machine-learning-3 2 x AMD EPYC 7F72 24-Core testing with a GIGABYTE MZ62-HD4-00 v01000100 (R18 BIOS) and ASPEED on Rocky Linux 8.6 via the Phoronix Test Suite. machine-learning-test-3: Processor: 2 x AMD EPYC 7F72 24-Core @ 3.20GHz (48 Cores / 96 Threads), Motherboard: GIGABYTE MZ62-HD4-00 v01000100 (R18 BIOS), Chipset: AMD Starship/Matisse, Memory: 8 x 32 GB DDR4-3200MT/s 36ASF4G72PZ-3G2R1, Disk: 1000GB INTEL SSDPE2KX010T8 + 960GB Micron_7300_MTFDHBE960TDF + 2 x 1920GB Micron_5210_MTFD + 480GB INTEL SSDSC2KB48, Graphics: ASPEED, Network: 2 x Intel I350 OS: Rocky Linux 8.6, Kernel: 4.18.0-372.13.1.el8_6.x86_64 (x86_64), Desktop: GNOME Shell 3.32.2, Display Server: X Server 1.20.11, Compiler: GCC 8.5.0 20210514 + CUDA 11.7, File-System: xfs, Screen Resolution: 800x600 SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: S3D SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Triad SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: FFT SP SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: MD5 Hash SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Reduction SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: GEMM SGEMM_N SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Max SP Flops SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Bus Speed Download SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Bus Speed Readback SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Texture Read Bandwidth LeelaChessZero 0.28 Backend: BLAS Nodes Per Second > Higher Is Better oneDNN 2.6 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better machine-learning-test-3 . 1.87094 |============================================ oneDNN 2.6 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU ms < Lower Is Better machine-learning-test-3 . 24.35 |============================================== oneDNN 2.6 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better machine-learning-test-3 . 6.79071 |============================================ oneDNN 2.6 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better machine-learning-test-3 . 0.724725 |=========================================== oneDNN 2.6 Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 2.6 Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU ms < Lower Is Better machine-learning-test-3 . 0.893769 |=========================================== oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better machine-learning-test-3 . 8.46134 |============================================ oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better machine-learning-test-3 . 3.16766 |============================================ oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better machine-learning-test-3 . 9.05214 |============================================ oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better machine-learning-test-3 . 2.01910 |============================================ oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better machine-learning-test-3 . 1.25242 |============================================ oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better machine-learning-test-3 . 2312.70 |============================================ oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better machine-learning-test-3 . 1490.01 |============================================ oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better machine-learning-test-3 . 2323.05 |============================================ oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better machine-learning-test-3 . 1495.30 |============================================ oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU ms < Lower Is Better machine-learning-test-3 . 1.93637 |============================================ oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better machine-learning-test-3 . 2377.02 |============================================ oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better machine-learning-test-3 . 1476.79 |============================================ oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better machine-learning-test-3 . 1.90390 |============================================ oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better Numpy Benchmark Score > Higher Is Better machine-learning-test-3 . 293.15 |============================================= DeepSpeech 0.6 Acceleration: CPU Seconds < Lower Is Better machine-learning-test-3 . 114.10 |============================================= R Benchmark Seconds < Lower Is Better RNNoise 2020-06-28 Seconds < Lower Is Better machine-learning-test-3 . 21.20 |============================================== TensorFlow Lite 2022-05-18 Model: SqueezeNet Microseconds < Lower Is Better TensorFlow Lite 2022-05-18 Model: Inception V4 Microseconds < Lower Is Better TensorFlow Lite 2022-05-18 Model: NASNet Mobile Microseconds < Lower Is Better TensorFlow Lite 2022-05-18 Model: Mobilenet Float Microseconds < Lower Is Better TensorFlow Lite 2022-05-18 Model: Mobilenet Quant Microseconds < Lower Is Better TensorFlow Lite 2022-05-18 Model: Inception ResNet V2 Microseconds < Lower Is Better Tensorflow Build: Cifar10 Seconds < Lower Is Better Caffe 2020-02-13 Model: AlexNet - Acceleration: CPU - Iterations: 100 Milli-Seconds < Lower Is Better Caffe 2020-02-13 Model: AlexNet - Acceleration: CPU - Iterations: 200 Milli-Seconds < Lower Is Better Caffe 2020-02-13 Model: AlexNet - Acceleration: CPU - Iterations: 1000 Milli-Seconds < Lower Is Better Caffe 2020-02-13 Model: GoogleNet - Acceleration: CPU - Iterations: 100 Milli-Seconds < Lower Is Better Caffe 2020-02-13 Model: GoogleNet - Acceleration: CPU - Iterations: 200 Milli-Seconds < Lower Is Better Caffe 2020-02-13 Model: GoogleNet - Acceleration: CPU - Iterations: 1000 Milli-Seconds < Lower Is Better Mobile Neural Network 1.2 Model: mobilenetV3 ms < Lower Is Better machine-learning-test-3 . 14.34 |============================================== Mobile Neural Network 1.2 Model: squeezenetv1.1 ms < Lower Is Better machine-learning-test-3 . 19.38 |============================================== Mobile Neural Network 1.2 Model: resnet-v2-50 ms < Lower Is Better machine-learning-test-3 . 79.92 |============================================== Mobile Neural Network 1.2 Model: SqueezeNetV1.0 ms < Lower Is Better machine-learning-test-3 . 25.79 |============================================== Mobile Neural Network 1.2 Model: MobileNetV2_224 ms < Lower Is Better machine-learning-test-3 . 25.42 |============================================== Mobile Neural Network 1.2 Model: mobilenet-v1-1.0 ms < Lower Is Better machine-learning-test-3 . 24.90 |============================================== Mobile Neural Network 1.2 Model: inception-v3 ms < Lower Is Better machine-learning-test-3 . 89.90 |============================================== NCNN 20210720 Target: CPU - Model: mobilenet ms < Lower Is Better machine-learning-test-3 . 77.31 |============================================== NCNN 20210720 Target: CPU-v2-v2 - Model: mobilenet-v2 ms < Lower Is Better machine-learning-test-3 . 35.48 |============================================== NCNN 20210720 Target: CPU-v3-v3 - Model: mobilenet-v3 ms < Lower Is Better machine-learning-test-3 . 30.74 |============================================== NCNN 20210720 Target: CPU - Model: shufflenet-v2 ms < Lower Is Better machine-learning-test-3 . 31.48 |============================================== NCNN 20210720 Target: CPU - Model: mnasnet ms < Lower Is Better machine-learning-test-3 . 32.47 |============================================== NCNN 20210720 Target: CPU - Model: efficientnet-b0 ms < Lower Is Better machine-learning-test-3 . 42.74 |============================================== NCNN 20210720 Target: CPU - Model: blazeface ms < Lower Is Better machine-learning-test-3 . 13.30 |============================================== NCNN 20210720 Target: CPU - Model: googlenet ms < Lower Is Better machine-learning-test-3 . 74.42 |============================================== NCNN 20210720 Target: CPU - Model: vgg16 ms < Lower Is Better machine-learning-test-3 . 728.49 |============================================= NCNN 20210720 Target: CPU - Model: resnet18 ms < Lower Is Better machine-learning-test-3 . 47.63 |============================================== NCNN 20210720 Target: CPU - Model: alexnet ms < Lower Is Better machine-learning-test-3 . 22.14 |============================================== NCNN 20210720 Target: CPU - Model: resnet50 ms < Lower Is Better machine-learning-test-3 . 108.20 |============================================= NCNN 20210720 Target: CPU - Model: yolov4-tiny ms < Lower Is Better machine-learning-test-3 . 87.95 |============================================== NCNN 20210720 Target: CPU - Model: squeezenet_ssd ms < Lower Is Better machine-learning-test-3 . 61.56 |============================================== NCNN 20210720 Target: CPU - Model: regnety_400m ms < Lower Is Better machine-learning-test-3 . 73.90 |============================================== NCNN 20210720 Target: Vulkan GPU - Model: mobilenet ms < Lower Is Better machine-learning-test-3 . 78.56 |============================================== NCNN 20210720 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 ms < Lower Is Better machine-learning-test-3 . 39.78 |============================================== NCNN 20210720 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 ms < Lower Is Better machine-learning-test-3 . 32.36 |============================================== NCNN 20210720 Target: Vulkan GPU - Model: shufflenet-v2 ms < Lower Is Better machine-learning-test-3 . 37.50 |============================================== NCNN 20210720 Target: Vulkan GPU - Model: mnasnet ms < Lower Is Better machine-learning-test-3 . 37.34 |============================================== NCNN 20210720 Target: Vulkan GPU - Model: efficientnet-b0 ms < Lower Is Better machine-learning-test-3 . 45.81 |============================================== NCNN 20210720 Target: Vulkan GPU - Model: blazeface ms < Lower Is Better machine-learning-test-3 . 14.71 |============================================== NCNN 20210720 Target: Vulkan GPU - Model: googlenet ms < Lower Is Better machine-learning-test-3 . 76.23 |============================================== NCNN 20210720 Target: Vulkan GPU - Model: vgg16 ms < Lower Is Better machine-learning-test-3 . 666.70 |============================================= NCNN 20210720 Target: Vulkan GPU - Model: resnet18 ms < Lower Is Better machine-learning-test-3 . 47.44 |============================================== NCNN 20210720 Target: Vulkan GPU - Model: alexnet ms < Lower Is Better machine-learning-test-3 . 24.47 |============================================== NCNN 20210720 Target: Vulkan GPU - Model: resnet50 ms < Lower Is Better machine-learning-test-3 . 102.02 |============================================= NCNN 20210720 Target: Vulkan GPU - Model: yolov4-tiny ms < Lower Is Better machine-learning-test-3 . 93.59 |============================================== NCNN 20210720 Target: Vulkan GPU - Model: squeezenet_ssd ms < Lower Is Better machine-learning-test-3 . 68.60 |============================================== NCNN 20210720 Target: Vulkan GPU - Model: regnety_400m ms < Lower Is Better machine-learning-test-3 . 80.45 |============================================== TNN 0.3 Target: CPU - Model: DenseNet ms < Lower Is Better machine-learning-test-3 . 2822.42 |============================================ TNN 0.3 Target: CPU - Model: MobileNet v2 ms < Lower Is Better machine-learning-test-3 . 315.27 |============================================= TNN 0.3 Target: CPU - Model: SqueezeNet v2 ms < Lower Is Better machine-learning-test-3 . 78.34 |============================================== TNN 0.3 Target: CPU - Model: SqueezeNet v1.1 ms < Lower Is Better machine-learning-test-3 . 282.54 |============================================= PlaidML FP16: No - Mode: Inference - Network: VGG16 - Device: CPU FPS > Higher Is Better machine-learning-test-3 . 16.99 |============================================== PlaidML FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU FPS > Higher Is Better machine-learning-test-3 . 4.82 |=============================================== ECP-CANDLE 0.4 Benchmark: P1B2 Seconds < Lower Is Better ECP-CANDLE 0.4 Benchmark: P3B1 Seconds < Lower Is Better ECP-CANDLE 0.4 Benchmark: P3B2 Seconds < Lower Is Better Numenta Anomaly Benchmark 1.1 Detector: EXPoSE Seconds < Lower Is Better machine-learning-test-3 . 1112.66 |============================================ Numenta Anomaly Benchmark 1.1 Detector: Relative Entropy Seconds < Lower Is Better machine-learning-test-3 . 16.29 |============================================== Numenta Anomaly Benchmark 1.1 Detector: Windowed Gaussian Seconds < Lower Is Better machine-learning-test-3 . 7.507 |============================================== Numenta Anomaly Benchmark 1.1 Detector: Earthgecko Skyline Seconds < Lower Is Better machine-learning-test-3 . 76.78 |============================================== Numenta Anomaly Benchmark 1.1 Detector: Bayesian Changepoint Seconds < Lower Is Better machine-learning-test-3 . 41.52 |============================================== ONNX Runtime 1.11 Model: GPT-2 - Device: CPU - Executor: Parallel Inferences Per Minute > Higher Is Better machine-learning-test-3 . 1029 |=============================================== ONNX Runtime 1.11 Model: GPT-2 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better machine-learning-test-3 . 2847 |=============================================== ONNX Runtime 1.11 Model: yolov4 - Device: CPU - Executor: Parallel Inferences Per Minute > Higher Is Better ONNX Runtime 1.11 Model: yolov4 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better ONNX Runtime 1.11 Model: bertsquad-12 - Device: CPU - Executor: Parallel Inferences Per Minute > Higher Is Better machine-learning-test-3 . 173 |================================================ ONNX Runtime 1.11 Model: bertsquad-12 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better machine-learning-test-3 . 204 |================================================ ONNX Runtime 1.11 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel Inferences Per Minute > Higher Is Better machine-learning-test-3 . 33 |================================================= ONNX Runtime 1.11 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better machine-learning-test-3 . 47 |================================================= ONNX Runtime 1.11 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel Inferences Per Minute > Higher Is Better machine-learning-test-3 . 395 |================================================ ONNX Runtime 1.11 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better machine-learning-test-3 . 417 |================================================ ONNX Runtime 1.11 Model: super-resolution-10 - Device: CPU - Executor: Parallel Inferences Per Minute > Higher Is Better machine-learning-test-3 . 2934 |=============================================== ONNX Runtime 1.11 Model: super-resolution-10 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better machine-learning-test-3 . 4419 |=============================================== AI Benchmark Alpha 0.1.2 Score > Higher Is Better Mlpack Benchmark Benchmark: scikit_ica Seconds < Lower Is Better machine-learning-test-3 . 98.22 |============================================== Mlpack Benchmark Benchmark: scikit_qda Seconds < Lower Is Better machine-learning-test-3 . 130.13 |============================================= Mlpack Benchmark Benchmark: scikit_svm Seconds < Lower Is Better machine-learning-test-3 . 18.48 |============================================== Mlpack Benchmark Benchmark: scikit_linearridgeregression Seconds < Lower Is Better machine-learning-test-3 . 5.10 |=============================================== Scikit-Learn 0.22.1 Seconds < Lower Is Better machine-learning-test-3 . 13.29 |============================================== OpenCV 4.6 Test: DNN - Deep Neural Network ms < Lower Is Better machine-learning-test-3 . 82374 |==============================================