new ts AMD Ryzen Threadripper 3990X 64-Core testing with a Gigabyte TRX40 AORUS PRO WIFI (F4p BIOS) and AMD Radeon RX 5700 8GB on Ubuntu 22.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2208196-NE-NEWTS190909&grs&rdt .
new ts Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL Vulkan Compiler File-System Screen Resolution A B C AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads) Gigabyte TRX40 AORUS PRO WIFI (F4p BIOS) AMD Starship/Matisse 128GB Samsung SSD 970 EVO Plus 500GB AMD Radeon RX 5700 8GB (1750/875MHz) AMD Navi 10 HDMI Audio DELL P2415Q Intel I211 + Intel Wi-Fi 6 AX200 Ubuntu 22.04 5.19.0-051900rc7-generic (x86_64) GNOME Shell 42.2 X Server + Wayland 4.6 Mesa 22.0.1 (LLVM 13.0.1 DRM 3.47) 1.2.204 GCC 11.2.0 ext4 3840x2160 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --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 -v Processor Details - Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8301039 Security Details - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Mitigation of untrained return thunk; SMT enabled with STIBP protection + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
new ts redis: LPOP - 50 redis: LPOP - 500 redis: GET - 50 ncnn: CPU - mobilenet mnn: SqueezeNetV1.0 ncnn: Vulkan GPU - squeezenet_ssd redis: SET - 1000 redis: SADD - 500 mnn: squeezenetv1.1 ncnn: Vulkan GPU-v3-v3 - mobilenet-v3 ncnn: CPU - squeezenet_ssd mnn: inception-v3 mnn: MobileNetV2_224 redis: SET - 500 ncnn: Vulkan GPU - shufflenet-v2 ncnn: CPU - yolov4-tiny ncnn: Vulkan GPU - FastestDet redis: GET - 1000 redis: LPOP - 1000 ncnn: Vulkan GPU - mnasnet redis: LPUSH - 500 ncnn: Vulkan GPU - googlenet ncnn: CPU - alexnet ncnn: CPU - googlenet ncnn: Vulkan GPU-v2-v2 - mobilenet-v2 ncnn: Vulkan GPU - blazeface ncnn: CPU - resnet50 redis: SET - 50 ncnn: Vulkan GPU - efficientnet-b0 ncnn: CPU - vgg16 mnn: mobilenetV3 redis: SADD - 1000 redis: LPUSH - 1000 redis: LPUSH - 50 ncnn: Vulkan GPU - vgg16 ncnn: CPU - vision_transformer redis: SADD - 50 ncnn: Vulkan GPU - alexnet ncnn: Vulkan GPU - resnet18 ncnn: CPU - regnety_400m ncnn: Vulkan GPU - vision_transformer ncnn: Vulkan GPU - mobilenet ncnn: Vulkan GPU - resnet50 ncnn: Vulkan GPU - regnety_400m ncnn: Vulkan GPU - yolov4-tiny ncnn: CPU - FastestDet ncnn: CPU - resnet18 ncnn: CPU - blazeface ncnn: CPU - efficientnet-b0 ncnn: CPU - mnasnet ncnn: CPU - shufflenet-v2 ncnn: CPU-v3-v3 - mobilenet-v3 ncnn: CPU-v2-v2 - mobilenet-v2 mnn: mobilenet-v1-1.0 mnn: resnet-v2-50 redis: GET - 500 A B C 2498183.8 1916702.63 2469009.92 31.04 7.313 316.70 1329224.63 1550371.42 3.982 164.83 34.83 27.030 5.030 1338680.82 97.43 40.70 98.49 1668219.58 1180993.50 182.91 1227521.85 447.41 17.99 35.10 163.75 43.88 44.63 1752688.12 306.21 50.01 2.421 1497193.50 1220257.96 1564561.87 1585.62 147.55 1947375.17 351.09 291.61 68.87 5699.22 409.96 814.60 281.09 531.51 20.71 24.06 9.37 23.86 18.10 18.52 17.94 19.20 4.333 26.909 1735192.35 1558194.25 1162784.5 2128422.25 34.56 6.653 321.74 1245858.12 1455206.5 4.056 155.32 35.62 28.462 4.899 1319110.88 102.29 41.12 101.22 1697526.25 1152163.25 178.89 1255074 442.91 18.07 35.45 160.38 43.97 43.86 1770758.12 309.69 49.25 2.45 1501072.38 1237332 1585970.62 1574.35 148.51 1956880.88 351.98 291.76 68.65 5705.84 410.49 814.71 275.06 513.97 23.24 22.5 9.39 23.49 17.35 18.21 17.38 18.17 4.072 24.913 1644604 1515224.5 1177600 2100667.75 33.04 7.321 338.4 1321178.38 1516465.38 4.238 155.83 36.74 27.967 5.152 1274362.75 101.49 39.56 101.12 1653373.12 1153624.25 181.77 1237737.88 452.63 17.69 35.84 163.37 43.09 44.73 1743710.5 310.94 49.61 2.458 1519118.38 1226720.12 1576320.88 1578.87 147.53 1960093.5 352.81 292.7 68.85 5709.48 410.09 814.64 264.94 516.33 24.91 23.42 8.76 22.52 17.58 18.35 16.26 18.43 3.896 24.493 1649541.25 OpenBenchmarking.org
Redis Test: LPOP - Parallel Connections: 50 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: LPOP - Parallel Connections: 50 A B C 500K 1000K 1500K 2000K 2500K SE +/- 32340.71, N = 3 2498183.80 1558194.25 1515224.50 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Redis Test: LPOP - Parallel Connections: 500 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: LPOP - Parallel Connections: 500 A B C 400K 800K 1200K 1600K 2000K SE +/- 7169.32, N = 3 1916702.63 1162784.50 1177600.00 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Redis Test: GET - Parallel Connections: 50 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: GET - Parallel Connections: 50 A B C 500K 1000K 1500K 2000K 2500K SE +/- 17359.14, N = 3 2469009.92 2128422.25 2100667.75 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
NCNN Target: CPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: mobilenet A B C 8 16 24 32 40 SE +/- 0.52, N = 12 31.04 34.56 33.04 MIN: 25.81 / MAX: 98.98 MIN: 28.25 / MAX: 40.74 MIN: 28.08 / MAX: 38.51 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Mobile Neural Network Model: SqueezeNetV1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.0 Model: SqueezeNetV1.0 A B C 2 4 6 8 10 SE +/- 0.236, N = 3 7.313 6.653 7.321 MIN: 6.32 / MAX: 9.01 MIN: 6.36 / MAX: 7.04 MIN: 6.52 / MAX: 8.62 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: Vulkan GPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: squeezenet_ssd A B C 70 140 210 280 350 SE +/- 3.47, N = 3 316.70 321.74 338.40 MIN: 275.77 / MAX: 453.58 MIN: 278.6 / MAX: 449.6 MIN: 279.78 / MAX: 467 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Redis Test: SET - Parallel Connections: 1000 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: SET - Parallel Connections: 1000 A B C 300K 600K 900K 1200K 1500K SE +/- 15024.63, N = 3 1329224.63 1245858.12 1321178.38 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Redis Test: SADD - Parallel Connections: 500 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: SADD - Parallel Connections: 500 A B C 300K 600K 900K 1200K 1500K SE +/- 17244.14, N = 15 1550371.42 1455206.50 1516465.38 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Mobile Neural Network Model: squeezenetv1.1 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.0 Model: squeezenetv1.1 A B C 0.9536 1.9072 2.8608 3.8144 4.768 SE +/- 0.070, N = 3 3.982 4.056 4.238 MIN: 3.76 / MAX: 4.48 MIN: 3.91 / MAX: 4.21 MIN: 4.02 / MAX: 4.44 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
NCNN Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 A B C 40 80 120 160 200 SE +/- 0.81, N = 3 164.83 155.32 155.83 MIN: 125.38 / MAX: 214.06 MIN: 144.2 / MAX: 188.29 MIN: 144.44 / MAX: 192.01 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: squeezenet_ssd A B C 8 16 24 32 40 SE +/- 0.23, N = 12 34.83 35.62 36.74 MIN: 31.09 / MAX: 92.26 MIN: 32.21 / MAX: 47.32 MIN: 32.7 / MAX: 67.25 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Mobile Neural Network Model: inception-v3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.0 Model: inception-v3 A B C 7 14 21 28 35 SE +/- 0.13, N = 3 27.03 28.46 27.97 MIN: 26.11 / MAX: 28.32 MIN: 27 / MAX: 30.52 MIN: 27.1 / MAX: 28.88 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
Mobile Neural Network Model: MobileNetV2_224 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.0 Model: MobileNetV2_224 A B C 1.1592 2.3184 3.4776 4.6368 5.796 SE +/- 0.095, N = 3 5.030 4.899 5.152 MIN: 4.62 / MAX: 5.6 MIN: 4.71 / MAX: 5.28 MIN: 4.85 / MAX: 5.72 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
Redis Test: SET - Parallel Connections: 500 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: SET - Parallel Connections: 500 A B C 300K 600K 900K 1200K 1500K SE +/- 17762.03, N = 12 1338680.82 1319110.88 1274362.75 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
NCNN Target: Vulkan GPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: shufflenet-v2 A B C 20 40 60 80 100 SE +/- 0.59, N = 3 97.43 102.29 101.49 MIN: 85.08 / MAX: 128.16 MIN: 98.68 / MAX: 118.03 MIN: 96.1 / MAX: 117.72 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: yolov4-tiny A B C 9 18 27 36 45 SE +/- 0.19, N = 12 40.70 41.12 39.56 MIN: 35.39 / MAX: 64.14 MIN: 37.25 / MAX: 53.93 MIN: 36.99 / MAX: 51.43 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: FastestDet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: FastestDet A B C 20 40 60 80 100 SE +/- 1.79, N = 3 98.49 101.22 101.12 MIN: 70.32 / MAX: 129.14 MIN: 92.21 / MAX: 110.44 MIN: 94.87 / MAX: 108.84 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Redis Test: GET - Parallel Connections: 1000 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: GET - Parallel Connections: 1000 A B C 400K 800K 1200K 1600K 2000K SE +/- 3728.73, N = 3 1668219.58 1697526.25 1653373.12 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Redis Test: LPOP - Parallel Connections: 1000 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: LPOP - Parallel Connections: 1000 A B C 300K 600K 900K 1200K 1500K SE +/- 9918.56, N = 3 1180993.50 1152163.25 1153624.25 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
NCNN Target: Vulkan GPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: mnasnet A B C 40 80 120 160 200 SE +/- 3.22, N = 3 182.91 178.89 181.77 MIN: 171 / MAX: 214.09 MIN: 169.54 / MAX: 217.51 MIN: 175.83 / MAX: 208.03 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Redis Test: LPUSH - Parallel Connections: 500 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: LPUSH - Parallel Connections: 500 A B C 300K 600K 900K 1200K 1500K SE +/- 13741.04, N = 4 1227521.85 1255074.00 1237737.88 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
NCNN Target: Vulkan GPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: googlenet A B C 100 200 300 400 500 SE +/- 1.28, N = 3 447.41 442.91 452.63 MIN: 415.84 / MAX: 531.22 MIN: 411.09 / MAX: 500.51 MIN: 409.36 / MAX: 526.35 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: alexnet A B C 4 8 12 16 20 SE +/- 0.09, N = 12 17.99 18.07 17.69 MIN: 13.86 / MAX: 27.32 MIN: 16.92 / MAX: 19.82 MIN: 15.41 / MAX: 20.66 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: googlenet A B C 8 16 24 32 40 SE +/- 0.28, N = 12 35.10 35.45 35.84 MIN: 30.11 / MAX: 120.79 MIN: 31.96 / MAX: 42.11 MIN: 32.46 / MAX: 46.55 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 A B C 40 80 120 160 200 SE +/- 2.24, N = 3 163.75 160.38 163.37 MIN: 139.72 / MAX: 192.58 MIN: 139.5 / MAX: 193.18 MIN: 141.13 / MAX: 196.25 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: blazeface A B C 10 20 30 40 50 SE +/- 0.17, N = 3 43.88 43.97 43.09 MIN: 28.03 / MAX: 57.23 MIN: 30.91 / MAX: 55.93 MIN: 31.72 / MAX: 55.77 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: resnet50 A B C 10 20 30 40 50 SE +/- 0.32, N = 12 44.63 43.86 44.73 MIN: 38.6 / MAX: 54.54 MIN: 38.61 / MAX: 85.93 MIN: 39.99 / MAX: 51.73 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Redis Test: SET - Parallel Connections: 50 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: SET - Parallel Connections: 50 A B C 400K 800K 1200K 1600K 2000K SE +/- 14504.57, N = 3 1752688.12 1770758.12 1743710.50 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
NCNN Target: Vulkan GPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: efficientnet-b0 A B C 70 140 210 280 350 SE +/- 3.03, N = 3 306.21 309.69 310.94 MIN: 257.3 / MAX: 345.94 MIN: 258.46 / MAX: 345.46 MIN: 257.08 / MAX: 341.17 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: vgg16 A B C 11 22 33 44 55 SE +/- 0.35, N = 12 50.01 49.25 49.61 MIN: 45.53 / MAX: 128.33 MIN: 46.47 / MAX: 61.53 MIN: 47.17 / MAX: 66.28 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Mobile Neural Network Model: mobilenetV3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.0 Model: mobilenetV3 A B C 0.5531 1.1062 1.6593 2.2124 2.7655 SE +/- 0.015, N = 3 2.421 2.450 2.458 MIN: 2.35 / MAX: 2.53 MIN: 2.39 / MAX: 2.53 MIN: 2.4 / MAX: 2.54 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
Redis Test: SADD - Parallel Connections: 1000 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: SADD - Parallel Connections: 1000 A B C 300K 600K 900K 1200K 1500K SE +/- 14869.73, N = 3 1497193.50 1501072.38 1519118.38 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Redis Test: LPUSH - Parallel Connections: 1000 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: LPUSH - Parallel Connections: 1000 A B C 300K 600K 900K 1200K 1500K SE +/- 8065.25, N = 3 1220257.96 1237332.00 1226720.12 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Redis Test: LPUSH - Parallel Connections: 50 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: LPUSH - Parallel Connections: 50 A B C 300K 600K 900K 1200K 1500K SE +/- 17781.41, N = 3 1564561.87 1585970.62 1576320.88 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
NCNN Target: Vulkan GPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: vgg16 A B C 300 600 900 1200 1500 SE +/- 11.02, N = 3 1585.62 1574.35 1578.87 MIN: 1568.23 / MAX: 1610.27 MIN: 1572.63 / MAX: 1577.82 MIN: 1573.69 / MAX: 1585.16 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: vision_transformer OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: vision_transformer A B C 30 60 90 120 150 SE +/- 0.52, N = 12 147.55 148.51 147.53 MIN: 142.34 / MAX: 1041.59 MIN: 146.02 / MAX: 164.39 MIN: 144.76 / MAX: 159.17 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Redis Test: SADD - Parallel Connections: 50 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: SADD - Parallel Connections: 50 A B C 400K 800K 1200K 1600K 2000K SE +/- 12303.47, N = 3 1947375.17 1956880.88 1960093.50 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
NCNN Target: Vulkan GPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: alexnet A B C 80 160 240 320 400 SE +/- 0.21, N = 3 351.09 351.98 352.81 MIN: 343.78 / MAX: 356.28 MIN: 344.14 / MAX: 355.91 MIN: 345.02 / MAX: 355.65 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: resnet18 A B C 60 120 180 240 300 SE +/- 0.30, N = 3 291.61 291.76 292.70 MIN: 288.98 / MAX: 298.84 MIN: 290.27 / MAX: 293.28 MIN: 291.43 / MAX: 297 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: regnety_400m A B C 15 30 45 60 75 SE +/- 0.78, N = 12 68.87 68.65 68.85 MIN: 61.34 / MAX: 144.19 MIN: 66.39 / MAX: 83.42 MIN: 62.84 / MAX: 146.14 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: vision_transformer OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: vision_transformer A B C 1200 2400 3600 4800 6000 SE +/- 4.26, N = 3 5699.22 5705.84 5709.48 MIN: 5539.51 / MAX: 5896.14 MIN: 5552.25 / MAX: 5867.93 MIN: 5590.1 / MAX: 5882.82 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: mobilenet A B C 90 180 270 360 450 SE +/- 1.60, N = 3 409.96 410.49 410.09 MIN: 404.05 / MAX: 467.74 MIN: 408.57 / MAX: 435 MIN: 408.24 / MAX: 426.16 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: resnet50 A B C 200 400 600 800 1000 SE +/- 0.28, N = 3 814.60 814.71 814.64 MIN: 812.89 / MAX: 818.39 MIN: 814.22 / MAX: 818.37 MIN: 813.82 / MAX: 819.05 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: regnety_400m A B C 60 120 180 240 300 SE +/- 11.12, N = 3 281.09 275.06 264.94 MIN: 229.29 / MAX: 333.96 MIN: 244.2 / MAX: 324.09 MIN: 227.59 / MAX: 326.78 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: yolov4-tiny A B C 110 220 330 440 550 SE +/- 21.83, N = 3 531.51 513.97 516.33 MIN: 504.59 / MAX: 586.62 MIN: 512.07 / MAX: 518.88 MIN: 509.29 / MAX: 518.86 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: FastestDet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: FastestDet A B C 6 12 18 24 30 SE +/- 0.86, N = 12 20.71 23.24 24.91 MIN: 15.93 / MAX: 31.05 MIN: 17.63 / MAX: 33.51 MIN: 16.54 / MAX: 28.92 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: resnet18 A B C 6 12 18 24 30 SE +/- 0.65, N = 12 24.06 22.50 23.42 MIN: 19.36 / MAX: 834.71 MIN: 20.29 / MAX: 26.85 MIN: 21.17 / MAX: 26.39 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: blazeface A B C 3 6 9 12 15 SE +/- 0.30, N = 12 9.37 9.39 8.76 MIN: 7.22 / MAX: 85.02 MIN: 8.41 / MAX: 10.53 MIN: 7.89 / MAX: 10.25 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: efficientnet-b0 A B C 6 12 18 24 30 SE +/- 0.75, N = 12 23.86 23.49 22.52 MIN: 18.24 / MAX: 102.92 MIN: 19.82 / MAX: 28.54 MIN: 18.75 / MAX: 30.56 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: mnasnet A B C 4 8 12 16 20 SE +/- 0.74, N = 12 18.10 17.35 17.58 MIN: 13.11 / MAX: 27.2 MIN: 13.87 / MAX: 20.12 MIN: 13.85 / MAX: 25.16 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: shufflenet-v2 A B C 5 10 15 20 25 SE +/- 0.40, N = 12 18.52 18.21 18.35 MIN: 15.24 / MAX: 90.43 MIN: 16.1 / MAX: 20.54 MIN: 15.78 / MAX: 24.33 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU-v3-v3 - Model: mobilenet-v3 A B C 4 8 12 16 20 SE +/- 0.69, N = 12 17.94 17.38 16.26 MIN: 13.14 / MAX: 70.28 MIN: 13.91 / MAX: 21.37 MIN: 13.19 / MAX: 21.28 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU-v2-v2 - Model: mobilenet-v2 A B C 5 10 15 20 25 SE +/- 0.77, N = 12 19.20 18.17 18.43 MIN: 13.79 / MAX: 87.76 MIN: 14.86 / MAX: 22.26 MIN: 14.44 / MAX: 23.71 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Mobile Neural Network Model: mobilenet-v1-1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.0 Model: mobilenet-v1-1.0 A B C 0.9749 1.9498 2.9247 3.8996 4.8745 SE +/- 0.216, N = 3 4.333 4.072 3.896 MIN: 3.81 / MAX: 5.2 MIN: 3.77 / MAX: 4.36 MIN: 3.77 / MAX: 4.25 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
Mobile Neural Network Model: resnet-v2-50 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.0 Model: resnet-v2-50 A B C 6 12 18 24 30 SE +/- 1.35, N = 3 26.91 24.91 24.49 MIN: 23.5 / MAX: 29.58 MIN: 23.73 / MAX: 26.99 MIN: 23.77 / MAX: 25.73 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
Redis Test: GET - Parallel Connections: 500 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: GET - Parallel Connections: 500 A B C 400K 800K 1200K 1600K 2000K SE +/- 29524.90, N = 15 1735192.35 1644604.00 1649541.25 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Phoronix Test Suite v10.8.5