AMD Ryzen 9 3900XT 12-Core testing with a MSI MEG X570 GODLIKE (MS-7C34) v1.0 (1.B3 BIOS) and AMD Radeon RX 56/64 8GB on Ubuntu 22.04 via the Phoronix Test Suite.
A Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vDisk Notes: NONE / errors=remount-ro,relatime,rw / Block Size: 4096Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8701021Graphics Notes: BAR1 / Visible vRAM Size: 256 MB - vBIOS Version: 113-D0500100-102Python Notes: Python 3.10.4Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
AA B C Processor: AMD Ryzen 9 3900XT 12-Core @ 3.80GHz (12 Cores / 24 Threads), Motherboard: MSI MEG X570 GODLIKE (MS-7C34) v1.0 (1.B3 BIOS), Chipset: AMD Starship/Matisse, Memory: 16GB, Disk: 500GB Seagate FireCuda 520 SSD ZP500GM30002, Graphics: AMD Radeon RX 56/64 8GB (1630/945MHz), Audio: AMD Vega 10 HDMI Audio, Monitor: ASUS MG28U, Network: Realtek Device 2600 + Realtek Killer E3000 2.5GbE + Intel Wi-Fi 6 AX200
OS: Ubuntu 22.04, Kernel: 5.15.0-40-generic (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 22.0.1 (LLVM 13.0.1 DRM 3.42), Vulkan: 1.3.204, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160
BRL-CAD BRL-CAD is a cross-platform, open-source solid modeling system with built-in benchmark mode. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org VGR Performance Metric, More Is Better BRL-CAD 7.32.6 VGR Performance Metric AA C B 40K 80K 120K 160K 200K 187035 188128 188216 1. (CXX) g++ options: -std=c++11 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -pedantic -ldl -lm
Blender OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.3 Blend File: Pabellon Barcelona - Compute: CPU-Only A C B AA 70 140 210 280 350 321.22 319.32 319.01 318.03
Mobile Neural Network MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. This MNN test profile is building the OpenMP / CPU threaded version for processor benchmarking and not any GPU-accelerated test. MNN does allow making use of AVX-512 extensions. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: inception-v3 AA C A B 7 14 21 28 35 29.87 29.31 28.56 28.38 MIN: 28.53 / MAX: 68.86 MIN: 28.85 / MAX: 37.57 MIN: 28.07 / MAX: 37.02 MIN: 27.9 / MAX: 37.14 1. (CXX) g++ options: -std=c++11 -O3 -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 2.1 Model: mobilenet-v1-1.0 AA B C A 1.3237 2.6474 3.9711 5.2948 6.6185 5.883 5.336 5.282 5.205 MIN: 5.14 / MAX: 33.46 MIN: 5.25 / MAX: 5.82 MIN: 5.18 / MAX: 5.73 MIN: 5.08 / MAX: 7.3 1. (CXX) g++ options: -std=c++11 -O3 -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 2.1 Model: MobileNetV2_224 AA C B A 1.1138 2.2276 3.3414 4.4552 5.569 4.950 4.364 4.336 4.002 MIN: 4.18 / MAX: 114.69 MIN: 4.32 / MAX: 4.77 MIN: 4.29 / MAX: 4.88 MIN: 3.96 / MAX: 5.11 1. (CXX) g++ options: -std=c++11 -O3 -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 2.1 Model: SqueezeNetV1.0 AA C B A 2 4 6 8 10 7.699 6.419 6.201 6.116 MIN: 6.51 / MAX: 58.65 MIN: 6.35 / MAX: 7.41 MIN: 6.12 / MAX: 13.82 MIN: 6.05 / MAX: 6.55 1. (CXX) g++ options: -std=c++11 -O3 -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 2.1 Model: resnet-v2-50 AA B C A 8 16 24 32 40 36.10 32.69 32.38 32.12 MIN: 29.81 / MAX: 128.2 MIN: 32.09 / MAX: 41.41 MIN: 31.76 / MAX: 39.9 MIN: 31.61 / MAX: 40.21 1. (CXX) g++ options: -std=c++11 -O3 -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 2.1 Model: squeezenetv1.1 AA C B A 1.1462 2.2924 3.4386 4.5848 5.731 5.094 4.232 4.147 4.098 MIN: 3.95 / MAX: 93.8 MIN: 4.18 / MAX: 4.86 MIN: 4.1 / MAX: 4.58 MIN: 4.05 / MAX: 5.82 1. (CXX) g++ options: -std=c++11 -O3 -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 2.1 Model: mobilenetV3 AA C B A 0.5418 1.0836 1.6254 2.1672 2.709 2.408 2.188 2.188 2.053 MIN: 2.16 / MAX: 26.83 MIN: 2.16 / MAX: 2.51 MIN: 2.16 / MAX: 2.54 MIN: 2.03 / MAX: 2.49 1. (CXX) g++ options: -std=c++11 -O3 -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 2.1 Model: nasnet AA B C A 4 8 12 16 20 16.04 13.92 13.90 13.27 MIN: 13.24 / MAX: 59.16 MIN: 13.83 / MAX: 14.72 MIN: 13.81 / MAX: 14.56 MIN: 13.15 / MAX: 21.58 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
ClickHouse ClickHouse is an open-source, high performance OLAP data management system. This test profile uses ClickHouse's standard benchmark recommendations per https://clickhouse.com/docs/en/operations/performance-test/ with the 100 million rows web analytics dataset. The reported value is the query processing time using the geometric mean of all queries performed. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.5.4.19 100M Rows Web Analytics Dataset, Third Run C AA B 40 80 120 160 200 160.78 164.16 164.51 MIN: 8.34 / MAX: 10000 MIN: 8.64 / MAX: 15000 MIN: 8.8 / MAX: 15000 1. ClickHouse server version 22.5.4.19 (official build).
OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.5.4.19 100M Rows Web Analytics Dataset, Second Run AA B C 40 80 120 160 200 152.36 157.24 164.39 MIN: 8.77 / MAX: 4000 MIN: 7.89 / MAX: 6000 MIN: 8.21 / MAX: 20000 1. ClickHouse server version 22.5.4.19 (official build).
OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.5.4.19 100M Rows Web Analytics Dataset, First Run / Cold Cache B AA C 30 60 90 120 150 137.77 141.26 141.89 MIN: 8.31 / MAX: 3750 MIN: 8.21 / MAX: 10000 MIN: 8.34 / MAX: 6666.67 1. ClickHouse server version 22.5.4.19 (official build).
NCNN NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: FastestDet C B AA A 1.2735 2.547 3.8205 5.094 6.3675 5.66 5.65 5.65 5.62 MIN: 5.6 / MAX: 5.98 MIN: 5.61 / MAX: 5.88 MIN: 5.6 / MAX: 5.9 MIN: 5.56 / MAX: 5.74 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: vision_transformer AA C B A 30 60 90 120 150 157.08 156.99 155.89 155.14 MIN: 155.45 / MAX: 162.23 MIN: 155.28 / MAX: 339.54 MIN: 155.39 / MAX: 159.87 MIN: 154.65 / MAX: 163.24 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: regnety_400m B C AA A 4 8 12 16 20 13.88 13.86 13.82 13.75 MIN: 13.75 / MAX: 14.54 MIN: 13.72 / MAX: 14.33 MIN: 13.71 / MAX: 14.65 MIN: 13.62 / MAX: 14.22 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: squeezenet_ssd C B AA A 5 10 15 20 25 21.20 21.16 21.03 21.03 MIN: 19.55 / MAX: 22.51 MIN: 19.08 / MAX: 22.51 MIN: 19.61 / MAX: 22.57 MIN: 19.53 / MAX: 22.34 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: yolov4-tiny C B A AA 6 12 18 24 30 25.99 25.87 25.75 25.73 MIN: 24.91 / MAX: 71 MIN: 24.93 / MAX: 27 MIN: 24.81 / MAX: 29.44 MIN: 24.98 / MAX: 26.6 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: resnet50 AA B C A 5 10 15 20 25 21.35 20.90 20.87 20.87 MIN: 20.94 / MAX: 22.57 MIN: 20.64 / MAX: 21.64 MIN: 20.65 / MAX: 21.68 MIN: 20.63 / MAX: 21.65 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: alexnet AA A C B 3 6 9 12 15 9.99 9.94 9.92 9.92 MIN: 9.6 / MAX: 10.63 MIN: 9.63 / MAX: 10.63 MIN: 9.62 / MAX: 10.47 MIN: 9.63 / MAX: 10.7 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: resnet18 AA B A C 3 6 9 12 15 12.68 12.64 12.62 12.59 MIN: 12.22 / MAX: 14.05 MIN: 12.31 / MAX: 13.26 MIN: 12.27 / MAX: 19.5 MIN: 12.24 / MAX: 13.42 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: vgg16 AA C B A 11 22 33 44 55 49.72 49.31 49.31 49.10 MIN: 48.67 / MAX: 75.83 MIN: 48.78 / MAX: 50.28 MIN: 48.7 / MAX: 50.46 MIN: 48.53 / MAX: 52.21 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: googlenet AA B A C 8 16 24 32 40 33.08 15.21 15.11 15.09 MIN: 14.26 / MAX: 3907.66 MIN: 14.46 / MAX: 16.37 MIN: 14.47 / MAX: 16.25 MIN: 14.47 / MAX: 16.27 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: blazeface C B AA A 0.477 0.954 1.431 1.908 2.385 2.12 2.11 2.10 2.09 MIN: 2.09 / MAX: 2.44 MIN: 2.09 / MAX: 2.46 MIN: 2.08 / MAX: 2.4 MIN: 2.07 / MAX: 2.36 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: efficientnet-b0 AA C B A 2 4 6 8 10 6.52 6.50 6.48 6.45 MIN: 6.45 / MAX: 7.26 MIN: 6.43 / MAX: 7.42 MIN: 6.42 / MAX: 7.1 MIN: 6.4 / MAX: 6.98 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: mnasnet C AA B A 0.9495 1.899 2.8485 3.798 4.7475 4.22 4.21 4.19 4.18 MIN: 4.17 / MAX: 4.52 MIN: 4.17 / MAX: 4.56 MIN: 4.14 / MAX: 4.65 MIN: 4.12 / MAX: 4.48 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: shufflenet-v2 C B AA A 1.0958 2.1916 3.2874 4.3832 5.479 4.87 4.87 4.87 4.84 MIN: 4.82 / MAX: 5.25 MIN: 4.79 / MAX: 5.16 MIN: 4.83 / MAX: 5.25 MIN: 4.77 / MAX: 5.08 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU-v3-v3 - Model: mobilenet-v3 C AA B A 0.9203 1.8406 2.7609 3.6812 4.6015 4.09 4.09 4.07 4.06 MIN: 4.04 / MAX: 4.56 MIN: 4.02 / MAX: 4.71 MIN: 4.01 / MAX: 4.53 MIN: 3.98 / MAX: 5.9 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU-v2-v2 - Model: mobilenet-v2 C AA B A 1.0553 2.1106 3.1659 4.2212 5.2765 4.69 4.65 4.64 4.63 MIN: 4.62 / MAX: 5.29 MIN: 4.58 / MAX: 5.2 MIN: 4.58 / MAX: 5.19 MIN: 4.57 / MAX: 5.41 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: mobilenet C AA B A 4 8 12 16 20 14.18 14.17 14.05 14.02 MIN: 14.01 / MAX: 14.71 MIN: 14.02 / MAX: 14.79 MIN: 13.85 / MAX: 14.54 MIN: 13.8 / MAX: 14.44 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
ClickHouse ClickHouse is an open-source, high performance OLAP data management system. This test profile uses ClickHouse's standard benchmark recommendations per https://clickhouse.com/docs/en/operations/performance-test/ with the 100 million rows web analytics dataset. The reported value is the query processing time using the geometric mean of all queries performed. Learn more via the OpenBenchmarking.org test page.
A: The test quit with a non-zero exit status.
NCNN NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: squeezenet_ssd AA C A B 1.161 2.322 3.483 4.644 5.805 5.16 5.13 5.13 5.12 MIN: 4.52 / MAX: 10.07 MIN: 4.92 / MAX: 6.8 MIN: 4.91 / MAX: 6.74 MIN: 4.92 / MAX: 6.75 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: alexnet C B AA A 0.4658 0.9316 1.3974 1.8632 2.329 2.07 2.07 2.07 2.05 MIN: 1.9 / MAX: 2.77 MIN: 1.91 / MAX: 2.77 MIN: 1.9 / MAX: 2.79 MIN: 1.89 / MAX: 2.77 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: resnet18 C AA B A 0.6053 1.2106 1.8159 2.4212 3.0265 2.69 2.69 2.68 2.68 MIN: 2.56 / MAX: 3.48 MIN: 2.56 / MAX: 3.58 MIN: 2.56 / MAX: 3.48 MIN: 2.55 / MAX: 3.49 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: vgg16 C AA A B 1.2555 2.511 3.7665 5.022 6.2775 5.58 5.58 5.58 5.57 MIN: 5.53 / MAX: 5.93 MIN: 5.54 / MAX: 5.81 MIN: 5.52 / MAX: 8.52 MIN: 5.53 / MAX: 5.84 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: blazeface C B AA A 0.36 0.72 1.08 1.44 1.8 1.60 1.60 1.60 1.59 MIN: 1.52 / MAX: 1.89 MIN: 1.52 / MAX: 2.08 MIN: 1.53 / MAX: 1.96 MIN: 1.51 / MAX: 1.85 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 C B AA A 0.6908 1.3816 2.0724 2.7632 3.454 3.07 3.07 3.07 3.07 MIN: 2.95 / MAX: 4.06 MIN: 2.94 / MAX: 4.06 MIN: 2.95 / MAX: 4.07 MIN: 2.93 / MAX: 5.4 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: mnasnet C AA B A 0.5715 1.143 1.7145 2.286 2.8575 2.54 2.54 2.53 2.52 MIN: 2.39 / MAX: 3.56 MIN: 2.39 / MAX: 3.56 MIN: 2.39 / MAX: 3.5 MIN: 2.38 / MAX: 3.53 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: FastestDet C B A AA 0.6548 1.3096 1.9644 2.6192 3.274 2.91 2.88 2.88 2.84 MIN: 2.86 / MAX: 7.7 MIN: 2.86 / MAX: 3.13 MIN: 2.86 / MAX: 3.19 MIN: 2.68 / MAX: 3.17 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: vision_transformer B C A AA 30 60 90 120 150 155.34 154.44 153.75 153.04 MIN: 154.17 / MAX: 159.14 MIN: 152.59 / MAX: 160.89 MIN: 152.07 / MAX: 161.2 MIN: 152.05 / MAX: 158 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: regnety_400m B C AA A 0.9608 1.9216 2.8824 3.8432 4.804 4.27 4.26 4.25 4.25 MIN: 4.2 / MAX: 5.66 MIN: 4.18 / MAX: 5.68 MIN: 4.17 / MAX: 5.65 MIN: 4.18 / MAX: 5.67 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: yolov4-tiny C B A AA 3 6 9 12 15 11.50 11.45 11.45 11.40 MIN: 11.26 / MAX: 12.05 MIN: 11.24 / MAX: 13.43 MIN: 11.18 / MAX: 12.04 MIN: 11.2 / MAX: 11.63 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: resnet50 C AA B A 1.143 2.286 3.429 4.572 5.715 5.08 5.08 5.07 5.05 MIN: 5.03 / MAX: 5.83 MIN: 5.01 / MAX: 7.86 MIN: 5.02 / MAX: 6.23 MIN: 4.99 / MAX: 5.82 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: googlenet C B AA A 1.1498 2.2996 3.4494 4.5992 5.749 5.11 5.10 5.10 5.09 MIN: 5.06 / MAX: 6.76 MIN: 5.06 / MAX: 6.73 MIN: 5.04 / MAX: 6.7 MIN: 5.03 / MAX: 6.71 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: efficientnet-b0 C AA A B 2 4 6 8 10 7.74 7.73 7.73 7.65 MIN: 7.63 / MAX: 8.18 MIN: 7.62 / MAX: 10.89 MIN: 7.61 / MAX: 11.64 MIN: 7.55 / MAX: 8.03 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: shufflenet-v2 C B AA A 0.5715 1.143 1.7145 2.286 2.8575 2.54 2.51 2.50 2.47 MIN: 2.31 / MAX: 2.96 MIN: 2.31 / MAX: 2.95 MIN: 2.31 / MAX: 2.97 MIN: 2.3 / MAX: 3.16 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 C AA B A 0.549 1.098 1.647 2.196 2.745 2.44 2.43 2.42 2.41 MIN: 2.26 / MAX: 3.35 MIN: 2.26 / MAX: 3.35 MIN: 2.25 / MAX: 3.33 MIN: 2.25 / MAX: 3.33 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: mobilenet B C AA A 2 4 6 8 10 8.51 8.46 8.42 8.42 MIN: 7.27 / MAX: 28.34 MIN: 7.3 / MAX: 9.27 MIN: 7.28 / MAX: 9.25 MIN: 7.27 / MAX: 9.34 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 4 - Input: Bosphorus 4K A C AA B 0.4273 0.8546 1.2819 1.7092 2.1365 1.875 1.889 1.897 1.899 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
etcd Etcd is a distributed, reliable key-value store intended for critical data of a distributed system. Etcd is written in Golang and part of the Cloud Native Computing Foundation (CNCF) and used by Kubernetes, Rook, CoreDNS, and other open-source software. This test profile uses Etcd's built-in benchmark to stress the PUT and RANGE performance of a single node / local system. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better etcd 3.5.4 Test: PUT - Connections: 100 - Clients: 100 - Average Latency C B AA A 0.5625 1.125 1.6875 2.25 2.8125 2.5 1.3 1.3 1.3
OpenBenchmarking.org Requests/sec, More Is Better etcd 3.5.4 Test: PUT - Connections: 100 - Clients: 100 C A AA B 16K 32K 48K 64K 80K 39885.16 75898.33 76528.48 76772.86
memtier_benchmark Memtier_benchmark is a NoSQL Redis/Memcache traffic generation plus benchmarking tool developed by Redis Labs. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Ops/sec, More Is Better memtier_benchmark 1.4 Protocol: Redis - Clients: 500 - Set To Get Ratio: 5:1 A AA C 400K 800K 1200K 1600K 2000K 1601060.47 1682664.97 1692892.31 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre Protocol: Redis - Clients: 500 - Set To Get Ratio: 5:1
B: The test run did not produce a result.
OpenBenchmarking.org Ops/sec, More Is Better memtier_benchmark 1.4 Protocol: Redis - Clients: 500 - Set To Get Ratio: 1:5 C B A 400K 800K 1200K 1600K 2000K 1712775.16 1717057.55 1956692.55 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Protocol: Redis - Clients: 500 - Set To Get Ratio: 1:10
A: The test run did not produce a result.
OpenBenchmarking.org Ops/sec, More Is Better memtier_benchmark 1.4 Protocol: Redis - Clients: 500 - Set To Get Ratio: 1:1 C B 300K 600K 900K 1200K 1500K 1591304.98 1624385.73 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.org Ops/sec, More Is Better memtier_benchmark 1.4 Protocol: Redis - Clients: 100 - Set To Get Ratio: 5:1 B AA A C 400K 800K 1200K 1600K 2000K 1621199.15 1640264.17 1648819.65 1666964.92 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.org Ops/sec, More Is Better memtier_benchmark 1.4 Protocol: Redis - Clients: 100 - Set To Get Ratio: 1:5 AA B A C 400K 800K 1200K 1600K 2000K 1794814.33 1811033.68 1824325.88 1857393.23 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.org Ops/sec, More Is Better memtier_benchmark 1.4 Protocol: Redis - Clients: 100 - Set To Get Ratio: 1:10 AA A C B 400K 800K 1200K 1600K 2000K 1816335.46 1852262.31 1868139.80 1918907.40 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.org Ops/sec, More Is Better memtier_benchmark 1.4 Protocol: Redis - Clients: 100 - Set To Get Ratio: 1:1 C B A AA 400K 800K 1200K 1600K 2000K 1693867.55 1694596.39 1696795.22 1699071.04 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Protocol: Redis - Clients: 500 - Set To Get Ratio: 1:5
AA: The test run did not produce a result.
Protocol: Redis - Clients: 500 - Set To Get Ratio: 1:1
A: The test run did not produce a result.
AA: The test run did not produce a result.
OpenBenchmarking.org Ops/sec, More Is Better memtier_benchmark 1.4 Protocol: Redis - Clients: 50 - Set To Get Ratio: 5:1 AA B C A 400K 800K 1200K 1600K 2000K 1631076.43 1642719.18 1663746.58 1684780.17 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.org Ops/sec, More Is Better memtier_benchmark 1.4 Protocol: Redis - Clients: 50 - Set To Get Ratio: 1:10 B A AA C 400K 800K 1200K 1600K 2000K 1875260.09 1891611.75 1909295.85 1936392.38 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.org Ops/sec, More Is Better memtier_benchmark 1.4 Protocol: Redis - Clients: 50 - Set To Get Ratio: 1:1 B C AA A 400K 800K 1200K 1600K 2000K 1719792.39 1730287.32 1739112.82 1810859.67 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.org Ops/sec, More Is Better memtier_benchmark 1.4 Protocol: Redis - Clients: 50 - Set To Get Ratio: 1:5 B C AA A 400K 800K 1200K 1600K 2000K 1844254.53 1865191.56 1868299.86 1911666.23 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Dragonflydb Dragonfly is an open-source database server that is a "modern Redis replacement" that aims to be the fastest memory store while being compliant with the Redis and Memcached protocols. For benchmarking Dragonfly, Memtier_benchmark is used as a NoSQL Redis/Memcache traffic generation plus benchmarking tool developed by Redis Labs. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 0.6 Clients: 200 - Set To Get Ratio: 5:1 B C AA A 600K 1200K 1800K 2400K 3000K 2558359.14 2574045.53 2575239.57 2581692.96 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 0.6 Clients: 200 - Set To Get Ratio: 1:1 B A C AA 600K 1200K 1800K 2400K 3000K 2678724.09 2678725.83 2685467.32 2698410.83 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 0.6 Clients: 200 - Set To Get Ratio: 1:5 A C B AA 600K 1200K 1800K 2400K 3000K 2849837.44 2859261.77 2869778.70 2872811.95 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 0.6 Clients: 50 - Set To Get Ratio: 1:1 AA A B C 600K 1200K 1800K 2400K 3000K 2907432.83 2920540.96 2934355.48 2949072.75 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 0.6 Clients: 50 - Set To Get Ratio: 5:1 A B C AA 600K 1200K 1800K 2400K 3000K 2772545.65 2808028.85 2819421.36 2828285.63 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 0.6 Clients: 50 - Set To Get Ratio: 1:5 A C B AA 700K 1400K 2100K 2800K 3500K 3129187.64 3129879.97 3135021.28 3135276.20 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
etcd Etcd is a distributed, reliable key-value store intended for critical data of a distributed system. Etcd is written in Golang and part of the Cloud Native Computing Foundation (CNCF) and used by Kubernetes, Rook, CoreDNS, and other open-source software. This test profile uses Etcd's built-in benchmark to stress the PUT and RANGE performance of a single node / local system. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better etcd 3.5.4 Test: PUT - Connections: 50 - Clients: 100 - Average Latency C B AA A 0.4725 0.945 1.4175 1.89 2.3625 2.1 1.3 1.3 1.3
OpenBenchmarking.org Requests/sec, More Is Better etcd 3.5.4 Test: PUT - Connections: 50 - Clients: 100 C B A AA 20K 40K 60K 80K 100K 47230.98 78206.35 78352.92 78823.28
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Person Detection FP32 - Device: CPU AA B A C 700 1400 2100 2800 3500 3105.06 3092.99 3084.38 3044.33 MIN: 2706.58 / MAX: 3469.14 MIN: 2798.44 / MAX: 3409.97 MIN: 2539.51 / MAX: 3366.56 MIN: 2536.5 / MAX: 3437.01 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Person Detection FP32 - Device: CPU AA B A C 0.4365 0.873 1.3095 1.746 2.1825 1.89 1.91 1.92 1.94 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Face Detection FP16 - Device: CPU AA A C B 500 1000 1500 2000 2500 2279.05 2269.21 2250.83 2238.36 MIN: 2164.97 / MAX: 2394.44 MIN: 2172.69 / MAX: 2379.8 MIN: 2090.14 / MAX: 2336.79 MIN: 2082.75 / MAX: 2340.6 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Face Detection FP16 - Device: CPU AA A C B 0.6008 1.2016 1.8024 2.4032 3.004 2.63 2.64 2.65 2.67 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Person Detection FP16 - Device: CPU AA B A C 700 1400 2100 2800 3500 3123.95 3120.76 3099.00 3087.45 MIN: 2805.37 / MAX: 3397.57 MIN: 2826.01 / MAX: 3435.4 MIN: 2806.76 / MAX: 3365.69 MIN: 1583.7 / MAX: 3401.16 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Person Detection FP16 - Device: CPU AA B A C 0.432 0.864 1.296 1.728 2.16 1.90 1.90 1.91 1.92 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
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 MT/s, More Is Better ASTC Encoder 4.0 Preset: Exhaustive B C AA A 0.1771 0.3542 0.5313 0.7084 0.8855 0.7858 0.7865 0.7866 0.7872 1. (CXX) g++ options: -O3 -flto -pthread
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Face Detection FP16-INT8 - Device: CPU C AA B A 300 600 900 1200 1500 1388.28 1387.00 1385.55 1378.25 MIN: 1368.44 / MAX: 1418.89 MIN: 1370.49 / MAX: 1411.36 MIN: 1351.27 / MAX: 1417.45 MIN: 1353.01 / MAX: 1432.99 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Face Detection FP16-INT8 - Device: CPU AA B C A 0.9788 1.9576 2.9364 3.9152 4.894 4.31 4.31 4.31 4.35 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU B AA C A 50 100 150 200 250 210.33 209.50 206.98 203.27 MIN: 163.75 / MAX: 236.77 MIN: 173.72 / MAX: 239.08 MIN: 172.44 / MAX: 233.79 MIN: 113.88 / MAX: 231.66 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU B AA C A 7 14 21 28 35 28.50 28.62 28.94 29.48 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU B C A AA 4 8 12 16 20 17.35 17.30 17.23 17.21 MIN: 8.63 / MAX: 30.43 MIN: 14.64 / MAX: 24.15 MIN: 9.63 / MAX: 31.12 MIN: 8.7 / MAX: 30.28 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU B C A AA 80 160 240 320 400 345.45 346.46 347.84 348.24 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
Facebook RocksDB OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.5.3 Test: Random Fill Sync B AA C A 3K 6K 9K 12K 15K 13040 13069 13076 13085 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16 - Device: CPU A C AA B 5 10 15 20 25 19.83 19.82 19.82 19.81 MIN: 10.34 / MAX: 29.08 MIN: 14.28 / MAX: 34.13 MIN: 10.46 / MAX: 44.36 MIN: 10.65 / MAX: 32.44 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16 - Device: CPU A C AA B 70 140 210 280 350 302.20 302.39 302.44 302.53 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
etcd Etcd is a distributed, reliable key-value store intended for critical data of a distributed system. Etcd is written in Golang and part of the Cloud Native Computing Foundation (CNCF) and used by Kubernetes, Rook, CoreDNS, and other open-source software. This test profile uses Etcd's built-in benchmark to stress the PUT and RANGE performance of a single node / local system. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better etcd 3.5.4 Test: PUT - Connections: 500 - Clients: 100 - Average Latency C B AA A 0.315 0.63 0.945 1.26 1.575 1.4 1.3 1.3 1.3
OpenBenchmarking.org Requests/sec, More Is Better etcd 3.5.4 Test: PUT - Connections: 500 - Clients: 100 C A B AA 17K 34K 51K 68K 85K 72877.72 77475.55 77587.31 77587.44
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU B C AA A 4 8 12 16 20 16.25 16.21 16.21 16.21 MIN: 11.68 / MAX: 26.33 MIN: 11.31 / MAX: 25.92 MIN: 11.48 / MAX: 24.91 MIN: 10.98 / MAX: 24.75 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU B C A AA 80 160 240 320 400 368.92 369.83 369.89 369.90 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16 - Device: CPU B A AA C 8 16 24 32 40 35.99 35.09 34.55 34.45 MIN: 12.61 / MAX: 44.51 MIN: 22.45 / MAX: 47.1 MIN: 13.25 / MAX: 50.41 MIN: 20.8 / MAX: 53.68 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16 - Device: CPU B A AA C 40 80 120 160 200 166.57 170.86 173.53 174.02 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16-INT8 - Device: CPU C B AA A 7 14 21 28 35 28.11 28.11 28.07 28.03 MIN: 21.15 / MAX: 36.53 MIN: 22.38 / MAX: 36.76 MIN: 20.47 / MAX: 37.33 MIN: 15.92 / MAX: 33.62 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16-INT8 - Device: CPU C B AA A 90 180 270 360 450 426.70 426.73 427.35 427.87 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
Facebook RocksDB OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.5.3 Test: Random Fill A AA B C 200K 400K 600K 800K 1000K 914759 916583 917048 917383 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU C B AA A 0.207 0.414 0.621 0.828 1.035 0.92 0.92 0.92 0.92 MIN: 0.55 / MAX: 2.72 MIN: 0.54 / MAX: 9.48 MIN: 0.54 / MAX: 2.2 MIN: 0.54 / MAX: 32.37 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU A C AA B 3K 6K 9K 12K 15K 12924.91 12937.00 12948.36 12954.74 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU B A C AA 0.2835 0.567 0.8505 1.134 1.4175 1.26 1.26 1.25 1.25 MIN: 0.7 / MAX: 12.17 MIN: 0.71 / MAX: 10.9 MIN: 0.7 / MAX: 12.45 MIN: 0.67 / MAX: 12.4 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU A B C AA 2K 4K 6K 8K 10K 9457.64 9479.38 9527.71 9530.87 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
GraphicsMagick This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Sharpen C A AA B 40 80 120 160 200 198 199 199 199 1. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
Facebook RocksDB OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.5.3 Test: Update Random B AA C A 120K 240K 360K 480K 600K 546189 547827 549826 550239 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
GraphicsMagick This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Noise-Gaussian C B AA A 80 160 240 320 400 366 369 370 375 1. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Enhanced C AA B A 70 140 210 280 350 307 308 308 309 1. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
Facebook RocksDB OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.5.3 Test: Read Random Write Random AA B A C 400K 800K 1200K 1600K 2000K 1908955 1909640 1918881 1924607 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.5.3 Test: Read While Writing AA A B C 600K 1200K 1800K 2400K 3000K 2597712 2614220 2643393 2749536 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.5.3 Test: Random Read B C AA A 13M 26M 39M 52M 65M 59015149 59735063 60052818 60836317 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
GraphicsMagick This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Resizing C B AA A 300 600 900 1200 1500 1402 1425 1431 1456 1. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Swirl C AA B A 150 300 450 600 750 694 703 703 710 1. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Rotate C AA B A 160 320 480 640 800 697 717 720 746 1. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: HWB Color Space C AA B A 300 600 900 1200 1500 1284 1334 1340 1410 1. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
etcd Etcd is a distributed, reliable key-value store intended for critical data of a distributed system. Etcd is written in Golang and part of the Cloud Native Computing Foundation (CNCF) and used by Kubernetes, Rook, CoreDNS, and other open-source software. This test profile uses Etcd's built-in benchmark to stress the PUT and RANGE performance of a single node / local system. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better etcd 3.5.4 Test: RANGE - Connections: 100 - Clients: 100 - Average Latency C B AA A 0.2925 0.585 0.8775 1.17 1.4625 1.3 1.3 1.3 1.3
OpenBenchmarking.org Requests/sec, More Is Better etcd 3.5.4 Test: RANGE - Connections: 100 - Clients: 100 C A AA B 16K 32K 48K 64K 80K 76167.57 76759.94 76764.82 76892.65
OpenBenchmarking.org ms, Fewer Is Better etcd 3.5.4 Test: RANGE - Connections: 500 - Clients: 100 - Average Latency C B AA A 0.2925 0.585 0.8775 1.17 1.4625 1.3 1.3 1.3 1.3
OpenBenchmarking.org Requests/sec, More Is Better etcd 3.5.4 Test: RANGE - Connections: 500 - Clients: 100 C B A AA 17K 34K 51K 68K 85K 77235.74 77467.64 77585.95 77604.28
OpenBenchmarking.org Requests/sec, More Is Better etcd 3.5.4 Test: PUT - Connections: 500 - Clients: 1000 B AA A C 20K 40K 60K 80K 100K 77402.76 77976.00 77982.75 78092.71
OpenBenchmarking.org Requests/sec, More Is Better etcd 3.5.4 Test: RANGE - Connections: 500 - Clients: 1000 A C B AA 20K 40K 60K 80K 100K 77738.86 78062.46 78090.46 78128.39
OpenBenchmarking.org ms, Fewer Is Better etcd 3.5.4 Test: RANGE - Connections: 50 - Clients: 100 - Average Latency C B AA A 0.2925 0.585 0.8775 1.17 1.4625 1.3 1.3 1.3 1.3
OpenBenchmarking.org Requests/sec, More Is Better etcd 3.5.4 Test: RANGE - Connections: 50 - Clients: 100 AA B A C 20K 40K 60K 80K 100K 77874.58 78644.10 78944.06 78992.10
Timed Wasmer Compilation This test times how long it takes to compile Wasmer. Wasmer is written in the Rust programming language and is a WebAssembly runtime implementation that supports WASI and EmScripten. This test profile builds Wasmer with the Cranelift and Singlepast compiler features enabled. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Timed Wasmer Compilation 2.3 Time To Compile B C A AA 13 26 39 52 65 56.58 56.57 55.92 55.39 1. (CC) gcc options: -m64 -ldl -lgcc_s -lutil -lrt -lpthread -lm -lc -pie -nodefaultlibs
etcd Etcd is a distributed, reliable key-value store intended for critical data of a distributed system. Etcd is written in Golang and part of the Cloud Native Computing Foundation (CNCF) and used by Kubernetes, Rook, CoreDNS, and other open-source software. This test profile uses Etcd's built-in benchmark to stress the PUT and RANGE performance of a single node / local system. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better etcd 3.5.4 Test: PUT - Connections: 100 - Clients: 1000 - Average Latency AA C B A 3 6 9 12 15 11.1 11.0 11.0 11.0
OpenBenchmarking.org Requests/sec, More Is Better etcd 3.5.4 Test: PUT - Connections: 100 - Clients: 1000 AA C A B 20K 40K 60K 80K 100K 90337.62 90622.20 90990.37 90993.39
OpenBenchmarking.org Requests/sec, More Is Better etcd 3.5.4 Test: RANGE - Connections: 100 - Clients: 1000 B AA A C 20K 40K 60K 80K 100K 90811.02 91001.37 91454.55 91457.69
OpenBenchmarking.org Requests/sec, More Is Better etcd 3.5.4 Test: PUT - Connections: 50 - Clients: 1000 C AA B A 20K 40K 60K 80K 100K 90956.38 94162.78 94329.67 94397.28
OpenBenchmarking.org Requests/sec, More Is Better etcd 3.5.4 Test: RANGE - Connections: 50 - Clients: 1000 B C AA A 20K 40K 60K 80K 100K 94577.72 94756.82 94925.40 94964.87
OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: LPUSH - Parallel Connections: 1000 B C AA A 400K 800K 1200K 1600K 2000K 1581548.50 1605826.75 1652420.50 1659306.00 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: LPUSH - Parallel Connections: 50 C AA A B 400K 800K 1200K 1600K 2000K 1535984.25 1556351.25 1626151.25 1634363.00 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
srsRAN srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM A AA B C 40 80 120 160 200 161.8 162.1 163.9 167.4 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM A AA B C 90 180 270 360 450 407.5 407.7 411.8 421.3 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -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 MT/s, More Is Better ASTC Encoder 4.0 Preset: Thorough AA B C A 2 4 6 8 10 7.1996 7.2038 7.2072 7.2108 1. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: SET - Parallel Connections: 1000 C AA A B 400K 800K 1200K 1600K 2000K 1678740.00 1692135.00 1709316.62 1756954.75 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: LPOP - Parallel Connections: 500 AA C B A 500K 1000K 1500K 2000K 2500K 1484164.50 1488288.88 1582056.50 2489960.50 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: SET - Parallel Connections: 50 B A C AA 400K 800K 1200K 1600K 2000K 1643631.00 1680645.88 1739321.38 1757006.62 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: SET - Parallel Connections: 500 B C AA A 400K 800K 1200K 1600K 2000K 1667975.38 1761153.00 1797752.75 1828453.75 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Unvanquished Unvanquished is a modern fork of the Tremulous first person shooter. Unvanquished is powered by the Daemon engine, a combination of the ioquake3 (id Tech 3) engine with the graphically-beautiful XreaL engine. Unvanquished supports a modern OpenGL 3 renderer and other advanced graphics features for this open-source, cross-platform shooter game. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.53 Resolution: 3840 x 2160 - Effects Quality: Ultra C B A AA 60 120 180 240 300 253.9 254.6 269.7 277.2
Unvanquished Unvanquished is a modern fork of the Tremulous first person shooter. Unvanquished is powered by the Daemon engine, a combination of the ioquake3 (id Tech 3) engine with the graphically-beautiful XreaL engine. Unvanquished supports a modern OpenGL 3 renderer and other advanced graphics features for this open-source, cross-platform shooter game. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.53 Resolution: 3840 x 2160 - Effects Quality: High AA B A C 60 120 180 240 300 268.9 273.1 276.6 281.1
Unvanquished Unvanquished is a modern fork of the Tremulous first person shooter. Unvanquished is powered by the Daemon engine, a combination of the ioquake3 (id Tech 3) engine with the graphically-beautiful XreaL engine. Unvanquished supports a modern OpenGL 3 renderer and other advanced graphics features for this open-source, cross-platform shooter game. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.53 Resolution: 1920 x 1200 - Effects Quality: Ultra C A B AA 80 160 240 320 400 265.9 268.6 288.6 365.1
srsRAN srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM C B A AA 30 60 90 120 150 152.2 153.6 153.7 153.8 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM C B A AA 80 160 240 320 400 381.0 382.9 384.0 384.1 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 4 - Input: Bosphorus 1080p B AA C A 1.1741 2.3482 3.5223 4.6964 5.8705 5.179 5.200 5.206 5.218 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Unvanquished Unvanquished is a modern fork of the Tremulous first person shooter. Unvanquished is powered by the Daemon engine, a combination of the ioquake3 (id Tech 3) engine with the graphically-beautiful XreaL engine. Unvanquished supports a modern OpenGL 3 renderer and other advanced graphics features for this open-source, cross-platform shooter game. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.53 Resolution: 2560 x 1440 - Effects Quality: Medium C AA A B 60 120 180 240 300 271.6 275.8 276.8 288.5
srsRAN srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Samples / Second, More Is Better srsRAN 22.04.1 Test: OFDM_Test B AA C A 30M 60M 90M 120M 150M 144100000 145400000 145800000 152100000 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
Unvanquished Unvanquished is a modern fork of the Tremulous first person shooter. Unvanquished is powered by the Daemon engine, a combination of the ioquake3 (id Tech 3) engine with the graphically-beautiful XreaL engine. Unvanquished supports a modern OpenGL 3 renderer and other advanced graphics features for this open-source, cross-platform shooter game. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.53 Resolution: 3840 x 2160 - Effects Quality: Medium B AA A C 70 140 210 280 350 269.7 275.7 277.6 308.6
OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: GET - Parallel Connections: 50 AA C B A 500K 1000K 1500K 2000K 2500K 2079443.25 2154908.00 2240760.50 2522240.50 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Unvanquished Unvanquished is a modern fork of the Tremulous first person shooter. Unvanquished is powered by the Daemon engine, a combination of the ioquake3 (id Tech 3) engine with the graphically-beautiful XreaL engine. Unvanquished supports a modern OpenGL 3 renderer and other advanced graphics features for this open-source, cross-platform shooter game. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.53 Resolution: 1920 x 1200 - Effects Quality: Medium AA A C B 80 160 240 320 400 282.1 290.3 333.3 372.4
Facebook RocksDB OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.5.3 Test: Sequential Fill B AA A C 200K 400K 600K 800K 1000K 1054349 1057965 1059712 1059729 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
srsRAN srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 22.04.1 Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM C AA B A 14 28 42 56 70 60.5 61.3 61.3 61.4 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 22.04.1 Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM C B AA A 20 40 60 80 100 107.5 109.0 109.1 109.2 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -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 MT/s, More Is Better ASTC Encoder 4.0 Preset: Fast A B C AA 40 80 120 160 200 186.91 187.22 187.36 187.98 1. (CXX) g++ options: -O3 -flto -pthread
srsRAN srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM AA B A C 40 80 120 160 200 174.4 174.4 174.5 182.5 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM B A AA C 90 180 270 360 450 409.7 410.8 411.6 432.6 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
srsRAN srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM AA A B C 40 80 120 160 200 163.7 166.3 166.3 174.5 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM AA A B C 90 180 270 360 450 381.5 384.4 385.0 405.5 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 8 - Input: Bosphorus 4K A B C AA 10 20 30 40 50 41.88 42.95 43.02 43.19 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 10 - Input: Bosphorus 4K B C A AA 20 40 60 80 100 72.55 72.69 74.16 75.63 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 12 - Input: Bosphorus 4K A C B AA 20 40 60 80 100 100.17 101.60 101.90 103.53 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 8 - Input: Bosphorus 1080p A C B AA 30 60 90 120 150 111.03 113.02 113.77 113.97 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 10 - Input: Bosphorus 1080p A AA B C 50 100 150 200 250 234.54 235.31 237.14 238.44 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 12 - Input: Bosphorus 1080p A B AA C 80 160 240 320 400 346.65 352.19 354.97 358.60 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
A Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vDisk Notes: NONE / errors=remount-ro,relatime,rw / Block Size: 4096Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8701021Graphics Notes: BAR1 / Visible vRAM Size: 256 MB - vBIOS Version: 113-D0500100-102Python Notes: Python 3.10.4Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 8 September 2022 20:37 by user pts.
AA Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vDisk Notes: NONE / errors=remount-ro,relatime,rw / Block Size: 4096Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8701021Graphics Notes: BAR1 / Visible vRAM Size: 256 MB - vBIOS Version: 113-D0500100-102Python Notes: Python 3.10.4Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 9 September 2022 04:31 by user pts.
B Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vDisk Notes: NONE / errors=remount-ro,relatime,rw / Block Size: 4096Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8701021Graphics Notes: BAR1 / Visible vRAM Size: 256 MB - vBIOS Version: 113-D0500100-102Python Notes: Python 3.10.4Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 9 September 2022 09:02 by user pts.
C Processor: AMD Ryzen 9 3900XT 12-Core @ 3.80GHz (12 Cores / 24 Threads), Motherboard: MSI MEG X570 GODLIKE (MS-7C34) v1.0 (1.B3 BIOS), Chipset: AMD Starship/Matisse, Memory: 16GB, Disk: 500GB Seagate FireCuda 520 SSD ZP500GM30002, Graphics: AMD Radeon RX 56/64 8GB (1630/945MHz), Audio: AMD Vega 10 HDMI Audio, Monitor: ASUS MG28U, Network: Realtek Device 2600 + Realtek Killer E3000 2.5GbE + Intel Wi-Fi 6 AX200
OS: Ubuntu 22.04, Kernel: 5.15.0-40-generic (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 22.0.1 (LLVM 13.0.1 DRM 3.42), Vulkan: 1.3.204, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vDisk Notes: NONE / errors=remount-ro,relatime,rw / Block Size: 4096Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8701021Graphics Notes: BAR1 / Visible vRAM Size: 256 MB - vBIOS Version: 113-D0500100-102Python Notes: Python 3.10.4Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 9 September 2022 12:41 by user pts.