Icelake NN + Couch

Intel Core i7-1065G7 testing with a Dell 06CDVY (1.0.9 BIOS) and Intel Iris Plus G7 3GB on Ubuntu 20.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2009266-PTS-ICELAKEN12&sor.

Icelake NN + CouchProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLVulkanCompilerFile-SystemScreen Resolution123Intel Core i7-1065G7 @ 3.90GHz (4 Cores / 8 Threads)Dell 06CDVY (1.0.9 BIOS)Intel Device 34ef16GBKBG40ZPZ512G NVMe TOSHIBA 512GBIntel Iris Plus G7 3GB (1100MHz)Realtek ALC289Intel Killer Wi-Fi 6 AX1650i 160MHzUbuntu 20.045.9.0-050900rc1daily20200819-generic (x86_64) 20200818GNOME Shell 3.36.4X Server 1.20.8modesetting 1.20.84.6 Mesa 20.0.41.2.131GCC 9.3.0ext41920x1200OpenBenchmarking.orgCompiler 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: intel_pstate powersave - CPU Microcode: 0x78Security Details- itlb_multihit: KVM: Mitigation of VMX disabled + 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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Icelake NN + Couchrealsr-ncnn: 4x - Nocouchdb: 100 - 1000 - 24ncnn: CPU - squeezenetncnn: 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: Vulkan GPU - squeezenetncnn: 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-tinytnn: CPU - MobileNet v2tnn: CPU - SqueezeNet v1.1123173.978191.19527.8732.807.606.835.908.4212.532.4226.0771.1522.4120.3552.1343.2434.8531.3611.9413.7411.1512.4627.513.0130.15124.3622.2923.3953.1355.91335.940321.807174.240192.41427.9132.937.626.895.938.4212.582.4026.2071.4422.5220.4052.4143.3034.4731.4611.9413.6811.1512.4627.552.8130.16124.1022.2623.4253.0256.07336.526321.882173.969192.77927.8432.777.626.865.908.4212.572.3826.1271.3722.5120.3352.2743.2134.6231.5311.8413.6911.1212.4227.482.6430.13124.1422.3323.4852.9355.95336.157321.810OpenBenchmarking.org

RealSR-NCNN

Scale: 4x - TAA: No

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: No3124080120160200SE +/- 0.98, N = 3SE +/- 0.86, N = 3SE +/- 0.95, N = 3173.97173.98174.24

Apache CouchDB

Bulk Size: 100 - Inserts: 1000 - Rounds: 24

OpenBenchmarking.orgSeconds, Fewer Is BetterApache CouchDB 3.1.1Bulk Size: 100 - Inserts: 1000 - Rounds: 241234080120160200SE +/- 0.99, N = 3SE +/- 0.27, N = 3SE +/- 1.62, N = 3191.20192.41192.781. (CXX) g++ options: -std=c++14 -lmozjs-68 -lm -lerl_interface -lei -fPIC -MMD

NCNN

Target: CPU - Model: squeezenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: squeezenet312714212835SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 327.8427.8727.91MIN: 27.23 / MAX: 32.71MIN: 27.28 / MAX: 32.78MIN: 27.26 / MAX: 32.841. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: mobilenet312816243240SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 332.7732.8032.93MIN: 31.37 / MAX: 37.66MIN: 31.5 / MAX: 48.3MIN: 31.41 / MAX: 48.841. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU-v2-v2 - Model: mobilenet-v2123246810SE +/- 1.01, N = 3SE +/- 1.03, N = 3SE +/- 1.04, N = 37.607.627.62MIN: 5.47 / MAX: 13.58MIN: 5.46 / MAX: 13.45MIN: 5.45 / MAX: 13.681. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU-v3-v3 - Model: mobilenet-v3132246810SE +/- 0.92, N = 3SE +/- 0.95, N = 3SE +/- 0.96, N = 36.836.866.89MIN: 4.89 / MAX: 12.59MIN: 4.89 / MAX: 12.41MIN: 4.89 / MAX: 12.711. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: shufflenet-v21321.33432.66864.00295.33726.6715SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 35.905.905.93MIN: 5.47 / MAX: 10.52MIN: 5.57 / MAX: 10.42MIN: 5.59 / MAX: 10.291. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: mnasnet123246810SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 38.428.428.42MIN: 7.96 / MAX: 13.34MIN: 7.97 / MAX: 13.44MIN: 7.93 / MAX: 13.351. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: efficientnet-b01323691215SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 312.5312.5712.58MIN: 12.25 / MAX: 17.27MIN: 11.82 / MAX: 17.67MIN: 11.81 / MAX: 23.931. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: blazeface3210.54451.0891.63352.1782.7225SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 32.382.402.42MIN: 2.23 / MAX: 6.98MIN: 2.23 / MAX: 6.76MIN: 2.23 / MAX: 15.551. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: googlenet132612182430SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 326.0726.1226.20MIN: 24.96 / MAX: 41.88MIN: 24.99 / MAX: 31.72MIN: 25.1 / MAX: 32.041. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: vgg161321632486480SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.10, N = 371.1571.3771.44MIN: 70.04 / MAX: 92.8MIN: 70.23 / MAX: 87.72MIN: 70.35 / MAX: 92.61. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: resnet18132510152025SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 322.4122.5122.52MIN: 20.42 / MAX: 28.62MIN: 20.38 / MAX: 37.75MIN: 20.42 / MAX: 28.571. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: alexnet312510152025SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 320.3320.3520.40MIN: 19.32 / MAX: 25.05MIN: 19.3 / MAX: 36.1MIN: 19.35 / MAX: 36.991. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: resnet501321224364860SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 352.1352.2752.41MIN: 50.22 / MAX: 57.76MIN: 50.33 / MAX: 67.52MIN: 50.4 / MAX: 58.291. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: yolov4-tiny3121020304050SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.09, N = 343.2143.2443.30MIN: 41.5 / MAX: 56.62MIN: 41.77 / MAX: 47.98MIN: 41.6 / MAX: 57.741. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: squeezenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: squeezenet231816243240SE +/- 0.22, N = 3SE +/- 0.30, N = 3SE +/- 0.20, N = 334.4734.6234.85MIN: 33.04 / MAX: 37.47MIN: 33.1 / MAX: 46.74MIN: 33.21 / MAX: 39.321. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mobilenet123714212835SE +/- 0.09, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 331.3631.4631.53MIN: 28.98 / MAX: 33.59MIN: 29.2 / MAX: 32.95MIN: 29.38 / MAX: 35.031. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU-v2-v2 - Model: mobilenet-v23123691215SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.07, N = 311.8411.9411.94MIN: 11.63 / MAX: 14.03MIN: 11.68 / MAX: 16.48MIN: 11.66 / MAX: 15.641. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU-v3-v3 - Model: mobilenet-v323148121620SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 313.6813.6913.74MIN: 13.22 / MAX: 14.62MIN: 13.41 / MAX: 14.57MIN: 13.47 / MAX: 16.621. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: shufflenet-v23123691215SE +/- 0.02, N = 3SE +/- 0.34, N = 3SE +/- 0.06, N = 311.1211.1511.15MIN: 10.84 / MAX: 13.89MIN: 10.35 / MAX: 14.53MIN: 10.94 / MAX: 13.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mnasnet3123691215SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 312.4212.4612.46MIN: 11.86 / MAX: 16.14MIN: 12.02 / MAX: 17.22MIN: 11.81 / MAX: 17.291. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: efficientnet-b0312612182430SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 327.4827.5127.55MIN: 27.21 / MAX: 27.9MIN: 27.14 / MAX: 27.66MIN: 27.11 / MAX: 27.771. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: blazeface3210.67731.35462.03192.70923.3865SE +/- 0.17, N = 3SE +/- 0.42, N = 3SE +/- 0.44, N = 32.642.813.01MIN: 2.16 / MAX: 3.31MIN: 2.19 / MAX: 3.85MIN: 2.33 / MAX: 4.021. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: googlenet312714212835SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 330.1330.1530.16MIN: 29.94 / MAX: 31.08MIN: 29.87 / MAX: 33.19MIN: 29.96 / MAX: 30.981. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: vgg16231306090120150SE +/- 0.11, N = 3SE +/- 0.21, N = 3SE +/- 0.01, N = 3124.10124.14124.36MIN: 123.23 / MAX: 125.16MIN: 123.17 / MAX: 125.25MIN: 123.51 / MAX: 125.151. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet18213510152025SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 322.2622.2922.33MIN: 21.99 / MAX: 22.81MIN: 22.1 / MAX: 22.55MIN: 22.08 / MAX: 22.731. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: alexnet123612182430SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 323.3923.4223.48MIN: 23.16 / MAX: 23.67MIN: 23.18 / MAX: 23.66MIN: 23.16 / MAX: 23.811. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet503211224364860SE +/- 0.07, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 352.9353.0253.13MIN: 52.57 / MAX: 53.48MIN: 52.6 / MAX: 53.48MIN: 52.68 / MAX: 53.471. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: yolov4-tiny1321326395265SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 355.9155.9556.07MIN: 50.23 / MAX: 73.02MIN: 49.96 / MAX: 62.95MIN: 49.62 / MAX: 76.741. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

TNN

Target: CPU - Model: MobileNet v2

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: MobileNet v213270140210280350SE +/- 0.05, N = 3SE +/- 0.27, N = 3SE +/- 0.04, N = 3335.94336.16336.53MIN: 334.54 / MAX: 339.57MIN: 334.34 / MAX: 341.65MIN: 334.51 / MAX: 341.241. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl

TNN

Target: CPU - Model: SqueezeNet v1.1

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: SqueezeNet v1.113270140210280350SE +/- 0.12, N = 3SE +/- 0.09, N = 3SE +/- 0.15, N = 3321.81321.81321.88MIN: 320.32 / MAX: 326.75MIN: 320.32 / MAX: 324.95MIN: 320.38 / MAX: 325.731. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl

Phoronix Test Suite v10.8.4