Coder Radio XPS 13 ML Ubuntu Benchmark Intel Core i7-10510U testing with a LENOVO 20U9CTO1WW (N2WET24W 1.14 BIOS) and Intel UHD 3GB on Fedora 33 via the Phoronix Test Suite. ,,"XPS 13 Tiger Lake Ubuntu 20.04","ThinkPad X1 Fedora Comet Lake" Processor,,Intel Core i5-1135G7 @ 4.20GHz (4 Cores / 8 Threads),Intel Core i7-10510U @ 4.90GHz (4 Cores / 8 Threads) Motherboard,,Dell 0THX8P (1.1.1 BIOS),LENOVO 20U9CTO1WW (N2WET24W 1.14 BIOS) Chipset,,Intel Device a0ef,Intel Comet Lake PCH-LP Memory,,16GB,2 x 8 GB LPDDR3-2133MT/s Samsung Disk,,Micron 2300 NVMe 512GB,256GB Western Digital PC SN730 SDBQNTY-256G-1001 Graphics,,Intel Xe 3GB (1300MHz),Intel UHD 3GB (1150MHz) Audio,,Realtek ALC289,Realtek ALC285 Network,,Intel Device a0f0,Intel + Intel Comet Lake PCH-LP CNVi WiFi OS,,Ubuntu 20.04,Fedora 33 Kernel,,5.6.0-1036-oem (x86_64),5.9.16-200.fc33.x86_64 (x86_64) Desktop,,GNOME Shell 3.36.4,KDE Plasma 5.20.4 Display Server,,X Server 1.20.8,X Server 1.20.10 Display Driver,,modesetting 1.20.8,modesetting 1.20.10 OpenGL,,4.6 Mesa 20.0.8,4.6 Mesa 20.2.6 Vulkan,,1.2.131, Compiler,,GCC 9.3.0,GCC 10.2.1 20201125 + Clang 11.0.0 File-System,,ext4,btrfs Screen Resolution,,1920x1200,2560x1440 ,,"XPS 13 Tiger Lake Ubuntu 20.04","ThinkPad X1 Fedora Comet Lake" "PlaidML - FP16: No - Mode: Inference - Network: VGG16 - Device: CPU (FPS)",HIB,6.47,3.74 "PlaidML - FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU (FPS)",HIB,3.27,2.57 "Numpy Benchmark - (Score)",HIB,293.18,299.99 "AI Benchmark Alpha - Device Inference Score (Score)",HIB,556, "AI Benchmark Alpha - Device Training Score (Score)",HIB,630, "AI Benchmark Alpha - Device AI Score (Score)",HIB,1186, "TensorFlow Lite - Model: SqueezeNet (us)",LIB,627487,769601 "TensorFlow Lite - Model: Inception V4 (us)",LIB,9220230,11134467 "TensorFlow Lite - Model: NASNet Mobile (us)",LIB,455525,597569 "TensorFlow Lite - Model: Mobilenet Float (us)",LIB,424309,525312 "TensorFlow Lite - Model: Mobilenet Quant (us)",LIB,419506,535897 "TensorFlow Lite - Model: Inception ResNet V2 (us)",LIB,8329360,10177933 "oneDNN - Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU (ms)",LIB,10.2773,15.77 "oneDNN - Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU (ms)",LIB,6.59350,17.95 "oneDNN - Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU (ms)",LIB,2.43051,5.88 "oneDNN - Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU (ms)",LIB,2.62981,3.95 "oneDNN - Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,25.8282, "oneDNN - Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,6.39979, "oneDNN - Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU (ms)",LIB,11.5632,22.02 "oneDNN - Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU (ms)",LIB,14.6326,20.71 "oneDNN - Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU (ms)",LIB,13.4125,15.85 "oneDNN - Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU (ms)",LIB,7.93450,21.14 "oneDNN - Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU (ms)",LIB,2.94262,21.88 "oneDNN - Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU (ms)",LIB,3.13684,8.18 "oneDNN - Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU (ms)",LIB,8862.65,15729.96 "oneDNN - Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU (ms)",LIB,5736.43,8215.08 "oneDNN - Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU (ms)",LIB,8875.33,15828.66 "oneDNN - Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,52.4284, "oneDNN - Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,57.0546, "oneDNN - Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,52.6824, "oneDNN - Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU (ms)",LIB,4528.11,8004.41 "oneDNN - Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU (ms)",LIB,3.93298,6.73 "oneDNN - Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,8859.05,15837.41 "oneDNN - Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,4516.60,7969.03 "oneDNN - Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU (ms)",LIB,2.12307,11.82 "oneDNN - Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,11.8072, "Mobile Neural Network - Model: SqueezeNetV1.0 (ms)",LIB,11.256,18.04 "Mobile Neural Network - Model: resnet-v2-50 (ms)",LIB,54.691,88.35 "Mobile Neural Network - Model: MobileNetV2_224 (ms)",LIB,6.238,9.62 "Mobile Neural Network - Model: mobilenet-v1-1.0 (ms)",LIB,8.320,13.15 "Mobile Neural Network - Model: inception-v3 (ms)",LIB,68.523,97.71 "NCNN - Target: CPU - Model: mobilenet (ms)",LIB,35.03,45.37 "NCNN - Target: CPU-v2-v2 - Model: mobilenet-v2 (ms)",LIB,7.78,10.67 "NCNN - Target: CPU-v3-v3 - Model: mobilenet-v3 (ms)",LIB,6.71,9.10 "NCNN - Target: CPU - Model: shufflenet-v2 (ms)",LIB,9.99,14.58 "NCNN - Target: CPU - Model: mnasnet (ms)",LIB,8.10,9.76 "NCNN - Target: CPU - Model: efficientnet-b0 (ms)",LIB,12.53,15.22 "NCNN - Target: CPU - Model: blazeface (ms)",LIB,2.85,3.80 "NCNN - Target: CPU - Model: googlenet (ms)",LIB,25.01,31.39 "NCNN - Target: CPU - Model: vgg16 (ms)",LIB,68.50,108.71 "NCNN - Target: CPU - Model: resnet18 (ms)",LIB,22.07,30.23 "NCNN - Target: CPU - Model: alexnet (ms)",LIB,19.06,26.55 "NCNN - Target: CPU - Model: resnet50 (ms)",LIB,51.01,67.20 "NCNN - Target: CPU - Model: yolov4-tiny (ms)",LIB,44.65,57.10 "NCNN - Target: CPU - Model: squeezenet_ssd (ms)",LIB,39.61,45.61 "NCNN - Target: CPU - Model: regnety_400m (ms)",LIB,21.11,22.34 "NCNN - Target: Vulkan GPU - Model: mobilenet (ms)",LIB,35.11,46.41 "NCNN - Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 (ms)",LIB,7.71,9.64 "NCNN - Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 (ms)",LIB,6.70,8.28 "NCNN - Target: Vulkan GPU - Model: shufflenet-v2 (ms)",LIB,10.30,12.80 "NCNN - Target: Vulkan GPU - Model: mnasnet (ms)",LIB,8.13,8.77 "NCNN - Target: Vulkan GPU - Model: efficientnet-b0 (ms)",LIB,11.83,13.74 "NCNN - Target: Vulkan GPU - Model: blazeface (ms)",LIB,2.80,3.24 "NCNN - Target: Vulkan GPU - Model: googlenet (ms)",LIB,24.58,28.85 "NCNN - Target: Vulkan GPU - Model: vgg16 (ms)",LIB,69.16,107.70 "NCNN - Target: Vulkan GPU - Model: resnet18 (ms)",LIB,22.25,28.33 "NCNN - Target: Vulkan GPU - Model: alexnet (ms)",LIB,19.23,25.75 "NCNN - Target: Vulkan GPU - Model: resnet50 (ms)",LIB,51.13,65.59 "NCNN - Target: Vulkan GPU - Model: yolov4-tiny (ms)",LIB,44.68,58.16 "NCNN - Target: Vulkan GPU - Model: squeezenet_ssd (ms)",LIB,39.53,44.71 "NCNN - Target: Vulkan GPU - Model: regnety_400m (ms)",LIB,21.01,20.14 "OpenCV - Test: DNN - Deep Neural Network (ms)",LIB,5351,7968 "NCNN - Target: CPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3 (ms)",LIB,,45.37 "NCNN - Target: Vulkan GPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3 (ms)",LIB,,46.41 "RNNoise - (sec)",LIB,31.947, "Numenta Anomaly Benchmark - Detector: EXPoSE (sec)",LIB,1139.241, "Numenta Anomaly Benchmark - Detector: Relative Entropy (sec)",LIB,48.609, "Numenta Anomaly Benchmark - Detector: Windowed Gaussian (sec)",LIB,27.702, "Numenta Anomaly Benchmark - Detector: Earthgecko Skyline (sec)",LIB,333.639, "Numenta Anomaly Benchmark - Detector: Bayesian Changepoint (sec)",LIB,81.062, "Mlpack Benchmark - Benchmark: scikit_ica (sec)",LIB,123.23, "Mlpack Benchmark - Benchmark: scikit_qda (sec)",LIB,138.24, "Mlpack Benchmark - Benchmark: scikit_svm (sec)",LIB,34.66, "Mlpack Benchmark - Benchmark: scikit_linearridgeregression (sec)",LIB,13.50, "Scikit-Learn - (sec)",LIB,17.900,