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 Jetson Nano Developer Kit - Phoronix Test Suite Jetson Nano Developer Kit ODROID-N2
HTML result view exported from: https://openbenchmarking.org/result/1904211-HV-ODROID75005&grt .
Jetson Nano Developer Kit 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 ARMv8 Cortex-A73 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 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 - 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 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 - ARMv8 Cortex-A73: Scaling Governor: arm-big-little performance 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 - ARMv8 Cortex-A73: Python 2.7.15rc1 + Python 3.6.7 Kernel Details - ODROID-XU4: usbhid.quirks=0x0eef:0x0005:0x0004 Graphics Details - ODROID-XU4: EXA
Jetson Nano Developer Kit compress-7zip: Compress Speed Test c-ray: Total Time - 4K, 16 Rays Per Pixel cuda-mini-nbody: Original encode-flac: WAV To FLAC glmark2: 1920 x 1080 lczero: BLAS lczero: CUDA + cuDNN lczero: CUDA + cuDNN FP16 tensorrt-inference: VGG16 - FP16 - 4 - Disabled tensorrt-inference: VGG16 - INT8 - 4 - Disabled tensorrt-inference: VGG19 - FP16 - 4 - Disabled tensorrt-inference: VGG19 - INT8 - 4 - Disabled tensorrt-inference: VGG16 - FP16 - 32 - Disabled tensorrt-inference: VGG16 - INT8 - 32 - Disabled tensorrt-inference: VGG19 - FP16 - 32 - 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 opencv-bench: pybench: Total For Average Test Times rust-prime: Prime Number Test To 200,000,000 tesseract-ocr: Time To OCR 7 Images ttsiod-renderer: Phong Rendering With Soft-Shadow Mapping compress-zstd: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19 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 ARMv8 Cortex-A73 4508 753 79.20 6339 128.45 45.09 145.80 3294 869 6.77 104.28 25.99 14.24 21.04 11.45 29.83 15.79 23.94 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 17.36 493 8735 170.25 28.85 253.80 5593 585 8.24 65.07 32.64 17.56 26.56 14.32 36.87 19.91 29.83 15.92 264 184 462 301 92.28 49.97 197 113 35.11 18.29 111 59.69 233 130 41.91 22.07 296 5408 104.96 49.26 144.97 19212 355 47.13 54.47 2876 47.62 953 2515.01 208.76 303.78 172.50 265.81 247.95 475.08 203.96 394.66 1200 1143 2038 3143 547.50 902.78 796 1146 224.19 372.73 636 1215.08 1006 1693 259.82 493.22 128 3007 32.37 71.94 133 80.06 4049 921 4.07 104.77 646 15.37 140 14.35 11.59 118 84.10 201 128 41.04 20.96 83.37 47.82 15.76 7.76 46.51 25.08 98.93 55.66 17.38 271.04 7084 150.19 132.67 40.94 129.87 2013 2030 339.53 2.74 20913 1097.69 17.66 342.23 2836 1718 279.05 11502 1821.05 21.22 496.62 4120 827 97.03 520.70 5009 574.11 180.66 41.96 5970 492 95.59 24.39 243.05 5231 73.11 110.73 57.42 152.04 OpenBenchmarking.org
7-Zip Compression Compress Speed Test OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 16.02 Compress Speed Test 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 ARMv8 Cortex-A73 4K 8K 12K 16K 20K SE +/- 13.43, N = 3 SE +/- 13.05, N = 3 SE +/- 20.85, N = 3 SE +/- 274.18, N = 12 SE +/- 18.00, N = 3 SE +/- 23.74, N = 11 SE +/- 34.93, N = 3 SE +/- 89.16, N = 12 SE +/- 2.40, N = 3 4508 3294 5593 19212 4049 2013 2836 4120 5970 1. (CXX) g++ options: -pipe -lpthread
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 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 ARMv8 Cortex-A73 20 40 60 80 100 9.03 5.50 9.34 14.79 40.90 57.51 42.97 66.45 91.92 1. Jetson TX1 Max-P: $499 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. 5. Jetson Nano: $99 reported cost. 6. Raspberry Pi 3 Model B+: $35 reported cost. 7. ASUS TinkerBoard: $66 reported cost. 8. ODROID-XU4: $62 reported cost. 9. ARMv8 Cortex-A73: $64.95 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 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 ARMv8 Cortex-A73 400 800 1200 1600 2000 SE +/- 10.23, N = 3 SE +/- 1.44, N = 3 SE +/- 49.09, N = 9 SE +/- 7.17, N = 9 SE +/- 0.35, N = 3 SE +/- 2.46, N = 3 SE +/- 22.09, N = 3 SE +/- 29.65, N = 9 SE +/- 0.25, N = 3 753 869 585 355 921 2030 1718 827 492 1. (CC) gcc options: -lm -lpthread -O3
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 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 ARMv8 Cortex-A73 110K 220K 330K 440K 550K 375747.00 520531.00 350415.00 461145.00 91179.00 71050.00 113388.00 51274.00 31940.46 1. Jetson TX1 Max-P: $499 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. 5. Jetson Nano: $99 reported cost. 6. Raspberry Pi 3 Model B+: $35 reported cost. 7. ASUS TinkerBoard: $66 reported cost. 8. ODROID-XU4: $62 reported cost. 9. ARMv8 Cortex-A73: $64.95 reported cost.
CUDA Mini-Nbody Test: Original OpenBenchmarking.org (NBody^2)/s, More Is Better CUDA Mini-Nbody 2015-11-10 Test: Original Jetson TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano 11 22 33 44 55 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 6.77 8.24 47.13 4.07
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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano 0.009 0.018 0.027 0.036 0.045 0.01 0.01 0.04 0.04 1. Jetson TX2 Max-Q: $599 reported cost. 2. Jetson TX2 Max-P: $599 reported cost. 3. Jetson AGX Xavier: $1299 reported cost. 4. Jetson Nano: $99 reported cost.
FLAC Audio Encoding WAV To FLAC OpenBenchmarking.org Seconds, Fewer Is Better FLAC Audio Encoding 1.3.2 WAV To FLAC 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 ARMv8 Cortex-A73 70 140 210 280 350 SE +/- 0.74, N = 5 SE +/- 0.18, N = 5 SE +/- 0.15, N = 5 SE +/- 0.61, N = 5 SE +/- 0.83, N = 5 SE +/- 0.98, N = 5 SE +/- 2.51, N = 5 SE +/- 0.31, N = 5 SE +/- 0.27, N = 5 79.20 104.28 65.07 54.47 104.77 339.53 279.05 97.03 95.59 1. (CXX) g++ options: -O2 -fvisibility=hidden -logg -lm
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 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 ARMv8 Cortex-A73 15K 30K 45K 60K 75K 39520.80 62463.72 38976.93 70756.53 10372.23 11883.55 18417.30 6015.86 6208.57 1. Jetson TX1 Max-P: $499 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. 5. Jetson Nano: $99 reported cost. 6. Raspberry Pi 3 Model B+: $35 reported cost. 7. ASUS TinkerBoard: $66 reported cost. 8. ODROID-XU4: $62 reported cost. 9. ARMv8 Cortex-A73: $64.95 reported cost.
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 AGX Xavier Jetson Nano 2 4 6 8 10 2.21 6.53 1. Jetson AGX Xavier: $1299 reported cost. 2. Jetson Nano: $99 reported cost.
LeelaChessZero Backend: BLAS OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.20.1 Backend: BLAS Jetson AGX Xavier Jetson Nano ARMv8 Cortex-A73 11 22 33 44 55 SE +/- 0.62, N = 7 SE +/- 0.03, N = 3 SE +/- 0.10, N = 3 47.62 15.37 24.39 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 Jetson AGX Xavier Jetson Nano ARMv8 Cortex-A73 0.0855 0.171 0.2565 0.342 0.4275 0.04 0.16 0.38 1. Jetson AGX Xavier: $1299 reported cost. 2. Jetson Nano: $99 reported cost. 3. ARMv8 Cortex-A73: $64.95 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 AGX Xavier Jetson Nano 0.3173 0.6346 0.9519 1.2692 1.5865 0.73 1.41 1. Jetson AGX Xavier: $1299 reported cost. 2. Jetson Nano: $99 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 ARMv8 Cortex-A73 5 10 15 20 25 19.17 1. $64.95 reported value. Average value: 1244.91.
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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano 50 100 150 200 250 SE +/- 0.13, N = 3 SE +/- 0.50, N = 4 SE +/- 0.10, N = 3 SE +/- 0.02, N = 2 25.99 32.64 208.76 14.35
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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier 70 140 210 280 350 SE +/- 0.20, N = 5 SE +/- 0.25, N = 6 SE +/- 0.46, N = 3 14.24 17.56 303.78
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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano 40 80 120 160 200 SE +/- 0.34, N = 3 SE +/- 0.38, N = 3 SE +/- 0.50, N = 3 SE +/- 0.05, N = 2 21.04 26.56 172.50 11.59
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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier 60 120 180 240 300 SE +/- 0.23, N = 3 SE +/- 0.25, N = 4 SE +/- 0.20, N = 3 11.45 14.32 265.81
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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier 50 100 150 200 250 SE +/- 0.18, N = 3 SE +/- 0.31, N = 3 SE +/- 0.12, N = 3 29.83 36.87 247.95
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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier 100 200 300 400 500 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 SE +/- 0.10, N = 3 15.79 19.91 475.08
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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier 40 80 120 160 200 SE +/- 0.07, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 23.94 29.83 203.96
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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier 90 180 270 360 450 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 SE +/- 0.23, N = 3 12.59 15.92 394.66
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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano 300 600 900 1200 1500 SE +/- 3.03, N = 6 SE +/- 7.77, N = 12 SE +/- 1.82, N = 3 SE +/- 2.12, N = 12 216 264 1200 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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano 200 400 600 800 1000 SE +/- 0.91, N = 3 SE +/- 2.79, N = 5 SE +/- 2.59, N = 3 SE +/- 0.72, N = 3 148.00 184.00 1143.00 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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano 400 800 1200 1600 2000 SE +/- 2.82, N = 3 SE +/- 7.68, N = 12 SE +/- 2.07, N = 3 SE +/- 1.59, N = 3 374 462 2038 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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano 700 1400 2100 2800 3500 SE +/- 1.39, N = 3 SE +/- 0.52, N = 3 SE +/- 1.06, N = 3 SE +/- 0.06, N = 3 237 301 3143 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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano 120 240 360 480 600 SE +/- 1.10, N = 12 SE +/- 1.32, N = 12 SE +/- 0.03, N = 3 SE +/- 0.25, N = 3 72.01 92.28 547.50 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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano 200 400 600 800 1000 SE +/- 0.64, N = 3 SE +/- 0.79, N = 4 SE +/- 1.86, N = 3 SE +/- 0.36, N = 3 39.15 49.97 902.78 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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano 200 400 600 800 1000 SE +/- 1.90, N = 12 SE +/- 2.27, N = 3 SE +/- 2.48, N = 3 SE +/- 0.70, N = 3 156.00 197.00 796.00 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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano 200 400 600 800 1000 SE +/- 1.32, N = 3 SE +/- 1.65, N = 3 SE +/- 4.31, N = 3 SE +/- 0.60, N = 3 88.88 113.00 1146.00 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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano 50 100 150 200 250 SE +/- 0.34, N = 3 SE +/- 0.36, N = 3 SE +/- 0.22, N = 3 SE +/- 0.04, N = 3 27.34 35.11 224.19 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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano 80 160 240 320 400 SE +/- 0.15, N = 3 SE +/- 0.14, N = 3 SE +/- 1.59, N = 3 SE +/- 0.03, N = 3 14.50 18.29 372.73 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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano 140 280 420 560 700 SE +/- 0.86, N = 3 SE +/- 1.22, N = 3 SE +/- 1.23, N = 3 SE +/- 0.02, N = 3 86.08 111.00 636.00 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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano 300 600 900 1200 1500 SE +/- 0.08, N = 3 SE +/- 0.04, N = 3 SE +/- 0.25, N = 3 SE +/- 0.06, N = 3 47.15 59.69 1215.08 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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano 200 400 600 800 1000 SE +/- 2.17, N = 8 SE +/- 4.50, N = 3 SE +/- 0.21, N = 3 SE +/- 0.19, N = 3 179.00 233.00 1006.00 98.93
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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano 400 800 1200 1600 2000 SE +/- 0.07, N = 3 SE +/- 0.74, N = 3 SE +/- 8.72, N = 3 SE +/- 0.18, N = 3 104.00 130.00 1693.00 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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano 60 120 180 240 300 SE +/- 0.10, N = 3 SE +/- 0.07, N = 3 SE +/- 0.26, N = 3 SE +/- 0.01, N = 3 32.67 41.91 259.82 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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier 110 220 330 440 550 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.81, N = 3 17.36 22.07 493.22
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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano 0.036 0.072 0.108 0.144 0.18 0.04 0.05 0.16 0.14 1. Jetson TX2 Max-Q: $599 reported cost. 2. Jetson TX2 Max-P: $599 reported cost. 3. Jetson AGX Xavier: $1299 reported cost. 4. Jetson Nano: $99 reported cost.
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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier 0.0518 0.1036 0.1554 0.2072 0.259 0.02 0.03 0.23 1. Jetson TX2 Max-Q: $599 reported cost. 2. Jetson TX2 Max-P: $599 reported cost. 3. Jetson AGX Xavier: $1299 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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano 0.0293 0.0586 0.0879 0.1172 0.1465 0.04 0.04 0.13 0.12 1. Jetson TX2 Max-Q: $599 reported cost. 2. Jetson TX2 Max-P: $599 reported cost. 3. Jetson AGX Xavier: $1299 reported cost. 4. Jetson Nano: $99 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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier 0.045 0.09 0.135 0.18 0.225 0.02 0.02 0.20 1. Jetson TX2 Max-Q: $599 reported cost. 2. Jetson TX2 Max-P: $599 reported cost. 3. Jetson AGX Xavier: $1299 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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier 0.0428 0.0856 0.1284 0.1712 0.214 0.05 0.06 0.19 1. Jetson TX2 Max-Q: $599 reported cost. 2. Jetson TX2 Max-P: $599 reported cost. 3. Jetson AGX Xavier: $1299 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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier 0.0833 0.1666 0.2499 0.3332 0.4165 0.03 0.03 0.37 1. Jetson TX2 Max-Q: $599 reported cost. 2. Jetson TX2 Max-P: $599 reported cost. 3. Jetson AGX Xavier: $1299 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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier 0.036 0.072 0.108 0.144 0.18 0.04 0.05 0.16 1. Jetson TX2 Max-Q: $599 reported cost. 2. Jetson TX2 Max-P: $599 reported cost. 3. Jetson AGX Xavier: $1299 reported cost.
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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier 0.0675 0.135 0.2025 0.27 0.3375 0.02 0.03 0.30 1. Jetson TX2 Max-Q: $599 reported cost. 2. Jetson TX2 Max-P: $599 reported cost. 3. Jetson AGX Xavier: $1299 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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano 0.2678 0.5356 0.8034 1.0712 1.339 0.36 0.44 0.92 1.19 1. Jetson TX2 Max-Q: $599 reported cost. 2. Jetson TX2 Max-P: $599 reported cost. 3. Jetson AGX Xavier: $1299 reported cost. 4. Jetson Nano: $99 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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano 0.198 0.396 0.594 0.792 0.99 0.25 0.31 0.88 0.85 1. Jetson TX2 Max-Q: $599 reported cost. 2. Jetson TX2 Max-P: $599 reported cost. 3. Jetson AGX Xavier: $1299 reported cost. 4. Jetson Nano: $99 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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano 0.4568 0.9136 1.3704 1.8272 2.284 0.62 0.77 1.57 2.03 1. Jetson TX2 Max-Q: $599 reported cost. 2. Jetson TX2 Max-P: $599 reported cost. 3. Jetson AGX Xavier: $1299 reported cost. 4. Jetson Nano: $99 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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano 0.5445 1.089 1.6335 2.178 2.7225 0.40 0.50 2.42 1.29 1. Jetson TX2 Max-Q: $599 reported cost. 2. Jetson TX2 Max-P: $599 reported cost. 3. Jetson AGX Xavier: $1299 reported cost. 4. Jetson Nano: $99 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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano 0.0945 0.189 0.2835 0.378 0.4725 0.12 0.15 0.42 0.41 1. Jetson TX2 Max-Q: $599 reported cost. 2. Jetson TX2 Max-P: $599 reported cost. 3. Jetson AGX Xavier: $1299 reported cost. 4. Jetson Nano: $99 reported cost.
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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano 0.1553 0.3106 0.4659 0.6212 0.7765 0.07 0.08 0.69 0.21 1. Jetson TX2 Max-Q: $599 reported cost. 2. Jetson TX2 Max-P: $599 reported cost. 3. Jetson AGX Xavier: $1299 reported cost. 4. Jetson Nano: $99 reported cost.
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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano 0.189 0.378 0.567 0.756 0.945 0.26 0.33 0.61 0.84 1. Jetson TX2 Max-Q: $599 reported cost. 2. Jetson TX2 Max-P: $599 reported cost. 3. Jetson AGX Xavier: $1299 reported cost. 4. Jetson Nano: $99 reported cost.
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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano 0.198 0.396 0.594 0.792 0.99 0.15 0.19 0.88 0.48 1. Jetson TX2 Max-Q: $599 reported cost. 2. Jetson TX2 Max-P: $599 reported cost. 3. Jetson AGX Xavier: $1299 reported cost. 4. Jetson Nano: $99 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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano 0.0383 0.0766 0.1149 0.1532 0.1915 0.05 0.06 0.17 0.16 1. Jetson TX2 Max-Q: $599 reported cost. 2. Jetson TX2 Max-P: $599 reported cost. 3. Jetson AGX Xavier: $1299 reported cost. 4. Jetson Nano: $99 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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano 0.0653 0.1306 0.1959 0.2612 0.3265 0.02 0.03 0.29 0.08 1. Jetson TX2 Max-Q: $599 reported cost. 2. Jetson TX2 Max-P: $599 reported cost. 3. Jetson AGX Xavier: $1299 reported cost. 4. Jetson Nano: $99 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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano 0.1103 0.2206 0.3309 0.4412 0.5515 0.14 0.19 0.49 0.47 1. Jetson TX2 Max-Q: $599 reported cost. 2. Jetson TX2 Max-P: $599 reported cost. 3. Jetson AGX Xavier: $1299 reported cost. 4. Jetson Nano: $99 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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano 0.2115 0.423 0.6345 0.846 1.0575 0.08 0.10 0.94 0.25 1. Jetson TX2 Max-Q: $599 reported cost. 2. Jetson TX2 Max-P: $599 reported cost. 3. Jetson AGX Xavier: $1299 reported cost. 4. Jetson Nano: $99 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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano 0.225 0.45 0.675 0.9 1.125 0.30 0.39 0.77 1.00 1. Jetson TX2 Max-Q: $599 reported cost. 2. Jetson TX2 Max-P: $599 reported cost. 3. Jetson AGX Xavier: $1299 reported cost. 4. Jetson Nano: $99 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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano 0.2925 0.585 0.8775 1.17 1.4625 0.17 0.22 1.30 0.56 1. Jetson TX2 Max-Q: $599 reported cost. 2. Jetson TX2 Max-P: $599 reported cost. 3. Jetson AGX Xavier: $1299 reported cost. 4. Jetson Nano: $99 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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano 0.045 0.09 0.135 0.18 0.225 0.05 0.07 0.20 0.18 1. Jetson TX2 Max-Q: $599 reported cost. 2. Jetson TX2 Max-P: $599 reported cost. 3. Jetson AGX Xavier: $1299 reported cost. 4. Jetson Nano: $99 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 TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier 0.0855 0.171 0.2565 0.342 0.4275 0.03 0.04 0.38 1. Jetson TX2 Max-Q: $599 reported cost. 2. Jetson TX2 Max-P: $599 reported cost. 3. Jetson AGX Xavier: $1299 reported cost.
OpenCV Benchmark OpenBenchmarking.org Seconds, Fewer Is Better OpenCV Benchmark 3.3.0 Jetson TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano Raspberry Pi 3 Model B+ ODROID-XU4 ARMv8 Cortex-A73 110 220 330 440 550 SE +/- 5.74, N = 3 SE +/- 0.27, N = 3 SE +/- 1.57, N = 3 SE +/- 4.66, N = 9 SE +/- 5.31, N = 3 SE +/- 0.26, N = 3 493.00 296.00 128.00 271.04 2.74 520.70 243.05 1. (CXX) g++ options: -std=c++11 -rdynamic
OpenCV Benchmark Performance / Cost - OpenBenchmarking.org Seconds x Dollar, Fewer Is Better OpenCV Benchmark 3.3.0 Performance / Cost - Jetson TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano Raspberry Pi 3 Model B+ ODROID-XU4 ARMv8 Cortex-A73 60K 120K 180K 240K 300K 295307.00 177304.00 166272.00 26832.96 95.90 32283.40 15786.10 1. Jetson TX2 Max-Q: $599 reported cost. 2. Jetson TX2 Max-P: $599 reported cost. 3. Jetson AGX Xavier: $1299 reported cost. 4. Jetson Nano: $99 reported cost. 5. Raspberry Pi 3 Model B+: $35 reported cost. 6. ODROID-XU4: $62 reported cost. 7. ARMv8 Cortex-A73: $64.95 reported cost.
PyBench Total For Average Test Times OpenBenchmarking.org Milliseconds, Fewer Is Better PyBench 2018-02-16 Total For Average Test Times 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 ARMv8 Cortex-A73 4K 8K 12K 16K 20K SE +/- 18.55, N = 3 SE +/- 42.52, N = 3 SE +/- 33.86, N = 3 SE +/- 4.67, N = 3 SE +/- 37.23, N = 3 SE +/- 43.80, N = 3 SE +/- 854.75, N = 9 SE +/- 30.99, N = 3 SE +/- 9.24, N = 3 6339 8735 5408 3007 7084 20913 11502 5009 5231
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 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 ARMv8 Cortex-A73 1.1M 2.2M 3.3M 4.4M 5.5M 3163161.00 5232265.00 3239392.00 3906093.00 701316.00 731955.00 759132.00 310558.00 339753.45 1. Jetson TX1 Max-P: $499 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. 5. Jetson Nano: $99 reported cost. 6. Raspberry Pi 3 Model B+: $35 reported cost. 7. ASUS TinkerBoard: $66 reported cost. 8. ODROID-XU4: $62 reported cost. 9. ARMv8 Cortex-A73: $64.95 reported cost.
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 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 ARMv8 Cortex-A73 400 800 1200 1600 2000 SE +/- 0.77, N = 3 SE +/- 0.09, N = 3 SE +/- 0.04, N = 3 SE +/- 0.00, N = 3 SE +/- 0.22, N = 3 SE +/- 1.55, N = 3 SE +/- 187.90, N = 6 SE +/- 0.37, N = 3 SE +/- 0.02, N = 3 128.45 170.25 104.96 32.37 150.19 1097.69 1821.05 574.11 73.11 -ldl -lrt -lpthread -lgcc_s -lc -lm -lutil 1. (CC) gcc options: -pie -nodefaultlibs
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 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 ARMv8 Cortex-A73 30K 60K 90K 120K 150K 64096.55 101979.75 62871.04 42048.63 14868.81 38419.15 120189.30 35594.82 4748.49 1. Jetson TX1 Max-P: $499 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. 5. Jetson Nano: $99 reported cost. 6. Raspberry Pi 3 Model B+: $35 reported cost. 7. ASUS TinkerBoard: $66 reported cost. 8. ODROID-XU4: $62 reported cost. 9. ARMv8 Cortex-A73: $64.95 reported cost.
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 Jetson Nano ODROID-XU4 ARMv8 Cortex-A73 40 80 120 160 200 SE +/- 0.89, N = 3 SE +/- 1.50, N = 3 SE +/- 1.38, N = 3 SE +/- 0.05, N = 3 71.94 132.67 180.66 110.73
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 Jetson AGX Xavier Jetson Nano ODROID-XU4 ARMv8 Cortex-A73 20K 40K 60K 80K 100K 93450.06 13134.33 11200.92 7191.91 1. Jetson AGX Xavier: $1299 reported cost. 2. Jetson Nano: $99 reported cost. 3. ODROID-XU4: $62 reported cost. 4. ARMv8 Cortex-A73: $64.95 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 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 ARMv8 Cortex-A73 30 60 90 120 150 SE +/- 0.04, N = 3 SE +/- 0.46, N = 4 SE +/- 0.15, N = 3 SE +/- 1.63, N = 12 SE +/- 0.11, N = 3 SE +/- 0.16, N = 3 SE +/- 0.27, N = 9 SE +/- 0.97, N = 9 SE +/- 0.05, N = 3 45.09 28.85 49.26 133.00 40.94 17.66 21.22 41.96 57.42 1. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -lSDL -fopenmp -fwhole-program -lstdc++
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 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 ARMv8 Cortex-A73 0.198 0.396 0.594 0.792 0.99 0.09 0.05 0.08 0.10 0.41 0.50 0.32 0.68 0.88 1. Jetson TX1 Max-P: $499 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. 5. Jetson Nano: $99 reported cost. 6. Raspberry Pi 3 Model B+: $35 reported cost. 7. ASUS TinkerBoard: $66 reported cost. 8. ODROID-XU4: $62 reported cost. 9. ARMv8 Cortex-A73: $64.95 reported cost.
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 TX1 Max-P Jetson TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano Raspberry Pi 3 Model B+ ASUS TinkerBoard ARMv8 Cortex-A73 110 220 330 440 550 SE +/- 0.42, N = 3 SE +/- 1.02, N = 3 SE +/- 0.29, N = 3 SE +/- 0.91, N = 3 SE +/- 0.23, N = 3 SE +/- 1.03, N = 3 SE +/- 2.16, N = 3 SE +/- 1.77, N = 3 145.80 253.80 144.97 80.06 129.87 342.23 496.62 152.04 1. (CC) gcc options: -O3 -pthread -lz -llzma
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 Jetson TX1 Max-P Jetson TX2 Max-Q Jetson TX2 Max-P Jetson AGX Xavier Jetson Nano Raspberry Pi 3 Model B+ ASUS TinkerBoard ARMv8 Cortex-A73 30K 60K 90K 120K 150K 72754.20 152026.20 86837.03 103997.94 12857.13 11978.05 32776.92 9875.00 1. Jetson TX1 Max-P: $499 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. 5. Jetson Nano: $99 reported cost. 6. Raspberry Pi 3 Model B+: $35 reported cost. 7. ASUS TinkerBoard: $66 reported cost. 8. ARMv8 Cortex-A73: $64.95 reported cost.
Phoronix Test Suite v10.8.4