slehpc-wk1-ML-05sep2020
VMware testing on SUSE Linux Enterprise High Performance Computing 15 SP2 15.2 via the Phoronix Test Suite.


slehpc-wk1-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: 129GB VMware Virtual S, Graphics: SVGA3D; build: RELEASE; LLVM;, Audio: Ensoniq ES1371/ES1373, Network: 2 x Intel 82545EM + 3 x AMD 79c970

	OS: SUSE Linux Enterprise High Performance Computing 15 SP2 15.2, Kernel: 5.3.18-24.9-default (x86_64), Desktop: GNOME Shell 3.34.4, Display Server: X Server, OpenGL: 2.1 Mesa 19.3.4, Compiler: GCC 7.5.0, File-System: btrfs, Screen Resolution: 1920x984, System Layer: VMware


oneDNN 1.5
Harness: IP Batch 1D - Data Type: f32 - Engine: CPU
ms < Lower Is Better
slehpc-wk1-ML-05sep2020 . 4.83926 |============================================


oneDNN 1.5
Harness: IP Batch All - Data Type: f32 - Engine: CPU
ms < Lower Is Better
slehpc-wk1-ML-05sep2020 . 72.88 |==============================================


oneDNN 1.5
Harness: IP Batch 1D - Data Type: u8s8f32 - Engine: CPU
ms < Lower Is Better
slehpc-wk1-ML-05sep2020 . 3.00709 |============================================


oneDNN 1.5
Harness: IP Batch All - Data Type: u8s8f32 - Engine: CPU
ms < Lower Is Better
slehpc-wk1-ML-05sep2020 . 39.96 |==============================================


oneDNN 1.5
Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU
ms < Lower Is Better
slehpc-wk1-ML-05sep2020 . 12.07 |==============================================


oneDNN 1.5
Harness: Deconvolution Batch deconv_1d - Data Type: f32 - Engine: CPU
ms < Lower Is Better
slehpc-wk1-ML-05sep2020 . 4.58224 |============================================


oneDNN 1.5
Harness: Deconvolution Batch deconv_3d - Data Type: f32 - Engine: CPU
ms < Lower Is Better
slehpc-wk1-ML-05sep2020 . 6.37756 |============================================


oneDNN 1.5
Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU
ms < Lower Is Better
slehpc-wk1-ML-05sep2020 . 12.72 |==============================================


oneDNN 1.5
Harness: Deconvolution Batch deconv_1d - Data Type: u8s8f32 - Engine: CPU
ms < Lower Is Better
slehpc-wk1-ML-05sep2020 . 7.46700 |============================================


oneDNN 1.5
Harness: Deconvolution Batch deconv_3d - Data Type: u8s8f32 - Engine: CPU
ms < Lower Is Better
slehpc-wk1-ML-05sep2020 . 5.82675 |============================================


oneDNN 1.5
Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU
ms < Lower Is Better
slehpc-wk1-ML-05sep2020 . 340.83 |=============================================


oneDNN 1.5
Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU
ms < Lower Is Better
slehpc-wk1-ML-05sep2020 . 81.21 |==============================================


oneDNN 1.5
Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU
ms < Lower Is Better
slehpc-wk1-ML-05sep2020 . 1.51949 |============================================


oneDNN 1.5
Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU
ms < Lower Is Better
slehpc-wk1-ML-05sep2020 . 2.93717 |============================================


Numpy Benchmark

Score > Higher Is Better
slehpc-wk1-ML-05sep2020 . 316.30 |=============================================


DeepSpeech 0.6

Seconds < Lower Is Better
slehpc-wk1-ML-05sep2020 . 64.63 |==============================================


TensorFlow Lite 2020-08-23
Model: SqueezeNet
Microseconds < Lower Is Better
slehpc-wk1-ML-05sep2020 . 143915 |=============================================


TensorFlow Lite 2020-08-23
Model: Inception V4
Microseconds < Lower Is Better
slehpc-wk1-ML-05sep2020 . 1957333 |============================================


TensorFlow Lite 2020-08-23
Model: NASNet Mobile
Microseconds < Lower Is Better
slehpc-wk1-ML-05sep2020 . 142150 |=============================================


TensorFlow Lite 2020-08-23
Model: Mobilenet Float
Microseconds < Lower Is Better
slehpc-wk1-ML-05sep2020 . 97177.2 |============================================


TensorFlow Lite 2020-08-23
Model: Mobilenet Quant
Microseconds < Lower Is Better
slehpc-wk1-ML-05sep2020 . 101128 |=============================================


TensorFlow Lite 2020-08-23
Model: Inception ResNet V2
Microseconds < Lower Is Better
slehpc-wk1-ML-05sep2020 . 1764193 |============================================


PlaidML
FP16: No - Mode: Inference - Network: VGG16 - Device: CPU
FPS > Higher Is Better
slehpc-wk1-ML-05sep2020 . 20.52 |==============================================


PlaidML
FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU
FPS > Higher Is Better
slehpc-wk1-ML-05sep2020 . 6.87 |===============================================


Numenta Anomaly Benchmark 1.1
Detector: EXPoSE
Seconds < Lower Is Better
slehpc-wk1-ML-05sep2020 . 919.45 |=============================================


Numenta Anomaly Benchmark 1.1
Detector: Relative Entropy
Seconds < Lower Is Better
slehpc-wk1-ML-05sep2020 . 23.76 |==============================================


Numenta Anomaly Benchmark 1.1
Detector: Windowed Gaussian
Seconds < Lower Is Better
slehpc-wk1-ML-05sep2020 . 12.07 |==============================================


Numenta Anomaly Benchmark 1.1
Detector: Earthgecko Skyline
Seconds < Lower Is Better
slehpc-wk1-ML-05sep2020 . 109.21 |=============================================


Numenta Anomaly Benchmark 1.1
Detector: Bayesian Changepoint
Seconds < Lower Is Better
slehpc-wk1-ML-05sep2020 . 43.98 |==============================================