NVIDIA Jetson Nano Benchmarks

ARMv8 rev 1 testing with a NVIDIA Jetson Nano Developer Kit and NVIDIA TEGRA on Ubuntu 18.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/1908084-HV-1903316HV84&grw&sor.

NVIDIA Jetson Nano BenchmarksProcessorMotherboardMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLVulkanCompilerFile-SystemScreen ResolutionJetson NanoNanonanoNano 5WNano 10wARMv8 rev 1 @ 1.43GHz (4 Cores)jetson-nano4096MB32GB GB1QTNVIDIA Tegra X1VE228Realtek RTL8111/8168/8411Ubuntu 18.044.9.140-tegra (aarch64)Unity 7.5.0X Server 1.19.6NVIDIA 32.1.04.6.01.1.85GCC 7.3.0 + CUDA 10.0ext41920x1080ARMv8 rev 1 @ 0.92GHz (2 Cores)NVIDIA Jetson Nano Developer Kit64GB SN64GNVIDIA TEGRANVIDIA 1.0.0GCC 7.4.0 + CUDA 10.0ARMv8 rev 1 @ 1.43GHz (4 Cores)OpenBenchmarking.orgCompiler Details- --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- Scaling Governor: tegra-cpufreq schedutilPython Details- Jetson Nano: Python 2.7.15rc1 + Python 3.6.7- Nano: Python 2.7.15+ + Python 3.6.8- nano: Python 2.7.15+ + Python 3.6.8- Nano 5W: Python 2.7.15+ + Python 3.6.8- Nano 10w: Python 2.7.15+ + Python 3.6.8Java Details- Nano: OpenJDK Runtime Environment (build 11.0.3+7-Ubuntu-1ubuntu218.04.1)- nano: OpenJDK Runtime Environment (build 11.0.3+7-Ubuntu-1ubuntu218.04.1)- Nano 5W: OpenJDK Runtime Environment (build 11.0.3+7-Ubuntu-1ubuntu218.04.1)- Nano 10w: OpenJDK Runtime Environment (build 11.0.4+11-post-Ubuntu-1ubuntu218.04.3)

NVIDIA Jetson Nano Benchmarkscuda-mini-nbody: SOA Data Layoutcuda-mini-nbody: Flush Denormals To Zerocuda-mini-nbody: Loop Unrollingtensorrt-inference: GoogleNet - INT8 - 1 - Disabledcompress-xz: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9mbw: Memory Copy - 128 MiBtensorrt-inference: ResNet50 - INT8 - 8 - Disabledmbw: Memory Copy - 512 MiBtensorrt-inference: AlexNet - INT8 - 32 - Disabledtensorrt-inference: GoogleNet - INT8 - 4 - Disabledtensorrt-inference: AlexNet - INT8 - 16 - Disabledtensorrt-inference: VGG16 - FP16 - 1 - Disabledtensorrt-inference: AlexNet - FP16 - 16 - Disabledtensorrt-inference: ResNet50 - FP16 - 8 - Disabledtensorrt-inference: ResNet50 - INT8 - 4 - Disabledtensorrt-inference: AlexNet - FP16 - 4 - Disabledtensorrt-inference: AlexNet - FP16 - 8 - Disabledtensorrt-inference: VGG19 - FP16 - 4 - Disabledtensorrt-inference: AlexNet - FP16 - 1 - Disabledtensorrt-inference: VGG19 - FP16 - 1 - Disabledtensorrt-inference: VGG16 - FP16 - 8 - Disabledtensorrt-inference: VGG16 - FP16 - 4 - Disabledtensorrt-inference: ResNet50 - FP16 - 1 - Disabledtensorrt-inference: AlexNet - INT8 - 1 - Disabledtensorrt-inference: ResNet50 - FP16 - 4 - Disabledtensorrt-inference: AlexNet - INT8 - 4 - Disabledtensorrt-inference: ResNet50 - INT8 - 1 - Disabledtensorrt-inference: AlexNet - INT8 - 8 - Disabledmbw: Memory Copy, Fixed Block Size - 128 MiBtensorrt-inference: AlexNet - FP16 - 32 - Disabledmbw: Memory Copy, Fixed Block Size - 512 MiBtensorrt-inference: GoogleNet - FP16 - 8 - Disabledt-test1: 1t-test1: 2ramspeed: Add - Integertensorrt-inference: GoogleNet - FP16 - 1 - Disabledtensorrt-inference: ResNet152 - FP16 - 16 - Disabledtensorrt-inference: ResNet152 - FP16 - 32 - Disabledtensorrt-inference: GoogleNet - INT8 - 16 - Disabledtensorrt-inference: GoogleNet - INT8 - 32 - Disabledtensorrt-inference: GoogleNet - FP16 - 16 - Disabledtensorrt-inference: GoogleNet - FP16 - 32 - Disabledtensorrt-inference: ResNet50 - INT8 - 16 - Disabledtensorrt-inference: ResNet50 - INT8 - 32 - Disabledtensorrt-inference: ResNet50 - FP16 - 16 - Disabledtensorrt-inference: ResNet50 - FP16 - 32 - Disabledtensorrt-inference: ResNet152 - INT8 - 1 - Disabledtensorrt-inference: ResNet152 - FP16 - 8 - Disabledtensorrt-inference: ResNet152 - FP16 - 4 - Disabledramspeed: Copy - Integerramspeed: Triad - Integertensorrt-inference: GoogleNet - FP16 - 4 - Disabledramspeed: Scale - Integerramspeed: Average - Integercuda-mini-nbody: Cache Blockingglmark2: 1024 x 768glmark2: 1280 x 1024glmark2: 1920 x 1080lczero: BLAStensorrt-inference: ResNet152 - FP16 - 1 - Disabledlczero: CUDA + cuDNNj2dbench: Text Renderingj2dbench: Image Renderingj2dbench: Vector Graphics Renderingcompress-7zip: Compress Speed Testtensorrt-inference: GoogleNet - INT8 - 8 - Disabledglmark2: 800 x 600compress-zstd: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19cuda-mini-nbody: Originalbuild-linux-kernel: Time To Compilex264: H.264 Video EncodingJetson NanoNanonanoNano 5WNano 10w3.663.668.9335.8744.43342022.163439128.5547.83113.7610.2916942.0520.5911513411.6154.868.7014.6014.1827.3740.4840.6582.3014.6192.543450202344985.9280.3127.35794465.6116.9817.2852.1955.4793.3398.7523.8225.0144.4946.265.4516.4215.789544485685.12914278408.47136290464615.3410.091396226.12897658.51486283.59405049.181915127.284.0923795.122.442.446.005.673.072.442.446.0033.25296316.62297789.8837.6883.129.1512230.9016.211071118.8357.107.6410.9910.9225.7038.4530.1469.0613.7971.922963149296767.95110.7037.54655059.3912.1312.3039.6040.1269.6870.5717.3117.6532.1432.795.3211.7911.398048516866.29709067105.6710.12203238.703.0654792.313.643.648.9248.32354323.763542130.9853.68119.5611.9217944.0523.4114115311.9068.6010.0514.8014.6836.4145.8942.8992.1019.50102.303537213354296.2278.7226.90807982.8517.2517.4857.1257.9398.5099.9824.8325.3145.9146.647.6316.7716.279697529894.18933180608.4414.35412955.784.1721635.43OpenBenchmarking.org

CUDA Mini-Nbody

Test: SOA Data Layout

OpenBenchmarking.org(NBody^2)/s, More Is BetterCUDA Mini-Nbody 2015-11-10Test: SOA Data LayoutJetson NanoNano 10wNano 5Wnano0.82351.6472.47053.2944.1175SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 33.663.642.442.44

CUDA Mini-Nbody

Test: Flush Denormals To Zero

OpenBenchmarking.org(NBody^2)/s, More Is BetterCUDA Mini-Nbody 2015-11-10Test: Flush Denormals To ZeroJetson NanoNano 10wNano 5Wnano0.82351.6472.47053.2944.1175SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 33.663.642.442.44

CUDA Mini-Nbody

Test: Loop Unrolling

OpenBenchmarking.org(NBody^2)/s, More Is BetterCUDA Mini-Nbody 2015-11-10Test: Loop UnrollingJetson NanoNano 10wNano 5Wnano246810SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 38.938.926.006.00

NVIDIA TensorRT Inference

Neural Network: GoogleNet - Precision: INT8 - Batch Size: 1 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: GoogleNet - Precision: INT8 - Batch Size: 1 - DLA Cores: DisabledNano 10wJetson NanoNano 5W1122334455SE +/- 0.11, N = 3SE +/- 0.50, N = 3SE +/- 0.21, N = 348.3235.8733.25

XZ Compression

Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9

OpenBenchmarking.orgSeconds, Fewer Is BetterXZ Compression 5.2.4Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9Jetson Nano1020304050SE +/- 0.86, N = 344.431. (CC) gcc options: -pthread -fvisibility=hidden -O2

MBW

Test: Memory Copy - Array Size: 128 MiB

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy - Array Size: 128 MiBNano 10wJetson NanoNano 5W8001600240032004000SE +/- 5.27, N = 3SE +/- 7.55, N = 3SE +/- 7.90, N = 33543342029631. (CC) gcc options: -O3 -march=native

NVIDIA TensorRT Inference

Neural Network: ResNet50 - Precision: INT8 - Batch Size: 8 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet50 - Precision: INT8 - Batch Size: 8 - DLA Cores: DisabledNano 10wJetson NanoNano 5W612182430SE +/- 0.17, N = 3SE +/- 0.15, N = 3SE +/- 0.00, N = 323.7622.1616.62

MBW

Test: Memory Copy - Array Size: 512 MiB

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy - Array Size: 512 MiBNano 10wJetson NanoNano 5W8001600240032004000SE +/- 2.80, N = 3SE +/- 12.45, N = 3SE +/- 3.31, N = 33542343929771. (CC) gcc options: -O3 -march=native

NVIDIA TensorRT Inference

Neural Network: AlexNet - Precision: INT8 - Batch Size: 32 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: AlexNet - Precision: INT8 - Batch Size: 32 - DLA Cores: DisabledNano 10wJetson NanoNano 5W306090120150SE +/- 0.07, N = 3SE +/- 0.58, N = 3SE +/- 0.04, N = 3130.98128.5589.88

NVIDIA TensorRT Inference

Neural Network: GoogleNet - Precision: INT8 - Batch Size: 4 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: GoogleNet - Precision: INT8 - Batch Size: 4 - DLA Cores: DisabledNano 10wJetson NanoNano 5W1224364860SE +/- 0.05, N = 3SE +/- 0.39, N = 3SE +/- 0.05, N = 353.6847.8337.68

NVIDIA TensorRT Inference

Neural Network: AlexNet - Precision: INT8 - Batch Size: 16 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: AlexNet - Precision: INT8 - Batch Size: 16 - DLA Cores: DisabledNano 10wJetson NanoNano 5W306090120150SE +/- 0.17, N = 3SE +/- 1.48, N = 3SE +/- 0.09, N = 3119.56113.7683.12

NVIDIA TensorRT Inference

Neural Network: VGG16 - Precision: FP16 - Batch Size: 1 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG16 - Precision: FP16 - Batch Size: 1 - DLA Cores: DisabledNano 10wJetson NanoNano 5W3691215SE +/- 0.03, N = 3SE +/- 0.13, N = 8SE +/- 0.03, N = 311.9210.299.15

NVIDIA TensorRT Inference

Neural Network: AlexNet - Precision: FP16 - Batch Size: 16 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: AlexNet - Precision: FP16 - Batch Size: 16 - DLA Cores: DisabledNano 10wJetson NanoNano 5W4080120160200SE +/- 0.31, N = 3SE +/- 1.25, N = 3SE +/- 1.89, N = 5179169122

NVIDIA TensorRT Inference

Neural Network: ResNet50 - Precision: FP16 - Batch Size: 8 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet50 - Precision: FP16 - Batch Size: 8 - DLA Cores: DisabledNano 10wJetson NanoNano 5W1020304050SE +/- 0.03, N = 3SE +/- 0.20, N = 3SE +/- 0.02, N = 344.0542.0530.90

NVIDIA TensorRT Inference

Neural Network: ResNet50 - Precision: INT8 - Batch Size: 4 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet50 - Precision: INT8 - Batch Size: 4 - DLA Cores: DisabledNano 10wJetson NanoNano 5W612182430SE +/- 0.01, N = 3SE +/- 0.30, N = 3SE +/- 0.05, N = 323.4120.5916.21

NVIDIA TensorRT Inference

Neural Network: AlexNet - Precision: FP16 - Batch Size: 4 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: AlexNet - Precision: FP16 - Batch Size: 4 - DLA Cores: DisabledNano 10wJetson NanoNano 5W306090120150SE +/- 0.15, N = 3SE +/- 2.17, N = 12SE +/- 0.39, N = 3141115107

NVIDIA TensorRT Inference

Neural Network: AlexNet - Precision: FP16 - Batch Size: 8 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: AlexNet - Precision: FP16 - Batch Size: 8 - DLA Cores: DisabledNano 10wJetson NanoNano 5W306090120150SE +/- 0.10, N = 3SE +/- 0.87, N = 3SE +/- 2.21, N = 3153134111

NVIDIA TensorRT Inference

Neural Network: VGG19 - Precision: FP16 - Batch Size: 4 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG19 - Precision: FP16 - Batch Size: 4 - DLA Cores: DisabledNano 10wJetson NanoNano 5W3691215SE +/- 0.02, N = 3SE +/- 0.08, N = 3SE +/- 0.01, N = 311.9011.618.83

NVIDIA TensorRT Inference

Neural Network: AlexNet - Precision: FP16 - Batch Size: 1 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: AlexNet - Precision: FP16 - Batch Size: 1 - DLA Cores: DisabledNano 10wNano 5WJetson Nano1530456075SE +/- 0.66, N = 3SE +/- 0.16, N = 3SE +/- 1.49, N = 968.6057.1054.86

NVIDIA TensorRT Inference

Neural Network: VGG19 - Precision: FP16 - Batch Size: 1 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG19 - Precision: FP16 - Batch Size: 1 - DLA Cores: DisabledNano 10wJetson NanoNano 5W3691215SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.00, N = 310.058.707.64

NVIDIA TensorRT Inference

Neural Network: VGG16 - Precision: FP16 - Batch Size: 8 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG16 - Precision: FP16 - Batch Size: 8 - DLA Cores: DisabledNano 10wJetson NanoNano 5W48121620SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 314.8014.6010.99

NVIDIA TensorRT Inference

Neural Network: VGG16 - Precision: FP16 - Batch Size: 4 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG16 - Precision: FP16 - Batch Size: 4 - DLA Cores: DisabledNano 10wJetson NanoNano 5W48121620SE +/- 0.01, N = 3SE +/- 0.08, N = 3SE +/- 0.00, N = 314.6814.1810.92

NVIDIA TensorRT Inference

Neural Network: ResNet50 - Precision: FP16 - Batch Size: 1 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet50 - Precision: FP16 - Batch Size: 1 - DLA Cores: DisabledNano 10wJetson NanoNano 5W816243240SE +/- 0.12, N = 3SE +/- 0.34, N = 9SE +/- 0.11, N = 336.4127.3725.70

NVIDIA TensorRT Inference

Neural Network: AlexNet - Precision: INT8 - Batch Size: 1 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: AlexNet - Precision: INT8 - Batch Size: 1 - DLA Cores: DisabledNano 10wJetson NanoNano 5W1020304050SE +/- 0.14, N = 3SE +/- 0.71, N = 3SE +/- 0.17, N = 345.8940.4838.45

NVIDIA TensorRT Inference

Neural Network: ResNet50 - Precision: FP16 - Batch Size: 4 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet50 - Precision: FP16 - Batch Size: 4 - DLA Cores: DisabledNano 10wJetson NanoNano 5W1020304050SE +/- 0.02, N = 3SE +/- 0.26, N = 3SE +/- 0.01, N = 342.8940.6530.14

NVIDIA TensorRT Inference

Neural Network: AlexNet - Precision: INT8 - Batch Size: 4 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: AlexNet - Precision: INT8 - Batch Size: 4 - DLA Cores: DisabledNano 10wJetson NanoNano 5W20406080100SE +/- 0.18, N = 3SE +/- 1.37, N = 4SE +/- 0.01, N = 392.1082.3069.06

NVIDIA TensorRT Inference

Neural Network: ResNet50 - Precision: INT8 - Batch Size: 1 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet50 - Precision: INT8 - Batch Size: 1 - DLA Cores: DisabledNano 10wJetson NanoNano 5W510152025SE +/- 0.15, N = 3SE +/- 0.12, N = 3SE +/- 0.13, N = 319.5014.6113.79

NVIDIA TensorRT Inference

Neural Network: AlexNet - Precision: INT8 - Batch Size: 8 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: AlexNet - Precision: INT8 - Batch Size: 8 - DLA Cores: DisabledNano 10wJetson NanoNano 5W20406080100SE +/- 0.32, N = 3SE +/- 0.96, N = 3SE +/- 0.03, N = 3102.3092.5471.92

MBW

Test: Memory Copy, Fixed Block Size - Array Size: 128 MiB

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy, Fixed Block Size - Array Size: 128 MiBNano 10wJetson NanoNano 5W8001600240032004000SE +/- 2.59, N = 3SE +/- 7.52, N = 3SE +/- 10.41, N = 33537345029631. (CC) gcc options: -O3 -march=native

NVIDIA TensorRT Inference

Neural Network: AlexNet - Precision: FP16 - Batch Size: 32 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: AlexNet - Precision: FP16 - Batch Size: 32 - DLA Cores: DisabledNano 10wJetson NanoNano 5W50100150200250SE +/- 0.21, N = 3SE +/- 0.75, N = 3SE +/- 0.07, N = 3213202149

MBW

Test: Memory Copy, Fixed Block Size - Array Size: 512 MiB

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy, Fixed Block Size - Array Size: 512 MiBNano 10wJetson NanoNano 5W8001600240032004000SE +/- 1.99, N = 3SE +/- 14.16, N = 3SE +/- 1.52, N = 33542344929671. (CC) gcc options: -O3 -march=native

NVIDIA TensorRT Inference

Neural Network: GoogleNet - Precision: FP16 - Batch Size: 8 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: GoogleNet - Precision: FP16 - Batch Size: 8 - DLA Cores: DisabledNano 10wJetson NanoNano 5W20406080100SE +/- 0.08, N = 3SE +/- 0.10, N = 3SE +/- 0.03, N = 396.2285.9267.95

t-test1

Threads: 1

OpenBenchmarking.orgSeconds, Fewer Is Bettert-test1 2017-01-13Threads: 1Nano 10wJetson NanoNano 5W20406080100SE +/- 0.32, N = 3SE +/- 0.23, N = 3SE +/- 0.05, N = 378.7280.31110.701. (CC) gcc options: -pthread

t-test1

Threads: 2

OpenBenchmarking.orgSeconds, Fewer Is Bettert-test1 2017-01-13Threads: 2Nano 10wJetson NanoNano 5W918273645SE +/- 0.04, N = 3SE +/- 0.07, N = 3SE +/- 0.10, N = 326.9027.3537.541. (CC) gcc options: -pthread

RAMspeed SMP

Type: Add - Benchmark: Integer

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Add - Benchmark: IntegerNano 10wJetson NanoNano 5W2K4K6K8K10K8079794465501. (CC) gcc options: -O3 -march=native

NVIDIA TensorRT Inference

Neural Network: GoogleNet - Precision: FP16 - Batch Size: 1 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: GoogleNet - Precision: FP16 - Batch Size: 1 - DLA Cores: DisabledNano 10wJetson NanoNano 5W20406080100SE +/- 0.25, N = 3SE +/- 0.96, N = 9SE +/- 0.02, N = 382.8565.6159.39

NVIDIA TensorRT Inference

Neural Network: ResNet152 - Precision: FP16 - Batch Size: 16 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet152 - Precision: FP16 - Batch Size: 16 - DLA Cores: DisabledNano 10wJetson NanoNano 5W48121620SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 317.2516.9812.13

NVIDIA TensorRT Inference

Neural Network: ResNet152 - Precision: FP16 - Batch Size: 32 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet152 - Precision: FP16 - Batch Size: 32 - DLA Cores: DisabledNano 10wJetson NanoNano 5W48121620SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 317.4817.2812.30

NVIDIA TensorRT Inference

Neural Network: GoogleNet - Precision: INT8 - Batch Size: 16 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: GoogleNet - Precision: INT8 - Batch Size: 16 - DLA Cores: DisabledNano 10wJetson NanoNano 5W1326395265SE +/- 0.04, N = 3SE +/- 0.34, N = 3SE +/- 0.02, N = 357.1252.1939.60

NVIDIA TensorRT Inference

Neural Network: GoogleNet - Precision: INT8 - Batch Size: 32 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: GoogleNet - Precision: INT8 - Batch Size: 32 - DLA Cores: DisabledNano 10wJetson NanoNano 5W1326395265SE +/- 0.01, N = 3SE +/- 0.21, N = 3SE +/- 0.00, N = 357.9355.4740.12

NVIDIA TensorRT Inference

Neural Network: GoogleNet - Precision: FP16 - Batch Size: 16 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: GoogleNet - Precision: FP16 - Batch Size: 16 - DLA Cores: DisabledNano 10wJetson NanoNano 5W20406080100SE +/- 0.06, N = 3SE +/- 1.84, N = 3SE +/- 0.03, N = 398.5093.3369.68

NVIDIA TensorRT Inference

Neural Network: GoogleNet - Precision: FP16 - Batch Size: 32 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: GoogleNet - Precision: FP16 - Batch Size: 32 - DLA Cores: DisabledNano 10wJetson NanoNano 5W20406080100SE +/- 0.04, N = 3SE +/- 0.20, N = 3SE +/- 0.05, N = 399.9898.7570.57

NVIDIA TensorRT Inference

Neural Network: ResNet50 - Precision: INT8 - Batch Size: 16 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet50 - Precision: INT8 - Batch Size: 16 - DLA Cores: DisabledNano 10wJetson NanoNano 5W612182430SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 324.8323.8217.31

NVIDIA TensorRT Inference

Neural Network: ResNet50 - Precision: INT8 - Batch Size: 32 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet50 - Precision: INT8 - Batch Size: 32 - DLA Cores: DisabledNano 10wJetson NanoNano 5W612182430SE +/- 0.00, N = 3SE +/- 0.06, N = 3SE +/- 0.00, N = 325.3125.0117.65

NVIDIA TensorRT Inference

Neural Network: ResNet50 - Precision: FP16 - Batch Size: 16 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet50 - Precision: FP16 - Batch Size: 16 - DLA Cores: DisabledNano 10wJetson NanoNano 5W1020304050SE +/- 0.03, N = 3SE +/- 0.39, N = 3SE +/- 0.01, N = 345.9144.4932.14

NVIDIA TensorRT Inference

Neural Network: ResNet50 - Precision: FP16 - Batch Size: 32 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet50 - Precision: FP16 - Batch Size: 32 - DLA Cores: DisabledNano 10wJetson NanoNano 5W1122334455SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 346.6446.2632.79

NVIDIA TensorRT Inference

Neural Network: ResNet152 - Precision: INT8 - Batch Size: 1 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet152 - Precision: INT8 - Batch Size: 1 - DLA Cores: DisabledNano 10wJetson NanoNano 5W246810SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 37.635.455.32

NVIDIA TensorRT Inference

Neural Network: ResNet152 - Precision: FP16 - Batch Size: 8 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet152 - Precision: FP16 - Batch Size: 8 - DLA Cores: DisabledNano 10wJetson NanoNano 5W48121620SE +/- 0.01, N = 3SE +/- 0.08, N = 3SE +/- 0.00, N = 316.7716.4211.79

NVIDIA TensorRT Inference

Neural Network: ResNet152 - Precision: FP16 - Batch Size: 4 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet152 - Precision: FP16 - Batch Size: 4 - DLA Cores: DisabledNano 10wJetson NanoNano 5W48121620SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.01, N = 316.2715.7811.39

RAMspeed SMP

Type: Copy - Benchmark: Integer

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Copy - Benchmark: IntegerNano 10wJetson NanoNano 5W2K4K6K8K10K9697954480481. (CC) gcc options: -O3 -march=native

RAMspeed SMP

Type: Triad - Benchmark: Integer

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Triad - Benchmark: IntegerNano 10wNano 5WJetson Nano110022003300440055005298516848561. (CC) gcc options: -O3 -march=native

NVIDIA TensorRT Inference

Neural Network: GoogleNet - Precision: FP16 - Batch Size: 4 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: GoogleNet - Precision: FP16 - Batch Size: 4 - DLA Cores: DisabledNano 10wJetson NanoNano 5W20406080100SE +/- 0.10, N = 3SE +/- 1.10, N = 12SE +/- 0.02, N = 394.1885.1266.29

RAMspeed SMP

Type: Scale - Benchmark: Integer

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Scale - Benchmark: IntegerNano 10wJetson NanoNano 5W2K4K6K8K10K9331914270901. (CC) gcc options: -O3 -march=native

RAMspeed SMP

Type: Average - Benchmark: Integer

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Average - Benchmark: IntegerNano 10wJetson NanoNano 5W2K4K6K8K10K8060784067101. (CC) gcc options: -O3 -march=native

CUDA Mini-Nbody

Test: Cache Blocking

OpenBenchmarking.org(NBody^2)/s, More Is BetterCUDA Mini-Nbody 2015-11-10Test: Cache BlockingJetson NanoNano 10wNano 5Wnano246810SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 38.478.445.675.67

GLmark2

Resolution: 1024 x 768

OpenBenchmarking.orgScore, More Is BetterGLmark2 276Resolution: 1024 x 768Jetson Nano300600900120015001362

GLmark2

Resolution: 1280 x 1024

OpenBenchmarking.orgScore, More Is BetterGLmark2 276Resolution: 1280 x 1024Jetson Nano2004006008001000904

GLmark2

Resolution: 1920 x 1080

OpenBenchmarking.orgScore, More Is BetterGLmark2 276Resolution: 1920 x 1080Jetson Nano140280420560700646

LeelaChessZero

Backend: BLAS

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.20.1Backend: BLASJetson Nano48121620SE +/- 0.10, N = 315.341. (CXX) g++ options: -lpthread -lz

NVIDIA TensorRT Inference

Neural Network: ResNet152 - Precision: FP16 - Batch Size: 1 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet152 - Precision: FP16 - Batch Size: 1 - DLA Cores: DisabledNano 10wNano 5WJetson Nano48121620SE +/- 0.04, N = 3SE +/- 0.00, N = 3SE +/- 0.05, N = 314.3510.1210.09

LeelaChessZero

Backend: CUDA + cuDNN

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.20.1Backend: CUDA + cuDNNJetson Nano306090120150SE +/- 0.64, N = 31391. (CXX) g++ options: -lpthread -lz

Java 2D Microbenchmark

Rendering Test: Text Rendering

OpenBenchmarking.orgUnits Per Second, More Is BetterJava 2D Microbenchmark 1.0Rendering Test: Text RenderingJetson Nano13002600390052006500SE +/- 34.48, N = 46226.12

Java 2D Microbenchmark

Rendering Test: Image Rendering

OpenBenchmarking.orgUnits Per Second, More Is BetterJava 2D Microbenchmark 1.0Rendering Test: Image RenderingJetson Nano200K400K600K800K1000KSE +/- 1827.16, N = 4897658.51

Java 2D Microbenchmark

Rendering Test: Vector Graphics Rendering

OpenBenchmarking.orgUnits Per Second, More Is BetterJava 2D Microbenchmark 1.0Rendering Test: Vector Graphics RenderingJetson Nano100K200K300K400K500KSE +/- 983.45, N = 4486283.59

7-Zip Compression

Compress Speed Test

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 16.02Compress Speed TestNano 10wJetson NanoNano 5W9001800270036004500SE +/- 2.96, N = 3SE +/- 17.21, N = 3SE +/- 7.09, N = 34129405020321. (CXX) g++ options: -pipe -lpthread

NVIDIA TensorRT Inference

Neural Network: GoogleNet - Precision: INT8 - Batch Size: 8 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: GoogleNet - Precision: INT8 - Batch Size: 8 - DLA Cores: DisabledNano 10wJetson NanoNano 5W1326395265SE +/- 0.03, N = 3SE +/- 0.47, N = 3SE +/- 0.02, N = 355.7849.1838.70

GLmark2

Resolution: 800 x 600

OpenBenchmarking.orgScore, More Is BetterGLmark2 276Resolution: 800 x 600Jetson Nano4008001200160020001915

Zstd Compression

Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19

OpenBenchmarking.orgSeconds, Fewer Is BetterZstd Compression 1.3.4Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19Jetson Nano306090120150SE +/- 0.22, N = 3127.281. (CC) gcc options: -O3 -pthread -lz -llzma

CUDA Mini-Nbody

Test: Original

OpenBenchmarking.org(NBody^2)/s, More Is BetterCUDA Mini-Nbody 2015-11-10Test: OriginalNano 10wJetson NanonanoNano 5W0.93831.87662.81493.75324.6915SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 34.174.093.073.06

Timed Linux Kernel Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 4.18Time To CompileNano 10wJetson NanoNano 5W12002400360048006000SE +/- 2.72, N = 3SE +/- 13.46, N = 3SE +/- 2.37, N = 3216323795479

x264

H.264 Video Encoding

OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2018-09-25H.264 Video EncodingNano 10wJetson NanoNano 5W1.22182.44363.66544.88726.109SE +/- 0.08, N = 4SE +/- 0.08, N = 3SE +/- 0.03, N = 35.435.122.311. (CC) gcc options: -ldl -lm -lpthread

Phoronix Test Suite v10.8.4