AMD EPYC 72F3 8-Core testing with a Supermicro H12SSL-i v1.01 (2.0 BIOS) and ASPEED on Ubuntu 21.04 via the Phoronix Test Suite.
A Processor: AMD EPYC 72F3 8-Core (8 Cores / 16 Threads), Motherboard: Supermicro H12SSL-i v1.01 (2.0 BIOS), Chipset: AMD Starship/Matisse, Memory: 126GB, Disk: 1000GB Corsair Force MP600, Graphics: ASPEED, Monitor: VE228, Network: 2 x Broadcom NetXtreme BCM5720 2-port PCIe
OS: Ubuntu 21.04, Kernel: 5.14.0-rc7-amd-pstate-phx (x86_64) 20210909, Desktop: GNOME Shell 3.38.4, Display Server: X Server, Compiler: GCC 10.3.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,hsa --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 -vProcessor Notes: CPU Microcode: 0xa001119Java Notes: OpenJDK Runtime Environment (build 11.0.11+9-Ubuntu-0ubuntu2)Python Notes: Python 3.9.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: 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 Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
AA Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,hsa --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 -vProcessor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001119Java Notes: OpenJDK Runtime Environment (build 11.0.11+9-Ubuntu-0ubuntu2)Python Notes: Python 3.9.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: 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 Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
B C Changed Processor to AMD EPYC 72F3 8-Core @ 3.70GHz (8 Cores / 16 Threads) .
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: NUMA C B AA 70 140 210 280 350 305.74 305.73 306.08 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: MEMFD C B AA 140 280 420 560 700 635.84 636.65 637.91 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Atomic C B AA 60K 120K 180K 240K 300K 285439.98 285472.50 285168.74 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Crypto C B AA 500 1000 1500 2000 2500 2420.07 2421.00 2419.41 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Malloc C B AA 40M 80M 120M 160M 200M 166491963.29 165987118.89 165535748.68 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
Test: RdRand
AA: stress-ng: error: [531054] No stress workers invoked (one or more were unsupported)
B: stress-ng: error: [2115693] No stress workers invoked (one or more were unsupported)
C: stress-ng: error: [3683822] No stress workers invoked (one or more were unsupported)
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Forking C B AA 7K 14K 21K 28K 35K 33684.07 33502.65 33935.48 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: IO_uring C B AA 10K 20K 30K 40K 50K 45964.56 41445.40 42384.59 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: SENDFILE C B AA 40K 80K 120K 160K 200K 189719.74 189882.98 190786.58 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: CPU Cache C B AA 14 28 42 56 70 55.66 60.86 58.99 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: CPU Stress C B AA 5K 10K 15K 20K 25K 24293.41 24464.86 23462.43 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Semaphores C B AA 300K 600K 900K 1200K 1500K 1196124.26 1196310.95 1196389.07 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Matrix Math C B AA 9K 18K 27K 36K 45K 40750.35 40513.27 40036.47 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Vector Math C B AA 10K 20K 30K 40K 50K 46521.63 46515.22 46504.21 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Memory Copying C B AA 800 1600 2400 3200 4000 3695.59 3692.06 3679.24 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Socket Activity C B AA 2K 4K 6K 8K 10K 11164.82 11101.43 11046.52 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Context Switching C B AA 1000K 2000K 3000K 4000K 5000K 4488677.09 4504723.94 4499566.44 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Glibc C String Functions C B AA 150K 300K 450K 600K 750K 692746.53 699066.00 694350.35 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Glibc Qsort Data Sorting C B AA 30 60 90 120 150 117.13 117.57 117.03 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: System V Message Passing C B AA 1000K 2000K 3000K 4000K 5000K 4708830.00 4708590.82 4701096.76 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Random Forest C B AA 200 400 600 800 1000 791.0 784.3 806.2 MIN: 690.69 / MAX: 964.93 MIN: 682.9 / MAX: 984.72 MIN: 690.56 / MAX: 921.02
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: ALS Movie Lens C B AA 1500 3000 4500 6000 7500 6991.9 7075.5 6987.2 MIN: 6782.85 / MAX: 7685.15 MIN: 7027.75 / MAX: 7493.32 MIN: 6869.04 / MAX: 7765.66
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Apache Spark ALS C B AA 400 800 1200 1600 2000 1860.1 1855.2 1831.1 MIN: 1752.8 / MAX: 1986.17 MIN: 1770.66 / MAX: 1983.41 MIN: 1738.11 / MAX: 1916.5
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Apache Spark Bayes C B AA 200 400 600 800 1000 1045.6 1047.3 1029.0 MIN: 742.82 / MAX: 1045.62 MIN: 731.55 / MAX: 1073.49 MIN: 712.89 / MAX: 1093.38
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Apache Spark PageRank C B AA 700 1400 2100 2800 3500 3315.3 3239.8 3348.8 MIN: 3033.27 / MAX: 3460.26 MIN: 2973.33 / MAX: 3239.81 MIN: 3099.7 / MAX: 3503.6
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Finagle HTTP Requests C B AA 500 1000 1500 2000 2500 2423.3 2363.0 2403.7 MIN: 2252.78 / MAX: 2536.28 MIN: 2182.02 / MAX: 2435.48 MIN: 2233.97 / MAX: 2452.96
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: In-Memory Database Shootout C B AA 1100 2200 3300 4400 5500 4646.4 4982.1 4908.6 MIN: 4264.63 / MAX: 5321.71 MIN: 4558.75 / MAX: 5219.66 MIN: 4594.33 / MAX: 5114.1
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Akka Unbalanced Cobwebbed Tree C B AA 3K 6K 9K 12K 15K 12449.5 13141.5 13270.6 MIN: 9235.34 MIN: 9733.34 MIN: 10373.8 / MAX: 13270.65
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Genetic Algorithm Using Jenetics + Futures C B AA 700 1400 2100 2800 3500 3338.4 3423.0 3186.6 MIN: 3196.18 / MAX: 3505.09 MIN: 3269.36 / MAX: 3575.3 MIN: 3041.66 / MAX: 3284.06
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 7.32.2 VGR Performance Metric B AA 30K 60K 90K 120K 150K 122638 122060 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 -pthread -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 3.0 Preset: Medium C B AA 0.9835 1.967 2.9505 3.934 4.9175 4.3709 4.3707 4.3565 1. (CXX) g++ options: -O3 -flto -pthread
JPEG XL Decoding libjxl The JPEG XL Image Coding System is designed to provide next-generation JPEG image capabilities with JPEG XL offering better image quality and compression over legacy JPEG. This test profile is suited for JPEG XL decode performance testing to PNG output file, the pts/jpexl test is for encode performance. The JPEG XL encoding/decoding is done using the libjxl codebase. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MP/s, More Is Better JPEG XL Decoding libjxl 0.5 CPU Threads: 1 C B AA 13 26 39 52 65 56.29 55.25 55.94
JPEG XL libjxl The JPEG XL Image Coding System is designed to provide next-generation JPEG image capabilities with JPEG XL offering better image quality and compression over legacy JPEG. This test profile is currently focused on the multi-threaded JPEG XL image encode performance using the reference libjxl library. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.5 Input: PNG - Encode Speed: 5 C B AA 10 20 30 40 50 42.54 43.68 44.11 1. (CXX) g++ options: -funwind-tables -O3 -O2 -pthread -fPIE -pie
OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.5 Input: PNG - Encode Speed: 8 C B AA 0.2138 0.4276 0.6414 0.8552 1.069 0.94 0.95 0.95 1. (CXX) g++ options: -funwind-tables -O3 -O2 -pthread -fPIE -pie
Google SynthMark SynthMark is a cross platform tool for benchmarking CPU performance under a variety of real-time audio workloads. It uses a polyphonic synthesizer model to provide standardized tests for latency, jitter and computational throughput. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Voices, More Is Better Google SynthMark 20201109 Test: VoiceMark_100 C B AA 200 400 600 800 1000 926.81 925.67 925.62 1. (CXX) g++ options: -lm -lpthread -std=c++11 -Ofast
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 1.2 Model: mobilenetV3 C B AA 0.6372 1.2744 1.9116 2.5488 3.186 2.803 2.832 2.818 MIN: 2.77 / MAX: 3.2 MIN: 2.79 / MAX: 3.35 MIN: 2.78 / MAX: 3.6 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 1.2 Model: squeezenetv1.1 C B AA 1.0528 2.1056 3.1584 4.2112 5.264 4.679 4.660 4.616 MIN: 4.38 / MAX: 5.35 MIN: 4.29 / MAX: 5.23 MIN: 4.28 / MAX: 5.41 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 1.2 Model: resnet-v2-50 C B AA 6 12 18 24 30 24.26 24.36 24.03 MIN: 23.88 / MAX: 34.22 MIN: 24.12 / MAX: 33.32 MIN: 23.71 / MAX: 24.73 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 1.2 Model: SqueezeNetV1.0 C B AA 2 4 6 8 10 7.679 7.849 7.540 MIN: 7.21 / MAX: 8.76 MIN: 7.36 / MAX: 8.27 MIN: 6.98 / MAX: 8.1 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 1.2 Model: MobileNetV2_224 C B AA 0.9131 1.8262 2.7393 3.6524 4.5655 4.024 4.058 4.003 MIN: 3.74 / MAX: 5.61 MIN: 3.77 / MAX: 4.8 MIN: 3.71 / MAX: 4.31 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 1.2 Model: mobilenet-v1-1.0 C B AA 0.7459 1.4918 2.2377 2.9836 3.7295 3.315 3.291 3.301 MIN: 3.26 / MAX: 3.8 MIN: 3.06 / MAX: 3.97 MIN: 3.05 / MAX: 13.36 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 1.2 Model: inception-v3 C B AA 8 16 24 32 40 34.52 34.53 34.43 MIN: 34.22 / MAX: 35.23 MIN: 34.29 / MAX: 46.07 MIN: 34.17 / MAX: 44.94 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
ONNX Runtime ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.8.2 Model: yolov4 - Device: OpenMP CPU C B AA 80 160 240 320 400 342 353 351 1. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.8.2 Model: bertsquad-10 - Device: OpenMP CPU C B AA 140 280 420 560 700 633 629 632 1. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.8.2 Model: fcn-resnet101-11 - Device: OpenMP CPU C B AA 20 40 60 80 100 83 81 83 1. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.8.2 Model: shufflenet-v2-10 - Device: OpenMP CPU C B AA 4K 8K 12K 16K 20K 19125 18753 18854 1. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.8.2 Model: super-resolution-10 - Device: OpenMP CPU C B AA 1000 2000 3000 4000 5000 4711 4711 4721 1. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
TNN TNN is an open-source deep learning reasoning framework developed by Tencent. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: DenseNet C B AA 800 1600 2400 3200 4000 3795.54 3790.08 3794.39 MIN: 3585.19 / MAX: 3870.65 MIN: 3583.45 / MAX: 3864.04 MIN: 3588.74 / MAX: 3871.13 1. (CXX) g++ options: -O3 -march=znver3 -fopenmp=libomp -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl
OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: MobileNet v2 C B AA 100 200 300 400 500 469.39 471.93 472.57 MIN: 466.46 / MAX: 476.94 MIN: 469.05 / MAX: 475.31 MIN: 469.64 / MAX: 476.63 1. (CXX) g++ options: -O3 -march=znver3 -fopenmp=libomp -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl
OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v2 C B AA 20 40 60 80 100 73.00 73.18 74.38 MIN: 72.9 / MAX: 73.13 MIN: 73.1 / MAX: 73.26 MIN: 74.28 / MAX: 74.51 1. (CXX) g++ options: -O3 -march=znver3 -fopenmp=libomp -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl
OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v1.1 C B AA 80 160 240 320 400 359.75 353.61 352.89 MIN: 359.44 / MAX: 363.95 MIN: 353.51 / MAX: 353.81 MIN: 352.73 / MAX: 353.01 1. (CXX) g++ options: -O3 -march=znver3 -fopenmp=libomp -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl
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 20210720 Target: CPU - Model: mobilenet C B AA 4 8 12 16 20 13.99 14.00 13.97 MIN: 13.8 / MAX: 14.49 MIN: 13.8 / MAX: 14.52 MIN: 13.76 / MAX: 14.43 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU-v2-v2 - Model: mobilenet-v2 C B AA 1.0935 2.187 3.2805 4.374 5.4675 4.85 4.82 4.86 MIN: 4.76 / MAX: 5.23 MIN: 4.73 / MAX: 5.15 MIN: 4.78 / MAX: 5.23 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU-v3-v3 - Model: mobilenet-v3 C B AA 1.0013 2.0026 3.0039 4.0052 5.0065 4.41 4.43 4.45 MIN: 4.35 / MAX: 4.84 MIN: 4.37 / MAX: 4.84 MIN: 4.36 / MAX: 4.93 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: shufflenet-v2 C B AA 1.1948 2.3896 3.5844 4.7792 5.974 5.26 5.19 5.31 MIN: 5.13 / MAX: 5.93 MIN: 5.13 / MAX: 5.8 MIN: 5.16 / MAX: 5.75 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: mnasnet C B AA 0.99 1.98 2.97 3.96 4.95 4.37 4.38 4.40 MIN: 4.32 / MAX: 4.64 MIN: 4.33 / MAX: 4.8 MIN: 4.35 / MAX: 5.77 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: efficientnet-b0 C B AA 2 4 6 8 10 6.35 6.36 6.38 MIN: 6.27 / MAX: 6.89 MIN: 6.28 / MAX: 6.7 MIN: 6.3 / MAX: 6.85 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: blazeface C B AA 0.4523 0.9046 1.3569 1.8092 2.2615 2.00 2.01 2.01 MIN: 1.98 / MAX: 2.17 MIN: 1.98 / MAX: 2.22 MIN: 1.98 / MAX: 2.16 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: googlenet C B AA 3 6 9 12 15 12.30 12.08 12.07 MIN: 12.01 / MAX: 12.97 MIN: 11.88 / MAX: 12.69 MIN: 11.64 / MAX: 12.97 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: vgg16 C B AA 7 14 21 28 35 30.72 30.98 30.63 MIN: 29.15 / MAX: 31.72 MIN: 29.36 / MAX: 41.86 MIN: 29.21 / MAX: 31.34 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: resnet18 C B AA 3 6 9 12 15 9.08 9.11 9.12 MIN: 8.85 / MAX: 9.62 MIN: 8.9 / MAX: 9.65 MIN: 8.93 / MAX: 9.66 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: alexnet C B AA 1.305 2.61 3.915 5.22 6.525 5.80 5.78 5.79 MIN: 5.53 / MAX: 6.07 MIN: 5.47 / MAX: 6.07 MIN: 5.53 / MAX: 6.05 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: resnet50 C B AA 5 10 15 20 25 18.55 18.58 18.44 MIN: 17.35 / MAX: 19.06 MIN: 17.41 / MAX: 19.34 MIN: 17.31 / MAX: 19.08 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: yolov4-tiny C B AA 5 10 15 20 25 21.40 21.16 21.35 MIN: 21.18 / MAX: 21.9 MIN: 20.93 / MAX: 21.78 MIN: 21.12 / MAX: 21.73 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: squeezenet_ssd C B AA 5 10 15 20 25 18.97 18.96 18.98 MIN: 18.64 / MAX: 19.81 MIN: 18.68 / MAX: 19.57 MIN: 18.68 / MAX: 19.73 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: regnety_400m C B AA 3 6 9 12 15 11.10 11.16 11.14 MIN: 10.92 / MAX: 19.3 MIN: 11.01 / MAX: 12.11 MIN: 10.99 / MAX: 11.52 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Quantum ESPRESSO Quantum ESPRESSO is an integrated suite of Open-Source computer codes for electronic-structure calculations and materials modeling at the nanoscale. It is based on density-functional theory, plane waves, and pseudopotentials. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Quantum ESPRESSO 6.8 Input: AUSURF112 C B AA 120 240 360 480 600 547.25 561.50 548.36 1. (F9X) gfortran options: -ldevXlib -lopenblas -lFoX_dom -lFoX_sax -lFoX_wxml -lFoX_common -lFoX_utils -lFoX_fsys -lfftw3 -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz
OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.10.0 Speed: Speed 5 - Input: Bosphorus 4K C B AA 4 8 12 16 20 16.35 15.98 15.74 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -march=znver3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.10.0 Speed: Speed 0 - Input: Bosphorus 1080p C B AA 4 8 12 16 20 15.95 16.07 15.99 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -march=znver3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.10.0 Speed: Speed 5 - Input: Bosphorus 1080p C B AA 8 16 24 32 40 33.81 34.61 34.20 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -march=znver3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
SVT-VP9 This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: VMAF Optimized - Input: Bosphorus 1080p C B AA 30 60 90 120 150 141.19 143.46 137.38 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p C B AA 30 60 90 120 150 148.35 149.60 147.85 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p C B AA 30 60 90 120 150 115.49 116.51 117.65 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.org FPS, More Is Better dav1d 0.9.2 Video Input: Summer Nature 4K C B AA 40 80 120 160 200 198.21 198.43 198.22 MIN: 186.08 / MAX: 225.64 MIN: 187.01 / MAX: 224.51 MIN: 186.96 / MAX: 224.56 1. (CC) gcc options: -pthread
OpenBenchmarking.org FPS, More Is Better dav1d 0.9.2 Video Input: Summer Nature 1080p C B AA 110 220 330 440 550 496.56 493.27 498.38 MIN: 434.64 / MAX: 538.81 MIN: 421.45 / MAX: 528.62 MIN: 456.97 / MAX: 537.87 1. (CC) gcc options: -pthread
OpenBenchmarking.org FPS, More Is Better dav1d 0.9.2 Video Input: Chimera 1080p 10-bit C B AA 100 200 300 400 500 449.67 449.93 456.10 MIN: 360.87 / MAX: 639.72 MIN: 361.39 / MAX: 674.89 MIN: 364.48 / MAX: 737.5 1. (CC) gcc options: -pthread
SVT-AV1 This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8.7 Encoder Mode: Preset 4 - Input: Bosphorus 4K C B AA 0.344 0.688 1.032 1.376 1.72 1.527 1.529 1.517 1. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8.7 Encoder Mode: Preset 8 - Input: Bosphorus 4K C B AA 4 8 12 16 20 14.64 14.64 14.63 1. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8.7 Encoder Mode: Preset 4 - Input: Bosphorus 1080p C B AA 1.1527 2.3054 3.4581 4.6108 5.7635 5.075 5.123 5.067 1. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8.7 Encoder Mode: Preset 8 - Input: Bosphorus 1080p C B AA 13 26 39 52 65 55.69 55.52 55.86 1. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
SVT-HEVC This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 1 - Input: Bosphorus 1080p C B AA 2 4 6 8 10 8.46 8.47 8.44 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 7 - Input: Bosphorus 1080p C B AA 20 40 60 80 100 109.03 109.41 108.87 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 10 - Input: Bosphorus 1080p C B AA 50 100 150 200 250 217.86 215.91 216.53 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 1.0 Benchmark: vklBenchmark Scalar C B AA 5 10 15 20 25 20 20 20 MIN: 2 / MAX: 563 MIN: 2 / MAX: 565 MIN: 2 / MAX: 560
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 1.0.2 Time To Compile C B AA 14 28 42 56 70 60.39 61.62 60.99 1. (CC) gcc options: -m64 -pie -nodefaultlibs -ldl -lgcc_s -lutil -lrt -lpthread -lm -lc
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 21.04 Test: OFDM_Test C B AA 30M 60M 90M 120M 150M 142400000 143100000 142900000 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM C B AA 90 180 270 360 450 415.3 417.9 416.7 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM C B AA 30 60 90 120 150 148.4 149.8 147.5 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM C B AA 90 180 270 360 450 419.1 419.3 418.8 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM C B AA 50 100 150 200 250 226.9 224.1 229.7 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM C B AA 100 200 300 400 500 457.4 457.4 456.6 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM C B AA 30 60 90 120 150 158.0 156.2 156.6 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM C B AA 100 200 300 400 500 457.0 448.5 452.2 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM C B AA 60 120 180 240 300 268.6 266.3 271.0 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 21.04 Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM C B AA 30 60 90 120 150 142.7 142.6 142.2 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 21.04 Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM C B AA 15 30 45 60 75 67.6 67.7 67.5 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 21.04 Test: 5G PHY_DL_NR Test 270 PRB SISO 256-QAM C B AA 30 60 90 120 150 154.0 156.8 153.0 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 21.04 Test: 5G PHY_DL_NR Test 270 PRB SISO 256-QAM C B AA 20 40 60 80 100 88.2 88.1 88.0 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
nginx This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the Golang "Bombardier" program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.21.1 Concurrent Requests: 1 C B AA 12K 24K 36K 48K 60K 50379.94 53856.04 50420.37 1. (CC) gcc options: -ldl -lpthread -lcrypt -lz -O3 -march=native
OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.21.1 Concurrent Requests: 20 C B AA 40K 80K 120K 160K 200K 202410.87 202588.11 204760.26 1. (CC) gcc options: -ldl -lpthread -lcrypt -lz -O3 -march=native
OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.21.1 Concurrent Requests: 100 C B AA 40K 80K 120K 160K 200K 204702.60 205750.87 207594.69 1. (CC) gcc options: -ldl -lpthread -lcrypt -lz -O3 -march=native
OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.21.1 Concurrent Requests: 200 C B AA 40K 80K 120K 160K 200K 203694.26 205159.87 207607.88 1. (CC) gcc options: -ldl -lpthread -lcrypt -lz -O3 -march=native
OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.21.1 Concurrent Requests: 500 C B AA 40K 80K 120K 160K 200K 202997.17 204525.40 206761.42 1. (CC) gcc options: -ldl -lpthread -lcrypt -lz -O3 -march=native
OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.21.1 Concurrent Requests: 1000 C B AA 40K 80K 120K 160K 200K 206521.13 201620.75 203835.67 1. (CC) gcc options: -ldl -lpthread -lcrypt -lz -O3 -march=native
Apache HTTP Server This is a test of the Apache HTTPD web server. This Apache HTTPD web server benchmark test profile makes use of the Golang "Bombardier" program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Requests Per Second, More Is Better Apache HTTP Server 2.4.48 Concurrent Requests: 1 C B AA 1500 3000 4500 6000 7500 7108.63 6988.71 6359.56 1. (CC) gcc options: -shared -fPIC -O2 -pthread
OpenSSL OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.0 Algorithm: SHA256 C B AA 3000M 6000M 9000M 12000M 15000M 13108074300 13091893760 12636003770 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.org sign/s, More Is Better OpenSSL 3.0 Algorithm: RSA4096 C B AA 500 1000 1500 2000 2500 2374.9 2374.8 2374.8 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.org verify/s, More Is Better OpenSSL 3.0 Algorithm: RSA4096 C B AA 30K 60K 90K 120K 150K 155058.8 154886.1 155046.9 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
Facebook RocksDB This is a benchmark of Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.
Test: Random Fill
AA: The test quit with a non-zero exit status.
B: The test quit with a non-zero exit status.
C: The test quit with a non-zero exit status.
Test: Random Read
AA: The test quit with a non-zero exit status.
B: The test quit with a non-zero exit status.
C: The test quit with a non-zero exit status.
Test: Update Random
AA: The test quit with a non-zero exit status.
B: The test quit with a non-zero exit status.
C: The test quit with a non-zero exit status.
Test: Sequential Fill
AA: The test quit with a non-zero exit status.
B: The test quit with a non-zero exit status.
C: The test quit with a non-zero exit status.
Test: Random Fill Sync
AA: The test quit with a non-zero exit status.
B: The test quit with a non-zero exit status.
C: The test quit with a non-zero exit status.
Test: Read While Writing
AA: The test quit with a non-zero exit status.
B: The test quit with a non-zero exit status.
C: The test quit with a non-zero exit status.
Test: Read Random Write Random
AA: The test quit with a non-zero exit status.
B: The test quit with a non-zero exit status.
C: The test quit with a non-zero exit status.
simdjson This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org GB/s, More Is Better simdjson 1.0 Throughput Test: Kostya C B AA 0.7268 1.4536 2.1804 2.9072 3.634 3.23 3.23 3.23 1. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.org GB/s, More Is Better simdjson 1.0 Throughput Test: PartialTweets C B AA 1.0013 2.0026 3.0039 4.0052 5.0065 4.45 4.45 4.45 1. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.org GB/s, More Is Better simdjson 1.0 Throughput Test: DistinctUserID C B AA 1.1025 2.205 3.3075 4.41 5.5125 4.90 4.88 4.90 1. (CXX) g++ options: -O3 -pthread
A Processor: AMD EPYC 72F3 8-Core (8 Cores / 16 Threads), Motherboard: Supermicro H12SSL-i v1.01 (2.0 BIOS), Chipset: AMD Starship/Matisse, Memory: 126GB, Disk: 1000GB Corsair Force MP600, Graphics: ASPEED, Monitor: VE228, Network: 2 x Broadcom NetXtreme BCM5720 2-port PCIe
OS: Ubuntu 21.04, Kernel: 5.14.0-rc7-amd-pstate-phx (x86_64) 20210909, Desktop: GNOME Shell 3.38.4, Display Server: X Server, Compiler: GCC 10.3.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,hsa --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 -vProcessor Notes: CPU Microcode: 0xa001119Java Notes: OpenJDK Runtime Environment (build 11.0.11+9-Ubuntu-0ubuntu2)Python Notes: Python 3.9.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: 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 Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 19 September 2021 18:49 by user phoronix.
AA Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,hsa --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 -vProcessor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001119Java Notes: OpenJDK Runtime Environment (build 11.0.11+9-Ubuntu-0ubuntu2)Python Notes: Python 3.9.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: 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 Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 19 September 2021 18:55 by user phoronix.
B Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,hsa --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 -vProcessor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001119Java Notes: OpenJDK Runtime Environment (build 11.0.11+9-Ubuntu-0ubuntu2)Python Notes: Python 3.9.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: 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 Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 20 September 2021 05:49 by user phoronix.
C Processor: AMD EPYC 72F3 8-Core @ 3.70GHz (8 Cores / 16 Threads), Motherboard: Supermicro H12SSL-i v1.01 (2.0 BIOS), Chipset: AMD Starship/Matisse, Memory: 126GB, Disk: 1000GB Corsair Force MP600, Graphics: ASPEED, Monitor: VE228, Network: 2 x Broadcom NetXtreme BCM5720 2-port PCIe
OS: Ubuntu 21.04, Kernel: 5.14.0-rc7-amd-pstate-phx (x86_64) 20210909, Desktop: GNOME Shell 3.38.4, Display Server: X Server, Compiler: GCC 10.3.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,hsa --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 -vProcessor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001119Java Notes: OpenJDK Runtime Environment (build 11.0.11+9-Ubuntu-0ubuntu2)Python Notes: Python 3.9.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: 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 Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 20 September 2021 13:54 by user phoronix.