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&grr.

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 + Couchcouchdb: 100 - 1000 - 24realsr-ncnn: 4x - Noncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - vgg16ncnn: Vulkan GPU - googlenetncnn: Vulkan GPU - blazefacencnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU - mnasnetncnn: Vulkan GPU - shufflenet-v2ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU - mobilenetncnn: Vulkan GPU - squeezenetncnn: CPU - yolov4-tinyncnn: CPU - resnet50ncnn: CPU - alexnetncnn: CPU - resnet18ncnn: CPU - vgg16ncnn: CPU - googlenetncnn: CPU - blazefacencnn: CPU - efficientnet-b0ncnn: CPU - mnasnetncnn: CPU - shufflenet-v2ncnn: CPU-v3-v3 - mobilenet-v3ncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU - mobilenetncnn: CPU - squeezenettnn: CPU - MobileNet v2tnn: CPU - SqueezeNet v1.1123191.195173.97855.9153.1323.3922.29124.3630.153.0127.5112.4611.1513.7411.9431.3634.8543.2452.1320.3522.4171.1526.072.4212.538.425.906.837.6032.8027.87335.940321.807192.414174.24056.0753.0223.4222.26124.1030.162.8127.5512.4611.1513.6811.9431.4634.4743.3052.4120.4022.5271.4426.202.4012.588.425.936.897.6232.9327.91336.526321.882192.779173.96955.9552.9323.4822.33124.1430.132.6427.4812.4211.1213.6911.8431.5334.6243.2152.2720.3322.5171.3726.122.3812.578.425.906.867.6232.7727.84336.157321.810OpenBenchmarking.org

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

RealSR-NCNN

Scale: 4x - TAA: No

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: No1234080120160200SE +/- 0.86, N = 3SE +/- 0.95, N = 3SE +/- 0.98, N = 3173.98174.24173.97

NCNN

Target: Vulkan GPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: yolov4-tiny1231326395265SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 355.9156.0755.95MIN: 50.23 / MAX: 73.02MIN: 49.62 / MAX: 76.74MIN: 49.96 / MAX: 62.951. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet501231224364860SE +/- 0.03, N = 3SE +/- 0.07, N = 3SE +/- 0.07, N = 353.1353.0252.93MIN: 52.68 / MAX: 53.47MIN: 52.6 / MAX: 53.48MIN: 52.57 / MAX: 53.481. (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: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet18123510152025SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 322.2922.2622.33MIN: 22.1 / MAX: 22.55MIN: 21.99 / MAX: 22.81MIN: 22.08 / MAX: 22.731. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: vgg16123306090120150SE +/- 0.01, N = 3SE +/- 0.11, N = 3SE +/- 0.21, N = 3124.36124.10124.14MIN: 123.51 / MAX: 125.15MIN: 123.23 / MAX: 125.16MIN: 123.17 / MAX: 125.251. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: googlenet123714212835SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 330.1530.1630.13MIN: 29.87 / MAX: 33.19MIN: 29.96 / MAX: 30.98MIN: 29.94 / MAX: 31.081. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: blazeface1230.67731.35462.03192.70923.3865SE +/- 0.44, N = 3SE +/- 0.42, N = 3SE +/- 0.17, N = 33.012.812.64MIN: 2.33 / MAX: 4.02MIN: 2.19 / MAX: 3.85MIN: 2.16 / MAX: 3.311. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: efficientnet-b0123612182430SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 327.5127.5527.48MIN: 27.14 / MAX: 27.66MIN: 27.11 / MAX: 27.77MIN: 27.21 / MAX: 27.91. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mnasnet1233691215SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 312.4612.4612.42MIN: 12.02 / MAX: 17.22MIN: 11.81 / MAX: 17.29MIN: 11.86 / MAX: 16.141. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: shufflenet-v21233691215SE +/- 0.34, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 311.1511.1511.12MIN: 10.35 / MAX: 14.53MIN: 10.94 / MAX: 13.7MIN: 10.84 / MAX: 13.891. (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-v312348121620SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 313.7413.6813.69MIN: 13.47 / MAX: 16.62MIN: 13.22 / MAX: 14.62MIN: 13.41 / MAX: 14.571. (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-v21233691215SE +/- 0.09, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 311.9411.9411.84MIN: 11.68 / MAX: 16.48MIN: 11.66 / MAX: 15.64MIN: 11.63 / MAX: 14.031. (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 - Model: squeezenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: squeezenet123816243240SE +/- 0.20, N = 3SE +/- 0.22, N = 3SE +/- 0.30, N = 334.8534.4734.62MIN: 33.21 / MAX: 39.32MIN: 33.04 / MAX: 37.47MIN: 33.1 / MAX: 46.741. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: yolov4-tiny1231020304050SE +/- 0.01, N = 3SE +/- 0.09, N = 3SE +/- 0.04, N = 343.2443.3043.21MIN: 41.77 / MAX: 47.98MIN: 41.6 / MAX: 57.74MIN: 41.5 / MAX: 56.621. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: resnet501231224364860SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 352.1352.4152.27MIN: 50.22 / MAX: 57.76MIN: 50.4 / MAX: 58.29MIN: 50.33 / MAX: 67.521. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: alexnet123510152025SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 320.3520.4020.33MIN: 19.3 / MAX: 36.1MIN: 19.35 / MAX: 36.99MIN: 19.32 / MAX: 25.051. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: resnet18123510152025SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 322.4122.5222.51MIN: 20.42 / MAX: 28.62MIN: 20.42 / MAX: 28.57MIN: 20.38 / MAX: 37.751. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: vgg161231632486480SE +/- 0.02, N = 3SE +/- 0.10, N = 3SE +/- 0.03, N = 371.1571.4471.37MIN: 70.04 / MAX: 92.8MIN: 70.35 / MAX: 92.6MIN: 70.23 / MAX: 87.721. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: googlenet123612182430SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 326.0726.2026.12MIN: 24.96 / MAX: 41.88MIN: 25.1 / MAX: 32.04MIN: 24.99 / MAX: 31.721. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: blazeface1230.54451.0891.63352.1782.7225SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 32.422.402.38MIN: 2.23 / MAX: 15.55MIN: 2.23 / MAX: 6.76MIN: 2.23 / MAX: 6.981. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: efficientnet-b01233691215SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 312.5312.5812.57MIN: 12.25 / MAX: 17.27MIN: 11.81 / MAX: 23.93MIN: 11.82 / MAX: 17.671. (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: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: shufflenet-v21231.33432.66864.00295.33726.6715SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 35.905.935.90MIN: 5.47 / MAX: 10.52MIN: 5.59 / MAX: 10.29MIN: 5.57 / MAX: 10.421. (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-v3123246810SE +/- 0.92, N = 3SE +/- 0.96, N = 3SE +/- 0.95, N = 36.836.896.86MIN: 4.89 / MAX: 12.59MIN: 4.89 / MAX: 12.71MIN: 4.89 / MAX: 12.411. (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 - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: mobilenet123816243240SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 332.8032.9332.77MIN: 31.5 / MAX: 48.3MIN: 31.41 / MAX: 48.84MIN: 31.37 / MAX: 37.661. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: squeezenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: squeezenet123714212835SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 327.8727.9127.84MIN: 27.28 / MAX: 32.78MIN: 27.26 / MAX: 32.84MIN: 27.23 / MAX: 32.711. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

TNN

Target: CPU - Model: MobileNet v2

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: MobileNet v212370140210280350SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.27, N = 3335.94336.53336.16MIN: 334.54 / MAX: 339.57MIN: 334.51 / MAX: 341.24MIN: 334.34 / MAX: 341.651. (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 v1.112370140210280350SE +/- 0.12, N = 3SE +/- 0.15, N = 3SE +/- 0.09, N = 3321.81321.88321.81MIN: 320.32 / MAX: 326.75MIN: 320.38 / MAX: 325.73MIN: 320.32 / MAX: 324.951. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl

Phoronix Test Suite v10.8.4