ODROID-N2 benchmarks for a future article.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 1904251-HV-ODROIDN2760 ODROID-N2 Benchmark Comparison - Phoronix Test Suite ODROID-N2 Benchmark Comparison ODROID-N2 benchmarks for a future article.
HTML result view exported from: https://openbenchmarking.org/result/1904251-HV-ODROIDN2760&gru&sor .
ODROID-N2 Benchmark Comparison Processor Motherboard Memory Disk Graphics Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Vulkan Compiler File-System Screen Resolution Jetson TX1 Max-P Jetson TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano Raspberry Pi 3 Model B+ ASUS TinkerBoard ODROID-XU4 ODROID-N2 ODROID-C2 ARMv8 rev 1 @ 1.73GHz (4 Cores) jetson_tx1 4096MB 16GB 016G32 NVIDIA Tegra X1 VE228 Ubuntu 16.04 4.4.38-tegra (aarch64) Unity 7.4.5 X Server 1.18.4 NVIDIA 28.1.0 4.5.0 1.0.8 GCC 5.4.0 20160609 ext4 1920x1080 ARMv8 rev 3 @ 1.27GHz (4 Cores / 6 Threads) quill 8192MB 31GB 032G34 NVIDIA TEGRA Unity 7.4.0 NVIDIA 28.2.1 GCC 5.4.0 20160609 + CUDA 9.0 ARMv8 rev 3 @ 2.04GHz (4 Cores / 6 Threads) ARMv8 rev 0 @ 2.27GHz (8 Cores) jetson-xavier 16384MB 31GB HBG4a2 NVIDIA Tegra Xavier Ubuntu 18.04 4.9.108-tegra (aarch64) Unity 7.5.0 X Server 1.19.6 NVIDIA 31.0.2 4.6.0 1.1.76 GCC 7.3.0 + CUDA 10.0 ARMv8 rev 1 @ 1.43GHz (4 Cores) jetson-nano 4096MB 32GB GB1QT NVIDIA TEGRA Realtek RTL8111/8168/8411 4.9.140-tegra (aarch64) NVIDIA 1.0.0 1.1.85 ARMv7 rev 4 @ 1.40GHz (4 Cores) BCM2835 Raspberry Pi 3 Model B Plus Rev 1.3 926MB 32GB GB2MW BCM2708 Raspbian 9.6 4.19.23-v7+ (armv7l) LXDE X Server 1.19.2 GCC 6.3.0 20170516 656x416 ARMv7 rev 1 @ 1.80GHz (4 Cores) Rockchip (Device Tree) 2048MB 32GB GB1QT Debian 9.0 4.4.16-00006-g4431f98-dirty (armv7l) X Server 1.18.4 1024x768 ARMv7 rev 3 @ 1.50GHz (8 Cores) ODROID-XU4 Hardkernel Odroid XU4 16GB AJTD4R llvmpipe 2GB VE228 Ubuntu 18.04 4.14.37-135 (armv7l) X Server 1.19.6 3.3 Mesa 18.0.0-rc5 (LLVM 6.0 128 bits) GCC 7.3.0 1920x1080 ARMv8 Cortex-A73 @ 1.90GHz (6 Cores) Hardkernel ODROID-N2 4096MB OSD 4.9.156-14 (aarch64) 1920x2160 Amlogic ARMv8 Cortex-A53 @ 1.54GHz (4 Cores) ODROID-C2 2048MB 32GB GB1QT 3.16.57-20 (aarch64) X Server 1.19.6 1920x1080 OpenBenchmarking.org Compiler Details - 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 - 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 - 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 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 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 - 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 - 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 - ODROID-N2: --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 - ODROID-C2: --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-as=/usr/bin/aarch64-linux-gnu-as --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-ld=/usr/bin/aarch64-linux-gnu-ld -v Processor Details - Jetson TX1 Max-P: Scaling Governor: tegra-cpufreq interactive - Jetson TX2 Max-Q: Scaling Governor: tegra_cpufreq schedutil - Jetson TX2 Max-P: Scaling Governor: tegra_cpufreq schedutil - Jetson AGX Xavier: Scaling Governor: tegra_cpufreq schedutil - Jetson Nano: Scaling Governor: tegra-cpufreq schedutil - Raspberry Pi 3 Model B+: Scaling Governor: BCM2835 Freq ondemand - ASUS TinkerBoard: Scaling Governor: cpufreq-dt interactive - ODROID-XU4: Scaling Governor: cpufreq-dt ondemand - ODROID-N2: Scaling Governor: arm-big-little performance - ODROID-C2: Scaling Governor: meson_cpufreq interactive Python Details - Jetson TX1 Max-P: Python 2.7.12 + Python 3.5.2 - Jetson TX2 Max-Q: Python 2.7.12 + Python 3.5.2 - Jetson TX2 Max-P: Python 2.7.12 + Python 3.5.2 - Jetson AGX Xavier: Python 2.7.15rc1 + Python 3.6.7 - Jetson Nano: Python 2.7.15rc1 + Python 3.6.7 - Raspberry Pi 3 Model B+: Python 2.7.13 + Python 3.5.3 - ASUS TinkerBoard: Python 2.7.13 + Python 3.5.3 - ODROID-XU4: Python 2.7.15rc1 + Python 3.6.7 - ODROID-N2: Python 2.7.15rc1 + Python 3.6.7 - ODROID-C2: Python 2.7.15rc1 + Python 3.6.7 Kernel Details - ODROID-XU4: usbhid.quirks=0x0eef:0x0005:0x0004 Graphics Details - ODROID-XU4: EXA
ODROID-N2 Benchmark Comparison cuda-mini-nbody: Original ttsiod-renderer: Phong Rendering With Soft-Shadow Mapping tensorrt-inference: VGG16 - FP16 - 4 - Disabled tensorrt-inference: VGG16 - INT8 - 4 - Disabled tensorrt-inference: VGG19 - INT8 - 32 - Disabled tensorrt-inference: AlexNet - FP16 - 4 - Disabled tensorrt-inference: AlexNet - INT8 - 4 - Disabled tensorrt-inference: AlexNet - FP16 - 32 - Disabled tensorrt-inference: AlexNet - INT8 - 32 - Disabled tensorrt-inference: ResNet50 - FP16 - 4 - Disabled tensorrt-inference: ResNet50 - INT8 - 4 - Disabled tensorrt-inference: GoogleNet - FP16 - 4 - Disabled tensorrt-inference: GoogleNet - INT8 - 4 - Disabled tensorrt-inference: ResNet152 - FP16 - 4 - Disabled tensorrt-inference: ResNet152 - INT8 - 4 - Disabled tensorrt-inference: ResNet50 - FP16 - 32 - Disabled tensorrt-inference: ResNet50 - INT8 - 32 - Disabled tensorrt-inference: GoogleNet - FP16 - 32 - Disabled tensorrt-inference: GoogleNet - INT8 - 32 - Disabled tensorrt-inference: ResNet152 - FP16 - 32 - Disabled tensorrt-inference: ResNet152 - INT8 - 32 - Disabled tensorrt-inference: VGG16 - FP16 - 32 - Disabled tensorrt-inference: VGG19 - FP16 - 32 - Disabled tensorrt-inference: VGG19 - FP16 - 4 - Disabled tensorrt-inference: VGG19 - INT8 - 4 - Disabled tensorrt-inference: VGG16 - INT8 - 32 - Disabled compress-7zip: Compress Speed Test lczero: BLAS lczero: CUDA + cuDNN lczero: CUDA + cuDNN FP16 glmark2: 1920 x 1080 pybench: Total For Average Test Times c-ray: Total Time - 4K, 16 Rays Per Pixel rust-prime: Prime Number Test To 200,000,000 compress-zstd: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19 encode-flac: WAV To FLAC opencv-bench: tesseract-ocr: Time To OCR 7 Images Jetson TX1 Max-P Jetson TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano Raspberry Pi 3 Model B+ ASUS TinkerBoard ODROID-XU4 ODROID-N2 ODROID-C2 45.09 4508 6339 753 128.45 145.80 79.20 6.77 28.85 25.99 14.24 12.59 216 148 374 237 72.01 39.15 156 88.88 27.34 14.50 86.08 47.15 179 104 32.67 17.36 29.83 23.94 21.04 11.45 15.79 3294 8735 869 170.25 253.80 104.28 493 8.24 49.26 32.64 17.56 15.92 264 184 462 301 92.28 49.97 197 113 35.11 18.29 111 59.69 233 130 41.91 22.07 36.87 29.83 26.56 14.32 19.91 5593 5408 585 104.96 144.97 65.07 296 47.13 133 208.76 303.78 394.66 1200 1143 2038 3143 547.50 902.78 796 1146 224.19 372.73 636 1215.08 1006 1693 259.82 493.22 247.95 203.96 172.50 265.81 475.08 19212 47.62 953 2515.01 2876 3007 355 32.37 80.06 54.47 128 71.94 4.07 40.94 14.35 118 84.10 201 128 41.04 20.96 83.37 47.82 15.76 7.76 46.51 25.08 98.93 55.66 17.38 11.59 4049 15.37 140 646 7084 921 150.19 129.87 104.77 271.04 132.67 17.66 2013 20913 2030 1097.69 342.23 339.53 2.74 21.22 2836 11502 1718 1821.05 496.62 279.05 41.96 4120 5009 827 574.11 97.03 520.70 180.66 57.42 5970 24.39 5231 492 73.11 152.04 95.59 243.05 110.73 22.10 2121 7.33 12184 1535 125.81 314.33 262.31 474.35 220.44 OpenBenchmarking.org
CUDA Mini-Nbody Performance / Cost - Test: Original OpenBenchmarking.org (NBody^2)/s Per Dollar, More Is Better CUDA Mini-Nbody 2015-11-10 Performance / Cost - Test: Original Jetson Nano Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q 0.009 0.018 0.027 0.036 0.045 0.04 0.04 0.01 0.01 1. Jetson Nano: $99 reported cost. 2. Jetson AGX Xavier: $1299 reported cost. 3. Jetson TX2 Max-P: $599 reported cost. 4. Jetson TX2 Max-Q: $599 reported cost.
CUDA Mini-Nbody Test: Original OpenBenchmarking.org (NBody^2)/s, More Is Better CUDA Mini-Nbody 2015-11-10 Test: Original Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q Jetson Nano 11 22 33 44 55 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 47.13 8.24 6.77 4.07
TTSIOD 3D Renderer Performance / Cost - Phong Rendering With Soft-Shadow Mapping OpenBenchmarking.org FPS Per Dollar, More Is Better TTSIOD 3D Renderer 2.3b Performance / Cost - Phong Rendering With Soft-Shadow Mapping ODROID-N2 ODROID-XU4 Raspberry Pi 3 Model B+ Jetson Nano ASUS TinkerBoard Jetson AGX Xavier Jetson TX1 Max-P Jetson TX2 Max-P Jetson TX2 Max-Q 0.198 0.396 0.594 0.792 0.99 0.88 0.68 0.50 0.41 0.32 0.10 0.09 0.08 0.05 1. ODROID-N2: $64.95 reported cost. 2. ODROID-XU4: $62 reported cost. 3. Raspberry Pi 3 Model B+: $35 reported cost. 4. Jetson Nano: $99 reported cost. 5. ASUS TinkerBoard: $66 reported cost. 6. Jetson AGX Xavier: $1299 reported cost. 7. Jetson TX1 Max-P: $499 reported cost. 8. Jetson TX2 Max-P: $599 reported cost. 9. Jetson TX2 Max-Q: $599 reported cost.
TTSIOD 3D Renderer Phong Rendering With Soft-Shadow Mapping OpenBenchmarking.org FPS, More Is Better TTSIOD 3D Renderer 2.3b Phong Rendering With Soft-Shadow Mapping Jetson AGX Xavier ODROID-N2 Jetson TX2 Max-P Jetson TX1 Max-P ODROID-XU4 Jetson Nano Jetson TX2 Max-Q ODROID-C2 ASUS TinkerBoard Raspberry Pi 3 Model B+ 30 60 90 120 150 SE +/- 1.63, N = 12 SE +/- 0.05, N = 3 SE +/- 0.15, N = 3 SE +/- 0.04, N = 3 SE +/- 0.97, N = 9 SE +/- 0.11, N = 3 SE +/- 0.46, N = 4 SE +/- 0.08, N = 3 SE +/- 0.27, N = 9 SE +/- 0.16, N = 3 133.00 57.42 49.26 45.09 41.96 40.94 28.85 22.10 21.22 17.66 1. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -lSDL -fopenmp -fwhole-program -lstdc++
NVIDIA TensorRT Inference Neural Network: VGG16 - Precision: FP16 - Batch Size: 4 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second, More Is Better NVIDIA TensorRT Inference Neural Network: VGG16 - Precision: FP16 - Batch Size: 4 - DLA Cores: Disabled Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q Jetson Nano 50 100 150 200 250 SE +/- 0.10, N = 3 SE +/- 0.50, N = 4 SE +/- 0.13, N = 3 SE +/- 0.02, N = 2 208.76 32.64 25.99 14.35
NVIDIA TensorRT Inference Performance / Cost - Neural Network: ResNet50 - Precision: INT8 - Batch Size: 4 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second Per Dollar, More Is Better NVIDIA TensorRT Inference Performance / Cost - Neural Network: ResNet50 - Precision: INT8 - Batch Size: 4 - DLA Cores: Disabled Jetson AGX Xavier Jetson Nano Jetson TX2 Max-P Jetson TX2 Max-Q 0.1553 0.3106 0.4659 0.6212 0.7765 0.69 0.21 0.08 0.07 1. Jetson AGX Xavier: $1299 reported cost. 2. Jetson Nano: $99 reported cost. 3. Jetson TX2 Max-P: $599 reported cost. 4. Jetson TX2 Max-Q: $599 reported cost.
NVIDIA TensorRT Inference Neural Network: VGG16 - Precision: INT8 - Batch Size: 4 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second, More Is Better NVIDIA TensorRT Inference Neural Network: VGG16 - Precision: INT8 - Batch Size: 4 - DLA Cores: Disabled Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q 70 140 210 280 350 SE +/- 0.46, N = 3 SE +/- 0.25, N = 6 SE +/- 0.20, N = 5 303.78 17.56 14.24
NVIDIA TensorRT Inference Neural Network: VGG19 - Precision: INT8 - Batch Size: 32 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second, More Is Better NVIDIA TensorRT Inference Neural Network: VGG19 - Precision: INT8 - Batch Size: 32 - DLA Cores: Disabled Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q 90 180 270 360 450 SE +/- 0.23, N = 3 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 394.66 15.92 12.59
NVIDIA TensorRT Inference Neural Network: AlexNet - Precision: FP16 - Batch Size: 4 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second, More Is Better NVIDIA TensorRT Inference Neural Network: AlexNet - Precision: FP16 - Batch Size: 4 - DLA Cores: Disabled Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q Jetson Nano 300 600 900 1200 1500 SE +/- 1.82, N = 3 SE +/- 7.77, N = 12 SE +/- 3.03, N = 6 SE +/- 2.12, N = 12 1200 264 216 118
NVIDIA TensorRT Inference Neural Network: AlexNet - Precision: INT8 - Batch Size: 4 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second, More Is Better NVIDIA TensorRT Inference Neural Network: AlexNet - Precision: INT8 - Batch Size: 4 - DLA Cores: Disabled Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q Jetson Nano 200 400 600 800 1000 SE +/- 2.59, N = 3 SE +/- 2.79, N = 5 SE +/- 0.91, N = 3 SE +/- 0.72, N = 3 1143.00 184.00 148.00 84.10
NVIDIA TensorRT Inference Neural Network: AlexNet - Precision: FP16 - Batch Size: 32 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second, More Is Better NVIDIA TensorRT Inference Neural Network: AlexNet - Precision: FP16 - Batch Size: 32 - DLA Cores: Disabled Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q Jetson Nano 400 800 1200 1600 2000 SE +/- 2.07, N = 3 SE +/- 7.68, N = 12 SE +/- 2.82, N = 3 SE +/- 1.59, N = 3 2038 462 374 201
NVIDIA TensorRT Inference Neural Network: AlexNet - Precision: INT8 - Batch Size: 32 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second, More Is Better NVIDIA TensorRT Inference Neural Network: AlexNet - Precision: INT8 - Batch Size: 32 - DLA Cores: Disabled Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q Jetson Nano 700 1400 2100 2800 3500 SE +/- 1.06, N = 3 SE +/- 0.52, N = 3 SE +/- 1.39, N = 3 SE +/- 0.06, N = 3 3143 301 237 128
NVIDIA TensorRT Inference Neural Network: ResNet50 - Precision: FP16 - Batch Size: 4 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second, More Is Better NVIDIA TensorRT Inference Neural Network: ResNet50 - Precision: FP16 - Batch Size: 4 - DLA Cores: Disabled Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q Jetson Nano 120 240 360 480 600 SE +/- 0.03, N = 3 SE +/- 1.32, N = 12 SE +/- 1.10, N = 12 SE +/- 0.25, N = 3 547.50 92.28 72.01 41.04
NVIDIA TensorRT Inference Neural Network: ResNet50 - Precision: INT8 - Batch Size: 4 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second, More Is Better NVIDIA TensorRT Inference Neural Network: ResNet50 - Precision: INT8 - Batch Size: 4 - DLA Cores: Disabled Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q Jetson Nano 200 400 600 800 1000 SE +/- 1.86, N = 3 SE +/- 0.79, N = 4 SE +/- 0.64, N = 3 SE +/- 0.36, N = 3 902.78 49.97 39.15 20.96
NVIDIA TensorRT Inference Neural Network: GoogleNet - Precision: FP16 - Batch Size: 4 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second, More Is Better NVIDIA TensorRT Inference Neural Network: GoogleNet - Precision: FP16 - Batch Size: 4 - DLA Cores: Disabled Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q Jetson Nano 200 400 600 800 1000 SE +/- 2.48, N = 3 SE +/- 2.27, N = 3 SE +/- 1.90, N = 12 SE +/- 0.70, N = 3 796.00 197.00 156.00 83.37
NVIDIA TensorRT Inference Neural Network: GoogleNet - Precision: INT8 - Batch Size: 4 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second, More Is Better NVIDIA TensorRT Inference Neural Network: GoogleNet - Precision: INT8 - Batch Size: 4 - DLA Cores: Disabled Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q Jetson Nano 200 400 600 800 1000 SE +/- 4.31, N = 3 SE +/- 1.65, N = 3 SE +/- 1.32, N = 3 SE +/- 0.60, N = 3 1146.00 113.00 88.88 47.82
NVIDIA TensorRT Inference Neural Network: ResNet152 - Precision: FP16 - Batch Size: 4 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second, More Is Better NVIDIA TensorRT Inference Neural Network: ResNet152 - Precision: FP16 - Batch Size: 4 - DLA Cores: Disabled Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q Jetson Nano 50 100 150 200 250 SE +/- 0.22, N = 3 SE +/- 0.36, N = 3 SE +/- 0.34, N = 3 SE +/- 0.04, N = 3 224.19 35.11 27.34 15.76
NVIDIA TensorRT Inference Neural Network: ResNet152 - Precision: INT8 - Batch Size: 4 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second, More Is Better NVIDIA TensorRT Inference Neural Network: ResNet152 - Precision: INT8 - Batch Size: 4 - DLA Cores: Disabled Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q Jetson Nano 80 160 240 320 400 SE +/- 1.59, N = 3 SE +/- 0.14, N = 3 SE +/- 0.15, N = 3 SE +/- 0.03, N = 3 372.73 18.29 14.50 7.76
NVIDIA TensorRT Inference Neural Network: ResNet50 - Precision: FP16 - Batch Size: 32 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second, More Is Better NVIDIA TensorRT Inference Neural Network: ResNet50 - Precision: FP16 - Batch Size: 32 - DLA Cores: Disabled Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q Jetson Nano 140 280 420 560 700 SE +/- 1.23, N = 3 SE +/- 1.22, N = 3 SE +/- 0.86, N = 3 SE +/- 0.02, N = 3 636.00 111.00 86.08 46.51
NVIDIA TensorRT Inference Neural Network: ResNet50 - Precision: INT8 - Batch Size: 32 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second, More Is Better NVIDIA TensorRT Inference Neural Network: ResNet50 - Precision: INT8 - Batch Size: 32 - DLA Cores: Disabled Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q Jetson Nano 300 600 900 1200 1500 SE +/- 0.25, N = 3 SE +/- 0.04, N = 3 SE +/- 0.08, N = 3 SE +/- 0.06, N = 3 1215.08 59.69 47.15 25.08
NVIDIA TensorRT Inference Neural Network: GoogleNet - Precision: FP16 - Batch Size: 32 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second, More Is Better NVIDIA TensorRT Inference Neural Network: GoogleNet - Precision: FP16 - Batch Size: 32 - DLA Cores: Disabled Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q Jetson Nano 200 400 600 800 1000 SE +/- 0.21, N = 3 SE +/- 4.50, N = 3 SE +/- 2.17, N = 8 SE +/- 0.19, N = 3 1006.00 233.00 179.00 98.93
NVIDIA TensorRT Inference Performance / Cost - Neural Network: VGG16 - Precision: FP16 - Batch Size: 4 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second Per Dollar, More Is Better NVIDIA TensorRT Inference Performance / Cost - Neural Network: VGG16 - Precision: FP16 - Batch Size: 4 - DLA Cores: Disabled Jetson AGX Xavier Jetson Nano Jetson TX2 Max-P Jetson TX2 Max-Q 0.036 0.072 0.108 0.144 0.18 0.16 0.14 0.05 0.04 1. Jetson AGX Xavier: $1299 reported cost. 2. Jetson Nano: $99 reported cost. 3. Jetson TX2 Max-P: $599 reported cost. 4. Jetson TX2 Max-Q: $599 reported cost.
NVIDIA TensorRT Inference Neural Network: GoogleNet - Precision: INT8 - Batch Size: 32 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second, More Is Better NVIDIA TensorRT Inference Neural Network: GoogleNet - Precision: INT8 - Batch Size: 32 - DLA Cores: Disabled Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q Jetson Nano 400 800 1200 1600 2000 SE +/- 8.72, N = 3 SE +/- 0.74, N = 3 SE +/- 0.07, N = 3 SE +/- 0.18, N = 3 1693.00 130.00 104.00 55.66
NVIDIA TensorRT Inference Neural Network: ResNet152 - Precision: FP16 - Batch Size: 32 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second, More Is Better NVIDIA TensorRT Inference Neural Network: ResNet152 - Precision: FP16 - Batch Size: 32 - DLA Cores: Disabled Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q Jetson Nano 60 120 180 240 300 SE +/- 0.26, N = 3 SE +/- 0.07, N = 3 SE +/- 0.10, N = 3 SE +/- 0.01, N = 3 259.82 41.91 32.67 17.38
NVIDIA TensorRT Inference Neural Network: ResNet152 - Precision: INT8 - Batch Size: 32 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second, More Is Better NVIDIA TensorRT Inference Neural Network: ResNet152 - Precision: INT8 - Batch Size: 32 - DLA Cores: Disabled Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q 110 220 330 440 550 SE +/- 0.81, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 493.22 22.07 17.36
NVIDIA TensorRT Inference Performance / Cost - Neural Network: VGG16 - Precision: INT8 - Batch Size: 4 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second Per Dollar, More Is Better NVIDIA TensorRT Inference Performance / Cost - Neural Network: VGG16 - Precision: INT8 - Batch Size: 4 - DLA Cores: Disabled Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q 0.0518 0.1036 0.1554 0.2072 0.259 0.23 0.03 0.02 1. Jetson AGX Xavier: $1299 reported cost. 2. Jetson TX2 Max-P: $599 reported cost. 3. Jetson TX2 Max-Q: $599 reported cost.
NVIDIA TensorRT Inference Performance / Cost - Neural Network: VGG19 - Precision: FP16 - Batch Size: 4 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second Per Dollar, More Is Better NVIDIA TensorRT Inference Performance / Cost - Neural Network: VGG19 - Precision: FP16 - Batch Size: 4 - DLA Cores: Disabled Jetson AGX Xavier Jetson Nano Jetson TX2 Max-P Jetson TX2 Max-Q 0.0293 0.0586 0.0879 0.1172 0.1465 0.13 0.12 0.04 0.04 1. Jetson AGX Xavier: $1299 reported cost. 2. Jetson Nano: $99 reported cost. 3. Jetson TX2 Max-P: $599 reported cost. 4. Jetson TX2 Max-Q: $599 reported cost.
NVIDIA TensorRT Inference Performance / Cost - Neural Network: VGG19 - Precision: INT8 - Batch Size: 4 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second Per Dollar, More Is Better NVIDIA TensorRT Inference Performance / Cost - Neural Network: VGG19 - Precision: INT8 - Batch Size: 4 - DLA Cores: Disabled Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q 0.045 0.09 0.135 0.18 0.225 0.20 0.02 0.02 1. Jetson AGX Xavier: $1299 reported cost. 2. Jetson TX2 Max-P: $599 reported cost. 3. Jetson TX2 Max-Q: $599 reported cost.
NVIDIA TensorRT Inference Performance / Cost - Neural Network: VGG16 - Precision: FP16 - Batch Size: 32 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second Per Dollar, More Is Better NVIDIA TensorRT Inference Performance / Cost - Neural Network: VGG16 - Precision: FP16 - Batch Size: 32 - DLA Cores: Disabled Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q 0.0428 0.0856 0.1284 0.1712 0.214 0.19 0.06 0.05 1. Jetson AGX Xavier: $1299 reported cost. 2. Jetson TX2 Max-P: $599 reported cost. 3. Jetson TX2 Max-Q: $599 reported cost.
NVIDIA TensorRT Inference Performance / Cost - Neural Network: VGG16 - Precision: INT8 - Batch Size: 32 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second Per Dollar, More Is Better NVIDIA TensorRT Inference Performance / Cost - Neural Network: VGG16 - Precision: INT8 - Batch Size: 32 - DLA Cores: Disabled Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q 0.0833 0.1666 0.2499 0.3332 0.4165 0.37 0.03 0.03 1. Jetson AGX Xavier: $1299 reported cost. 2. Jetson TX2 Max-P: $599 reported cost. 3. Jetson TX2 Max-Q: $599 reported cost.
NVIDIA TensorRT Inference Performance / Cost - Neural Network: VGG19 - Precision: FP16 - Batch Size: 32 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second Per Dollar, More Is Better NVIDIA TensorRT Inference Performance / Cost - Neural Network: VGG19 - Precision: FP16 - Batch Size: 32 - DLA Cores: Disabled Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q 0.036 0.072 0.108 0.144 0.18 0.16 0.05 0.04 1. Jetson AGX Xavier: $1299 reported cost. 2. Jetson TX2 Max-P: $599 reported cost. 3. Jetson TX2 Max-Q: $599 reported cost.
NVIDIA TensorRT Inference Neural Network: VGG16 - Precision: FP16 - Batch Size: 32 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second, More Is Better NVIDIA TensorRT Inference Neural Network: VGG16 - Precision: FP16 - Batch Size: 32 - DLA Cores: Disabled Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q 50 100 150 200 250 SE +/- 0.12, N = 3 SE +/- 0.31, N = 3 SE +/- 0.18, N = 3 247.95 36.87 29.83
NVIDIA TensorRT Inference Neural Network: VGG19 - Precision: FP16 - Batch Size: 32 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second, More Is Better NVIDIA TensorRT Inference Neural Network: VGG19 - Precision: FP16 - Batch Size: 32 - DLA Cores: Disabled Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q 40 80 120 160 200 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.07, N = 3 203.96 29.83 23.94
NVIDIA TensorRT Inference Performance / Cost - Neural Network: VGG19 - Precision: INT8 - Batch Size: 32 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second Per Dollar, More Is Better NVIDIA TensorRT Inference Performance / Cost - Neural Network: VGG19 - Precision: INT8 - Batch Size: 32 - DLA Cores: Disabled Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q 0.0675 0.135 0.2025 0.27 0.3375 0.30 0.03 0.02 1. Jetson AGX Xavier: $1299 reported cost. 2. Jetson TX2 Max-P: $599 reported cost. 3. Jetson TX2 Max-Q: $599 reported cost.
NVIDIA TensorRT Inference Performance / Cost - Neural Network: AlexNet - Precision: FP16 - Batch Size: 4 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second Per Dollar, More Is Better NVIDIA TensorRT Inference Performance / Cost - Neural Network: AlexNet - Precision: FP16 - Batch Size: 4 - DLA Cores: Disabled Jetson Nano Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q 0.2678 0.5356 0.8034 1.0712 1.339 1.19 0.92 0.44 0.36 1. Jetson Nano: $99 reported cost. 2. Jetson AGX Xavier: $1299 reported cost. 3. Jetson TX2 Max-P: $599 reported cost. 4. Jetson TX2 Max-Q: $599 reported cost.
NVIDIA TensorRT Inference Performance / Cost - Neural Network: AlexNet - Precision: INT8 - Batch Size: 4 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second Per Dollar, More Is Better NVIDIA TensorRT Inference Performance / Cost - Neural Network: AlexNet - Precision: INT8 - Batch Size: 4 - DLA Cores: Disabled Jetson AGX Xavier Jetson Nano Jetson TX2 Max-P Jetson TX2 Max-Q 0.198 0.396 0.594 0.792 0.99 0.88 0.85 0.31 0.25 1. Jetson AGX Xavier: $1299 reported cost. 2. Jetson Nano: $99 reported cost. 3. Jetson TX2 Max-P: $599 reported cost. 4. Jetson TX2 Max-Q: $599 reported cost.
NVIDIA TensorRT Inference Performance / Cost - Neural Network: AlexNet - Precision: FP16 - Batch Size: 32 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second Per Dollar, More Is Better NVIDIA TensorRT Inference Performance / Cost - Neural Network: AlexNet - Precision: FP16 - Batch Size: 32 - DLA Cores: Disabled Jetson Nano Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q 0.4568 0.9136 1.3704 1.8272 2.284 2.03 1.57 0.77 0.62 1. Jetson Nano: $99 reported cost. 2. Jetson AGX Xavier: $1299 reported cost. 3. Jetson TX2 Max-P: $599 reported cost. 4. Jetson TX2 Max-Q: $599 reported cost.
NVIDIA TensorRT Inference Performance / Cost - Neural Network: AlexNet - Precision: INT8 - Batch Size: 32 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second Per Dollar, More Is Better NVIDIA TensorRT Inference Performance / Cost - Neural Network: AlexNet - Precision: INT8 - Batch Size: 32 - DLA Cores: Disabled Jetson AGX Xavier Jetson Nano Jetson TX2 Max-P Jetson TX2 Max-Q 0.5445 1.089 1.6335 2.178 2.7225 2.42 1.29 0.50 0.40 1. Jetson AGX Xavier: $1299 reported cost. 2. Jetson Nano: $99 reported cost. 3. Jetson TX2 Max-P: $599 reported cost. 4. Jetson TX2 Max-Q: $599 reported cost.
NVIDIA TensorRT Inference Performance / Cost - Neural Network: ResNet50 - Precision: FP16 - Batch Size: 4 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second Per Dollar, More Is Better NVIDIA TensorRT Inference Performance / Cost - Neural Network: ResNet50 - Precision: FP16 - Batch Size: 4 - DLA Cores: Disabled Jetson AGX Xavier Jetson Nano Jetson TX2 Max-P Jetson TX2 Max-Q 0.0945 0.189 0.2835 0.378 0.4725 0.42 0.41 0.15 0.12 1. Jetson AGX Xavier: $1299 reported cost. 2. Jetson Nano: $99 reported cost. 3. Jetson TX2 Max-P: $599 reported cost. 4. Jetson TX2 Max-Q: $599 reported cost.
NVIDIA TensorRT Inference Neural Network: VGG19 - Precision: FP16 - Batch Size: 4 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second, More Is Better NVIDIA TensorRT Inference Neural Network: VGG19 - Precision: FP16 - Batch Size: 4 - DLA Cores: Disabled Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q Jetson Nano 40 80 120 160 200 SE +/- 0.50, N = 3 SE +/- 0.38, N = 3 SE +/- 0.34, N = 3 SE +/- 0.05, N = 2 172.50 26.56 21.04 11.59
NVIDIA TensorRT Inference Performance / Cost - Neural Network: GoogleNet - Precision: FP16 - Batch Size: 4 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second Per Dollar, More Is Better NVIDIA TensorRT Inference Performance / Cost - Neural Network: GoogleNet - Precision: FP16 - Batch Size: 4 - DLA Cores: Disabled Jetson Nano Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q 0.189 0.378 0.567 0.756 0.945 0.84 0.61 0.33 0.26 1. Jetson Nano: $99 reported cost. 2. Jetson AGX Xavier: $1299 reported cost. 3. Jetson TX2 Max-P: $599 reported cost. 4. Jetson TX2 Max-Q: $599 reported cost.
NVIDIA TensorRT Inference Neural Network: VGG19 - Precision: INT8 - Batch Size: 4 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second, More Is Better NVIDIA TensorRT Inference Neural Network: VGG19 - Precision: INT8 - Batch Size: 4 - DLA Cores: Disabled Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q 60 120 180 240 300 SE +/- 0.20, N = 3 SE +/- 0.25, N = 4 SE +/- 0.23, N = 3 265.81 14.32 11.45
NVIDIA TensorRT Inference Performance / Cost - Neural Network: GoogleNet - Precision: INT8 - Batch Size: 4 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second Per Dollar, More Is Better NVIDIA TensorRT Inference Performance / Cost - Neural Network: GoogleNet - Precision: INT8 - Batch Size: 4 - DLA Cores: Disabled Jetson AGX Xavier Jetson Nano Jetson TX2 Max-P Jetson TX2 Max-Q 0.198 0.396 0.594 0.792 0.99 0.88 0.48 0.19 0.15 1. Jetson AGX Xavier: $1299 reported cost. 2. Jetson Nano: $99 reported cost. 3. Jetson TX2 Max-P: $599 reported cost. 4. Jetson TX2 Max-Q: $599 reported cost.
NVIDIA TensorRT Inference Performance / Cost - Neural Network: ResNet152 - Precision: FP16 - Batch Size: 4 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second Per Dollar, More Is Better NVIDIA TensorRT Inference Performance / Cost - Neural Network: ResNet152 - Precision: FP16 - Batch Size: 4 - DLA Cores: Disabled Jetson AGX Xavier Jetson Nano Jetson TX2 Max-P Jetson TX2 Max-Q 0.0383 0.0766 0.1149 0.1532 0.1915 0.17 0.16 0.06 0.05 1. Jetson AGX Xavier: $1299 reported cost. 2. Jetson Nano: $99 reported cost. 3. Jetson TX2 Max-P: $599 reported cost. 4. Jetson TX2 Max-Q: $599 reported cost.
NVIDIA TensorRT Inference Performance / Cost - Neural Network: ResNet152 - Precision: INT8 - Batch Size: 4 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second Per Dollar, More Is Better NVIDIA TensorRT Inference Performance / Cost - Neural Network: ResNet152 - Precision: INT8 - Batch Size: 4 - DLA Cores: Disabled Jetson AGX Xavier Jetson Nano Jetson TX2 Max-P Jetson TX2 Max-Q 0.0653 0.1306 0.1959 0.2612 0.3265 0.29 0.08 0.03 0.02 1. Jetson AGX Xavier: $1299 reported cost. 2. Jetson Nano: $99 reported cost. 3. Jetson TX2 Max-P: $599 reported cost. 4. Jetson TX2 Max-Q: $599 reported cost.
NVIDIA TensorRT Inference Performance / Cost - Neural Network: ResNet50 - Precision: FP16 - Batch Size: 32 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second Per Dollar, More Is Better NVIDIA TensorRT Inference Performance / Cost - Neural Network: ResNet50 - Precision: FP16 - Batch Size: 32 - DLA Cores: Disabled Jetson AGX Xavier Jetson Nano Jetson TX2 Max-P Jetson TX2 Max-Q 0.1103 0.2206 0.3309 0.4412 0.5515 0.49 0.47 0.19 0.14 1. Jetson AGX Xavier: $1299 reported cost. 2. Jetson Nano: $99 reported cost. 3. Jetson TX2 Max-P: $599 reported cost. 4. Jetson TX2 Max-Q: $599 reported cost.
NVIDIA TensorRT Inference Performance / Cost - Neural Network: ResNet50 - Precision: INT8 - Batch Size: 32 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second Per Dollar, More Is Better NVIDIA TensorRT Inference Performance / Cost - Neural Network: ResNet50 - Precision: INT8 - Batch Size: 32 - DLA Cores: Disabled Jetson AGX Xavier Jetson Nano Jetson TX2 Max-P Jetson TX2 Max-Q 0.2115 0.423 0.6345 0.846 1.0575 0.94 0.25 0.10 0.08 1. Jetson AGX Xavier: $1299 reported cost. 2. Jetson Nano: $99 reported cost. 3. Jetson TX2 Max-P: $599 reported cost. 4. Jetson TX2 Max-Q: $599 reported cost.
NVIDIA TensorRT Inference Performance / Cost - Neural Network: GoogleNet - Precision: FP16 - Batch Size: 32 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second Per Dollar, More Is Better NVIDIA TensorRT Inference Performance / Cost - Neural Network: GoogleNet - Precision: FP16 - Batch Size: 32 - DLA Cores: Disabled Jetson Nano Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q 0.225 0.45 0.675 0.9 1.125 1.00 0.77 0.39 0.30 1. Jetson Nano: $99 reported cost. 2. Jetson AGX Xavier: $1299 reported cost. 3. Jetson TX2 Max-P: $599 reported cost. 4. Jetson TX2 Max-Q: $599 reported cost.
NVIDIA TensorRT Inference Performance / Cost - Neural Network: GoogleNet - Precision: INT8 - Batch Size: 32 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second Per Dollar, More Is Better NVIDIA TensorRT Inference Performance / Cost - Neural Network: GoogleNet - Precision: INT8 - Batch Size: 32 - DLA Cores: Disabled Jetson AGX Xavier Jetson Nano Jetson TX2 Max-P Jetson TX2 Max-Q 0.2925 0.585 0.8775 1.17 1.4625 1.30 0.56 0.22 0.17 1. Jetson AGX Xavier: $1299 reported cost. 2. Jetson Nano: $99 reported cost. 3. Jetson TX2 Max-P: $599 reported cost. 4. Jetson TX2 Max-Q: $599 reported cost.
NVIDIA TensorRT Inference Performance / Cost - Neural Network: ResNet152 - Precision: FP16 - Batch Size: 32 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second Per Dollar, More Is Better NVIDIA TensorRT Inference Performance / Cost - Neural Network: ResNet152 - Precision: FP16 - Batch Size: 32 - DLA Cores: Disabled Jetson AGX Xavier Jetson Nano Jetson TX2 Max-P Jetson TX2 Max-Q 0.045 0.09 0.135 0.18 0.225 0.20 0.18 0.07 0.05 1. Jetson AGX Xavier: $1299 reported cost. 2. Jetson Nano: $99 reported cost. 3. Jetson TX2 Max-P: $599 reported cost. 4. Jetson TX2 Max-Q: $599 reported cost.
NVIDIA TensorRT Inference Performance / Cost - Neural Network: ResNet152 - Precision: INT8 - Batch Size: 32 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second Per Dollar, More Is Better NVIDIA TensorRT Inference Performance / Cost - Neural Network: ResNet152 - Precision: INT8 - Batch Size: 32 - DLA Cores: Disabled Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q 0.0855 0.171 0.2565 0.342 0.4275 0.38 0.04 0.03 1. Jetson AGX Xavier: $1299 reported cost. 2. Jetson TX2 Max-P: $599 reported cost. 3. Jetson TX2 Max-Q: $599 reported cost.
NVIDIA TensorRT Inference Neural Network: VGG16 - Precision: INT8 - Batch Size: 32 - DLA Cores: Disabled OpenBenchmarking.org Images Per Second, More Is Better NVIDIA TensorRT Inference Neural Network: VGG16 - Precision: INT8 - Batch Size: 32 - DLA Cores: Disabled Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q 100 200 300 400 500 SE +/- 0.10, N = 3 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 475.08 19.91 15.79
7-Zip Compression Performance / Cost - Compress Speed Test OpenBenchmarking.org MIPS Per Dollar, More Is Better 7-Zip Compression 16.02 Performance / Cost - Compress Speed Test ODROID-N2 ODROID-XU4 Raspberry Pi 3 Model B+ ASUS TinkerBoard Jetson Nano Jetson AGX Xavier Jetson TX2 Max-P Jetson TX1 Max-P Jetson TX2 Max-Q 20 40 60 80 100 91.92 66.45 57.51 42.97 40.90 14.79 9.34 9.03 5.50 1. ODROID-N2: $64.95 reported cost. 2. ODROID-XU4: $62 reported cost. 3. Raspberry Pi 3 Model B+: $35 reported cost. 4. ASUS TinkerBoard: $66 reported cost. 5. Jetson Nano: $99 reported cost. 6. Jetson AGX Xavier: $1299 reported cost. 7. Jetson TX2 Max-P: $599 reported cost. 8. Jetson TX1 Max-P: $499 reported cost. 9. Jetson TX2 Max-Q: $599 reported cost.
7-Zip Compression Compress Speed Test OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 16.02 Compress Speed Test Jetson AGX Xavier ODROID-N2 Jetson TX2 Max-P Jetson TX1 Max-P ODROID-XU4 Jetson Nano Jetson TX2 Max-Q ASUS TinkerBoard ODROID-C2 Raspberry Pi 3 Model B+ 4K 8K 12K 16K 20K SE +/- 274.18, N = 12 SE +/- 2.40, N = 3 SE +/- 20.85, N = 3 SE +/- 13.43, N = 3 SE +/- 89.16, N = 12 SE +/- 18.00, N = 3 SE +/- 13.05, N = 3 SE +/- 34.93, N = 3 SE +/- 7.36, N = 3 SE +/- 23.74, N = 11 19212 5970 5593 4508 4120 4049 3294 2836 2121 2013 1. (CXX) g++ options: -pipe -lpthread
LeelaChessZero Backend: BLAS OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.20.1 Backend: BLAS Jetson AGX Xavier ODROID-N2 Jetson Nano ODROID-C2 11 22 33 44 55 SE +/- 0.62, N = 7 SE +/- 0.10, N = 3 SE +/- 0.03, N = 3 SE +/- 0.09, N = 7 47.62 24.39 15.37 7.33 1. (CXX) g++ options: -lpthread -lz
LeelaChessZero Backend: CUDA + cuDNN OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.20.1 Backend: CUDA + cuDNN Jetson AGX Xavier Jetson Nano 200 400 600 800 1000 SE +/- 6.14, N = 3 SE +/- 0.26, N = 3 953 140 1. (CXX) g++ options: -lpthread -lz
LeelaChessZero Backend: CUDA + cuDNN FP16 OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.20.1 Backend: CUDA + cuDNN FP16 Jetson AGX Xavier 500 1000 1500 2000 2500 SE +/- 7.60, N = 3 2515.01 1. (CXX) g++ options: -lpthread -lz
LeelaChessZero Performance / Cost - Backend: BLAS OpenBenchmarking.org Nodes Per Second Per Dollar, More Is Better LeelaChessZero 0.20.1 Performance / Cost - Backend: BLAS ODROID-N2 Jetson Nano Jetson AGX Xavier 0.0855 0.171 0.2565 0.342 0.4275 0.38 0.16 0.04 1. ODROID-N2: $64.95 reported cost. 2. Jetson Nano: $99 reported cost. 3. Jetson AGX Xavier: $1299 reported cost.
LeelaChessZero Performance / Cost - Backend: CUDA + cuDNN OpenBenchmarking.org Nodes Per Second Per Dollar, More Is Better LeelaChessZero 0.20.1 Performance / Cost - Backend: CUDA + cuDNN Jetson Nano Jetson AGX Xavier 0.3173 0.6346 0.9519 1.2692 1.5865 1.41 0.73 1. Jetson Nano: $99 reported cost. 2. Jetson AGX Xavier: $1299 reported cost.
LeelaChessZero Performance / Cost - Backend: CUDA + cuDNN FP16 OpenBenchmarking.org Nodes Per Second Per Dollar, More Is Better LeelaChessZero 0.20.1 Performance / Cost - Backend: CUDA + cuDNN FP16 Jetson AGX Xavier 0.4365 0.873 1.3095 1.746 2.1825 1.94 1. $1299 reported cost.
Meta Performance Per Dollar Performance Per Dollar OpenBenchmarking.org Performance Per Dollar, More Is Better Meta Performance Per Dollar Performance Per Dollar ODROID-N2 5 10 15 20 25 19.17 1. $64.95 reported value. Average value: 1244.91.
GLmark2 Resolution: 1920 x 1080 OpenBenchmarking.org Score, More Is Better GLmark2 Resolution: 1920 x 1080 Jetson AGX Xavier Jetson Nano 600 1200 1800 2400 3000 2876 646
GLmark2 Performance / Cost - Resolution: 1920 x 1080 OpenBenchmarking.org Score Per Dollar, More Is Better GLmark2 Performance / Cost - Resolution: 1920 x 1080 Jetson Nano Jetson AGX Xavier 2 4 6 8 10 6.53 2.21 1. Jetson Nano: $99 reported cost. 2. Jetson AGX Xavier: $1299 reported cost.
PyBench Total For Average Test Times OpenBenchmarking.org Milliseconds, Fewer Is Better PyBench 2018-02-16 Total For Average Test Times Jetson AGX Xavier ODROID-XU4 ODROID-N2 Jetson TX2 Max-P Jetson TX1 Max-P Jetson Nano Jetson TX2 Max-Q ASUS TinkerBoard ODROID-C2 Raspberry Pi 3 Model B+ 4K 8K 12K 16K 20K SE +/- 4.67, N = 3 SE +/- 30.99, N = 3 SE +/- 9.24, N = 3 SE +/- 33.86, N = 3 SE +/- 18.55, N = 3 SE +/- 37.23, N = 3 SE +/- 42.52, N = 3 SE +/- 854.75, N = 9 SE +/- 28.15, N = 3 SE +/- 43.80, N = 3 3007 5009 5231 5408 6339 7084 8735 11502 12184 20913
PyBench Performance / Cost - Total For Average Test Times OpenBenchmarking.org Milliseconds x Dollar, Fewer Is Better PyBench 2018-02-16 Performance / Cost - Total For Average Test Times ODROID-XU4 ODROID-N2 Jetson Nano Raspberry Pi 3 Model B+ ASUS TinkerBoard Jetson TX1 Max-P Jetson TX2 Max-P Jetson AGX Xavier Jetson TX2 Max-Q 1.1M 2.2M 3.3M 4.4M 5.5M 310558.00 339753.45 701316.00 731955.00 759132.00 3163161.00 3239392.00 3906093.00 5232265.00 1. ODROID-XU4: $62 reported cost. 2. ODROID-N2: $64.95 reported cost. 3. Jetson Nano: $99 reported cost. 4. Raspberry Pi 3 Model B+: $35 reported cost. 5. ASUS TinkerBoard: $66 reported cost. 6. Jetson TX1 Max-P: $499 reported cost. 7. Jetson TX2 Max-P: $599 reported cost. 8. Jetson AGX Xavier: $1299 reported cost. 9. Jetson TX2 Max-Q: $599 reported cost.
C-Ray Total Time - 4K, 16 Rays Per Pixel OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 1.1 Total Time - 4K, 16 Rays Per Pixel Jetson AGX Xavier ODROID-N2 Jetson TX2 Max-P Jetson TX1 Max-P ODROID-XU4 Jetson TX2 Max-Q Jetson Nano ODROID-C2 ASUS TinkerBoard Raspberry Pi 3 Model B+ 400 800 1200 1600 2000 SE +/- 7.17, N = 9 SE +/- 0.25, N = 3 SE +/- 49.09, N = 9 SE +/- 10.23, N = 3 SE +/- 29.65, N = 9 SE +/- 1.44, N = 3 SE +/- 0.35, N = 3 SE +/- 0.16, N = 3 SE +/- 22.09, N = 3 SE +/- 2.46, N = 3 355 492 585 753 827 869 921 1535 1718 2030 1. (CC) gcc options: -lm -lpthread -O3
Rust Prime Benchmark Prime Number Test To 200,000,000 OpenBenchmarking.org Seconds, Fewer Is Better Rust Prime Benchmark Prime Number Test To 200,000,000 Jetson AGX Xavier ODROID-N2 Jetson TX2 Max-P ODROID-C2 Jetson TX1 Max-P Jetson Nano Jetson TX2 Max-Q ODROID-XU4 Raspberry Pi 3 Model B+ ASUS TinkerBoard 400 800 1200 1600 2000 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.30, N = 3 SE +/- 0.77, N = 3 SE +/- 0.22, N = 3 SE +/- 0.09, N = 3 SE +/- 0.37, N = 3 SE +/- 1.55, N = 3 SE +/- 187.90, N = 6 32.37 73.11 104.96 125.81 128.45 150.19 170.25 574.11 1097.69 1821.05 -ldl -lrt -lpthread -lgcc_s -lc -lm -lutil 1. (CC) gcc options: -pie -nodefaultlibs
Zstd Compression Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19 OpenBenchmarking.org Seconds, Fewer Is Better Zstd Compression 1.3.4 Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19 Jetson AGX Xavier Jetson Nano Jetson TX2 Max-P Jetson TX1 Max-P ODROID-N2 Jetson TX2 Max-Q ODROID-C2 Raspberry Pi 3 Model B+ ASUS TinkerBoard 110 220 330 440 550 SE +/- 0.91, N = 3 SE +/- 0.23, N = 3 SE +/- 0.29, N = 3 SE +/- 0.42, N = 3 SE +/- 1.77, N = 3 SE +/- 1.02, N = 3 SE +/- 1.41, N = 3 SE +/- 1.03, N = 3 SE +/- 2.16, N = 3 80.06 129.87 144.97 145.80 152.04 253.80 314.33 342.23 496.62 1. (CC) gcc options: -O3 -pthread -lz -llzma
FLAC Audio Encoding WAV To FLAC OpenBenchmarking.org Seconds, Fewer Is Better FLAC Audio Encoding 1.3.2 WAV To FLAC Jetson AGX Xavier Jetson TX2 Max-P Jetson TX1 Max-P ODROID-N2 ODROID-XU4 Jetson TX2 Max-Q Jetson Nano ODROID-C2 ASUS TinkerBoard Raspberry Pi 3 Model B+ 70 140 210 280 350 SE +/- 0.61, N = 5 SE +/- 0.15, N = 5 SE +/- 0.74, N = 5 SE +/- 0.27, N = 5 SE +/- 0.31, N = 5 SE +/- 0.18, N = 5 SE +/- 0.83, N = 5 SE +/- 1.49, N = 5 SE +/- 2.51, N = 5 SE +/- 0.98, N = 5 54.47 65.07 79.20 95.59 97.03 104.28 104.77 262.31 279.05 339.53 1. (CXX) g++ options: -O2 -fvisibility=hidden -logg -lm
OpenCV Benchmark OpenBenchmarking.org Seconds, Fewer Is Better OpenCV Benchmark 3.3.0 Raspberry Pi 3 Model B+ Jetson AGX Xavier ODROID-N2 Jetson Nano Jetson TX2 Max-P ODROID-C2 Jetson TX2 Max-Q ODROID-XU4 110 220 330 440 550 SE +/- 1.57, N = 3 SE +/- 0.26, N = 3 SE +/- 4.66, N = 9 SE +/- 0.27, N = 3 SE +/- 3.48, N = 3 SE +/- 5.74, N = 3 SE +/- 5.31, N = 3 2.74 128.00 243.05 271.04 296.00 474.35 493.00 520.70 1. (CXX) g++ options: -std=c++11 -rdynamic
Tesseract OCR Time To OCR 7 Images OpenBenchmarking.org Seconds, Fewer Is Better Tesseract OCR 4.0.0-beta.1 Time To OCR 7 Images Jetson AGX Xavier ODROID-N2 Jetson Nano ODROID-XU4 ODROID-C2 50 100 150 200 250 SE +/- 0.89, N = 3 SE +/- 0.05, N = 3 SE +/- 1.50, N = 3 SE +/- 1.38, N = 3 SE +/- 0.86, N = 3 71.94 110.73 132.67 180.66 220.44
C-Ray Performance / Cost - Total Time - 4K, 16 Rays Per Pixel OpenBenchmarking.org Seconds x Dollar, Fewer Is Better C-Ray 1.1 Performance / Cost - Total Time - 4K, 16 Rays Per Pixel ODROID-N2 ODROID-XU4 Raspberry Pi 3 Model B+ Jetson Nano ASUS TinkerBoard Jetson TX2 Max-P Jetson TX1 Max-P Jetson AGX Xavier Jetson TX2 Max-Q 110K 220K 330K 440K 550K 31940.46 51274.00 71050.00 91179.00 113388.00 350415.00 375747.00 461145.00 520531.00 1. ODROID-N2: $64.95 reported cost. 2. ODROID-XU4: $62 reported cost. 3. Raspberry Pi 3 Model B+: $35 reported cost. 4. Jetson Nano: $99 reported cost. 5. ASUS TinkerBoard: $66 reported cost. 6. Jetson TX2 Max-P: $599 reported cost. 7. Jetson TX1 Max-P: $499 reported cost. 8. Jetson AGX Xavier: $1299 reported cost. 9. Jetson TX2 Max-Q: $599 reported cost.
Rust Prime Benchmark Performance / Cost - Prime Number Test To 200,000,000 OpenBenchmarking.org Seconds x Dollar, Fewer Is Better Rust Prime Benchmark Performance / Cost - Prime Number Test To 200,000,000 ODROID-N2 Jetson Nano ODROID-XU4 Raspberry Pi 3 Model B+ Jetson AGX Xavier Jetson TX2 Max-P Jetson TX1 Max-P Jetson TX2 Max-Q ASUS TinkerBoard 30K 60K 90K 120K 150K 4748.49 14868.81 35594.82 38419.15 42048.63 62871.04 64096.55 101979.75 120189.30 1. ODROID-N2: $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 AGX Xavier: $1299 reported cost. 6. Jetson TX2 Max-P: $599 reported cost. 7. Jetson TX1 Max-P: $499 reported cost. 8. Jetson TX2 Max-Q: $599 reported cost. 9. ASUS TinkerBoard: $66 reported cost.
Zstd Compression Performance / Cost - Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19 OpenBenchmarking.org Seconds x Dollar, Fewer Is Better Zstd Compression 1.3.4 Performance / Cost - Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19 ODROID-N2 Raspberry Pi 3 Model B+ Jetson Nano ASUS TinkerBoard Jetson TX1 Max-P Jetson TX2 Max-P Jetson AGX Xavier Jetson TX2 Max-Q 30K 60K 90K 120K 150K 9875.00 11978.05 12857.13 32776.92 72754.20 86837.03 103997.94 152026.20 1. ODROID-N2: $64.95 reported cost. 2. Raspberry Pi 3 Model B+: $35 reported cost. 3. Jetson Nano: $99 reported cost. 4. ASUS TinkerBoard: $66 reported cost. 5. Jetson TX1 Max-P: $499 reported cost. 6. Jetson TX2 Max-P: $599 reported cost. 7. Jetson AGX Xavier: $1299 reported cost. 8. Jetson TX2 Max-Q: $599 reported cost.
FLAC Audio Encoding Performance / Cost - WAV To FLAC OpenBenchmarking.org Seconds x Dollar, Fewer Is Better FLAC Audio Encoding 1.3.2 Performance / Cost - WAV To FLAC ODROID-XU4 ODROID-N2 Jetson Nano Raspberry Pi 3 Model B+ ASUS TinkerBoard Jetson TX2 Max-P Jetson TX1 Max-P Jetson TX2 Max-Q Jetson AGX Xavier 15K 30K 45K 60K 75K 6015.86 6208.57 10372.23 11883.55 18417.30 38976.93 39520.80 62463.72 70756.53 1. ODROID-XU4: $62 reported cost. 2. ODROID-N2: $64.95 reported cost. 3. Jetson Nano: $99 reported cost. 4. Raspberry Pi 3 Model B+: $35 reported cost. 5. ASUS TinkerBoard: $66 reported cost. 6. Jetson TX2 Max-P: $599 reported cost. 7. Jetson TX1 Max-P: $499 reported cost. 8. Jetson TX2 Max-Q: $599 reported cost. 9. Jetson AGX Xavier: $1299 reported cost.
OpenCV Benchmark Performance / Cost - OpenBenchmarking.org Seconds x Dollar, Fewer Is Better OpenCV Benchmark 3.3.0 Performance / Cost - Raspberry Pi 3 Model B+ ODROID-N2 Jetson Nano ODROID-XU4 Jetson AGX Xavier Jetson TX2 Max-P Jetson TX2 Max-Q 60K 120K 180K 240K 300K 95.90 15786.10 26832.96 32283.40 166272.00 177304.00 295307.00 1. Raspberry Pi 3 Model B+: $35 reported cost. 2. ODROID-N2: $64.95 reported cost. 3. Jetson Nano: $99 reported cost. 4. ODROID-XU4: $62 reported cost. 5. Jetson AGX Xavier: $1299 reported cost. 6. Jetson TX2 Max-P: $599 reported cost. 7. Jetson TX2 Max-Q: $599 reported cost.
Tesseract OCR Performance / Cost - Time To OCR 7 Images OpenBenchmarking.org Seconds x Dollar, Fewer Is Better Tesseract OCR 4.0.0-beta.1 Performance / Cost - Time To OCR 7 Images ODROID-N2 ODROID-XU4 Jetson Nano Jetson AGX Xavier 20K 40K 60K 80K 100K 7191.91 11200.92 13134.33 93450.06 1. ODROID-N2: $64.95 reported cost. 2. ODROID-XU4: $62 reported cost. 3. Jetson Nano: $99 reported cost. 4. Jetson AGX Xavier: $1299 reported cost.
Phoronix Test Suite v10.8.4