Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 1703205-RI-1703172RI77 Nvidia Jetson TX2 vs regular ARM parts - Phoronix Test Suite Nvidia Jetson TX2 vs regular ARM parts Testing an array of Will-o'-the-cheap devices vs Jetson TX2
HTML result view exported from: https://openbenchmarking.org/result/1703205-RI-1703172RI77&sro&grt .
Nvidia Jetson TX2 vs regular ARM parts Processor Motherboard Memory Disk Graphics OS Kernel Desktop Display Server Display Driver OpenGL Vulkan Compiler File-System Screen Resolution Jetson TX2 ODROID-C2 Mini M8S ODROID-C1 ARMv8 rev 3 @ 2.00GHz (6 Cores) quill 8192MB 31GB 032G34 GP10B (nvgpu)/ Ubuntu 16.04 4.4.15-tegra (aarch64) Unity 7.4.0 X Server 1.18.3 NVIDIA 27.1.0 4.5.0 1.0.8 GCC 5.4.0 20160609 + CUDA 8.0 ext4 3840x2160 Unknown @ 1.54GHz (4 Cores) ODROID-C2 2048MB 16GB SD16G LLVMpipe 3.14.79-108 (aarch64) MATE 1.12.1 X Server 1.18.4 3.3 Mesa 12.0.6 Gallium 0.4 (LLVM 3.8 128 bits) GCC 5.4.0 20160609 Amlogic 32GB 00000 3.14.79-vegas95 (aarch64) GCC 6.3.1 20170316 + Clang 3.8.0-2ubuntu4 + LLVM 3.8.0 1280x1440 ARMv7 rev 1 @ 1.82GHz (4 Cores) ODROIDC 915MB 64GB 00000 Ubuntu 14.04 3.10.80-20-odrobian (armv7l) X Server 1.15.1 GCC 6.3.1 20170319 + Clang 3.6.0-2ubuntu1~trusty1 + LLVM 3.6.0 1280x1024 OpenBenchmarking.org Compiler Details - Jetson TX2: --build=aarch64-linux-gnu --disable-browser-plugin --disable-libquadmath --disable-werror --enable-checking=release --enable-clocale=gnu --enable-fix-cortex-a53-843419 --enable-gnu-unique-object --enable-gtk-cairo --enable-java-awt=gtk --enable-java-home --enable-languages=c,ada,c++,java,go,d,fortran,objc,obj-c++ --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --target=aarch64-linux-gnu --with-arch-directory=aarch64 --with-default-libstdcxx-abi=new -v - ODROID-C2: --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 - Mini M8S: --build=aarch64-linux-gnu --disable-bootstrap --disable-browser-plugin --disable-libquadmath --disable-werror --enable-checking=release --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,c++,fortran --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 - ODROID-C1: --build=arm-linux-gnueabihf --disable-bootstrap --disable-browser-plugin --disable-libitm --disable-libquadmath --disable-libstdcxx-dual-abi --disable-sjlj-exceptions --disable-werror --enable-checking=release --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,c++,fortran --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-multilib --enable-nls --enable-plugin --enable-shared --enable-threads=posix --host=arm-linux-gnueabihf --target=arm-linux-gnueabihf --with-arch-directory=arm --with-arch=armv7-a --with-default-libstdcxx-abi=gcc4-compatible --with-float=hard --with-fpu=vfpv3 --with-mode=arm -v Processor Details - Jetson TX2: Scaling Governor: tegra_cpufreq schedutil - ODROID-C2: Scaling Governor: meson_cpufreq interactive - Mini M8S: Scaling Governor: meson_cpufreq performance - ODROID-C1: Scaling Governor: meson_cpufreq performance
Nvidia Jetson TX2 vs regular ARM parts c-ray: Total Time fftw: Stock - 2D FFT Size 256 encode-flac: WAV To FLAC himeno: Poisson Pressure Solver john-the-ripper: Blowfish openssl: RSA 4096-bit Performance redis: SET redis: GET smallpt: Global Illumination Renderer; 100 Samples mafft: Multiple Sequence Alignment Jetson TX2 ODROID-C2 Mini M8S ODROID-C1 102.53 1795.84 40.05 236.02 1525 42.87 503868.60 652114.77 400 15.10 185.44 160.62 160.88 65.09 861 21 178664.42 228612.62 692 36.59 144.09 218.53 156.87 70.89 942 21.27 205347.64 254151.31 168 35.38 265.79 153.05 174.09 85.35 614 20.60 126411.86 152391.84 292 39.89 OpenBenchmarking.org
C-Ray Total Time OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 1.1 Total Time Jetson TX2 Mini M8S ODROID-C1 ODROID-C2 60 120 180 240 300 SE +/- 12.08, N = 6 SE +/- 0.10, N = 3 SE +/- 0.89, N = 3 SE +/- 0.09, N = 3 102.53 144.09 265.79 185.44 -Ofast -mtune=cortex-a57 -fomit-frame-pointer -march=armv8-a+crc -mcpu=cortex-a5 -Ofast -marm -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize 1. (CC) gcc options: -lm -lpthread -O3
FFTW Build: Stock - Size: 2D FFT Size 256 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.4 Build: Stock - Size: 2D FFT Size 256 Jetson TX2 Mini M8S ODROID-C1 ODROID-C2 400 800 1200 1600 2000 SE +/- 11.43, N = 5 SE +/- 1.50, N = 5 SE +/- 0.47, N = 5 SE +/- 0.45, N = 5 1795.84 218.53 153.05 160.62 -O3 -mtune=native -fstrict-aliasing -fno-schedule-insns -ffast-math -Ofast -mtune=cortex-a57 -march=armv8-a+crc 1. (CC) gcc options: -fomit-frame-pointer -lm
FFTW Performance / Cost - Build: Stock - Size: 2D FFT Size 256 OpenBenchmarking.org Mflops Per Dollar, More Is Better FFTW 3.3.4 Performance / Cost - Build: Stock - Size: 2D FFT Size 256 Jetson TX2 Mini M8S ODROID-C1 ODROID-C2 2 4 6 8 10 3.00 6.07 3.64 3.49 1. Jetson TX2: $599 reported cost. 2. Mini M8S: $35.99 reported cost. 3. ODROID-C1: $42 reported cost. 4. ODROID-C2: $46 reported cost.
FLAC Audio Encoding WAV To FLAC OpenBenchmarking.org Seconds, Fewer Is Better FLAC Audio Encoding 1.3.1 WAV To FLAC Jetson TX2 Mini M8S ODROID-C1 ODROID-C2 40 80 120 160 200 SE +/- 0.05, N = 5 SE +/- 0.15, N = 5 SE +/- 0.19, N = 5 SE +/- 1.50, N = 5 40.05 156.87 174.09 160.88 -O2 -Ofast -mtune=cortex-a57 -fomit-frame-pointer -march=armv8-a+crc -logg -mcpu=cortex-a5 -Ofast -marm -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -logg -O2 1. (CXX) g++ options: -fvisibility=hidden -lm
Himeno Benchmark Poisson Pressure Solver OpenBenchmarking.org MFLOPS, More Is Better Himeno Benchmark 3.0 Poisson Pressure Solver Jetson TX2 Mini M8S ODROID-C1 ODROID-C2 50 100 150 200 250 SE +/- 12.73, N = 6 SE +/- 0.64, N = 3 SE +/- 0.09, N = 3 SE +/- 0.64, N = 3 236.02 70.89 85.35 65.09 -Ofast -mtune=cortex-a57 -fomit-frame-pointer -march=armv8-a+crc -mcpu=cortex-a5 -Ofast -marm -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize 1. (CC) gcc options: -O3
Himeno Benchmark Performance / Cost - Poisson Pressure Solver OpenBenchmarking.org MFLOPS Per Dollar, More Is Better Himeno Benchmark 3.0 Performance / Cost - Poisson Pressure Solver Jetson TX2 Mini M8S ODROID-C1 ODROID-C2 0.4568 0.9136 1.3704 1.8272 2.284 0.39 1.97 2.03 1.42 1. Jetson TX2: $599 reported cost. 2. Mini M8S: $35.99 reported cost. 3. ODROID-C1: $42 reported cost. 4. ODROID-C2: $46 reported cost.
John The Ripper Test: Blowfish OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.8.0 Test: Blowfish Jetson TX2 Mini M8S ODROID-C1 ODROID-C2 300 600 900 1200 1500 SE +/- 15.84, N = 3 SE +/- 0.67, N = 3 SE +/- 0.67, N = 3 SE +/- 1.00, N = 3 1525 942 614 861 1. (CC) gcc options: -fopenmp
John The Ripper Performance / Cost - Test: Blowfish OpenBenchmarking.org Real C/S Per Dollar, More Is Better John The Ripper 1.8.0 Performance / Cost - Test: Blowfish Jetson TX2 Mini M8S ODROID-C1 ODROID-C2 6 12 18 24 30 2.55 26.17 14.62 18.72 1. Jetson TX2: $599 reported cost. 2. Mini M8S: $35.99 reported cost. 3. ODROID-C1: $42 reported cost. 4. ODROID-C2: $46 reported cost.
Meta Performance Per Dollar Performance Per Dollar OpenBenchmarking.org Performance Per Dollar, More Is Better Meta Performance Per Dollar Performance Per Dollar Jetson TX2 Mini M8S ODROID-C1 ODROID-C2 500 1000 1500 2000 2500 322.64 2133.70 1109.83 1479.65 1. Jetson TX2: $599 reported cost. Average result: 193263.85. 2. Mini M8S: $35.99 reported cost. Average result: 76791.94. 3. ODROID-C1: $42 reported cost. Average result: 46612.78. 4. ODROID-C2: $46 reported cost. Average result: 68064.13.
OpenSSL RSA 4096-bit Performance OpenBenchmarking.org Signs Per Second, More Is Better OpenSSL 1.0.1g RSA 4096-bit Performance Jetson TX2 Mini M8S ODROID-C1 ODROID-C2 10 20 30 40 50 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 42.87 21.27 20.60 21.00 -fomit-frame-pointer -fomit-frame-pointer -march=armv7-a -fomit-frame-pointer 1. (CC) gcc options: -O3 -lssl -lcrypto -ldl
OpenSSL Performance / Cost - RSA 4096-bit Performance OpenBenchmarking.org Signs Per Second Per Dollar, More Is Better OpenSSL 1.0.1g Performance / Cost - RSA 4096-bit Performance Jetson TX2 Mini M8S ODROID-C1 ODROID-C2 0.1328 0.2656 0.3984 0.5312 0.664 0.07 0.59 0.49 0.46 1. Jetson TX2: $599 reported cost. 2. Mini M8S: $35.99 reported cost. 3. ODROID-C1: $42 reported cost. 4. ODROID-C2: $46 reported cost.
Redis Test: SET OpenBenchmarking.org Requests Per Second, More Is Better Redis 3.0.1 Test: SET Jetson TX2 Mini M8S ODROID-C1 ODROID-C2 110K 220K 330K 440K 550K SE +/- 1191.18, N = 3 SE +/- 1527.89, N = 3 SE +/- 2412.15, N = 6 SE +/- 2604.21, N = 6 503868.60 205347.64 126411.86 178664.42 -std=gnu99 -pipe -g3 -O3 -funroll-loops -O2 -Ofast -mtune=cortex-a57 -fomit-frame-pointer -march=armv8-a+crc -O2 -mcpu=cortex-a5 -Ofast -marm -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -std=gnu99 -pipe -g3 -O3 -funroll-loops 1. (CC) gcc options: -ggdb -rdynamic -lm -pthread -ldl
Redis Performance / Cost - Test: SET OpenBenchmarking.org Requests Per Second Per Dollar, More Is Better Redis 3.0.1 Performance / Cost - Test: SET Jetson TX2 Mini M8S ODROID-C1 ODROID-C2 1200 2400 3600 4800 6000 841.18 5705.69 3009.81 3884.01 1. Jetson TX2: $599 reported cost. 2. Mini M8S: $35.99 reported cost. 3. ODROID-C1: $42 reported cost. 4. ODROID-C2: $46 reported cost.
Redis Test: GET OpenBenchmarking.org Requests Per Second, More Is Better Redis 3.0.1 Test: GET Jetson TX2 Mini M8S ODROID-C1 ODROID-C2 140K 280K 420K 560K 700K SE +/- 5170.83, N = 3 SE +/- 1665.67, N = 3 SE +/- 1310.01, N = 3 SE +/- 1643.47, N = 3 652114.77 254151.31 152391.84 228612.62 -std=gnu99 -pipe -g3 -O3 -funroll-loops -O2 -Ofast -mtune=cortex-a57 -fomit-frame-pointer -march=armv8-a+crc -O2 -mcpu=cortex-a5 -Ofast -marm -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -std=gnu99 -pipe -g3 -O3 -funroll-loops 1. (CC) gcc options: -ggdb -rdynamic -lm -pthread -ldl
Redis Performance / Cost - Test: GET OpenBenchmarking.org Requests Per Second Per Dollar, More Is Better Redis 3.0.1 Performance / Cost - Test: GET Jetson TX2 Mini M8S ODROID-C1 ODROID-C2 1500 3000 4500 6000 7500 1088.67 7061.72 3628.38 4969.84 1. Jetson TX2: $599 reported cost. 2. Mini M8S: $35.99 reported cost. 3. ODROID-C1: $42 reported cost. 4. ODROID-C2: $46 reported cost.
Smallpt Global Illumination Renderer; 100 Samples OpenBenchmarking.org Seconds, Fewer Is Better Smallpt 1.0 Global Illumination Renderer; 100 Samples Jetson TX2 Mini M8S ODROID-C1 ODROID-C2 150 300 450 600 750 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 3.33, N = 3 400 168 292 692 -Ofast -mtune=cortex-a57 -fomit-frame-pointer -march=armv8-a+crc -mcpu=cortex-a5 -Ofast -marm -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize 1. (CXX) g++ options: -fopenmp
Timed MAFFT Alignment Multiple Sequence Alignment OpenBenchmarking.org Seconds, Fewer Is Better Timed MAFFT Alignment 6.864 Multiple Sequence Alignment Jetson TX2 Mini M8S ODROID-C1 ODROID-C2 9 18 27 36 45 SE +/- 0.48, N = 6 SE +/- 0.76, N = 6 SE +/- 3.25, N = 6 SE +/- 0.64, N = 6 15.10 35.38 39.89 36.59 1. (CC) gcc options: -O3 -lm -lpthread
Phoronix Test Suite v10.8.4