susel-vm2-ML-05sep2020 VMware testing on openSUSE Leap 15.2 via the Phoronix Test Suite. susel-vm2-ML-05sep2020: Processor: 8 x AMD Ryzen Threadripper 3960X 24-Core (16 Cores), Motherboard: Intel 440BX (6.00 BIOS), Chipset: Intel 440BX/ZX/DX, Memory: 16GB, Disk: 107GB VMware Virtual S, Graphics: SVGA3D; build: RELEASE; LLVM;, Audio: Ensoniq ES1371/ES1373, Network: 2 x Intel 82545EM + 3 x AMD 79c970 OS: openSUSE Leap 15.2, Kernel: 5.3.18-lp152.36-default (x86_64), Desktop: GNOME Shell 3.34.5, Display Server: X Server + Wayland, OpenGL: 2.1 Mesa 19.3.4, Compiler: GCC 7.5.0, File-System: btrfs, Screen Resolution: 1714x924, System Layer: VMware oneDNN 1.5 Harness: IP Batch 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better susel-vm2-ML-05sep2020 . 5.87528 |============================================= oneDNN 1.5 Harness: IP Batch All - Data Type: f32 - Engine: CPU ms < Lower Is Better susel-vm2-ML-05sep2020 . 80.11 |=============================================== oneDNN 1.5 Harness: IP Batch 1D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better susel-vm2-ML-05sep2020 . 5.19694 |============================================= oneDNN 1.5 Harness: IP Batch All - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better susel-vm2-ML-05sep2020 . 65.92 |=============================================== oneDNN 1.5 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU ms < Lower Is Better susel-vm2-ML-05sep2020 . 8.18878 |============================================= oneDNN 1.5 Harness: Deconvolution Batch deconv_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better susel-vm2-ML-05sep2020 . 10.56 |=============================================== oneDNN 1.5 Harness: Deconvolution Batch deconv_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better susel-vm2-ML-05sep2020 . 14.68 |=============================================== oneDNN 1.5 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better susel-vm2-ML-05sep2020 . 32.34 |=============================================== oneDNN 1.5 Harness: Deconvolution Batch deconv_1d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better susel-vm2-ML-05sep2020 . 11.33 |=============================================== oneDNN 1.5 Harness: Deconvolution Batch deconv_3d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better susel-vm2-ML-05sep2020 . 10.65 |=============================================== oneDNN 1.5 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better susel-vm2-ML-05sep2020 . 571.33 |============================================== oneDNN 1.5 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better susel-vm2-ML-05sep2020 . 81.13 |=============================================== oneDNN 1.5 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU ms < Lower Is Better susel-vm2-ML-05sep2020 . 1.95099 |============================================= oneDNN 1.5 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better susel-vm2-ML-05sep2020 . 3.34470 |============================================= Numpy Benchmark Score > Higher Is Better susel-vm2-ML-05sep2020 . 296.15 |============================================== DeepSpeech 0.6 Seconds < Lower Is Better susel-vm2-ML-05sep2020 . 72.44 |=============================================== TensorFlow Lite 2020-08-23 Model: SqueezeNet Microseconds < Lower Is Better susel-vm2-ML-05sep2020 . 168897 |============================================== TensorFlow Lite 2020-08-23 Model: Inception V4 Microseconds < Lower Is Better susel-vm2-ML-05sep2020 . 2005140 |============================================= TensorFlow Lite 2020-08-23 Model: NASNet Mobile Microseconds < Lower Is Better susel-vm2-ML-05sep2020 . 148811 |============================================== TensorFlow Lite 2020-08-23 Model: Mobilenet Float Microseconds < Lower Is Better susel-vm2-ML-05sep2020 . 121773.0 |============================================ TensorFlow Lite 2020-08-23 Model: Mobilenet Quant Microseconds < Lower Is Better susel-vm2-ML-05sep2020 . 128428 |============================================== TensorFlow Lite 2020-08-23 Model: Inception ResNet V2 Microseconds < Lower Is Better susel-vm2-ML-05sep2020 . 2326460 |============================================= PlaidML FP16: No - Mode: Inference - Network: VGG16 - Device: CPU FPS > Higher Is Better susel-vm2-ML-05sep2020 . 18.92 |=============================================== PlaidML FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU FPS > Higher Is Better susel-vm2-ML-05sep2020 . 6.33 |================================================ Numenta Anomaly Benchmark 1.1 Detector: EXPoSE Seconds < Lower Is Better susel-vm2-ML-05sep2020 . 999.39 |============================================== Numenta Anomaly Benchmark 1.1 Detector: Relative Entropy Seconds < Lower Is Better susel-vm2-ML-05sep2020 . 28.86 |=============================================== Numenta Anomaly Benchmark 1.1 Detector: Windowed Gaussian Seconds < Lower Is Better susel-vm2-ML-05sep2020 . 15.32 |=============================================== Numenta Anomaly Benchmark 1.1 Detector: Earthgecko Skyline Seconds < Lower Is Better susel-vm2-ML-05sep2020 . 140.13 |============================================== Numenta Anomaly Benchmark 1.1 Detector: Bayesian Changepoint Seconds < Lower Is Better susel-vm2-ML-05sep2020 . 55.47 |===============================================