 -std=c99
OpenBenchmarking.orgSeconds, Fewer Is BettereSpeak-NG Speech Engine 20200907Text-To-Speech SynthesisRPi 4 Model BRaspberry Pi 4306090120150Min: 171.78 / Avg: 178.12 / Max: 204.52Min: 176.99 / Avg: 183.28 / Max: 188.061. (CC) gcc options: -O2 -std=c99

MPV

MPV is an open-source, cross-platform media player. This test profile tests the frame-rate that can be achieved unsynchronized in a desynchronized mode. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterMPVVideo Input: Big Buck Bunny Sunflower 1080p - Decode: Software OnlyRPi 4 Model BRaspberry Pi 41122334455SE +/- 0.14, N = 3SE +/- 0.10, N = 347.0646.69MIN: 43.76 / MAX: 48.16MIN: 41.97 / MAX: 49.451. mpv 0.29.1
OpenBenchmarking.orgFPS, More Is BetterMPVVideo Input: Big Buck Bunny Sunflower 1080p - Decode: Software OnlyRPi 4 Model BRaspberry Pi 41020304050Min: 46.79 / Avg: 47.06 / Max: 47.22Min: 46.51 / Avg: 46.69 / Max: 46.871. mpv 0.29.1

Caffe

This is a benchmark of the Caffe deep learning framework and currently supports the AlexNet and Googlenet model and execution on both CPUs and NVIDIA GPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: CPU - Iterations: 100RPi 4 Model BRaspberry Pi 4120K240K360K480K600KSE +/- 35117.00, N = 9SE +/- 20842.85, N = 95684365089081. (CXX) g++ options: -fPIC -O3 -rdynamic -lboost_system -lboost_thread -lboost_filesystem -lboost_chrono -lboost_date_time -lboost_atomic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: CPU - Iterations: 100RPi 4 Model BRaspberry Pi 4100K200K300K400K500KMin: 451038 / Avg: 568435.56 / Max: 800617Min: 426203 / Avg: 508908.11 / Max: 5883311. (CXX) g++ options: -fPIC -O3 -rdynamic -lboost_system -lboost_thread -lboost_filesystem -lboost_chrono -lboost_date_time -lboost_atomic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: CPU - Iterations: 100RPi 4 Model BRaspberry Pi 4500K1000K1500K2000K2500KSE +/- 279770.40, N = 6SE +/- 237047.36, N = 6173460323037021. (CXX) g++ options: -fPIC -O3 -rdynamic -lboost_system -lboost_thread -lboost_filesystem -lboost_chrono -lboost_date_time -lboost_atomic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: CPU - Iterations: 100RPi 4 Model BRaspberry Pi 4400K800K1200K1600K2000KMin: 1096860 / Avg: 1734603.33 / Max: 2951840Min: 1773040 / Avg: 2303701.67 / Max: 33719001. (CXX) g++ options: -fPIC -O3 -rdynamic -lboost_system -lboost_thread -lboost_filesystem -lboost_chrono -lboost_date_time -lboost_atomic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

Mobile Neural Network

MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by ALibaba. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2020-09-17Model: SqueezeNetV1.0RPi 4 Model BRaspberry Pi 420406080100SE +/- 0.16, N = 3SE +/- 0.15, N = 383.0969.13MIN: 81.15 / MAX: 240.09MIN: 68.37 / MAX: 102.331. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2020-09-17Model: SqueezeNetV1.0RPi 4 Model BRaspberry Pi 41632486480Min: 82.85 / Avg: 83.09 / Max: 83.39Min: 68.84 / Avg: 69.13 / Max: 69.361. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2020-09-17Model: resnet-v2-50RPi 4 Model BRaspberry Pi 480160240320400SE +/- 1.46, N = 3SE +/- 0.73, N = 3381.60338.59MIN: 378.13 / MAX: 640.7MIN: 335.86 / MAX: 348.971. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2020-09-17Model: resnet-v2-50RPi 4 Model BRaspberry Pi 470140210280350Min: 380.04 / Avg: 381.6 / Max: 384.52Min: 337.77 / Avg: 338.59 / Max: 340.051. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2020-09-17Model: MobileNetV2_224RPi 4 Model BRaspberry Pi 41020304050SE +/- 0.03, N = 3SE +/- 0.05, N = 345.4139.01MIN: 45.12 / MAX: 54.48MIN: 38.62 / MAX: 47.661. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2020-09-17Model: MobileNetV2_224RPi 4 Model BRaspberry Pi 4918273645Min: 45.36 / Avg: 45.4 / Max: 45.46Min: 38.94 / Avg: 39.01 / Max: 39.11. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2020-09-17Model: mobilenet-v1-1.0RPi 4 Model BRaspberry Pi 41632486480SE +/- 0.19, N = 3SE +/- 0.15, N = 373.9067.28MIN: 72.74 / MAX: 86.19MIN: 65.57 / MAX: 76.511. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2020-09-17Model: mobilenet-v1-1.0RPi 4 Model BRaspberry Pi 41428425670Min: 73.61 / Avg: 73.9 / Max: 74.24Min: 67.06 / Avg: 67.28 / Max: 67.561. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2020-09-17Model: inception-v3RPi 4 Model BRaspberry Pi 4110220330440550SE +/- 0.22, N = 3SE +/- 1.96, N = 3520.13477.97MIN: 515.44 / MAX: 642.73MIN: 467.32 / MAX: 595.121. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2020-09-17Model: inception-v3RPi 4 Model BRaspberry Pi 490180270360450Min: 519.83 / Avg: 520.13 / Max: 520.57Min: 474.34 / Avg: 477.97 / Max: 481.081. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

TNN

TNN is an open-source deep learning reasoning framework developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: MobileNet v2RPi 4 Model BRaspberry Pi 430060090012001500SE +/- 7.65, N = 3SE +/- 7.91, N = 31199.761203.94MIN: 1189.76 / MAX: 1216.61MIN: 1193.77 / MAX: 1247.741. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: MobileNet v2RPi 4 Model BRaspberry Pi 42004006008001000Min: 1190.5 / Avg: 1199.76 / Max: 1214.93Min: 1194.56 / Avg: 1203.94 / Max: 1219.671. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: SqueezeNet v1.1RPi 4 Model BRaspberry Pi 42004006008001000SE +/- 4.99, N = 3SE +/- 2.06, N = 31091.811033.42MIN: 1076.49 / MAX: 1103.72MIN: 1021.98 / MAX: 1042.641. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: SqueezeNet v1.1RPi 4 Model BRaspberry Pi 42004006008001000Min: 1082.89 / Avg: 1091.81 / Max: 1100.15Min: 1029.94 / Avg: 1033.42 / Max: 1037.081. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl

Hierarchical INTegration

This test runs the U.S. Department of Energy's Ames Laboratory Hierarchical INTegration (HINT) benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQUIPs, More Is BetterHierarchical INTegration 1.0Test: FLOATRPi 4 Model BRaspberry Pi 420M40M60M80M100MSE +/- 75647.09, N = 3SE +/- 47982.99, N = 392144528.5592186428.721. (CC) gcc options: -O3 -march=native -lm
OpenBenchmarking.orgQUIPs, More Is BetterHierarchical INTegration 1.0Test: FLOATRPi 4 Model BRaspberry Pi 416M32M48M64M80MMin: 91995233.28 / Avg: 92144528.55 / Max: 92240404.47Min: 92090543.56 / Avg: 92186428.72 / Max: 92237781.461. (CC) gcc options: -O3 -march=native -lm

GLmark2

This is a test of Linaro's glmark2 port, currently using the X11 OpenGL 2.0 target. GLmark2 is a basic OpenGL benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterGLmark2 2020.04Resolution: 1024 x 768RPi 4 Model BRaspberry Pi 4204060801008995

OpenBenchmarking.orgScore, More Is BetterGLmark2 2020.04Resolution: 1280 x 1024RPi 4 Model BRaspberry Pi 412243648605054

OpenBenchmarking.orgScore, More Is BetterGLmark2 2020.04Resolution: 1920 x 1080RPi 4 Model BRaspberry Pi 48162432403535

RPi 4 Model B

Kernel Notes: snd_bcm2835.enable_compat_alsa=0 snd_bcm2835.enable_hdmi=1 snd_bcm2835.enable_headphones=1
Compiler Notes: --build=arm-linux-gnueabihf --disable-libitm --disable-libquadmath --disable-libquadmath-support --disable-sjlj-exceptions --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++ --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-objc-gc=auto --enable-plugin --enable-shared --enable-threads=posix --host=arm-linux-gnueabihf --program-prefix=arm-linux-gnueabihf- --target=arm-linux-gnueabihf --with-arch=armv6 --with-default-libstdcxx-abi=new --with-float=hard --with-fpu=vfp --with-gcc-major-version-only --with-target-system-zlib -v
Processor Notes: Scaling Governor: cpufreq-dt ondemand
Python Notes: Python 2.7.16 + Python 3.7.3

Testing initiated at 5 October 2020 22:46 by user pi.

Raspberry Pi 4

Processor: ARMv7 Cortex-A72 @ 1.50GHz (4 Cores), Motherboard: BCM2711 Raspberry Pi 4 Model B Rev 1.1, Memory: 2048MB, Disk: 32GB SC32G, Graphics: V3D 4.2 2GB, Monitor: VA2431

OS: Raspbian 10, Kernel: 5.4.51-v7l+ (armv7l), Desktop: LXDE 0.10.0, Display Server: X Server 1.20.4, Display Driver: modesetting 1.20.4, OpenGL: 2.1 Mesa 19.3.2, Compiler: GCC 8.3.0, File-System: ext4, Screen Resolution: 1920x1080

Kernel Notes: snd_bcm2835.enable_compat_alsa=0 snd_bcm2835.enable_hdmi=1 snd_bcm2835.enable_headphones=1
Compiler Notes: --build=arm-linux-gnueabihf --disable-libitm --disable-libquadmath --disable-libquadmath-support --disable-sjlj-exceptions --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++ --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-objc-gc=auto --enable-plugin --enable-shared --enable-threads=posix --host=arm-linux-gnueabihf --program-prefix=arm-linux-gnueabihf- --target=arm-linux-gnueabihf --with-arch=armv6 --with-default-libstdcxx-abi=new --with-float=hard --with-fpu=vfp --with-gcc-major-version-only --with-target-system-zlib -v
Processor Notes: Scaling Governor: cpufreq-dt ondemand
Python Notes: Python 2.7.16 + Python 3.7.3

Testing initiated at 6 October 2020 14:10 by user pi.