ubu20-wk1-ML-05sep2020 VMware testing on Ubuntu 20.04 via the Phoronix Test Suite. ubu20-wk1-ML-05sep2020: Processor: 16 x AMD Ryzen Threadripper 3960X 24-Core (31 Cores), Motherboard: Intel 440BX (6.00 BIOS), Chipset: Intel 440BX/ZX/DX, Memory: 16GB, Disk: 193GB VMware Virtual S, Graphics: SVGA3D; build: RELEASE; LLVM;, Audio: Ensoniq ES1371/ES1373, Network: Intel 82545EM + 4 x AMD 79c970 OS: Ubuntu 20.04, Kernel: 5.4.0-45-generic (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, OpenGL: 2.1 Mesa 20.0.8, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1680x968, System Layer: VMware PlaidML FP16: No - Mode: Inference - Network: VGG16 - Device: CPU FPS > Higher Is Better ubu20-wk1-ML-05sep2020 . 16.65 |=============================================== PlaidML FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU FPS > Higher Is Better ubu20-wk1-ML-05sep2020 . 6.10 |================================================ Numenta Anomaly Benchmark 1.1 Detector: EXPoSE Seconds < Lower Is Better ubu20-wk1-ML-05sep2020 . 800.85 |============================================== Numenta Anomaly Benchmark 1.1 Detector: Relative Entropy Seconds < Lower Is Better ubu20-wk1-ML-05sep2020 . 16.98 |=============================================== Numenta Anomaly Benchmark 1.1 Detector: Windowed Gaussian Seconds < Lower Is Better ubu20-wk1-ML-05sep2020 . 9.223 |=============================================== Numenta Anomaly Benchmark 1.1 Detector: Earthgecko Skyline Seconds < Lower Is Better ubu20-wk1-ML-05sep2020 . 97.09 |=============================================== Numenta Anomaly Benchmark 1.1 Detector: Bayesian Changepoint Seconds < Lower Is Better ubu20-wk1-ML-05sep2020 . 29.97 |=============================================== Scikit-Learn 0.22.1 Seconds < Lower Is Better ubu20-wk1-ML-05sep2020 . 9.024 |=============================================== Numpy Benchmark Score > Higher Is Better ubu20-wk1-ML-05sep2020 . 345.45 |============================================== DeepSpeech 0.6 Seconds < Lower Is Better ubu20-wk1-ML-05sep2020 . 60.80 |=============================================== TensorFlow Lite 2020-08-23 Model: SqueezeNet Microseconds < Lower Is Better ubu20-wk1-ML-05sep2020 . 155523 |============================================== TensorFlow Lite 2020-08-23 Model: Inception V4 Microseconds < Lower Is Better ubu20-wk1-ML-05sep2020 . 2127763 |============================================= TensorFlow Lite 2020-08-23 Model: NASNet Mobile Microseconds < Lower Is Better ubu20-wk1-ML-05sep2020 . 161302 |============================================== TensorFlow Lite 2020-08-23 Model: Mobilenet Float Microseconds < Lower Is Better ubu20-wk1-ML-05sep2020 . 105987 |============================================== TensorFlow Lite 2020-08-23 Model: Mobilenet Quant Microseconds < Lower Is Better ubu20-wk1-ML-05sep2020 . 112000 |============================================== TensorFlow Lite 2020-08-23 Model: Inception ResNet V2 Microseconds < Lower Is Better ubu20-wk1-ML-05sep2020 . 1909437 |============================================= Mlpack Benchmark Benchmark: scikit_ica Seconds < Lower Is Better ubu20-wk1-ML-05sep2020 . 54.84 |=============================================== Mlpack Benchmark Benchmark: scikit_qda Seconds < Lower Is Better ubu20-wk1-ML-05sep2020 . 60.99 |=============================================== Mlpack Benchmark Benchmark: scikit_svm Seconds < Lower Is Better ubu20-wk1-ML-05sep2020 . 21.29 |=============================================== Mlpack Benchmark Benchmark: scikit_linearridgeregression Seconds < Lower Is Better ubu20-wk1-ML-05sep2020 . 2.71 |================================================ oneDNN 1.5 Harness: IP Batch 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better ubu20-wk1-ML-05sep2020 . 6.68402 |============================================= oneDNN 1.5 Harness: IP Batch All - Data Type: f32 - Engine: CPU ms < Lower Is Better ubu20-wk1-ML-05sep2020 . 78.44 |=============================================== oneDNN 1.5 Harness: IP Batch 1D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better ubu20-wk1-ML-05sep2020 . 3.80789 |============================================= oneDNN 1.5 Harness: IP Batch All - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better ubu20-wk1-ML-05sep2020 . 43.87 |=============================================== oneDNN 1.5 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU ms < Lower Is Better ubu20-wk1-ML-05sep2020 . 15.75 |=============================================== oneDNN 1.5 Harness: Deconvolution Batch deconv_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better ubu20-wk1-ML-05sep2020 . 6.02825 |============================================= oneDNN 1.5 Harness: Deconvolution Batch deconv_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better ubu20-wk1-ML-05sep2020 . 9.92993 |============================================= oneDNN 1.5 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better ubu20-wk1-ML-05sep2020 . 16.58 |=============================================== oneDNN 1.5 Harness: Deconvolution Batch deconv_1d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better ubu20-wk1-ML-05sep2020 . 7.91315 |============================================= oneDNN 1.5 Harness: Deconvolution Batch deconv_3d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better ubu20-wk1-ML-05sep2020 . 6.16964 |============================================= oneDNN 1.5 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better ubu20-wk1-ML-05sep2020 . 381.48 |============================================== oneDNN 1.5 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better ubu20-wk1-ML-05sep2020 . 97.91 |=============================================== oneDNN 1.5 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU ms < Lower Is Better ubu20-wk1-ML-05sep2020 . 1.84022 |============================================= oneDNN 1.5 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better ubu20-wk1-ML-05sep2020 . 2.90286 |=============================================