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&gru&sro.

new tsProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionABCAMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads)Gigabyte TRX40 AORUS PRO WIFI (F4p BIOS)AMD Starship/Matisse128GBSamsung SSD 970 EVO Plus 500GBAMD Radeon RX 5700 8GB (1750/875MHz)AMD Navi 10 HDMI AudioDELL P2415QIntel I211 + Intel Wi-Fi 6 AX200Ubuntu 22.045.19.0-051900rc7-generic (x86_64)GNOME Shell 42.2X Server + Wayland4.6 Mesa 22.0.1 (LLVM 13.0.1 DRM 3.47)1.2.204GCC 11.2.0ext43840x2160OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler 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: 0x8301039Security 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 tsredis: GET - 50redis: SET - 50redis: GET - 500redis: LPOP - 50redis: SADD - 50redis: SET - 500redis: GET - 1000redis: LPOP - 500redis: LPUSH - 50redis: SADD - 500redis: SET - 1000redis: LPOP - 1000redis: LPUSH - 500redis: SADD - 1000redis: LPUSH - 1000mnn: mobilenetV3mnn: squeezenetv1.1mnn: resnet-v2-50mnn: SqueezeNetV1.0mnn: MobileNetV2_224mnn: mobilenet-v1-1.0mnn: inception-v3ncnn: CPU - mobilenetncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU-v3-v3 - mobilenet-v3ncnn: CPU - shufflenet-v2ncnn: CPU - mnasnetncnn: CPU - efficientnet-b0ncnn: CPU - blazefacencnn: CPU - googlenetncnn: CPU - vgg16ncnn: CPU - resnet18ncnn: CPU - alexnetncnn: CPU - resnet50ncnn: CPU - yolov4-tinyncnn: CPU - squeezenet_ssdncnn: CPU - regnety_400mncnn: CPU - vision_transformerncnn: CPU - FastestDetncnn: Vulkan GPU - mobilenetncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU - shufflenet-v2ncnn: Vulkan GPU - mnasnetncnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU - blazefacencnn: Vulkan GPU - googlenetncnn: Vulkan GPU - vgg16ncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - regnety_400mncnn: Vulkan GPU - vision_transformerncnn: Vulkan GPU - FastestDetABC2469009.921752688.121735192.352498183.81947375.171338680.821668219.581916702.631564561.871550371.421329224.631180993.501227521.851497193.501220257.962.4213.98226.9097.3135.0304.33327.03031.0419.2017.9418.5218.1023.869.3735.1050.0124.0617.9944.6340.7034.8368.87147.5520.71409.96163.75164.8397.43182.91306.2143.88447.411585.62291.61351.09814.60531.51316.70281.095699.2298.492128422.251770758.1216446041558194.251956880.881319110.881697526.251162784.51585970.621455206.51245858.121152163.2512550741501072.3812373322.454.05624.9136.6534.8994.07228.46234.5618.1717.3818.2117.3523.499.3935.4549.2522.518.0743.8641.1235.6268.65148.5123.24410.49160.38155.32102.29178.89309.6943.97442.911574.35291.76351.98814.71513.97321.74275.065705.84101.222100667.751743710.51649541.251515224.51960093.51274362.751653373.1211776001576320.881516465.381321178.381153624.251237737.881519118.381226720.122.4584.23824.4937.3215.1523.89627.96733.0418.4316.2618.3517.5822.528.7635.8449.6123.4217.6944.7339.5636.7468.85147.5324.91410.09163.37155.83101.49181.77310.9443.09452.631578.87292.7352.81814.64516.33338.4264.945709.48101.12OpenBenchmarking.org

Redis

Test: GET - Parallel Connections: 50

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: GET - Parallel Connections: 50ABC500K1000K1500K2000K2500KSE +/- 17359.14, N = 32469009.922128422.252100667.751. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Redis

Test: SET - Parallel Connections: 50

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: SET - Parallel Connections: 50ABC400K800K1200K1600K2000KSE +/- 14504.57, N = 31752688.121770758.121743710.501. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Redis

Test: GET - Parallel Connections: 500

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: GET - Parallel Connections: 500ABC400K800K1200K1600K2000KSE +/- 29524.90, N = 151735192.351644604.001649541.251. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Redis

Test: LPOP - Parallel Connections: 50

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: LPOP - Parallel Connections: 50ABC500K1000K1500K2000K2500KSE +/- 32340.71, N = 32498183.801558194.251515224.501. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Redis

Test: SADD - Parallel Connections: 50

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: SADD - Parallel Connections: 50ABC400K800K1200K1600K2000KSE +/- 12303.47, N = 31947375.171956880.881960093.501. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Redis

Test: SET - Parallel Connections: 500

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: SET - Parallel Connections: 500ABC300K600K900K1200K1500KSE +/- 17762.03, N = 121338680.821319110.881274362.751. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Redis

Test: GET - Parallel Connections: 1000

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: GET - Parallel Connections: 1000ABC400K800K1200K1600K2000KSE +/- 3728.73, N = 31668219.581697526.251653373.121. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Redis

Test: LPOP - Parallel Connections: 500

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: LPOP - Parallel Connections: 500ABC400K800K1200K1600K2000KSE +/- 7169.32, N = 31916702.631162784.501177600.001. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Redis

Test: LPUSH - Parallel Connections: 50

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: LPUSH - Parallel Connections: 50ABC300K600K900K1200K1500KSE +/- 17781.41, N = 31564561.871585970.621576320.881. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Redis

Test: SADD - Parallel Connections: 500

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: SADD - Parallel Connections: 500ABC300K600K900K1200K1500KSE +/- 17244.14, N = 151550371.421455206.501516465.381. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Redis

Test: SET - Parallel Connections: 1000

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: SET - Parallel Connections: 1000ABC300K600K900K1200K1500KSE +/- 15024.63, N = 31329224.631245858.121321178.381. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Redis

Test: LPOP - Parallel Connections: 1000

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: LPOP - Parallel Connections: 1000ABC300K600K900K1200K1500KSE +/- 9918.56, N = 31180993.501152163.251153624.251. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Redis

Test: LPUSH - Parallel Connections: 500

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: LPUSH - Parallel Connections: 500ABC300K600K900K1200K1500KSE +/- 13741.04, N = 41227521.851255074.001237737.881. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Redis

Test: SADD - Parallel Connections: 1000

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: SADD - Parallel Connections: 1000ABC300K600K900K1200K1500KSE +/- 14869.73, N = 31497193.501501072.381519118.381. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Redis

Test: LPUSH - Parallel Connections: 1000

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: LPUSH - Parallel Connections: 1000ABC300K600K900K1200K1500KSE +/- 8065.25, N = 31220257.961237332.001226720.121. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Mobile Neural Network

Model: mobilenetV3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: mobilenetV3ABC0.55311.10621.65932.21242.7655SE +/- 0.015, N = 32.4212.4502.458MIN: 2.35 / MAX: 2.53MIN: 2.39 / MAX: 2.53MIN: 2.4 / MAX: 2.541. (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: squeezenetv1.1

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: squeezenetv1.1ABC0.95361.90722.86083.81444.768SE +/- 0.070, N = 33.9824.0564.238MIN: 3.76 / MAX: 4.48MIN: 3.91 / MAX: 4.21MIN: 4.02 / MAX: 4.441. (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.orgms, Fewer Is BetterMobile Neural Network 2.0Model: resnet-v2-50ABC612182430SE +/- 1.35, N = 326.9124.9124.49MIN: 23.5 / MAX: 29.58MIN: 23.73 / MAX: 26.99MIN: 23.77 / MAX: 25.731. (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: SqueezeNetV1.0

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: SqueezeNetV1.0ABC246810SE +/- 0.236, N = 37.3136.6537.321MIN: 6.32 / MAX: 9.01MIN: 6.36 / MAX: 7.04MIN: 6.52 / MAX: 8.621. (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.orgms, Fewer Is BetterMobile Neural Network 2.0Model: MobileNetV2_224ABC1.15922.31843.47764.63685.796SE +/- 0.095, N = 35.0304.8995.152MIN: 4.62 / MAX: 5.6MIN: 4.71 / MAX: 5.28MIN: 4.85 / MAX: 5.721. (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: mobilenet-v1-1.0

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: mobilenet-v1-1.0ABC0.97491.94982.92473.89964.8745SE +/- 0.216, N = 34.3334.0723.896MIN: 3.81 / MAX: 5.2MIN: 3.77 / MAX: 4.36MIN: 3.77 / MAX: 4.251. (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: inception-v3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: inception-v3ABC714212835SE +/- 0.13, N = 327.0328.4627.97MIN: 26.11 / MAX: 28.32MIN: 27 / MAX: 30.52MIN: 27.1 / MAX: 28.881. (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: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mobilenetABC816243240SE +/- 0.52, N = 1231.0434.5633.04MIN: 25.81 / MAX: 98.98MIN: 28.25 / MAX: 40.74MIN: 28.08 / MAX: 38.511. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU-v2-v2 - Model: mobilenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v2-v2 - Model: mobilenet-v2ABC510152025SE +/- 0.77, N = 1219.2018.1718.43MIN: 13.79 / MAX: 87.76MIN: 14.86 / MAX: 22.26MIN: 14.44 / MAX: 23.711. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU-v3-v3 - Model: mobilenet-v3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v3-v3 - Model: mobilenet-v3ABC48121620SE +/- 0.69, N = 1217.9417.3816.26MIN: 13.14 / MAX: 70.28MIN: 13.91 / MAX: 21.37MIN: 13.19 / MAX: 21.281. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: shufflenet-v2ABC510152025SE +/- 0.40, N = 1218.5218.2118.35MIN: 15.24 / MAX: 90.43MIN: 16.1 / MAX: 20.54MIN: 15.78 / MAX: 24.331. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mnasnetABC48121620SE +/- 0.74, N = 1218.1017.3517.58MIN: 13.11 / MAX: 27.2MIN: 13.87 / MAX: 20.12MIN: 13.85 / MAX: 25.161. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: efficientnet-b0ABC612182430SE +/- 0.75, N = 1223.8623.4922.52MIN: 18.24 / MAX: 102.92MIN: 19.82 / MAX: 28.54MIN: 18.75 / MAX: 30.561. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: blazefaceABC3691215SE +/- 0.30, N = 129.379.398.76MIN: 7.22 / MAX: 85.02MIN: 8.41 / MAX: 10.53MIN: 7.89 / MAX: 10.251. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: googlenetABC816243240SE +/- 0.28, N = 1235.1035.4535.84MIN: 30.11 / MAX: 120.79MIN: 31.96 / MAX: 42.11MIN: 32.46 / MAX: 46.551. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vgg16ABC1122334455SE +/- 0.35, N = 1250.0149.2549.61MIN: 45.53 / MAX: 128.33MIN: 46.47 / MAX: 61.53MIN: 47.17 / MAX: 66.281. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet18ABC612182430SE +/- 0.65, N = 1224.0622.5023.42MIN: 19.36 / MAX: 834.71MIN: 20.29 / MAX: 26.85MIN: 21.17 / MAX: 26.391. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: alexnetABC48121620SE +/- 0.09, N = 1217.9918.0717.69MIN: 13.86 / MAX: 27.32MIN: 16.92 / MAX: 19.82MIN: 15.41 / MAX: 20.661. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet50ABC1020304050SE +/- 0.32, N = 1244.6343.8644.73MIN: 38.6 / MAX: 54.54MIN: 38.61 / MAX: 85.93MIN: 39.99 / MAX: 51.731. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: yolov4-tinyABC918273645SE +/- 0.19, N = 1240.7041.1239.56MIN: 35.39 / MAX: 64.14MIN: 37.25 / MAX: 53.93MIN: 36.99 / MAX: 51.431. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: squeezenet_ssdABC816243240SE +/- 0.23, N = 1234.8335.6236.74MIN: 31.09 / MAX: 92.26MIN: 32.21 / MAX: 47.32MIN: 32.7 / MAX: 67.251. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: regnety_400mABC1530456075SE +/- 0.78, N = 1268.8768.6568.85MIN: 61.34 / MAX: 144.19MIN: 66.39 / MAX: 83.42MIN: 62.84 / MAX: 146.141. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vision_transformerABC306090120150SE +/- 0.52, N = 12147.55148.51147.53MIN: 142.34 / MAX: 1041.59MIN: 146.02 / MAX: 164.39MIN: 144.76 / MAX: 159.171. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: FastestDetABC612182430SE +/- 0.86, N = 1220.7123.2424.91MIN: 15.93 / MAX: 31.05MIN: 17.63 / MAX: 33.51MIN: 16.54 / MAX: 28.921. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: mobilenetABC90180270360450SE +/- 1.60, N = 3409.96410.49410.09MIN: 404.05 / MAX: 467.74MIN: 408.57 / MAX: 435MIN: 408.24 / MAX: 426.161. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2ABC4080120160200SE +/- 2.24, N = 3163.75160.38163.37MIN: 139.72 / MAX: 192.58MIN: 139.5 / MAX: 193.18MIN: 141.13 / MAX: 196.251. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3ABC4080120160200SE +/- 0.81, N = 3164.83155.32155.83MIN: 125.38 / MAX: 214.06MIN: 144.2 / MAX: 188.29MIN: 144.44 / MAX: 192.011. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: shufflenet-v2ABC20406080100SE +/- 0.59, N = 397.43102.29101.49MIN: 85.08 / MAX: 128.16MIN: 98.68 / MAX: 118.03MIN: 96.1 / MAX: 117.721. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: mnasnetABC4080120160200SE +/- 3.22, N = 3182.91178.89181.77MIN: 171 / MAX: 214.09MIN: 169.54 / MAX: 217.51MIN: 175.83 / MAX: 208.031. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: efficientnet-b0ABC70140210280350SE +/- 3.03, N = 3306.21309.69310.94MIN: 257.3 / MAX: 345.94MIN: 258.46 / MAX: 345.46MIN: 257.08 / MAX: 341.171. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: blazefaceABC1020304050SE +/- 0.17, N = 343.8843.9743.09MIN: 28.03 / MAX: 57.23MIN: 30.91 / MAX: 55.93MIN: 31.72 / MAX: 55.771. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: googlenetABC100200300400500SE +/- 1.28, N = 3447.41442.91452.63MIN: 415.84 / MAX: 531.22MIN: 411.09 / MAX: 500.51MIN: 409.36 / MAX: 526.351. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: vgg16ABC30060090012001500SE +/- 11.02, N = 31585.621574.351578.87MIN: 1568.23 / MAX: 1610.27MIN: 1572.63 / MAX: 1577.82MIN: 1573.69 / MAX: 1585.161. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: resnet18ABC60120180240300SE +/- 0.30, N = 3291.61291.76292.70MIN: 288.98 / MAX: 298.84MIN: 290.27 / MAX: 293.28MIN: 291.43 / MAX: 2971. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: alexnetABC80160240320400SE +/- 0.21, N = 3351.09351.98352.81MIN: 343.78 / MAX: 356.28MIN: 344.14 / MAX: 355.91MIN: 345.02 / MAX: 355.651. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: resnet50ABC2004006008001000SE +/- 0.28, N = 3814.60814.71814.64MIN: 812.89 / MAX: 818.39MIN: 814.22 / MAX: 818.37MIN: 813.82 / MAX: 819.051. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: yolov4-tinyABC110220330440550SE +/- 21.83, N = 3531.51513.97516.33MIN: 504.59 / MAX: 586.62MIN: 512.07 / MAX: 518.88MIN: 509.29 / MAX: 518.861. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: squeezenet_ssdABC70140210280350SE +/- 3.47, N = 3316.70321.74338.40MIN: 275.77 / MAX: 453.58MIN: 278.6 / MAX: 449.6MIN: 279.78 / MAX: 4671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: regnety_400mABC60120180240300SE +/- 11.12, N = 3281.09275.06264.94MIN: 229.29 / MAX: 333.96MIN: 244.2 / MAX: 324.09MIN: 227.59 / MAX: 326.781. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: vision_transformerABC12002400360048006000SE +/- 4.26, N = 35699.225705.845709.48MIN: 5539.51 / MAX: 5896.14MIN: 5552.25 / MAX: 5867.93MIN: 5590.1 / MAX: 5882.821. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: FastestDetABC20406080100SE +/- 1.79, N = 398.49101.22101.12MIN: 70.32 / MAX: 129.14MIN: 92.21 / MAX: 110.44MIN: 94.87 / MAX: 108.841. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread


Phoronix Test Suite v10.8.5