Jetson Nano Developer Kit

ODROID-N2

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 1904211-HV-ODROID75005
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
Show Result Confidence Charts

Limit displaying results to tests within:

C/C++ Compiler Tests 4 Tests
Compression Tests 2 Tests
CPU Massive 8 Tests
Creator Workloads 4 Tests
Multi-Core 5 Tests
Programmer / Developer System Benchmarks 2 Tests
Python Tests 2 Tests
Renderers 2 Tests
Server CPU Tests 6 Tests
Single-Threaded 4 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

Additional Graphs

Show Perf Per Core/Thread Calculation Graphs Where Applicable
Show Perf Per Clock Calculation Graphs Where Applicable

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs
Condense Test Profiles With Multiple Version Results Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
Jetson TX1 Max-P
March 17 2019
  1 Hour, 20 Minutes
Jetson TX2 Max-Q
March 16 2019
  7 Hours, 23 Minutes
Jetson TX2 Max-P
March 15 2019
  6 Hours, 25 Minutes
Jetson AGX Xavier
March 15 2019
  4 Hours, 1 Minute
Jetson Nano
March 17 2019
  7 Hours, 18 Minutes
Raspberry Pi 3 Model B+
March 16 2019
  4 Hours, 32 Minutes
ASUS TinkerBoard
March 16 2019
  7 Hours, 20 Minutes
ODROID-XU4
March 17 2019
  4 Hours, 21 Minutes
ARMv8 Cortex-A73
April 21 2019
  1 Hour, 59 Minutes
Invert Hiding All Results Option
  4 Hours, 58 Minutes

Only show results where is faster than
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):


Jetson Nano Developer KitProcessorMotherboardMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLVulkanCompilerFile-SystemScreen ResolutionJetson AGX XavierJetson TX2 Max-PJetson TX2 Max-QRaspberry Pi 3 Model B+ASUS TinkerBoardJetson TX1 Max-PODROID-XU4Jetson NanoARMv8 Cortex-A73ARMv8 rev 0 @ 2.27GHz (8 Cores)jetson-xavier16384MB31GB HBG4a2NVIDIA Tegra XavierVE228Ubuntu 18.044.9.108-tegra (aarch64)Unity 7.5.0X Server 1.19.6NVIDIA 31.0.24.6.01.1.76GCC 7.3.0 + CUDA 10.0ext41920x1080ARMv8 rev 3 @ 2.04GHz (4 Cores / 6 Threads)quill8192MB31GB 032G34NVIDIA TEGRAUbuntu 16.044.4.38-tegra (aarch64)Unity 7.4.0X Server 1.18.4NVIDIA 28.2.14.5.0GCC 5.4.0 20160609 + CUDA 9.0ARMv8 rev 3 @ 1.27GHz (4 Cores / 6 Threads)ARMv7 rev 4 @ 1.40GHz (4 Cores)BCM2835 Raspberry Pi 3 Model B Plus Rev 1.3926MB32GB GB2MWBCM2708Raspbian 9.64.19.23-v7+ (armv7l)LXDEX Server 1.19.2GCC 6.3.0 20170516656x416ARMv7 rev 1 @ 1.80GHz (4 Cores)Rockchip (Device Tree)2048MB32GB GB1QTDebian 9.04.4.16-00006-g4431f98-dirty (armv7l)X Server 1.18.41024x768ARMv8 rev 1 @ 1.73GHz (4 Cores)jetson_tx14096MB16GB 016G32NVIDIA Tegra X1VE228Ubuntu 16.044.4.38-tegra (aarch64)Unity 7.4.5NVIDIA 28.1.04.5.01.0.8GCC 5.4.0 201606091920x1080ARMv7 rev 3 @ 1.50GHz (8 Cores)ODROID-XU4 Hardkernel Odroid XU42048MB16GB AJTD4Rllvmpipe 2GBUbuntu 18.044.14.37-135 (armv7l)X Server 1.19.63.3 Mesa 18.0.0-rc5 (LLVM 6.0 128 bits)GCC 7.3.0ARMv8 rev 1 @ 1.43GHz (4 Cores)jetson-nano4096MB32GB GB1QTNVIDIA TEGRARealtek RTL8111/8168/84114.9.140-tegra (aarch64)Unity 7.5.0NVIDIA 1.0.01.1.85GCC 7.3.0 + CUDA 10.0ARMv8 Cortex-A73 @ 1.90GHz (6 Cores)Hardkernel ODROID-N216GB AJTD4ROSD4.9.156-14 (aarch64)GCC 7.3.01920x2160OpenBenchmarking.orgCompiler Details- Jetson AGX Xavier: --build=aarch64-linux-gnu --disable-libquadmath --disable-libquadmath-support --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-fix-cortex-a53-843419 --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-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --program-prefix=aarch64-linux-gnu- --target=aarch64-linux-gnu --with-default-libstdcxx-abi=new --with-gcc-major-version-only -v - Jetson TX2 Max-P: --build=aarch64-linux-gnu --disable-browser-plugin --disable-libquadmath --disable-werror --enable-checking=release --enable-clocale=gnu --enable-fix-cortex-a53-843419 --enable-gnu-unique-object --enable-gtk-cairo --enable-java-awt=gtk --enable-java-home --enable-languages=c,ada,c++,java,go,d,fortran,objc,obj-c++ --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --target=aarch64-linux-gnu --with-arch-directory=aarch64 --with-default-libstdcxx-abi=new -v - Jetson TX2 Max-Q: --build=aarch64-linux-gnu --disable-browser-plugin --disable-libquadmath --disable-werror --enable-checking=release --enable-clocale=gnu --enable-fix-cortex-a53-843419 --enable-gnu-unique-object --enable-gtk-cairo --enable-java-awt=gtk --enable-java-home --enable-languages=c,ada,c++,java,go,d,fortran,objc,obj-c++ --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --target=aarch64-linux-gnu --with-arch-directory=aarch64 --with-default-libstdcxx-abi=new -v - Raspberry Pi 3 Model B+: --build=arm-linux-gnueabihf --disable-browser-plugin --disable-libitm --disable-libquadmath --disable-sjlj-exceptions --enable-checking=release --enable-clocale=gnu --enable-gnu-unique-object --enable-gtk-cairo --enable-java-awt=gtk --enable-java-home --enable-languages=c,ada,c++,java,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-directory=arm --with-arch=armv6 --with-default-libstdcxx-abi=new --with-float=hard --with-fpu=vfp --with-target-system-zlib -v - ASUS TinkerBoard: --build=arm-linux-gnueabihf --disable-browser-plugin --disable-libitm --disable-libquadmath --disable-sjlj-exceptions --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-gtk-cairo --enable-java-awt=gtk --enable-java-home --enable-languages=c,ada,c++,java,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-directory=arm --with-arch=armv7-a --with-default-libstdcxx-abi=new --with-float=hard --with-fpu=vfpv3-d16 --with-mode=thumb --with-target-system-zlib -v - Jetson TX1 Max-P: --build=aarch64-linux-gnu --disable-browser-plugin --disable-libquadmath --disable-werror --enable-checking=release --enable-clocale=gnu --enable-fix-cortex-a53-843419 --enable-gnu-unique-object --enable-gtk-cairo --enable-java-awt=gtk --enable-java-home --enable-languages=c,ada,c++,java,go,d,fortran,objc,obj-c++ --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --target=aarch64-linux-gnu --with-arch-directory=aarch64 --with-default-libstdcxx-abi=new -v - ODROID-XU4: --build=arm-linux-gnueabihf --disable-libitm --disable-libquadmath --disable-libquadmath-support --disable-sjlj-exceptions --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --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-multilib --enable-multilib --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=armv7-a --with-default-libstdcxx-abi=new --with-float=hard --with-fpu=vfpv3-d16 --with-gcc-major-version-only --with-mode=thumb --with-target-system-zlib -v - Jetson Nano: --build=aarch64-linux-gnu --disable-libquadmath --disable-libquadmath-support --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-fix-cortex-a53-843419 --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-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --program-prefix=aarch64-linux-gnu- --target=aarch64-linux-gnu --with-default-libstdcxx-abi=new --with-gcc-major-version-only -v - ARMv8 Cortex-A73: --build=aarch64-linux-gnu --disable-libquadmath --disable-libquadmath-support --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-fix-cortex-a53-843419 --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-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --program-prefix=aarch64-linux-gnu- --target=aarch64-linux-gnu --with-default-libstdcxx-abi=new --with-gcc-major-version-only -v Processor Details- Jetson AGX Xavier: Scaling Governor: tegra_cpufreq schedutil- Jetson TX2 Max-P: Scaling Governor: tegra_cpufreq schedutil- Jetson TX2 Max-Q: Scaling Governor: tegra_cpufreq schedutil- Raspberry Pi 3 Model B+: Scaling Governor: BCM2835 Freq ondemand- ASUS TinkerBoard: Scaling Governor: cpufreq-dt interactive- Jetson TX1 Max-P: Scaling Governor: tegra-cpufreq interactive- ODROID-XU4: Scaling Governor: cpufreq-dt ondemand- Jetson Nano: Scaling Governor: tegra-cpufreq schedutil- ARMv8 Cortex-A73: Scaling Governor: arm-big-little performancePython Details- Jetson AGX Xavier: Python 2.7.15rc1 + Python 3.6.7- Jetson TX2 Max-P: Python 2.7.12 + Python 3.5.2- Jetson TX2 Max-Q: Python 2.7.12 + Python 3.5.2- Raspberry Pi 3 Model B+: Python 2.7.13 + Python 3.5.3- ASUS TinkerBoard: Python 2.7.13 + Python 3.5.3- Jetson TX1 Max-P: Python 2.7.12 + Python 3.5.2- ODROID-XU4: Python 2.7.15rc1 + Python 3.6.7- Jetson Nano: Python 2.7.15rc1 + Python 3.6.7- ARMv8 Cortex-A73: Python 2.7.15rc1 + Python 3.6.7Kernel Details- ODROID-XU4: usbhid.quirks=0x0eef:0x0005:0x0004Graphics Details- ODROID-XU4: EXA

Jetson AGX XavierJetson TX2 Max-PJetson TX2 Max-QRaspberry Pi 3 Model B+ASUS TinkerBoardJetson TX1 Max-PODROID-XU4Jetson NanoARMv8 Cortex-A73Logarithmic Result OverviewPhoronix Test Suite7-Zip CompressionTTSIOD 3D RendererPyBenchFLAC Audio EncodingRust Prime BenchmarkC-Ray

Jetson Nano Developer Kitc-ray: Total Time - 4K, 16 Rays Per Pixellczero: BLASrust-prime: Prime Number Test To 200,000,000ttsiod-renderer: Phong Rendering With Soft-Shadow Mappingcuda-mini-nbody: Originalopencv-bench: tensorrt-inference: ResNet152 - FP16 - 32 - Disabledtensorrt-inference: ResNet152 - INT8 - 32 - Disabledtensorrt-inference: VGG19 - INT8 - 32 - Disabledtensorrt-inference: VGG19 - FP16 - 32 - Disabledtensorrt-inference: ResNet152 - INT8 - 4 - Disabledtensorrt-inference: VGG16 - INT8 - 32 - Disabledpybench: Total For Average Test Timestensorrt-inference: VGG16 - FP16 - 32 - Disabledencode-flac: WAV To FLACcompress-zstd: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19tensorrt-inference: ResNet152 - FP16 - 4 - Disabledtensorrt-inference: ResNet50 - FP16 - 4 - Disabledtensorrt-inference: VGG16 - INT8 - 4 - Disabledtensorrt-inference: ResNet50 - INT8 - 32 - Disabledtensorrt-inference: VGG19 - FP16 - 4 - Disabledtensorrt-inference: VGG16 - FP16 - 4 - Disabledcompress-7zip: Compress Speed Testtensorrt-inference: ResNet50 - FP16 - 32 - Disabledtensorrt-inference: VGG19 - INT8 - 4 - Disabledtensorrt-inference: GoogleNet - FP16 - 32 - Disabledtensorrt-inference: GoogleNet - INT8 - 32 - Disabledtensorrt-inference: AlexNet - FP16 - 4 - Disabledtesseract-ocr: Time To OCR 7 Imagesglmark2: 1920 x 1080tensorrt-inference: GoogleNet - FP16 - 4 - Disabledtensorrt-inference: ResNet50 - INT8 - 4 - Disabledtensorrt-inference: AlexNet - FP16 - 32 - Disabledtensorrt-inference: GoogleNet - INT8 - 4 - Disabledlczero: CUDA + cuDNNtensorrt-inference: AlexNet - INT8 - 32 - Disabledtensorrt-inference: AlexNet - INT8 - 4 - Disabledlczero: CUDA + cuDNN FP16Jetson AGX XavierJetson TX2 Max-PJetson TX2 Max-QRaspberry Pi 3 Model B+ASUS TinkerBoardJetson TX1 Max-PODROID-XU4Jetson NanoARMv8 Cortex-A7335547.6232.3713347.13128259.82493.22394.66203.96372.73475.083007247.9554.4780.06224.19547.50303.781215.08172.50208.7619212636265.8110061693120071.942876796902.7820381146953314311432515.01585104.9649.268.2429641.9122.0715.9229.8318.2919.91540836.8765.07144.9735.1192.2817.5659.6926.5632.64559311114.3223313026419749.97462113301184869170.2528.856.7749332.6717.3612.5923.9414.5015.79873529.83104.28253.8027.3472.0114.2447.1521.0425.99329486.0811.4517910421615639.1537488.8823714820301097.6917.662.7420913339.53342.23201317181821.0521.2211502279.05496.622836753128.4545.09633979.20145.804508827574.1141.96520.70500997.034120180.6692115.37150.1940.944.07271.0417.387.767084104.77129.8715.7641.0425.0811.5914.35404946.5198.9355.66118132.6764683.3720.9620147.8214012884.1049224.3973.1157.42243.05523195.59152.045970110.73OpenBenchmarking.org

C-Ray

This is a test of C-Ray, a simple raytracer designed to test the floating-point CPU performance. This test is multi-threaded (16 threads per core), will shoot 8 rays per pixel for anti-aliasing, and will generate a 1600 x 1200 image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per PixelARMv8 Cortex-A73Jetson NanoODROID-XU4Jetson TX1 Max-PASUS TinkerBoardRaspberry Pi 3 Model B+Jetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier400800120016002000SE +/- 0.25, N = 3SE +/- 0.35, N = 3SE +/- 29.65, N = 9SE +/- 10.23, N = 3SE +/- 22.09, N = 3SE +/- 2.46, N = 3SE +/- 1.44, N = 3SE +/- 49.09, N = 9SE +/- 7.17, N = 9492921827753171820308695853551. (CC) gcc options: -lm -lpthread -O3

LeelaChessZero

LeelaChessZero (lc0 / lczero) is a chess engine automated vian neural networks. This test profile can be used for OpenCL, CUDA + cuDNN, and BLAS (CPU-based) benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.20.1Backend: BLASARMv8 Cortex-A73Jetson NanoJetson AGX Xavier1122334455SE +/- 0.10, N = 3SE +/- 0.03, N = 3SE +/- 0.62, N = 724.3915.3747.621. (CXX) g++ options: -lpthread -lz

Rust Prime Benchmark

Based on petehunt/rust-benchmark, this is a prime number benchmark that is multi-threaded and written in Rustlang. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRust Prime BenchmarkPrime Number Test To 200,000,000ARMv8 Cortex-A73Jetson NanoODROID-XU4Jetson TX1 Max-PASUS TinkerBoardRaspberry Pi 3 Model B+Jetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier400800120016002000SE +/- 0.02, N = 3SE +/- 0.22, N = 3SE +/- 0.37, N = 3SE +/- 0.77, N = 3SE +/- 187.90, N = 6SE +/- 1.55, N = 3SE +/- 0.09, N = 3SE +/- 0.04, N = 3SE +/- 0.00, N = 373.11150.19574.11128.451821.051097.69170.25104.9632.37-ldl -lrt -lpthread -lgcc_s -lc -lm -lutil1. (CC) gcc options: -pie -nodefaultlibs

TTSIOD 3D Renderer

A portable GPL 3D software renderer that supports OpenMP and Intel Threading Building Blocks with many different rendering modes. This version does not use OpenGL but is entirely CPU/software based. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterTTSIOD 3D Renderer 2.3bPhong Rendering With Soft-Shadow MappingARMv8 Cortex-A73Jetson NanoODROID-XU4Jetson TX1 Max-PASUS TinkerBoardRaspberry Pi 3 Model B+Jetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier306090120150SE +/- 0.05, N = 3SE +/- 0.11, N = 3SE +/- 0.97, N = 9SE +/- 0.04, N = 3SE +/- 0.27, N = 9SE +/- 0.16, N = 3SE +/- 0.46, N = 4SE +/- 0.15, N = 3SE +/- 1.63, N = 1257.4240.9441.9645.0921.2217.6628.8549.26133.001. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -lSDL -fopenmp -fwhole-program -lstdc++

CUDA Mini-Nbody

OpenBenchmarking.org(NBody^2)/s, More Is BetterCUDA Mini-Nbody 2015-11-10Test: OriginalJetson NanoJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier1122334455SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 34.076.778.2447.13

OpenCV Benchmark

Stress benchmark tests to measure time consumed by the OpenCV libraries installed Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenCV Benchmark 3.3.0ARMv8 Cortex-A73Jetson NanoODROID-XU4Raspberry Pi 3 Model B+Jetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier110220330440550SE +/- 0.26, N = 3SE +/- 4.66, N = 9SE +/- 5.31, N = 3SE +/- 5.74, N = 3SE +/- 0.27, N = 3SE +/- 1.57, N = 3243.05271.04520.702.74493.00296.00128.001. (CXX) g++ options: -std=c++11 -rdynamic

NVIDIA TensorRT Inference

This test profile uses any existing system installation of NVIDIA TensorRT for carrying out inference benchmarks with various neural networks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet152 - Precision: FP16 - Batch Size: 32 - DLA Cores: DisabledJetson NanoJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier60120180240300SE +/- 0.01, N = 3SE +/- 0.10, N = 3SE +/- 0.07, N = 3SE +/- 0.26, N = 317.3832.6741.91259.82

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet152 - Precision: INT8 - Batch Size: 32 - DLA Cores: DisabledJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier110220330440550SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.81, N = 317.3622.07493.22

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG19 - Precision: INT8 - Batch Size: 32 - DLA Cores: DisabledJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier90180270360450SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.23, N = 312.5915.92394.66

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG19 - Precision: FP16 - Batch Size: 32 - DLA Cores: DisabledJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier4080120160200SE +/- 0.07, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 323.9429.83203.96

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet152 - Precision: INT8 - Batch Size: 4 - DLA Cores: DisabledJetson NanoJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier80160240320400SE +/- 0.03, N = 3SE +/- 0.15, N = 3SE +/- 0.14, N = 3SE +/- 1.59, N = 37.7614.5018.29372.73

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG16 - Precision: INT8 - Batch Size: 32 - DLA Cores: DisabledJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier100200300400500SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.10, N = 315.7919.91475.08

PyBench

This test profile reports the total time of the different average timed test results from PyBench. PyBench reports average test times for different functions such as BuiltinFunctionCalls and NestedForLoops, with this total result providing a rough estimate as to Python's average performance on a given system. This test profile runs PyBench each time for 20 rounds. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test TimesARMv8 Cortex-A73Jetson NanoODROID-XU4Jetson TX1 Max-PASUS TinkerBoardRaspberry Pi 3 Model B+Jetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier4K8K12K16K20KSE +/- 9.24, N = 3SE +/- 37.23, N = 3SE +/- 30.99, N = 3SE +/- 18.55, N = 3SE +/- 854.75, N = 9SE +/- 43.80, N = 3SE +/- 42.52, N = 3SE +/- 33.86, N = 3SE +/- 4.67, N = 352317084500963391150220913873554083007

NVIDIA TensorRT Inference

This test profile uses any existing system installation of NVIDIA TensorRT for carrying out inference benchmarks with various neural networks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG16 - Precision: FP16 - Batch Size: 32 - DLA Cores: DisabledJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier50100150200250SE +/- 0.18, N = 3SE +/- 0.31, N = 3SE +/- 0.12, N = 329.8336.87247.95

FLAC Audio Encoding

This test times how long it takes to encode a sample WAV file to FLAC format five times. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.3.2WAV To FLACARMv8 Cortex-A73Jetson NanoODROID-XU4Jetson TX1 Max-PASUS TinkerBoardRaspberry Pi 3 Model B+Jetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier70140210280350SE +/- 0.27, N = 5SE +/- 0.83, N = 5SE +/- 0.31, N = 5SE +/- 0.74, N = 5SE +/- 2.51, N = 5SE +/- 0.98, N = 5SE +/- 0.18, N = 5SE +/- 0.15, N = 5SE +/- 0.61, N = 595.59104.7797.0379.20279.05339.53104.2865.0754.471. (CXX) g++ options: -O2 -fvisibility=hidden -logg -lm

Zstd Compression

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

OpenBenchmarking.orgSeconds, Fewer Is BetterZstd Compression 1.3.4Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19ARMv8 Cortex-A73Jetson NanoJetson TX1 Max-PASUS TinkerBoardRaspberry Pi 3 Model B+Jetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier110220330440550SE +/- 1.77, N = 3SE +/- 0.23, N = 3SE +/- 0.42, N = 3SE +/- 2.16, N = 3SE +/- 1.03, N = 3SE +/- 1.02, N = 3SE +/- 0.29, N = 3SE +/- 0.91, N = 3152.04129.87145.80496.62342.23253.80144.9780.061. (CC) gcc options: -O3 -pthread -lz -llzma

NVIDIA TensorRT Inference

This test profile uses any existing system installation of NVIDIA TensorRT for carrying out inference benchmarks with various neural networks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet152 - Precision: FP16 - Batch Size: 4 - DLA Cores: DisabledJetson NanoJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier50100150200250SE +/- 0.04, N = 3SE +/- 0.34, N = 3SE +/- 0.36, N = 3SE +/- 0.22, N = 315.7627.3435.11224.19

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet50 - Precision: FP16 - Batch Size: 4 - DLA Cores: DisabledJetson NanoJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier120240360480600SE +/- 0.25, N = 3SE +/- 1.10, N = 12SE +/- 1.32, N = 12SE +/- 0.03, N = 341.0472.0192.28547.50

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG16 - Precision: INT8 - Batch Size: 4 - DLA Cores: DisabledJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier70140210280350SE +/- 0.20, N = 5SE +/- 0.25, N = 6SE +/- 0.46, N = 314.2417.56303.78

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet50 - Precision: INT8 - Batch Size: 32 - DLA Cores: DisabledJetson NanoJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier30060090012001500SE +/- 0.06, N = 3SE +/- 0.08, N = 3SE +/- 0.04, N = 3SE +/- 0.25, N = 325.0847.1559.691215.08

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG19 - Precision: FP16 - Batch Size: 4 - DLA Cores: DisabledJetson NanoJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier4080120160200SE +/- 0.05, N = 2SE +/- 0.34, N = 3SE +/- 0.38, N = 3SE +/- 0.50, N = 311.5921.0426.56172.50

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG16 - Precision: FP16 - Batch Size: 4 - DLA Cores: DisabledJetson NanoJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier50100150200250SE +/- 0.02, N = 2SE +/- 0.13, N = 3SE +/- 0.50, N = 4SE +/- 0.10, N = 314.3525.9932.64208.76

7-Zip Compression

This is a test of 7-Zip using p7zip with its integrated benchmark feature or upstream 7-Zip for the Windows x64 build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 16.02Compress Speed TestARMv8 Cortex-A73Jetson NanoODROID-XU4Jetson TX1 Max-PASUS TinkerBoardRaspberry Pi 3 Model B+Jetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier4K8K12K16K20KSE +/- 2.40, N = 3SE +/- 18.00, N = 3SE +/- 89.16, N = 12SE +/- 13.43, N = 3SE +/- 34.93, N = 3SE +/- 23.74, N = 11SE +/- 13.05, N = 3SE +/- 20.85, N = 3SE +/- 274.18, N = 1259704049412045082836201332945593192121. (CXX) g++ options: -pipe -lpthread

NVIDIA TensorRT Inference

This test profile uses any existing system installation of NVIDIA TensorRT for carrying out inference benchmarks with various neural networks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet50 - Precision: FP16 - Batch Size: 32 - DLA Cores: DisabledJetson NanoJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier140280420560700SE +/- 0.02, N = 3SE +/- 0.86, N = 3SE +/- 1.22, N = 3SE +/- 1.23, N = 346.5186.08111.00636.00

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG19 - Precision: INT8 - Batch Size: 4 - DLA Cores: DisabledJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier60120180240300SE +/- 0.23, N = 3SE +/- 0.25, N = 4SE +/- 0.20, N = 311.4514.32265.81

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: GoogleNet - Precision: FP16 - Batch Size: 32 - DLA Cores: DisabledJetson NanoJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier2004006008001000SE +/- 0.19, N = 3SE +/- 2.17, N = 8SE +/- 4.50, N = 3SE +/- 0.21, N = 398.93179.00233.001006.00

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: GoogleNet - Precision: INT8 - Batch Size: 32 - DLA Cores: DisabledJetson NanoJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier400800120016002000SE +/- 0.18, N = 3SE +/- 0.07, N = 3SE +/- 0.74, N = 3SE +/- 8.72, N = 355.66104.00130.001693.00

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: AlexNet - Precision: FP16 - Batch Size: 4 - DLA Cores: DisabledJetson NanoJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier30060090012001500SE +/- 2.12, N = 12SE +/- 3.03, N = 6SE +/- 7.77, N = 12SE +/- 1.82, N = 31182162641200

Tesseract OCR

Tesseract-OCR is the open-source optical character recognition (OCR) engine for the conversion of text within images to raw text output. This test profile relies upon a system-supplied Tesseract installation. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTesseract OCR 4.0.0-beta.1Time To OCR 7 ImagesARMv8 Cortex-A73Jetson NanoODROID-XU4Jetson AGX Xavier4080120160200SE +/- 0.05, N = 3SE +/- 1.50, N = 3SE +/- 1.38, N = 3SE +/- 0.89, N = 3110.73132.67180.6671.94

GLmark2

This is a test of any system-installed GLMark2 OpenGL benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterGLmark2Resolution: 1920 x 1080Jetson NanoJetson AGX Xavier60012001800240030006462876

NVIDIA TensorRT Inference

This test profile uses any existing system installation of NVIDIA TensorRT for carrying out inference benchmarks with various neural networks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: GoogleNet - Precision: FP16 - Batch Size: 4 - DLA Cores: DisabledJetson NanoJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier2004006008001000SE +/- 0.70, N = 3SE +/- 1.90, N = 12SE +/- 2.27, N = 3SE +/- 2.48, N = 383.37156.00197.00796.00

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet50 - Precision: INT8 - Batch Size: 4 - DLA Cores: DisabledJetson NanoJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier2004006008001000SE +/- 0.36, N = 3SE +/- 0.64, N = 3SE +/- 0.79, N = 4SE +/- 1.86, N = 320.9639.1549.97902.78

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: AlexNet - Precision: FP16 - Batch Size: 32 - DLA Cores: DisabledJetson NanoJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier400800120016002000SE +/- 1.59, N = 3SE +/- 2.82, N = 3SE +/- 7.68, N = 12SE +/- 2.07, N = 32013744622038

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: GoogleNet - Precision: INT8 - Batch Size: 4 - DLA Cores: DisabledJetson NanoJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier2004006008001000SE +/- 0.60, N = 3SE +/- 1.32, N = 3SE +/- 1.65, N = 3SE +/- 4.31, N = 347.8288.88113.001146.00

LeelaChessZero

LeelaChessZero (lc0 / lczero) is a chess engine automated vian neural networks. This test profile can be used for OpenCL, CUDA + cuDNN, and BLAS (CPU-based) benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.20.1Backend: CUDA + cuDNNJetson NanoJetson AGX Xavier2004006008001000SE +/- 0.26, N = 3SE +/- 6.14, N = 31409531. (CXX) g++ options: -lpthread -lz

NVIDIA TensorRT Inference

This test profile uses any existing system installation of NVIDIA TensorRT for carrying out inference benchmarks with various neural networks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: AlexNet - Precision: INT8 - Batch Size: 32 - DLA Cores: DisabledJetson NanoJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier7001400210028003500SE +/- 0.06, N = 3SE +/- 1.39, N = 3SE +/- 0.52, N = 3SE +/- 1.06, N = 31282373013143

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: AlexNet - Precision: INT8 - Batch Size: 4 - DLA Cores: DisabledJetson NanoJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier2004006008001000SE +/- 0.72, N = 3SE +/- 0.91, N = 3SE +/- 2.79, N = 5SE +/- 2.59, N = 384.10148.00184.001143.00

LeelaChessZero

LeelaChessZero (lc0 / lczero) is a chess engine automated vian neural networks. This test profile can be used for OpenCL, CUDA + cuDNN, and BLAS (CPU-based) benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.20.1Backend: CUDA + cuDNN FP16Jetson AGX Xavier5001000150020002500SE +/- 7.60, N = 32515.011. (CXX) g++ options: -lpthread -lz

Meta Performance Per Dollar

OpenBenchmarking.orgPerformance Per Dollar, More Is BetterMeta Performance Per DollarPerformance Per DollarARMv8 Cortex-A7351015202519.171. $64.95 reported value. Average value: 1244.91.

Tesseract OCR

OpenBenchmarking.orgSeconds x Dollar, Fewer Is BetterTesseract OCR 4.0.0-beta.1Performance / Cost - Time To OCR 7 ImagesARMv8 Cortex-A73Jetson NanoODROID-XU4Jetson AGX Xavier20K40K60K80K100K7191.9113134.3311200.9293450.061. ARMv8 Cortex-A73: $64.95 reported cost.2. Jetson Nano: $99 reported cost.3. ODROID-XU4: $62 reported cost.4. Jetson AGX Xavier: $1299 reported cost.

LeelaChessZero

OpenBenchmarking.orgNodes Per Second Per Dollar, More Is BetterLeelaChessZero 0.20.1Performance / Cost - Backend: CUDA + cuDNN FP16Jetson AGX Xavier0.43650.8731.30951.7462.18251.941. $1299 reported cost.

OpenBenchmarking.orgNodes Per Second Per Dollar, More Is BetterLeelaChessZero 0.20.1Performance / Cost - Backend: CUDA + cuDNNJetson NanoJetson AGX Xavier0.31730.63460.95191.26921.58651.410.731. Jetson Nano: $99 reported cost.2. Jetson AGX Xavier: $1299 reported cost.

OpenBenchmarking.orgNodes Per Second Per Dollar, More Is BetterLeelaChessZero 0.20.1Performance / Cost - Backend: BLASARMv8 Cortex-A73Jetson NanoJetson AGX Xavier0.08550.1710.25650.3420.42750.380.160.041. ARMv8 Cortex-A73: $64.95 reported cost.2. Jetson Nano: $99 reported cost.3. Jetson AGX Xavier: $1299 reported cost.

GLmark2

OpenBenchmarking.orgScore Per Dollar, More Is BetterGLmark2Performance / Cost - Resolution: 1920 x 1080Jetson NanoJetson AGX Xavier2468106.532.211. Jetson Nano: $99 reported cost.2. Jetson AGX Xavier: $1299 reported cost.

OpenCV Benchmark

OpenBenchmarking.orgSeconds x Dollar, Fewer Is BetterOpenCV Benchmark 3.3.0Performance / Cost -ARMv8 Cortex-A73Jetson NanoODROID-XU4Raspberry Pi 3 Model B+Jetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier60K120K180K240K300K15786.1026832.9632283.4095.90295307.00177304.00166272.001. ARMv8 Cortex-A73: $64.95 reported cost.2. Jetson Nano: $99 reported cost.3. ODROID-XU4: $62 reported cost.4. Raspberry Pi 3 Model B+: $35 reported cost.5. Jetson TX2 Max-Q: $599 reported cost.6. Jetson TX2 Max-P: $599 reported cost.7. Jetson AGX Xavier: $1299 reported cost.

NVIDIA TensorRT Inference

OpenBenchmarking.orgImages Per Second Per Dollar, More Is BetterNVIDIA TensorRT InferencePerformance / Cost - Neural Network: ResNet152 - Precision: INT8 - Batch Size: 32 - DLA Cores: DisabledJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier0.08550.1710.25650.3420.42750.030.040.381. Jetson TX2 Max-Q: $599 reported cost.2. Jetson TX2 Max-P: $599 reported cost.3. Jetson AGX Xavier: $1299 reported cost.

OpenBenchmarking.orgImages Per Second Per Dollar, More Is BetterNVIDIA TensorRT InferencePerformance / Cost - Neural Network: ResNet152 - Precision: FP16 - Batch Size: 32 - DLA Cores: DisabledJetson NanoJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier0.0450.090.1350.180.2250.180.050.070.201. Jetson Nano: $99 reported cost.2. Jetson TX2 Max-Q: $599 reported cost.3. Jetson TX2 Max-P: $599 reported cost.4. Jetson AGX Xavier: $1299 reported cost.

OpenBenchmarking.orgImages Per Second Per Dollar, More Is BetterNVIDIA TensorRT InferencePerformance / Cost - Neural Network: GoogleNet - Precision: INT8 - Batch Size: 32 - DLA Cores: DisabledJetson NanoJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier0.29250.5850.87751.171.46250.560.170.221.301. Jetson Nano: $99 reported cost.2. Jetson TX2 Max-Q: $599 reported cost.3. Jetson TX2 Max-P: $599 reported cost.4. Jetson AGX Xavier: $1299 reported cost.

OpenBenchmarking.orgImages Per Second Per Dollar, More Is BetterNVIDIA TensorRT InferencePerformance / Cost - Neural Network: GoogleNet - Precision: FP16 - Batch Size: 32 - DLA Cores: DisabledJetson NanoJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier0.2250.450.6750.91.1251.000.300.390.771. Jetson Nano: $99 reported cost.2. Jetson TX2 Max-Q: $599 reported cost.3. Jetson TX2 Max-P: $599 reported cost.4. Jetson AGX Xavier: $1299 reported cost.

OpenBenchmarking.orgImages Per Second Per Dollar, More Is BetterNVIDIA TensorRT InferencePerformance / Cost - Neural Network: ResNet50 - Precision: INT8 - Batch Size: 32 - DLA Cores: DisabledJetson NanoJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier0.21150.4230.63450.8461.05750.250.080.100.941. Jetson Nano: $99 reported cost.2. Jetson TX2 Max-Q: $599 reported cost.3. Jetson TX2 Max-P: $599 reported cost.4. Jetson AGX Xavier: $1299 reported cost.

OpenBenchmarking.orgImages Per Second Per Dollar, More Is BetterNVIDIA TensorRT InferencePerformance / Cost - Neural Network: ResNet50 - Precision: FP16 - Batch Size: 32 - DLA Cores: DisabledJetson NanoJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier0.11030.22060.33090.44120.55150.470.140.190.491. Jetson Nano: $99 reported cost.2. Jetson TX2 Max-Q: $599 reported cost.3. Jetson TX2 Max-P: $599 reported cost.4. Jetson AGX Xavier: $1299 reported cost.

OpenBenchmarking.orgImages Per Second Per Dollar, More Is BetterNVIDIA TensorRT InferencePerformance / Cost - Neural Network: ResNet152 - Precision: INT8 - Batch Size: 4 - DLA Cores: DisabledJetson NanoJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier0.06530.13060.19590.26120.32650.080.020.030.291. Jetson Nano: $99 reported cost.2. Jetson TX2 Max-Q: $599 reported cost.3. Jetson TX2 Max-P: $599 reported cost.4. Jetson AGX Xavier: $1299 reported cost.

OpenBenchmarking.orgImages Per Second Per Dollar, More Is BetterNVIDIA TensorRT InferencePerformance / Cost - Neural Network: ResNet152 - Precision: FP16 - Batch Size: 4 - DLA Cores: DisabledJetson NanoJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier0.03830.07660.11490.15320.19150.160.050.060.171. Jetson Nano: $99 reported cost.2. Jetson TX2 Max-Q: $599 reported cost.3. Jetson TX2 Max-P: $599 reported cost.4. Jetson AGX Xavier: $1299 reported cost.

OpenBenchmarking.orgImages Per Second Per Dollar, More Is BetterNVIDIA TensorRT InferencePerformance / Cost - Neural Network: GoogleNet - Precision: INT8 - Batch Size: 4 - DLA Cores: DisabledJetson NanoJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier0.1980.3960.5940.7920.990.480.150.190.881. Jetson Nano: $99 reported cost.2. Jetson TX2 Max-Q: $599 reported cost.3. Jetson TX2 Max-P: $599 reported cost.4. Jetson AGX Xavier: $1299 reported cost.

OpenBenchmarking.orgImages Per Second Per Dollar, More Is BetterNVIDIA TensorRT InferencePerformance / Cost - Neural Network: GoogleNet - Precision: FP16 - Batch Size: 4 - DLA Cores: DisabledJetson NanoJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier0.1890.3780.5670.7560.9450.840.260.330.611. Jetson Nano: $99 reported cost.2. Jetson TX2 Max-Q: $599 reported cost.3. Jetson TX2 Max-P: $599 reported cost.4. Jetson AGX Xavier: $1299 reported cost.

OpenBenchmarking.orgImages Per Second Per Dollar, More Is BetterNVIDIA TensorRT InferencePerformance / Cost - Neural Network: ResNet50 - Precision: INT8 - Batch Size: 4 - DLA Cores: DisabledJetson NanoJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier0.15530.31060.46590.62120.77650.210.070.080.691. Jetson Nano: $99 reported cost.2. Jetson TX2 Max-Q: $599 reported cost.3. Jetson TX2 Max-P: $599 reported cost.4. Jetson AGX Xavier: $1299 reported cost.

OpenBenchmarking.orgImages Per Second Per Dollar, More Is BetterNVIDIA TensorRT InferencePerformance / Cost - Neural Network: ResNet50 - Precision: FP16 - Batch Size: 4 - DLA Cores: DisabledJetson NanoJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier0.09450.1890.28350.3780.47250.410.120.150.421. Jetson Nano: $99 reported cost.2. Jetson TX2 Max-Q: $599 reported cost.3. Jetson TX2 Max-P: $599 reported cost.4. Jetson AGX Xavier: $1299 reported cost.

OpenBenchmarking.orgImages Per Second Per Dollar, More Is BetterNVIDIA TensorRT InferencePerformance / Cost - Neural Network: AlexNet - Precision: INT8 - Batch Size: 32 - DLA Cores: DisabledJetson NanoJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier0.54451.0891.63352.1782.72251.290.400.502.421. Jetson Nano: $99 reported cost.2. Jetson TX2 Max-Q: $599 reported cost.3. Jetson TX2 Max-P: $599 reported cost.4. Jetson AGX Xavier: $1299 reported cost.

OpenBenchmarking.orgImages Per Second Per Dollar, More Is BetterNVIDIA TensorRT InferencePerformance / Cost - Neural Network: AlexNet - Precision: FP16 - Batch Size: 32 - DLA Cores: DisabledJetson NanoJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier0.45680.91361.37041.82722.2842.030.620.771.571. Jetson Nano: $99 reported cost.2. Jetson TX2 Max-Q: $599 reported cost.3. Jetson TX2 Max-P: $599 reported cost.4. Jetson AGX Xavier: $1299 reported cost.

OpenBenchmarking.orgImages Per Second Per Dollar, More Is BetterNVIDIA TensorRT InferencePerformance / Cost - Neural Network: AlexNet - Precision: INT8 - Batch Size: 4 - DLA Cores: DisabledJetson NanoJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier0.1980.3960.5940.7920.990.850.250.310.881. Jetson Nano: $99 reported cost.2. Jetson TX2 Max-Q: $599 reported cost.3. Jetson TX2 Max-P: $599 reported cost.4. Jetson AGX Xavier: $1299 reported cost.

OpenBenchmarking.orgImages Per Second Per Dollar, More Is BetterNVIDIA TensorRT InferencePerformance / Cost - Neural Network: AlexNet - Precision: FP16 - Batch Size: 4 - DLA Cores: DisabledJetson NanoJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier0.26780.53560.80341.07121.3391.190.360.440.921. Jetson Nano: $99 reported cost.2. Jetson TX2 Max-Q: $599 reported cost.3. Jetson TX2 Max-P: $599 reported cost.4. Jetson AGX Xavier: $1299 reported cost.

OpenBenchmarking.orgImages Per Second Per Dollar, More Is BetterNVIDIA TensorRT InferencePerformance / Cost - Neural Network: VGG19 - Precision: INT8 - Batch Size: 32 - DLA Cores: DisabledJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier0.06750.1350.20250.270.33750.020.030.301. Jetson TX2 Max-Q: $599 reported cost.2. Jetson TX2 Max-P: $599 reported cost.3. Jetson AGX Xavier: $1299 reported cost.

OpenBenchmarking.orgImages Per Second Per Dollar, More Is BetterNVIDIA TensorRT InferencePerformance / Cost - Neural Network: VGG19 - Precision: FP16 - Batch Size: 32 - DLA Cores: DisabledJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier0.0360.0720.1080.1440.180.040.050.161. Jetson TX2 Max-Q: $599 reported cost.2. Jetson TX2 Max-P: $599 reported cost.3. Jetson AGX Xavier: $1299 reported cost.

OpenBenchmarking.orgImages Per Second Per Dollar, More Is BetterNVIDIA TensorRT InferencePerformance / Cost - Neural Network: VGG16 - Precision: INT8 - Batch Size: 32 - DLA Cores: DisabledJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier0.08330.16660.24990.33320.41650.030.030.371. Jetson TX2 Max-Q: $599 reported cost.2. Jetson TX2 Max-P: $599 reported cost.3. Jetson AGX Xavier: $1299 reported cost.

OpenBenchmarking.orgImages Per Second Per Dollar, More Is BetterNVIDIA TensorRT InferencePerformance / Cost - Neural Network: VGG16 - Precision: FP16 - Batch Size: 32 - DLA Cores: DisabledJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier0.04280.08560.12840.17120.2140.050.060.191. Jetson TX2 Max-Q: $599 reported cost.2. Jetson TX2 Max-P: $599 reported cost.3. Jetson AGX Xavier: $1299 reported cost.

OpenBenchmarking.orgImages Per Second Per Dollar, More Is BetterNVIDIA TensorRT InferencePerformance / Cost - Neural Network: VGG19 - Precision: INT8 - Batch Size: 4 - DLA Cores: DisabledJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier0.0450.090.1350.180.2250.020.020.201. Jetson TX2 Max-Q: $599 reported cost.2. Jetson TX2 Max-P: $599 reported cost.3. Jetson AGX Xavier: $1299 reported cost.

OpenBenchmarking.orgImages Per Second Per Dollar, More Is BetterNVIDIA TensorRT InferencePerformance / Cost - Neural Network: VGG19 - Precision: FP16 - Batch Size: 4 - DLA Cores: DisabledJetson NanoJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier0.02930.05860.08790.11720.14650.120.040.040.131. Jetson Nano: $99 reported cost.2. Jetson TX2 Max-Q: $599 reported cost.3. Jetson TX2 Max-P: $599 reported cost.4. Jetson AGX Xavier: $1299 reported cost.

OpenBenchmarking.orgImages Per Second Per Dollar, More Is BetterNVIDIA TensorRT InferencePerformance / Cost - Neural Network: VGG16 - Precision: INT8 - Batch Size: 4 - DLA Cores: DisabledJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier0.05180.10360.15540.20720.2590.020.030.231. Jetson TX2 Max-Q: $599 reported cost.2. Jetson TX2 Max-P: $599 reported cost.3. Jetson AGX Xavier: $1299 reported cost.

OpenBenchmarking.orgImages Per Second Per Dollar, More Is BetterNVIDIA TensorRT InferencePerformance / Cost - Neural Network: VGG16 - Precision: FP16 - Batch Size: 4 - DLA Cores: DisabledJetson NanoJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier0.0360.0720.1080.1440.180.140.040.050.161. Jetson Nano: $99 reported cost.2. Jetson TX2 Max-Q: $599 reported cost.3. Jetson TX2 Max-P: $599 reported cost.4. Jetson AGX Xavier: $1299 reported cost.

CUDA Mini-Nbody

OpenBenchmarking.org(NBody^2)/s Per Dollar, More Is BetterCUDA Mini-Nbody 2015-11-10Performance / Cost - Test: OriginalJetson NanoJetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier0.0090.0180.0270.0360.0450.040.010.010.041. Jetson Nano: $99 reported cost.2. Jetson TX2 Max-Q: $599 reported cost.3. Jetson TX2 Max-P: $599 reported cost.4. Jetson AGX Xavier: $1299 reported cost.

PyBench

OpenBenchmarking.orgMilliseconds x Dollar, Fewer Is BetterPyBench 2018-02-16Performance / Cost - Total For Average Test TimesARMv8 Cortex-A73Jetson NanoODROID-XU4Jetson TX1 Max-PASUS TinkerBoardRaspberry Pi 3 Model B+Jetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier1.1M2.2M3.3M4.4M5.5M339753.45701316.00310558.003163161.00759132.00731955.005232265.003239392.003906093.001. ARMv8 Cortex-A73: $64.95 reported cost.2. Jetson Nano: $99 reported cost.3. ODROID-XU4: $62 reported cost.4. Jetson TX1 Max-P: $499 reported cost.5. ASUS TinkerBoard: $66 reported cost.6. Raspberry Pi 3 Model B+: $35 reported cost.7. Jetson TX2 Max-Q: $599 reported cost.8. Jetson TX2 Max-P: $599 reported cost.9. Jetson AGX Xavier: $1299 reported cost.

FLAC Audio Encoding

OpenBenchmarking.orgSeconds x Dollar, Fewer Is BetterFLAC Audio Encoding 1.3.2Performance / Cost - WAV To FLACARMv8 Cortex-A73Jetson NanoODROID-XU4Jetson TX1 Max-PASUS TinkerBoardRaspberry Pi 3 Model B+Jetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier15K30K45K60K75K6208.5710372.236015.8639520.8018417.3011883.5562463.7238976.9370756.531. ARMv8 Cortex-A73: $64.95 reported cost.2. Jetson Nano: $99 reported cost.3. ODROID-XU4: $62 reported cost.4. Jetson TX1 Max-P: $499 reported cost.5. ASUS TinkerBoard: $66 reported cost.6. Raspberry Pi 3 Model B+: $35 reported cost.7. Jetson TX2 Max-Q: $599 reported cost.8. Jetson TX2 Max-P: $599 reported cost.9. Jetson AGX Xavier: $1299 reported cost.

Zstd Compression

OpenBenchmarking.orgSeconds x Dollar, Fewer Is BetterZstd Compression 1.3.4Performance / Cost - Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19ARMv8 Cortex-A73Jetson NanoJetson TX1 Max-PASUS TinkerBoardRaspberry Pi 3 Model B+Jetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier30K60K90K120K150K9875.0012857.1372754.2032776.9211978.05152026.2086837.03103997.941. ARMv8 Cortex-A73: $64.95 reported cost.2. Jetson Nano: $99 reported cost.3. Jetson TX1 Max-P: $499 reported cost.4. ASUS TinkerBoard: $66 reported cost.5. Raspberry Pi 3 Model B+: $35 reported cost.6. Jetson TX2 Max-Q: $599 reported cost.7. Jetson TX2 Max-P: $599 reported cost.8. Jetson AGX Xavier: $1299 reported cost.

Rust Prime Benchmark

OpenBenchmarking.orgSeconds x Dollar, Fewer Is BetterRust Prime BenchmarkPerformance / Cost - Prime Number Test To 200,000,000ARMv8 Cortex-A73Jetson NanoODROID-XU4Jetson TX1 Max-PASUS TinkerBoardRaspberry Pi 3 Model B+Jetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier30K60K90K120K150K4748.4914868.8135594.8264096.55120189.3038419.15101979.7562871.0442048.631. ARMv8 Cortex-A73: $64.95 reported cost.2. Jetson Nano: $99 reported cost.3. ODROID-XU4: $62 reported cost.4. Jetson TX1 Max-P: $499 reported cost.5. ASUS TinkerBoard: $66 reported cost.6. Raspberry Pi 3 Model B+: $35 reported cost.7. Jetson TX2 Max-Q: $599 reported cost.8. Jetson TX2 Max-P: $599 reported cost.9. Jetson AGX Xavier: $1299 reported cost.

C-Ray

OpenBenchmarking.orgSeconds x Dollar, Fewer Is BetterC-Ray 1.1Performance / Cost - Total Time - 4K, 16 Rays Per PixelARMv8 Cortex-A73Jetson NanoODROID-XU4Jetson TX1 Max-PASUS TinkerBoardRaspberry Pi 3 Model B+Jetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier110K220K330K440K550K31940.4691179.0051274.00375747.00113388.0071050.00520531.00350415.00461145.001. ARMv8 Cortex-A73: $64.95 reported cost.2. Jetson Nano: $99 reported cost.3. ODROID-XU4: $62 reported cost.4. Jetson TX1 Max-P: $499 reported cost.5. ASUS TinkerBoard: $66 reported cost.6. Raspberry Pi 3 Model B+: $35 reported cost.7. Jetson TX2 Max-Q: $599 reported cost.8. Jetson TX2 Max-P: $599 reported cost.9. Jetson AGX Xavier: $1299 reported cost.

7-Zip Compression

OpenBenchmarking.orgMIPS Per Dollar, More Is Better7-Zip Compression 16.02Performance / Cost - Compress Speed TestARMv8 Cortex-A73Jetson NanoODROID-XU4Jetson TX1 Max-PASUS TinkerBoardRaspberry Pi 3 Model B+Jetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier2040608010091.9240.9066.459.0342.9757.515.509.3414.791. ARMv8 Cortex-A73: $64.95 reported cost.2. Jetson Nano: $99 reported cost.3. ODROID-XU4: $62 reported cost.4. Jetson TX1 Max-P: $499 reported cost.5. ASUS TinkerBoard: $66 reported cost.6. Raspberry Pi 3 Model B+: $35 reported cost.7. Jetson TX2 Max-Q: $599 reported cost.8. Jetson TX2 Max-P: $599 reported cost.9. Jetson AGX Xavier: $1299 reported cost.

TTSIOD 3D Renderer

OpenBenchmarking.orgFPS Per Dollar, More Is BetterTTSIOD 3D Renderer 2.3bPerformance / Cost - Phong Rendering With Soft-Shadow MappingARMv8 Cortex-A73Jetson NanoODROID-XU4Jetson TX1 Max-PASUS TinkerBoardRaspberry Pi 3 Model B+Jetson TX2 Max-QJetson TX2 Max-PJetson AGX Xavier0.1980.3960.5940.7920.990.880.410.680.090.320.500.050.080.101. ARMv8 Cortex-A73: $64.95 reported cost.2. Jetson Nano: $99 reported cost.3. ODROID-XU4: $62 reported cost.4. Jetson TX1 Max-P: $499 reported cost.5. ASUS TinkerBoard: $66 reported cost.6. Raspberry Pi 3 Model B+: $35 reported cost.7. Jetson TX2 Max-Q: $599 reported cost.8. Jetson TX2 Max-P: $599 reported cost.9. Jetson AGX Xavier: $1299 reported cost.

77 Results Shown

C-Ray
LeelaChessZero
Rust Prime Benchmark
TTSIOD 3D Renderer
CUDA Mini-Nbody
OpenCV Benchmark
NVIDIA TensorRT Inference:
  ResNet152 - FP16 - 32 - Disabled
  ResNet152 - INT8 - 32 - Disabled
  VGG19 - INT8 - 32 - Disabled
  VGG19 - FP16 - 32 - Disabled
  ResNet152 - INT8 - 4 - Disabled
  VGG16 - INT8 - 32 - Disabled
PyBench
NVIDIA TensorRT Inference
FLAC Audio Encoding
Zstd Compression
NVIDIA TensorRT Inference:
  ResNet152 - FP16 - 4 - Disabled
  ResNet50 - FP16 - 4 - Disabled
  VGG16 - INT8 - 4 - Disabled
  ResNet50 - INT8 - 32 - Disabled
  VGG19 - FP16 - 4 - Disabled
  VGG16 - FP16 - 4 - Disabled
7-Zip Compression
NVIDIA TensorRT Inference:
  ResNet50 - FP16 - 32 - Disabled
  VGG19 - INT8 - 4 - Disabled
  GoogleNet - FP16 - 32 - Disabled
  GoogleNet - INT8 - 32 - Disabled
  AlexNet - FP16 - 4 - Disabled
Tesseract OCR
GLmark2
NVIDIA TensorRT Inference:
  GoogleNet - FP16 - 4 - Disabled
  ResNet50 - INT8 - 4 - Disabled
  AlexNet - FP16 - 32 - Disabled
  GoogleNet - INT8 - 4 - Disabled
LeelaChessZero
NVIDIA TensorRT Inference:
  AlexNet - INT8 - 32 - Disabled
  AlexNet - INT8 - 4 - Disabled
LeelaChessZero
Meta Performance Per Dollar:
  Performance Per Dollar
  Performance / Cost - Time To OCR 7 Images
  Performance / Cost - CUDA + cuDNN FP16
  Performance / Cost - CUDA + cuDNN
  Performance / Cost - BLAS
  Performance / Cost - 1920 x 1080
  Performance / Cost -
  Performance / Cost - ResNet152 - INT8 - 32 - Disabled
  Performance / Cost - ResNet152 - FP16 - 32 - Disabled
  Performance / Cost - GoogleNet - INT8 - 32 - Disabled
  Performance / Cost - GoogleNet - FP16 - 32 - Disabled
  Performance / Cost - ResNet50 - INT8 - 32 - Disabled
  Performance / Cost - ResNet50 - FP16 - 32 - Disabled
  Performance / Cost - ResNet152 - INT8 - 4 - Disabled
  Performance / Cost - ResNet152 - FP16 - 4 - Disabled
  Performance / Cost - GoogleNet - INT8 - 4 - Disabled
  Performance / Cost - GoogleNet - FP16 - 4 - Disabled
  Performance / Cost - ResNet50 - INT8 - 4 - Disabled
  Performance / Cost - ResNet50 - FP16 - 4 - Disabled
  Performance / Cost - AlexNet - INT8 - 32 - Disabled
  Performance / Cost - AlexNet - FP16 - 32 - Disabled
  Performance / Cost - AlexNet - INT8 - 4 - Disabled
  Performance / Cost - AlexNet - FP16 - 4 - Disabled
  Performance / Cost - VGG19 - INT8 - 32 - Disabled
  Performance / Cost - VGG19 - FP16 - 32 - Disabled
  Performance / Cost - VGG16 - INT8 - 32 - Disabled
  Performance / Cost - VGG16 - FP16 - 32 - Disabled
  Performance / Cost - VGG19 - INT8 - 4 - Disabled
  Performance / Cost - VGG19 - FP16 - 4 - Disabled
  Performance / Cost - VGG16 - INT8 - 4 - Disabled
  Performance / Cost - VGG16 - FP16 - 4 - Disabled
  Performance / Cost - Original
  Performance / Cost - Total For Average Test Times
  Performance / Cost - WAV To FLAC
  Performance / Cost - Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19
  Performance / Cost - Prime Number Test To 200,000,000
  Performance / Cost - Total Time - 4K, 16 Rays Per Pixel
  Performance / Cost - Compress Speed Test
  Performance / Cost - Phong Rendering With Soft-Shadow Mapping