Ryzen 5 3600XT Fest AMD Ryzen 5 3600XT 6-Core testing with a MSI X470 GAMING M7 AC (MS-7B77) v1.0 (1.E0 BIOS) and MSI AMD Radeon R7 370 / R9 270/370 OEM 4GB on Ubuntu 20.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2009233-FI-RYZEN536012&sor&grs .
Ryzen 5 3600XT Fest Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution Old 5.9 Git 5.8 v5.8 AMD Ryzen 5 3600XT 6-Core @ 3.80GHz (6 Cores / 12 Threads) MSI X470 GAMING M7 AC (MS-7B77) v1.0 (1.E0 BIOS) AMD Starship/Matisse 16GB Samsung SSD 960 EVO 500GB MSI AMD Radeon R7 370 / R9 270/370 OEM 4GB AMD Oland/Hainan/Cape G237HL Qualcomm Atheros Killer E2500 + Intel 8265 / 8275 Ubuntu 20.04 5.9.0-050900rc2daily20200825-generic (x86_64) 20200824 GNOME Shell 3.36.4 X Server 1.20.8 modesetting 1.20.8 4.5 Mesa 20.0.4 (LLVM 9.0.1) GCC 9.3.0 ext4 1920x1080 5.8.0-050800-generic (x86_64) OpenBenchmarking.org Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,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-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 -v Processor Details - Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8701021 Graphics Details - GLAMOR Python Details - Python 3.8.2 Security Details - 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 STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Ryzen 5 3600XT Fest osbench: Create Threads osbench: Launch Programs lczero: Eigen aom-av1: Speed 8 Realtime perf-bench: Sched Pipe perf-bench: Futex Hash lczero: BLAS aom-av1: Speed 6 Realtime aom-av1: Speed 4 Two-Pass mnn: SqueezeNetV1.0 osbench: Create Files aom-av1: Speed 6 Two-Pass webp: Quality 100, Highest Compression lammps: Rhodopsin Protein espeak: Text-To-Speech Synthesis ncnn: CPU - mobilenetv2_yolov3 ncnn: CPU - resnet50_int8 mnn: MobileNetV2_224 ncnn: CPU - resnet18_int8 mnn: inception-v3 perf-bench: Syscall Basic mnn: resnet-v2-50 webp: Quality 100 compress-zstd: 3 opencv: Object Detection build-llvm: Time To Compile system-decompress-zlib: webp: Quality 100, Lossless perf-bench: Memcpy 1MB mnn: mobilenet-v1-1.0 osbench: Memory Allocations ncnn: CPU - squeezenet mocassin: Dust 2D tau100.0 lammps: 20k Atoms webp: Default incompact3d: Cylinder webp: Quality 100, Lossless, Highest Compression perf-bench: Memset 1MB espeak: Text-To-Speech Synthesis ncnn: CPU - mnasnet glmark2: 1280 x 1024 ncnn: CPU - blazeface system-decompress-gzip: perf-bench: Futex Lock-Pi ncnn: CPU - alexnet ncnn: CPU - vgg16_int8 gromacs: Water Benchmark glmark2: 1920 x 1080 libraw: Post-Processing Benchmark namd: ATPase Simulation - 327,506 Atoms perf-bench: Epoll Wait ncnn: CPU - mobilenet_v3 ncnn: CPU - googlenet_int8 gpaw: Carbon Nanotube ncnn: CPU - squeezenet_int8 aom-av1: Speed 0 Two-Pass compress-zstd: 19 opencv: DNN - Deep Neural Network opencv: Features 2D kripke: osbench: Create Processes Old 5.9 Git 5.8 v5.8 9.837151 40.216446 772 37.22 309596 5265368 771 18.88 2.52 6.921 11.825870 3.95 6.843 4.953 27.598 18.69 86.80 4.144 25.54 40.032 21123079 32.390 2.199 4457.0 63537 763.835 1571.849150 15.563 14.538993 5.763 68.310341 4.21 236 4.909 1.443 460.785604 33.251 71.900876 27.886 4.82 4736 1.73 2.770 1371 18.38 136.50 0.695 3413 31.80 3.03067 125432 5.13 42.41 398.417 15.88 0.3 26.3 4937 153037 14694650 25.190513 9.084225 37.372907 739 38.10 325775 5518128 739 19.13 2.54 6.897 11.546709 3.97 6.947 4.872 28.177 18.38 85.33 4.137 25.93 40.307 20854429 32.832 2.206 4482.0 62714 762.031 1564.678697 15.689 14.600785 5.744 67.600330 4.24 238 4.940 1.443 457.224762 33.151 71.789212 28.066 4.80 1.74 2.775 1372 18.32 136.30 0.696 3406 31.73 3.02951 125180 5.12 42.47 398.047 15.87 0.3 26.3 4622 155569 10608357 19.270420 9.009043 37.302971 728 36.12 309796 5332405 742 18.41 2.47 7.068 11.614856 3.88 6.996 4.845 27.752 18.71 85.51 4.207 25.63 40.643 20814032 32.861 2.230 4422.0 63264 770.773 1582.122523 15.736 14.443479 5.806 68.081697 4.25 238 4.899 1.455 459.966319 32.996 71.354645 28.067 4.83 4764 1.74 2.763 1367 18.32 136.08 0.697 3404 31.76 3.03595 125238 5.13 42.48 398.138 15.88 0.3 26.3 4977 162679 9352232 19.383430 OpenBenchmarking.org
OSBench Test: Create Threads OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Threads v5.8 5.8 Old 5.9 Git 3 6 9 12 15 SE +/- 0.100422, N = 3 SE +/- 0.119046, N = 5 SE +/- 0.152146, N = 3 9.009043 9.084225 9.837151 1. (CC) gcc options: -lm
OSBench Test: Launch Programs OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Launch Programs v5.8 5.8 Old 5.9 Git 9 18 27 36 45 SE +/- 0.21, N = 3 SE +/- 0.49, N = 3 SE +/- 0.37, N = 3 37.30 37.37 40.22 1. (CC) gcc options: -lm
LeelaChessZero Backend: Eigen OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.26 Backend: Eigen Old 5.9 Git 5.8 v5.8 170 340 510 680 850 SE +/- 4.26, N = 3 SE +/- 10.41, N = 3 SE +/- 7.77, N = 3 772 739 728 1. (CXX) g++ options: -flto -pthread
AOM AV1 Encoder Mode: Speed 8 Realtime OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 2.0 Encoder Mode: Speed 8 Realtime 5.8 Old 5.9 Git v5.8 9 18 27 36 45 SE +/- 0.10, N = 3 SE +/- 0.14, N = 3 SE +/- 0.51, N = 4 38.10 37.22 36.12 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
perf-bench Benchmark: Sched Pipe OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Sched Pipe 5.8 v5.8 Old 5.9 Git 70K 140K 210K 280K 350K SE +/- 2830.49, N = 3 SE +/- 3921.92, N = 15 SE +/- 3186.07, N = 15 325775 309796 309596 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lz -llzma -lnuma
perf-bench Benchmark: Futex Hash OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Futex Hash 5.8 v5.8 Old 5.9 Git 1.2M 2.4M 3.6M 4.8M 6M SE +/- 2879.98, N = 3 SE +/- 83297.47, N = 3 SE +/- 10090.27, N = 3 5518128 5332405 5265368 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lz -llzma -lnuma
LeelaChessZero Backend: BLAS OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.26 Backend: BLAS Old 5.9 Git v5.8 5.8 170 340 510 680 850 SE +/- 9.33, N = 9 SE +/- 8.94, N = 5 SE +/- 6.69, N = 3 771 742 739 1. (CXX) g++ options: -flto -pthread
AOM AV1 Encoder Mode: Speed 6 Realtime OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 2.0 Encoder Mode: Speed 6 Realtime 5.8 Old 5.9 Git v5.8 5 10 15 20 25 SE +/- 0.07, N = 3 SE +/- 0.02, N = 3 SE +/- 0.16, N = 3 19.13 18.88 18.41 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
AOM AV1 Encoder Mode: Speed 4 Two-Pass OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 2.0 Encoder Mode: Speed 4 Two-Pass 5.8 Old 5.9 Git v5.8 0.5715 1.143 1.7145 2.286 2.8575 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 2.54 2.52 2.47 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
Mobile Neural Network Model: SqueezeNetV1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: SqueezeNetV1.0 5.8 Old 5.9 Git v5.8 2 4 6 8 10 SE +/- 0.102, N = 4 SE +/- 0.079, N = 6 SE +/- 0.001, N = 3 6.897 6.921 7.068 MIN: 6.57 / MAX: 9.93 MIN: 6.48 / MAX: 18.53 MIN: 6.92 / MAX: 9.33 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
OSBench Test: Create Files OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Files 5.8 v5.8 Old 5.9 Git 3 6 9 12 15 SE +/- 0.06, N = 3 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 11.55 11.61 11.83 1. (CC) gcc options: -lm
AOM AV1 Encoder Mode: Speed 6 Two-Pass OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 2.0 Encoder Mode: Speed 6 Two-Pass 5.8 Old 5.9 Git v5.8 0.8933 1.7866 2.6799 3.5732 4.4665 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 3.97 3.95 3.88 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
WebP Image Encode Encode Settings: Quality 100, Highest Compression OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Quality 100, Highest Compression Old 5.9 Git 5.8 v5.8 2 4 6 8 10 SE +/- 0.028, N = 3 SE +/- 0.084, N = 3 SE +/- 0.006, N = 3 6.843 6.947 6.996 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
LAMMPS Molecular Dynamics Simulator Model: Rhodopsin Protein OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 24Aug2020 Model: Rhodopsin Protein Old 5.9 Git 5.8 v5.8 1.1144 2.2288 3.3432 4.4576 5.572 SE +/- 0.047, N = 3 SE +/- 0.052, N = 15 SE +/- 0.082, N = 3 4.953 4.872 4.845 1. (CXX) g++ options: -O3 -pthread -lm
eSpeak-NG Speech Engine Text-To-Speech Synthesis OpenBenchmarking.org Seconds, Fewer Is Better eSpeak-NG Speech Engine 20200907 Text-To-Speech Synthesis Old 5.9 Git v5.8 5.8 7 14 21 28 35 SE +/- 0.30, N = 4 SE +/- 0.09, N = 4 SE +/- 0.06, N = 4 27.60 27.75 28.18 1. (CC) gcc options: -O2 -std=c99
NCNN Target: CPU - Model: mobilenetv2_yolov3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: mobilenetv2_yolov3 5.8 Old 5.9 Git v5.8 5 10 15 20 25 SE +/- 0.10, N = 3 SE +/- 0.19, N = 3 SE +/- 0.13, N = 3 18.38 18.69 18.71 MIN: 18.05 / MAX: 22.07 MIN: 18.16 / MAX: 23.94 MIN: 18.37 / MAX: 19.3 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: resnet50_int8 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: resnet50_int8 5.8 v5.8 Old 5.9 Git 20 40 60 80 100 SE +/- 0.09, N = 3 SE +/- 0.05, N = 3 SE +/- 0.88, N = 3 85.33 85.51 86.80 MIN: 84.86 / MAX: 99.05 MIN: 84.84 / MAX: 102.61 MIN: 84.44 / MAX: 116.92 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Mobile Neural Network Model: MobileNetV2_224 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: MobileNetV2_224 5.8 Old 5.9 Git v5.8 0.9466 1.8932 2.8398 3.7864 4.733 SE +/- 0.056, N = 4 SE +/- 0.017, N = 6 SE +/- 0.020, N = 3 4.137 4.144 4.207 MIN: 3.98 / MAX: 5.38 MIN: 4.03 / MAX: 10.62 MIN: 4.12 / MAX: 5.39 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
NCNN Target: CPU - Model: resnet18_int8 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: resnet18_int8 Old 5.9 Git v5.8 5.8 6 12 18 24 30 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 SE +/- 0.41, N = 3 25.54 25.63 25.93 MIN: 25.18 / MAX: 28.86 MIN: 25.34 / MAX: 48.92 MIN: 25.23 / MAX: 64.21 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Mobile Neural Network Model: inception-v3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: inception-v3 Old 5.9 Git 5.8 v5.8 9 18 27 36 45 SE +/- 0.23, N = 6 SE +/- 0.37, N = 4 SE +/- 0.19, N = 3 40.03 40.31 40.64 MIN: 38.85 / MAX: 52.8 MIN: 39.25 / MAX: 52.73 MIN: 40.11 / MAX: 52.54 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
perf-bench Benchmark: Syscall Basic OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Syscall Basic Old 5.9 Git 5.8 v5.8 5M 10M 15M 20M 25M SE +/- 191971.76, N = 3 SE +/- 216267.96, N = 3 SE +/- 59982.84, N = 3 21123079 20854429 20814032 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lz -llzma -lnuma
Mobile Neural Network Model: resnet-v2-50 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: resnet-v2-50 Old 5.9 Git 5.8 v5.8 8 16 24 32 40 SE +/- 0.11, N = 6 SE +/- 0.08, N = 4 SE +/- 0.10, N = 3 32.39 32.83 32.86 MIN: 31.51 / MAX: 43.85 MIN: 31.55 / MAX: 45.76 MIN: 32.49 / MAX: 43.86 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
WebP Image Encode Encode Settings: Quality 100 OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Quality 100 Old 5.9 Git 5.8 v5.8 0.5018 1.0036 1.5054 2.0072 2.509 SE +/- 0.018, N = 3 SE +/- 0.019, N = 3 SE +/- 0.020, N = 3 2.199 2.206 2.230 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
Zstd Compression Compression Level: 3 OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.5 Compression Level: 3 5.8 Old 5.9 Git v5.8 1000 2000 3000 4000 5000 SE +/- 1.59, N = 3 SE +/- 33.17, N = 3 SE +/- 25.94, N = 3 4482.0 4457.0 4422.0 1. (CC) gcc options: -O3 -pthread -lz -llzma
OpenCV Test: Object Detection OpenBenchmarking.org ms, Fewer Is Better OpenCV 4.4 Test: Object Detection 5.8 v5.8 Old 5.9 Git 14K 28K 42K 56K 70K SE +/- 810.17, N = 15 SE +/- 610.27, N = 15 SE +/- 902.31, N = 15 62714 63264 63537 1. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -ldl -lm -lpthread -lrt
Timed LLVM Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 10.0 Time To Compile 5.8 Old 5.9 Git v5.8 170 340 510 680 850 SE +/- 1.38, N = 3 SE +/- 2.30, N = 3 SE +/- 6.90, N = 3 762.03 763.84 770.77
System ZLIB Decompression OpenBenchmarking.org ms, Fewer Is Better System ZLIB Decompression 1.2.7 5.8 Old 5.9 Git v5.8 300 600 900 1200 1500 SE +/- 7.81, N = 10 SE +/- 7.01, N = 10 SE +/- 4.55, N = 10 1564.68 1571.85 1582.12
WebP Image Encode Encode Settings: Quality 100, Lossless OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Quality 100, Lossless Old 5.9 Git 5.8 v5.8 4 8 12 16 20 SE +/- 0.17, N = 3 SE +/- 0.18, N = 3 SE +/- 0.18, N = 3 15.56 15.69 15.74 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
perf-bench Benchmark: Memcpy 1MB OpenBenchmarking.org GB/sec, More Is Better perf-bench Benchmark: Memcpy 1MB 5.8 Old 5.9 Git v5.8 4 8 12 16 20 SE +/- 0.06, N = 3 SE +/- 0.22, N = 3 SE +/- 0.18, N = 15 14.60 14.54 14.44 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lz -llzma -lnuma
Mobile Neural Network Model: mobilenet-v1-1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: mobilenet-v1-1.0 5.8 Old 5.9 Git v5.8 1.3064 2.6128 3.9192 5.2256 6.532 SE +/- 0.015, N = 4 SE +/- 0.014, N = 6 SE +/- 0.014, N = 3 5.744 5.763 5.806 MIN: 5.64 / MAX: 8.07 MIN: 5.64 / MAX: 13.53 MIN: 5.71 / MAX: 8.44 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
OSBench Test: Memory Allocations OpenBenchmarking.org Ns Per Event, Fewer Is Better OSBench Test: Memory Allocations 5.8 v5.8 Old 5.9 Git 15 30 45 60 75 SE +/- 0.25, N = 3 SE +/- 0.39, N = 3 SE +/- 0.03, N = 3 67.60 68.08 68.31 1. (CC) gcc options: -lm
NCNN Target: CPU - Model: squeezenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: squeezenet Old 5.9 Git 5.8 v5.8 0.9563 1.9126 2.8689 3.8252 4.7815 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 4.21 4.24 4.25 MIN: 4.1 / MAX: 4.46 MIN: 4.15 / MAX: 4.3 MIN: 4.17 / MAX: 4.32 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Monte Carlo Simulations of Ionised Nebulae Input: Dust 2D tau100.0 OpenBenchmarking.org Seconds, Fewer Is Better Monte Carlo Simulations of Ionised Nebulae 2019-03-24 Input: Dust 2D tau100.0 Old 5.9 Git 5.8 v5.8 50 100 150 200 250 236 238 238 1. (F9X) gfortran options: -cpp -Jsource/ -ffree-line-length-0 -lm -std=legacy -O3 -O2 -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
LAMMPS Molecular Dynamics Simulator Model: 20k Atoms OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 24Aug2020 Model: 20k Atoms 5.8 Old 5.9 Git v5.8 1.1115 2.223 3.3345 4.446 5.5575 SE +/- 0.020, N = 3 SE +/- 0.012, N = 3 SE +/- 0.026, N = 3 4.940 4.909 4.899 1. (CXX) g++ options: -O3 -pthread -lm
WebP Image Encode Encode Settings: Default OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Default Old 5.9 Git 5.8 v5.8 0.3274 0.6548 0.9822 1.3096 1.637 SE +/- 0.010, N = 3 SE +/- 0.010, N = 3 SE +/- 0.008, N = 3 1.443 1.443 1.455 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
Incompact3D Input: Cylinder OpenBenchmarking.org Seconds, Fewer Is Better Incompact3D 2020-09-17 Input: Cylinder 5.8 v5.8 Old 5.9 Git 100 200 300 400 500 SE +/- 2.76, N = 3 SE +/- 2.59, N = 3 SE +/- 4.93, N = 3 457.22 459.97 460.79 1. (F9X) gfortran options: -cpp -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
WebP Image Encode Encode Settings: Quality 100, Lossless, Highest Compression OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Quality 100, Lossless, Highest Compression v5.8 5.8 Old 5.9 Git 8 16 24 32 40 SE +/- 0.05, N = 3 SE +/- 0.08, N = 3 SE +/- 0.15, N = 3 33.00 33.15 33.25 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
perf-bench Benchmark: Memset 1MB OpenBenchmarking.org GB/sec, More Is Better perf-bench Benchmark: Memset 1MB Old 5.9 Git 5.8 v5.8 16 32 48 64 80 SE +/- 0.67, N = 15 SE +/- 0.85, N = 15 SE +/- 0.83, N = 3 71.90 71.79 71.35 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lz -llzma -lnuma
eSpeak Speech Engine Text-To-Speech Synthesis OpenBenchmarking.org Seconds, Fewer Is Better eSpeak Speech Engine 1.48.04 Text-To-Speech Synthesis Old 5.9 Git 5.8 v5.8 7 14 21 28 35 SE +/- 0.17, N = 3 SE +/- 0.23, N = 3 SE +/- 0.16, N = 3 27.89 28.07 28.07 1. (CXX) g++ options: -lstdc++ -lespeak -O2 -fpic -fvisibility=hidden -pedantic -fno-exceptions
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: mnasnet 5.8 Old 5.9 Git v5.8 1.0868 2.1736 3.2604 4.3472 5.434 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 4.80 4.82 4.83 MIN: 4.72 / MAX: 4.89 MIN: 4.75 / MAX: 5.63 MIN: 4.77 / MAX: 5.49 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
GLmark2 Resolution: 1280 x 1024 OpenBenchmarking.org Score, More Is Better GLmark2 2020.04 Resolution: 1280 x 1024 v5.8 Old 5.9 Git 1000 2000 3000 4000 5000 4764 4736
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: blazeface Old 5.9 Git 5.8 v5.8 0.3915 0.783 1.1745 1.566 1.9575 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 1.73 1.74 1.74 MIN: 1.69 / MAX: 1.83 MIN: 1.7 / MAX: 2.25 MIN: 1.69 / MAX: 2.37 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
System GZIP Decompression OpenBenchmarking.org Seconds, Fewer Is Better System GZIP Decompression v5.8 Old 5.9 Git 5.8 0.6244 1.2488 1.8732 2.4976 3.122 SE +/- 0.024, N = 3 SE +/- 0.020, N = 3 SE +/- 0.036, N = 3 2.763 2.770 2.775
perf-bench Benchmark: Futex Lock-Pi OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Futex Lock-Pi 5.8 Old 5.9 Git v5.8 300 600 900 1200 1500 SE +/- 2.00, N = 3 SE +/- 1.67, N = 3 SE +/- 2.85, N = 3 1372 1371 1367 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lz -llzma -lnuma
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: alexnet 5.8 v5.8 Old 5.9 Git 5 10 15 20 25 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.07, N = 3 18.32 18.32 18.38 MIN: 18.24 / MAX: 18.43 MIN: 18.22 / MAX: 20.46 MIN: 18.2 / MAX: 24.94 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: vgg16_int8 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: vgg16_int8 v5.8 5.8 Old 5.9 Git 30 60 90 120 150 SE +/- 0.38, N = 3 SE +/- 0.04, N = 3 SE +/- 0.18, N = 3 136.08 136.30 136.50 MIN: 133.33 / MAX: 142.76 MIN: 134.12 / MAX: 169.24 MIN: 133.75 / MAX: 155.01 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
GROMACS Water Benchmark OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2020.1 Water Benchmark v5.8 5.8 Old 5.9 Git 0.1568 0.3136 0.4704 0.6272 0.784 SE +/- 0.002, N = 3 SE +/- 0.001, N = 3 SE +/- 0.001, N = 3 0.697 0.696 0.695 1. (CXX) g++ options: -O3 -pthread -lrt -lpthread -lm
GLmark2 Resolution: 1920 x 1080 OpenBenchmarking.org Score, More Is Better GLmark2 2020.04 Resolution: 1920 x 1080 Old 5.9 Git 5.8 v5.8 700 1400 2100 2800 3500 3413 3406 3404
LibRaw Post-Processing Benchmark OpenBenchmarking.org Mpix/sec, More Is Better LibRaw 0.20 Post-Processing Benchmark Old 5.9 Git v5.8 5.8 7 14 21 28 35 SE +/- 0.07, N = 3 SE +/- 0.09, N = 3 SE +/- 0.10, N = 3 31.80 31.76 31.73 1. (CXX) g++ options: -O2 -fopenmp -ljpeg -lz -lm
NAMD ATPase Simulation - 327,506 Atoms OpenBenchmarking.org days/ns, Fewer Is Better NAMD 2.14 ATPase Simulation - 327,506 Atoms 5.8 Old 5.9 Git v5.8 0.6831 1.3662 2.0493 2.7324 3.4155 SE +/- 0.00138, N = 3 SE +/- 0.00094, N = 3 SE +/- 0.00219, N = 3 3.02951 3.03067 3.03595
perf-bench Benchmark: Epoll Wait OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Epoll Wait Old 5.9 Git v5.8 5.8 30K 60K 90K 120K 150K SE +/- 545.49, N = 3 SE +/- 233.15, N = 3 SE +/- 61.41, N = 3 125432 125238 125180 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lz -llzma -lnuma
NCNN Target: CPU - Model: mobilenet_v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: mobilenet_v3 5.8 Old 5.9 Git v5.8 1.1543 2.3086 3.4629 4.6172 5.7715 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 5.12 5.13 5.13 MIN: 5.04 / MAX: 5.81 MIN: 4.96 / MAX: 11.01 MIN: 5.02 / MAX: 8.14 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: googlenet_int8 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: googlenet_int8 Old 5.9 Git 5.8 v5.8 10 20 30 40 50 SE +/- 0.14, N = 3 SE +/- 0.06, N = 3 SE +/- 0.10, N = 3 42.41 42.47 42.48 MIN: 41.81 / MAX: 44.99 MIN: 41.94 / MAX: 44.82 MIN: 41.89 / MAX: 44.27 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
GPAW Input: Carbon Nanotube OpenBenchmarking.org Seconds, Fewer Is Better GPAW 20.1 Input: Carbon Nanotube 5.8 v5.8 Old 5.9 Git 90 180 270 360 450 SE +/- 0.62, N = 3 SE +/- 0.69, N = 3 SE +/- 0.61, N = 3 398.05 398.14 398.42 1. (CC) gcc options: -pthread -shared -fwrapv -O2 -lxc -lblas -lmpi
NCNN Target: CPU - Model: squeezenet_int8 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: squeezenet_int8 5.8 Old 5.9 Git v5.8 4 8 12 16 20 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 SE +/- 0.07, N = 3 15.87 15.88 15.88 MIN: 15.65 / MAX: 26.42 MIN: 15.72 / MAX: 17.4 MIN: 15.62 / MAX: 26.89 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
AOM AV1 Encoder Mode: Speed 0 Two-Pass OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 2.0 Encoder Mode: Speed 0 Two-Pass v5.8 5.8 Old 5.9 Git 0.0675 0.135 0.2025 0.27 0.3375 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.3 0.3 0.3 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
Zstd Compression Compression Level: 19 OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.5 Compression Level: 19 v5.8 5.8 Old 5.9 Git 6 12 18 24 30 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 26.3 26.3 26.3 1. (CC) gcc options: -O3 -pthread -lz -llzma
OpenCV Test: DNN - Deep Neural Network OpenBenchmarking.org ms, Fewer Is Better OpenCV 4.4 Test: DNN - Deep Neural Network 5.8 Old 5.9 Git v5.8 1100 2200 3300 4400 5500 SE +/- 170.62, N = 15 SE +/- 183.15, N = 15 SE +/- 240.89, N = 12 4622 4937 4977 1. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -ldl -lm -lpthread -lrt
OpenCV Test: Features 2D OpenBenchmarking.org ms, Fewer Is Better OpenCV 4.4 Test: Features 2D Old 5.9 Git 5.8 v5.8 30K 60K 90K 120K 150K SE +/- 1985.27, N = 4 SE +/- 3318.33, N = 12 SE +/- 2780.42, N = 12 153037 155569 162679 1. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -ldl -lm -lpthread -lrt
Kripke OpenBenchmarking.org Throughput FoM, More Is Better Kripke 1.2.4 Old 5.9 Git 5.8 v5.8 3M 6M 9M 12M 15M SE +/- 232369.32, N = 3 SE +/- 473207.63, N = 9 SE +/- 50313.60, N = 3 14694650 10608357 9352232 1. (CXX) g++ options: -O3 -fopenmp
OSBench Test: Create Processes OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Processes 5.8 v5.8 Old 5.9 Git 6 12 18 24 30 SE +/- 0.30, N = 15 SE +/- 0.24, N = 3 SE +/- 0.27, N = 3 19.27 19.38 25.19 1. (CC) gcc options: -lm
Phoronix Test Suite v10.8.4