Ampere Altra ARMv8 Neoverse-N1 testing with a WIWYNN Mt.Jade (1.1.20201019 BIOS) and ASPEED on CentOS 8.0.1905 via the Phoronix Test Suite.
ARMv8.2 Tuned Processor: Ampere Altra ARMv8 Neoverse-N1 @ 3.30GHz (160 Cores), Motherboard: WIWYNN Mt.Jade (1.1.20201019 BIOS), Chipset: Ampere Computing LLC Device e100, Memory: 16 x 32 GB DDR4-3200MT/s Samsung M393A4K40DB3-CWE, Disk: Samsung SSD 983 DCT 960GB + 960GB SAMSUNG MZ1LB960HAJQ-00007, Graphics: ASPEED, Monitor: VE228, Network: Mellanox MT28908 + Intel I210
OS: CentOS 8.0.1905, Kernel: 4.18.0-80.11.2.el8.20201007+amp.aarch64 (aarch64) 20201007, Compiler: GCC 8.3.1 20191121, File-System: xfs, Screen Resolution: 1920x1080
Environment Notes: CFLAGS="-O3 -march=armv8.2-a" CXXFLAGS="-O3 -march=armv8.2-a"Compiler Notes: --build=aarch64-redhat-linux --disable-libmpx --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-gcc-major-version-only --with-isl --with-linker-hash-style=gnuProcessor Notes: Scaling Governor: cppc_cpufreq performanceJava Notes: OpenJDK Runtime Environment (build 1.8.0_272-b10)Python Notes: Python 3.6.8Security Notes: l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Not affected
OpenBenchmarking.org MiB/second, More Is Better Crypto++ 8.2 Test: Keyed Algorithms ARMv8.2 Tuned 90 180 270 360 450 SE +/- 0.07, N = 3 429.19 1. (CXX) g++ options: -O3 -march=armv8.2-a -fPIC -pthread -pipe
OpenBenchmarking.org MiB/second, More Is Better Crypto++ 8.2 Test: Unkeyed Algorithms ARMv8.2 Tuned 100 200 300 400 500 SE +/- 0.04, N = 3 464.07 1. (CXX) g++ options: -O3 -march=armv8.2-a -fPIC -pthread -pipe
OpenBenchmarking.org MiB/second, More Is Better Crypto++ 8.2 Test: Integer + Elliptic Curve Public Key Algorithms ARMv8.2 Tuned 400 800 1200 1600 2000 SE +/- 0.47, N = 3 1690.09 1. (CXX) g++ options: -O3 -march=armv8.2-a -fPIC -pthread -pipe
WebP Image Encode This is a test of Google's libwebp with the cwebp image encode utility and using a sample 6000x4000 pixel JPEG image as the input. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Default ARMv8.2 Tuned 0.6134 1.2268 1.8402 2.4536 3.067 SE +/- 0.010, N = 3 2.726 1. (CC) gcc options: -fvisibility=hidden -O3 -march=armv8.2-a -pthread -lm -ljpeg -lpng16 -ltiff
OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Quality 100 ARMv8.2 Tuned 0.8386 1.6772 2.5158 3.3544 4.193 SE +/- 0.002, N = 3 3.727 1. (CC) gcc options: -fvisibility=hidden -O3 -march=armv8.2-a -pthread -lm -ljpeg -lpng16 -ltiff
OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Quality 100, Lossless ARMv8.2 Tuned 6 12 18 24 30 SE +/- 0.19, N = 3 23.19 1. (CC) gcc options: -fvisibility=hidden -O3 -march=armv8.2-a -pthread -lm -ljpeg -lpng16 -ltiff
OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Quality 100, Highest Compression ARMv8.2 Tuned 2 4 6 8 10 SE +/- 0.001, N = 3 8.695 1. (CC) gcc options: -fvisibility=hidden -O3 -march=armv8.2-a -pthread -lm -ljpeg -lpng16 -ltiff
OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Quality 100, Lossless, Highest Compression ARMv8.2 Tuned 14 28 42 56 70 SE +/- 4.91, N = 15 62.76 1. (CC) gcc options: -fvisibility=hidden -O3 -march=armv8.2-a -pthread -lm -ljpeg -lpng16 -ltiff
C-Ray This is a test of C-Ray, a simple raytracer designed to test the floating-point CPU performance. This test is multi-threaded (16 threads per core), will shoot 8 rays per pixel for anti-aliasing, and will generate a 1600 x 1200 image. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 1.1 Total Time - 4K, 16 Rays Per Pixel ARMv8.2 Tuned 3 6 9 12 15 SE +/- 0.036, N = 3 9.448 1. (CC) gcc options: -lm -lpthread -O3 -march=armv8.2-a
POV-Ray This is a test of POV-Ray, the Persistence of Vision Raytracer. POV-Ray is used to create 3D graphics using ray-tracing. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better POV-Ray 3.7.0.7 Trace Time ARMv8.2 Tuned 3 6 9 12 15 SE +/- 0.21, N = 15 13.20 1. (CXX) g++ options: -pipe -O3 -ffast-math -march=armv8.2-a -pthread -lX11 -lIlmImf -lImath -lHalf -lIex -lIexMath -lIlmThread -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system
RNNoise RNNoise is a recurrent neural network for audio noise reduction developed by Mozilla and Xiph.Org. This test profile is a single-threaded test measuring the time to denoise a sample 26 minute long 16-bit RAW audio file using this recurrent neural network noise suppression library. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better RNNoise 2020-06-28 ARMv8.2 Tuned 5 10 15 20 25 SE +/- 0.03, N = 3 18.29 1. (CC) gcc options: -O3 -march=armv8.2-a -pedantic -fvisibility=hidden -lm
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 100 - Mode: Read Only - Average Latency ARMv8.2 Tuned 0.0405 0.081 0.1215 0.162 0.2025 SE +/- 0.005, N = 15 0.180 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=armv8.2-a -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 250 - Mode: Read Only ARMv8.2 Tuned 160K 320K 480K 640K 800K SE +/- 64027.59, N = 15 740744 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=armv8.2-a -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 250 - Mode: Read Only - Average Latency ARMv8.2 Tuned 0.0979 0.1958 0.2937 0.3916 0.4895 SE +/- 0.010, N = 15 0.435 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=armv8.2-a -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 100 - Mode: Read Write ARMv8.2 Tuned 400 800 1200 1600 2000 SE +/- 31.39, N = 15 1858 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=armv8.2-a -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 100 - Mode: Read Write - Average Latency ARMv8.2 Tuned 12 24 36 48 60 SE +/- 0.84, N = 15 54.06 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=armv8.2-a -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 250 - Mode: Read Write ARMv8.2 Tuned 300 600 900 1200 1500 SE +/- 15.79, N = 8 1517 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=armv8.2-a -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 250 - Mode: Read Write - Average Latency ARMv8.2 Tuned 40 80 120 160 200 SE +/- 1.69, N = 8 165.21 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=armv8.2-a -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Only ARMv8.2 Tuned 70K 140K 210K 280K 350K SE +/- 5244.74, N = 3 333422 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=armv8.2-a -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average Latency ARMv8.2 Tuned 0.0675 0.135 0.2025 0.27 0.3375 SE +/- 0.005, N = 3 0.300 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=armv8.2-a -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Only ARMv8.2 Tuned 60K 120K 180K 240K 300K SE +/- 2326.16, N = 11 266949 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=armv8.2-a -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average Latency ARMv8.2 Tuned 0.2113 0.4226 0.6339 0.8452 1.0565 SE +/- 0.009, N = 11 0.939 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=armv8.2-a -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Write ARMv8.2 Tuned 5K 10K 15K 20K 25K SE +/- 325.83, N = 15 23459 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=armv8.2-a -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Write - Average Latency ARMv8.2 Tuned 0.9623 1.9246 2.8869 3.8492 4.8115 SE +/- 0.057, N = 15 4.277 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=armv8.2-a -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Write ARMv8.2 Tuned 4K 8K 12K 16K 20K SE +/- 245.10, N = 3 20142 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=armv8.2-a -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average Latency ARMv8.2 Tuned 3 6 9 12 15 SE +/- 0.15, N = 3 12.44 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=armv8.2-a -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
ASTC Encoder ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.0 Preset: Fast ARMv8.2 Tuned 1.2735 2.547 3.8205 5.094 6.3675 SE +/- 0.03, N = 3 5.66 1. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -lpthread
OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.0 Preset: Medium ARMv8.2 Tuned 2 4 6 8 10 SE +/- 0.01, N = 3 6.03 1. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -lpthread
OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.0 Preset: Thorough ARMv8.2 Tuned 1.2375 2.475 3.7125 4.95 6.1875 SE +/- 0.03, N = 3 5.50 1. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -lpthread
OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.0 Preset: Exhaustive ARMv8.2 Tuned 7 14 21 28 35 SE +/- 0.07, N = 3 27.96 1. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -lpthread
OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.12 Settings: UASTC Level 0 ARMv8.2 Tuned 6 12 18 24 30 SE +/- 0.31, N = 15 26.29 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O2 -rdynamic -lm -lpthread
OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.12 Settings: UASTC Level 2 ARMv8.2 Tuned 6 12 18 24 30 SE +/- 0.34, N = 15 26.08 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O2 -rdynamic -lm -lpthread
OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.12 Settings: UASTC Level 3 ARMv8.2 Tuned 6 12 18 24 30 SE +/- 0.30, N = 15 25.68 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O2 -rdynamic -lm -lpthread
OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.12 Settings: UASTC Level 2 + RDO Post-Processing ARMv8.2 Tuned 200 400 600 800 1000 SE +/- 1.94, N = 2 780.06 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O2 -rdynamic -lm -lpthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: NUMA ARMv8.2 Tuned 5 10 15 20 25 22 1. (CC) gcc options: -O3 -march=armv8.2-a -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: MEMFD ARMv8.2 Tuned 300 600 900 1200 1500 SE +/- 1.60, N = 3 1163.12 1. (CC) gcc options: -O3 -march=armv8.2-a -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Atomic ARMv8.2 Tuned 1400 2800 4200 5600 7000 SE +/- 58.58, N = 11 6663.03 1. (CC) gcc options: -O3 -march=armv8.2-a -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Crypto ARMv8.2 Tuned 7K 14K 21K 28K 35K SE +/- 6.23, N = 3 31890.58 1. (CC) gcc options: -O3 -march=armv8.2-a -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Malloc ARMv8.2 Tuned 400M 800M 1200M 1600M 2000M SE +/- 2956674.44, N = 3 1647420685.54 1. (CC) gcc options: -O3 -march=armv8.2-a -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Forking ARMv8.2 Tuned 7K 14K 21K 28K 35K SE +/- 414.90, N = 3 32233.07 1. (CC) gcc options: -O3 -march=armv8.2-a -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: SENDFILE ARMv8.2 Tuned 7M 14M 21M 28M 35M SE +/- 5692.19, N = 3 34180573.88 1. (CC) gcc options: -O3 -march=armv8.2-a -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: CPU Cache ARMv8.2 Tuned 1000 2000 3000 4000 5000 SE +/- 107.11, N = 15 4834.59 1. (CC) gcc options: -O3 -march=armv8.2-a -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: CPU Stress ARMv8.2 Tuned 5K 10K 15K 20K 25K SE +/- 7.87, N = 3 23833.08 1. (CC) gcc options: -O3 -march=armv8.2-a -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Semaphores ARMv8.2 Tuned 2M 4M 6M 8M 10M SE +/- 14025.94, N = 3 11236443.58 1. (CC) gcc options: -O3 -march=armv8.2-a -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Matrix Math ARMv8.2 Tuned 160K 320K 480K 640K 800K SE +/- 535.45, N = 3 727861.11 1. (CC) gcc options: -O3 -march=armv8.2-a -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Vector Math ARMv8.2 Tuned 200K 400K 600K 800K 1000K SE +/- 70.97, N = 3 1165469.29 1. (CC) gcc options: -O3 -march=armv8.2-a -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Memory Copying ARMv8.2 Tuned 2K 4K 6K 8K 10K SE +/- 4.86, N = 3 10752.42 1. (CC) gcc options: -O3 -march=armv8.2-a -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Socket Activity ARMv8.2 Tuned 4K 8K 12K 16K 20K SE +/- 113.65, N = 3 17471.14 1. (CC) gcc options: -O3 -march=armv8.2-a -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Context Switching ARMv8.2 Tuned 6M 12M 18M 24M 30M SE +/- 1011188.10, N = 15 26703794.40 1. (CC) gcc options: -O3 -march=armv8.2-a -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Glibc C String Functions ARMv8.2 Tuned 2M 4M 6M 8M 10M SE +/- 899.67, N = 3 11058757.81 1. (CC) gcc options: -O3 -march=armv8.2-a -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Glibc Qsort Data Sorting ARMv8.2 Tuned 300 600 900 1200 1500 SE +/- 0.89, N = 3 1540.72 1. (CC) gcc options: -O3 -march=armv8.2-a -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: System V Message Passing ARMv8.2 Tuned 500K 1000K 1500K 2000K 2500K SE +/- 3929.13, N = 3 2168661.78 1. (CC) gcc options: -O3 -march=armv8.2-a -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
Mobile Neural Network MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by ALibaba. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: SqueezeNetV1.0 ARMv8.2 Tuned 5 10 15 20 25 SE +/- 0.26, N = 4 19.86 MIN: 17.42 / MAX: 47.08 1. (CXX) g++ options: -O3 -march=armv8.2-a -std=c++11 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: resnet-v2-50 ARMv8.2 Tuned 11 22 33 44 55 SE +/- 2.24, N = 4 50.12 MIN: 38.46 / MAX: 68.54 1. (CXX) g++ options: -O3 -march=armv8.2-a -std=c++11 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: MobileNetV2_224 ARMv8.2 Tuned 2 4 6 8 10 SE +/- 0.236, N = 4 8.168 MIN: 7.27 / MAX: 18.16 1. (CXX) g++ options: -O3 -march=armv8.2-a -std=c++11 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: mobilenet-v1-1.0 ARMv8.2 Tuned 2 4 6 8 10 SE +/- 0.504, N = 4 6.867 MIN: 5.88 / MAX: 8.88 1. (CXX) g++ options: -O3 -march=armv8.2-a -std=c++11 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: inception-v3 ARMv8.2 Tuned 15 30 45 60 75 SE +/- 2.14, N = 4 67.14 MIN: 58.58 / MAX: 99 1. (CXX) g++ options: -O3 -march=armv8.2-a -std=c++11 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.org ms, Fewer Is Better TNN 0.2.3 Target: CPU - Model: SqueezeNet v1.1 ARMv8.2 Tuned 60 120 180 240 300 SE +/- 4.12, N = 3 280.84 MIN: 263.77 / MAX: 414.34 1. (CXX) g++ options: -O3 -march=armv8.2-a -fopenmp -pthread -fvisibility=hidden -O2 -rdynamic -ldl
ARMv8.2 Tuned Processor: Ampere Altra ARMv8 Neoverse-N1 @ 3.30GHz (160 Cores), Motherboard: WIWYNN Mt.Jade (1.1.20201019 BIOS), Chipset: Ampere Computing LLC Device e100, Memory: 16 x 32 GB DDR4-3200MT/s Samsung M393A4K40DB3-CWE, Disk: Samsung SSD 983 DCT 960GB + 960GB SAMSUNG MZ1LB960HAJQ-00007, Graphics: ASPEED, Monitor: VE228, Network: Mellanox MT28908 + Intel I210
OS: CentOS 8.0.1905, Kernel: 4.18.0-80.11.2.el8.20201007+amp.aarch64 (aarch64) 20201007, Compiler: GCC 8.3.1 20191121, File-System: xfs, Screen Resolution: 1920x1080
Environment Notes: CFLAGS="-O3 -march=armv8.2-a" CXXFLAGS="-O3 -march=armv8.2-a"Compiler Notes: --build=aarch64-redhat-linux --disable-libmpx --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-gcc-major-version-only --with-isl --with-linker-hash-style=gnuProcessor Notes: Scaling Governor: cppc_cpufreq performanceJava Notes: OpenJDK Runtime Environment (build 1.8.0_272-b10)Python Notes: Python 3.6.8Security Notes: l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Not affected
Testing initiated at 17 December 2020 04:18 by user .