f33-machine-learning Intel Core i7-6700 testing with a ASUS Z170I PRO GAMING (0806 BIOS) and Intel HD 530 3GB on Fedora 33 via the Phoronix Test Suite. dtdesk.z170.16GB.nvme: Processor: Intel Core i7-6700 @ 4.00GHz (4 Cores / 8 Threads), Motherboard: ASUS Z170I PRO GAMING (0806 BIOS), Chipset: Intel Xeon E3-1200 v5/E3-1500, Memory: 16384MB, Disk: Samsung SSD 950 PRO 512GB + 3001GB Western Digital WD30EFRX-68E + 5001GB Seagate ST5000DM000-1FK1, Graphics: Intel HD 530 3GB (1150MHz), Audio: Realtek ALC1150, Monitor: DELL ST2220T, Network: Intel I219-V + Qualcomm Atheros QCA6174 802.11ac OS: Fedora 33, Kernel: 5.8.16-300.fc33.x86_64 (x86_64), Desktop: Cinnamon 4.6.7, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, OpenGL: 4.6 Mesa 20.2.1, Vulkan: 1.2.145, Compiler: Clang 11.0.0 + LLVM 11.0.0, File-System: ext4, Screen Resolution: 1920x1080 oneDNN 1.5 Harness: IP Batch 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better dtdesk.z170.16GB.nvme . 10.33 |================================================ oneDNN 1.5 Harness: IP Batch All - Data Type: f32 - Engine: CPU ms < Lower Is Better dtdesk.z170.16GB.nvme . 140.28 |=============================================== oneDNN 1.5 Harness: IP Batch 1D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better dtdesk.z170.16GB.nvme . 4.01 |================================================= oneDNN 1.5 Harness: IP Batch All - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better dtdesk.z170.16GB.nvme . 58.46 |================================================ oneDNN 1.5 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU ms < Lower Is Better dtdesk.z170.16GB.nvme . 24.03 |================================================ oneDNN 1.5 Harness: Deconvolution Batch deconv_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better dtdesk.z170.16GB.nvme . 9.73 |================================================= oneDNN 1.5 Harness: Deconvolution Batch deconv_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better dtdesk.z170.16GB.nvme . 14.98 |================================================ oneDNN 1.5 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better dtdesk.z170.16GB.nvme . 22.19 |================================================ oneDNN 1.5 Harness: Deconvolution Batch deconv_1d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better dtdesk.z170.16GB.nvme . 10.99 |================================================ oneDNN 1.5 Harness: Deconvolution Batch deconv_3d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better dtdesk.z170.16GB.nvme . 7.97 |================================================= oneDNN 1.5 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better dtdesk.z170.16GB.nvme . 686.12 |=============================================== oneDNN 1.5 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better dtdesk.z170.16GB.nvme . 416.01 |=============================================== oneDNN 1.5 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU ms < Lower Is Better dtdesk.z170.16GB.nvme . 6.91 |================================================= oneDNN 1.5 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better dtdesk.z170.16GB.nvme . 11.09 |================================================ Numpy Benchmark Score > Higher Is Better dtdesk.z170.16GB.nvme . 280.04 |=============================================== DeepSpeech 0.6 Acceleration: CPU Seconds < Lower Is Better dtdesk.z170.16GB.nvme . 90.20 |================================================ R Benchmark Seconds < Lower Is Better dtdesk.z170.16GB.nvme . 0.2206 |=============================================== RNNoise 2020-06-28 Seconds < Lower Is Better dtdesk.z170.16GB.nvme . 30.06 |================================================ TensorFlow Lite 2020-08-23 Model: SqueezeNet Microseconds < Lower Is Better dtdesk.z170.16GB.nvme . 495865 |=============================================== TensorFlow Lite 2020-08-23 Model: Inception V4 Microseconds < Lower Is Better dtdesk.z170.16GB.nvme . 7154893 |============================================== TensorFlow Lite 2020-08-23 Model: NASNet Mobile Microseconds < Lower Is Better dtdesk.z170.16GB.nvme . 394954 |=============================================== TensorFlow Lite 2020-08-23 Model: Mobilenet Float Microseconds < Lower Is Better dtdesk.z170.16GB.nvme . 343014 |=============================================== TensorFlow Lite 2020-08-23 Model: Mobilenet Quant Microseconds < Lower Is Better dtdesk.z170.16GB.nvme . 352165 |=============================================== TensorFlow Lite 2020-08-23 Model: Inception ResNet V2 Microseconds < Lower Is Better dtdesk.z170.16GB.nvme . 6482527 |============================================== Mobile Neural Network 2020-09-17 Model: SqueezeNetV1.0 ms < Lower Is Better dtdesk.z170.16GB.nvme . 13.50 |================================================ Mobile Neural Network 2020-09-17 Model: resnet-v2-50 ms < Lower Is Better dtdesk.z170.16GB.nvme . 72.62 |================================================ Mobile Neural Network 2020-09-17 Model: MobileNetV2_224 ms < Lower Is Better dtdesk.z170.16GB.nvme . 7.68 |================================================= Mobile Neural Network 2020-09-17 Model: mobilenet-v1-1.0 ms < Lower Is Better dtdesk.z170.16GB.nvme . 10.73 |================================================ Mobile Neural Network 2020-09-17 Model: inception-v3 ms < Lower Is Better dtdesk.z170.16GB.nvme . 82.56 |================================================ PlaidML FP16: No - Mode: Inference - Network: VGG16 - Device: CPU FPS > Higher Is Better dtdesk.z170.16GB.nvme . 6.46 |================================================= PlaidML FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU FPS > Higher Is Better dtdesk.z170.16GB.nvme . 2.94 |================================================= Numenta Anomaly Benchmark 1.1 Detector: EXPoSE Seconds < Lower Is Better dtdesk.z170.16GB.nvme . 2763.45 |============================================== Numenta Anomaly Benchmark 1.1 Detector: Relative Entropy Seconds < Lower Is Better dtdesk.z170.16GB.nvme . 36.12 |================================================ Numenta Anomaly Benchmark 1.1 Detector: Windowed Gaussian Seconds < Lower Is Better dtdesk.z170.16GB.nvme . 25.19 |================================================ Numenta Anomaly Benchmark 1.1 Detector: Earthgecko Skyline Seconds < Lower Is Better dtdesk.z170.16GB.nvme . 277.57 |=============================================== Numenta Anomaly Benchmark 1.1 Detector: Bayesian Changepoint Seconds < Lower Is Better dtdesk.z170.16GB.nvme . 75.28 |================================================ Mlpack Benchmark Benchmark: scikit_ica Seconds < Lower Is Better dtdesk.z170.16GB.nvme . 48.90 |================================================ Mlpack Benchmark Benchmark: scikit_qda Seconds < Lower Is Better dtdesk.z170.16GB.nvme . 95.66 |================================================ Mlpack Benchmark Benchmark: scikit_svm Seconds < Lower Is Better dtdesk.z170.16GB.nvme . 28.54 |================================================ Mlpack Benchmark Benchmark: scikit_linearridgeregression Seconds < Lower Is Better dtdesk.z170.16GB.nvme . 4.04 |================================================= Scikit-Learn 0.22.1 Seconds < Lower Is Better dtdesk.z170.16GB.nvme . 10.79 |================================================