LC0

Intel Core i7-7700 testing with a HP 8298 (P01 Ver. 02.15 BIOS) and NVIDIA GeForce GTX 1060 6GB on Fedora 32 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2010299-AS-LC016735930.

LC0ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLVulkanCompilerFile-SystemScreen ResolutionLC0Intel Core i7-7700 @ 4.20GHz (4 Cores / 8 Threads)HP 8298 (P01 Ver. 02.15 BIOS)Intel Xeon E3-1200 v6/7th + Q27016384MB256GB SAMSUNG MZVLW256HEHP-000H1 + 1000GB Western Digital WD10EZEX-60WNVIDIA GeForce GTX 1060 6GB (1544/4006MHz)Conexant CX20632HP E243Intel I219-LMFedora 325.8.4-200.fc32.x86_64 (x86_64)KDE Plasma 5.18.5X Server 1.20.8NVIDIA 450.664.6.01.2.133Clang 10.0.0 + CUDA 10.2ext41920x1080OpenBenchmarking.org- Scaling Governor: intel_pstate powersave- SELinux + itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + 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 generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Mitigation of Microcode + tsx_async_abort: Mitigation of Clear buffers; SMT vulnerable

LC0ncnn: 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: CPUv2-yolov3v2-yolov3 - mobilenetv2-yolov3ncnn: 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 GPUv2-yolov3v2-yolov3 - mobilenetv2-yolov3ncnn: Vulkan GPU - yolov4-tinyLC038.3427.717.226.024.156.049.721.7456.88191.7333.2619.64123.1827.7138.5438.816.352.532.441.682.103.630.7856.78190.1033.414.96122.936.3511.13OpenBenchmarking.org

NCNN

Target: CPU - Model: squeezenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: squeezenetLC0918273645SE +/- 0.14, N = 638.34MIN: 37.84 / MAX: 42.64

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: mobilenetLC0714212835SE +/- 0.15, N = 627.71MIN: 27.22 / MAX: 155.91

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU-v2-v2 - Model: mobilenet-v2LC0246810SE +/- 0.02, N = 67.22MIN: 7.1 / MAX: 9.67

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU-v3-v3 - Model: mobilenet-v3LC0246810SE +/- 0.01, N = 66.02MIN: 5.94 / MAX: 8.63

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: shufflenet-v2LC00.93381.86762.80143.73524.669SE +/- 0.01, N = 64.15MIN: 4.09 / MAX: 6.48

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: mnasnetLC0246810SE +/- 0.01, N = 66.04MIN: 5.98 / MAX: 8.64

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: efficientnet-b0LC03691215SE +/- 0.02, N = 69.72MIN: 9.6 / MAX: 12.61

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: blazefaceLC00.39150.7831.17451.5661.9575SE +/- 0.01, N = 61.74MIN: 1.7 / MAX: 3.23

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: googlenetLC01326395265SE +/- 0.09, N = 656.88MIN: 56.43 / MAX: 62.88

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: vgg16LC04080120160200SE +/- 1.17, N = 6191.73MIN: 188.53 / MAX: 829.77

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: resnet18LC0816243240SE +/- 0.04, N = 633.26MIN: 33 / MAX: 44.21

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: alexnetLC0510152025SE +/- 0.06, N = 619.64MIN: 19.42 / MAX: 22.61

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: resnet50LC0306090120150SE +/- 0.12, N = 6123.18MIN: 122.37 / MAX: 126.78

NCNN

Target: CPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3LC0714212835SE +/- 0.15, N = 627.71MIN: 27.22 / MAX: 155.91

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: yolov4-tinyLC0918273645SE +/- 0.14, N = 638.54MIN: 38.06 / MAX: 58.38

NCNN

Target: Vulkan GPU - Model: squeezenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: squeezenetLC0918273645SE +/- 0.28, N = 638.81MIN: 37.7 / MAX: 133.54

NCNN

Target: Vulkan GPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mobilenetLC0246810SE +/- 0.00, N = 66.35MIN: 6.3 / MAX: 7.14

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2LC00.56931.13861.70792.27722.8465SE +/- 0.11, N = 62.53MIN: 2 / MAX: 11.07

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3LC00.5491.0981.6472.1962.745SE +/- 0.01, N = 62.44MIN: 2.4 / MAX: 8.6

NCNN

Target: Vulkan GPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: shufflenet-v2LC00.3780.7561.1341.5121.89SE +/- 0.00, N = 61.68MIN: 1.66 / MAX: 2.45

NCNN

Target: Vulkan GPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mnasnetLC00.47250.9451.41751.892.3625SE +/- 0.00, N = 62.10MIN: 2.08 / MAX: 2.94

NCNN

Target: Vulkan GPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: efficientnet-b0LC00.81681.63362.45043.26724.084SE +/- 0.00, N = 63.63MIN: 3.61 / MAX: 4.45

NCNN

Target: Vulkan GPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: blazefaceLC00.17550.3510.52650.7020.8775SE +/- 0.00, N = 60.78MIN: 0.76 / MAX: 1.59

NCNN

Target: Vulkan GPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: googlenetLC01326395265SE +/- 0.04, N = 656.78MIN: 56.46 / MAX: 59.12

NCNN

Target: Vulkan GPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: vgg16LC04080120160200SE +/- 0.61, N = 6190.10MIN: 186.79 / MAX: 219.12

NCNN

Target: Vulkan GPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet18LC0816243240SE +/- 0.15, N = 633.41MIN: 32.99 / MAX: 133.04

NCNN

Target: Vulkan GPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: alexnetLC01.1162.2323.3484.4645.58SE +/- 0.01, N = 64.96MIN: 4.87 / MAX: 5.74

NCNN

Target: Vulkan GPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet50LC0306090120150SE +/- 0.09, N = 6122.93MIN: 122.19 / MAX: 134.38

NCNN

Target: Vulkan GPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3LC0246810SE +/- 0.00, N = 66.35MIN: 6.3 / MAX: 7.14

NCNN

Target: Vulkan GPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: yolov4-tinyLC03691215SE +/- 0.07, N = 611.13MIN: 10.95 / MAX: 13.22

Phoronix Test Suite v10.8.4