ml_test_results1 wsl testing on Ubuntu 20.04 via the Phoronix Test Suite. rtx3080_12900K: Processor: Intel Core i9-12900K (12 Cores / 24 Threads), Memory: 16GB, Disk: 4 x 275GB Virtual Disk, Graphics: NVIDIA GeForce RTX 3080 10GB OS: Ubuntu 20.04, Kernel: 5.10.16.3-microsoft-standard-WSL2 (x86_64), Display Server: Wayland, Vulkan: 1.1.182, Compiler: GCC 9.4.0, File-System: ext4, System Layer: wsl LeelaChessZero 0.28 Backend: BLAS Nodes Per Second > Higher Is Better rtx3080_12900K . 873 |========================================================= oneDNN 2.6 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better rtx3080_12900K . 3.37187 |===================================================== oneDNN 2.6 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU ms < Lower Is Better rtx3080_12900K . 4.58015 |===================================================== oneDNN 2.6 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better rtx3080_12900K . 1.23886 |===================================================== oneDNN 2.6 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better rtx3080_12900K . 1.14148 |===================================================== 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 rtx3080_12900K . 10.30 |======================================================= oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better rtx3080_12900K . 48.48 |======================================================= oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better rtx3080_12900K . 5.93345 |===================================================== oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better rtx3080_12900K . 7.75715 |===================================================== oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better rtx3080_12900K . 1.81062 |===================================================== oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better rtx3080_12900K . 2.45489 |===================================================== oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better rtx3080_12900K . 3228.29 |===================================================== oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better rtx3080_12900K . 1887.17 |===================================================== oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better rtx3080_12900K . 3286.90 |===================================================== 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 rtx3080_12900K . 1904.80 |===================================================== oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU ms < Lower Is Better rtx3080_12900K . 1.74786 |===================================================== oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better rtx3080_12900K . 3313.03 |===================================================== oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better rtx3080_12900K . 1901.01 |===================================================== oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better rtx3080_12900K . 1.09774 |===================================================== oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better Numpy Benchmark Score > Higher Is Better rtx3080_12900K . 632.18 |====================================================== DeepSpeech 0.6 Acceleration: CPU Seconds < Lower Is Better rtx3080_12900K . 53.66 |======================================================= R Benchmark Seconds < Lower Is Better RNNoise 2020-06-28 Seconds < Lower Is Better rtx3080_12900K . 13.79 |======================================================= TensorFlow Lite 2022-05-18 Model: SqueezeNet Microseconds < Lower Is Better rtx3080_12900K . 2118.02 |===================================================== TensorFlow Lite 2022-05-18 Model: Inception V4 Microseconds < Lower Is Better rtx3080_12900K . 27824.6 |===================================================== TensorFlow Lite 2022-05-18 Model: NASNet Mobile Microseconds < Lower Is Better rtx3080_12900K . 10433.3 |===================================================== TensorFlow Lite 2022-05-18 Model: Mobilenet Float Microseconds < Lower Is Better rtx3080_12900K . 1453.48 |===================================================== TensorFlow Lite 2022-05-18 Model: Mobilenet Quant Microseconds < Lower Is Better rtx3080_12900K . 3506.22 |===================================================== TensorFlow Lite 2022-05-18 Model: Inception ResNet V2 Microseconds < Lower Is Better rtx3080_12900K . 28252.7 |===================================================== 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 rtx3080_12900K . 1.505 |======================================================= Mobile Neural Network 1.2 Model: squeezenetv1.1 ms < Lower Is Better rtx3080_12900K . 3.217 |======================================================= Mobile Neural Network 1.2 Model: resnet-v2-50 ms < Lower Is Better rtx3080_12900K . 24.55 |======================================================= Mobile Neural Network 1.2 Model: SqueezeNetV1.0 ms < Lower Is Better rtx3080_12900K . 4.843 |======================================================= Mobile Neural Network 1.2 Model: MobileNetV2_224 ms < Lower Is Better rtx3080_12900K . 2.966 |======================================================= Mobile Neural Network 1.2 Model: mobilenet-v1-1.0 ms < Lower Is Better rtx3080_12900K . 3.688 |======================================================= Mobile Neural Network 1.2 Model: inception-v3 ms < Lower Is Better rtx3080_12900K . 27.71 |======================================================= NCNN 20210720 Target: CPU - Model: mobilenet ms < Lower Is Better rtx3080_12900K . 13.31 |======================================================= NCNN 20210720 Target: CPU-v2-v2 - Model: mobilenet-v2 ms < Lower Is Better rtx3080_12900K . 3.99 |======================================================== NCNN 20210720 Target: CPU-v3-v3 - Model: mobilenet-v3 ms < Lower Is Better rtx3080_12900K . 3.63 |======================================================== NCNN 20210720 Target: CPU - Model: shufflenet-v2 ms < Lower Is Better rtx3080_12900K . 3.69 |======================================================== NCNN 20210720 Target: CPU - Model: mnasnet ms < Lower Is Better rtx3080_12900K . 3.85 |======================================================== NCNN 20210720 Target: CPU - Model: efficientnet-b0 ms < Lower Is Better rtx3080_12900K . 6.05 |======================================================== NCNN 20210720 Target: CPU - Model: blazeface ms < Lower Is Better rtx3080_12900K . 1.76 |======================================================== NCNN 20210720 Target: CPU - Model: googlenet ms < Lower Is Better rtx3080_12900K . 13.28 |======================================================= NCNN 20210720 Target: CPU - Model: vgg16 ms < Lower Is Better rtx3080_12900K . 36.60 |======================================================= NCNN 20210720 Target: CPU - Model: resnet18 ms < Lower Is Better rtx3080_12900K . 13.06 |======================================================= NCNN 20210720 Target: CPU - Model: alexnet ms < Lower Is Better rtx3080_12900K . 10.10 |======================================================= NCNN 20210720 Target: CPU - Model: resnet50 ms < Lower Is Better rtx3080_12900K . 22.87 |======================================================= NCNN 20210720 Target: CPU - Model: yolov4-tiny ms < Lower Is Better rtx3080_12900K . 21.03 |======================================================= NCNN 20210720 Target: CPU - Model: squeezenet_ssd ms < Lower Is Better rtx3080_12900K . 18.22 |======================================================= NCNN 20210720 Target: CPU - Model: regnety_400m ms < Lower Is Better rtx3080_12900K . 10.65 |======================================================= NCNN 20210720 Target: Vulkan GPU - Model: mobilenet ms < Lower Is Better rtx3080_12900K . 430.58 |====================================================== NCNN 20210720 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 ms < Lower Is Better rtx3080_12900K . 137.48 |====================================================== NCNN 20210720 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 ms < Lower Is Better rtx3080_12900K . 135.86 |====================================================== NCNN 20210720 Target: Vulkan GPU - Model: shufflenet-v2 ms < Lower Is Better rtx3080_12900K . 114.99 |====================================================== NCNN 20210720 Target: Vulkan GPU - Model: mnasnet ms < Lower Is Better rtx3080_12900K . 142.62 |====================================================== NCNN 20210720 Target: Vulkan GPU - Model: efficientnet-b0 ms < Lower Is Better rtx3080_12900K . 217.87 |====================================================== NCNN 20210720 Target: Vulkan GPU - Model: blazeface ms < Lower Is Better rtx3080_12900K . 56.20 |======================================================= NCNN 20210720 Target: Vulkan GPU - Model: googlenet ms < Lower Is Better rtx3080_12900K . 488.70 |====================================================== NCNN 20210720 Target: Vulkan GPU - Model: vgg16 ms < Lower Is Better rtx3080_12900K . 2434.37 |===================================================== NCNN 20210720 Target: Vulkan GPU - Model: resnet18 ms < Lower Is Better rtx3080_12900K . 520.87 |====================================================== NCNN 20210720 Target: Vulkan GPU - Model: alexnet ms < Lower Is Better rtx3080_12900K . 403.91 |====================================================== NCNN 20210720 Target: Vulkan GPU - Model: resnet50 ms < Lower Is Better rtx3080_12900K . 1310.27 |===================================================== NCNN 20210720 Target: Vulkan GPU - Model: yolov4-tiny ms < Lower Is Better rtx3080_12900K . 883.04 |====================================================== NCNN 20210720 Target: Vulkan GPU - Model: squeezenet_ssd ms < Lower Is Better rtx3080_12900K . 689.50 |====================================================== NCNN 20210720 Target: Vulkan GPU - Model: regnety_400m ms < Lower Is Better rtx3080_12900K . 212.73 |====================================================== TNN 0.3 Target: CPU - Model: DenseNet ms < Lower Is Better rtx3080_12900K . 2000.47 |===================================================== TNN 0.3 Target: CPU - Model: MobileNet v2 ms < Lower Is Better rtx3080_12900K . 179.55 |====================================================== TNN 0.3 Target: CPU - Model: SqueezeNet v2 ms < Lower Is Better rtx3080_12900K . 39.15 |======================================================= TNN 0.3 Target: CPU - Model: SqueezeNet v1.1 ms < Lower Is Better rtx3080_12900K . 140.45 |====================================================== PlaidML FP16: No - Mode: Inference - Network: VGG16 - Device: CPU FPS > Higher Is Better rtx3080_12900K . 26.55 |======================================================= PlaidML FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU FPS > Higher Is Better rtx3080_12900K . 8.26 |======================================================== OpenVINO 2021.1 Model: Face Detection 0106 FP16 - Device: CPU FPS > Higher Is Better OpenVINO 2021.1 Model: Face Detection 0106 FP32 - Device: CPU FPS > Higher Is Better OpenVINO 2021.1 Model: Person Detection 0106 FP16 - Device: CPU FPS > Higher Is Better OpenVINO 2021.1 Model: Person Detection 0106 FP32 - Device: CPU FPS > Higher Is Better OpenVINO 2021.1 Model: Face Detection 0106 FP16 - Device: Intel GPU FPS > Higher Is Better OpenVINO 2021.1 Model: Face Detection 0106 FP32 - Device: Intel GPU FPS > Higher Is Better OpenVINO 2021.1 Model: Person Detection 0106 FP16 - Device: Intel GPU FPS > Higher Is Better OpenVINO 2021.1 Model: Person Detection 0106 FP32 - Device: Intel GPU FPS > Higher Is Better OpenVINO 2021.1 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU FPS > Higher Is Better OpenVINO 2021.1 Model: Age Gender Recognition Retail 0013 FP32 - Device: CPU FPS > Higher Is Better OpenVINO 2021.1 Model: Age Gender Recognition Retail 0013 FP16 - Device: Intel GPU FPS > Higher Is Better OpenVINO 2021.1 Model: Age Gender Recognition Retail 0013 FP32 - Device: Intel GPU FPS > Higher Is Better ECP-CANDLE 0.4 Benchmark: P1B2 Seconds < Lower Is Better rtx3080_12900K . 21.50 |======================================================= ECP-CANDLE 0.4 Benchmark: P3B1 Seconds < Lower Is Better rtx3080_12900K . 403.02 |====================================================== ECP-CANDLE 0.4 Benchmark: P3B2 Seconds < Lower Is Better rtx3080_12900K . 480.90 |====================================================== Numenta Anomaly Benchmark 1.1 Detector: EXPoSE Seconds < Lower Is Better rtx3080_12900K . 212.82 |====================================================== Numenta Anomaly Benchmark 1.1 Detector: Relative Entropy Seconds < Lower Is Better rtx3080_12900K . 9.524 |======================================================= Numenta Anomaly Benchmark 1.1 Detector: Windowed Gaussian Seconds < Lower Is Better rtx3080_12900K . 4.872 |======================================================= Numenta Anomaly Benchmark 1.1 Detector: Earthgecko Skyline Seconds < Lower Is Better rtx3080_12900K . 75.05 |======================================================= Numenta Anomaly Benchmark 1.1 Detector: Bayesian Changepoint Seconds < Lower Is Better rtx3080_12900K . 16.63 |======================================================= ONNX Runtime 1.11 Model: GPT-2 - Device: CPU - Executor: Parallel Inferences Per Minute > Higher Is Better ONNX Runtime 1.11 Model: GPT-2 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better 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 ONNX Runtime 1.11 Model: bertsquad-12 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better ONNX Runtime 1.11 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel Inferences Per Minute > Higher Is Better ONNX Runtime 1.11 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better ONNX Runtime 1.11 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel Inferences Per Minute > Higher Is Better ONNX Runtime 1.11 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better ONNX Runtime 1.11 Model: super-resolution-10 - Device: CPU - Executor: Parallel Inferences Per Minute > Higher Is Better ONNX Runtime 1.11 Model: super-resolution-10 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better Mlpack Benchmark Benchmark: scikit_ica Seconds < Lower Is Better Mlpack Benchmark Benchmark: scikit_qda Seconds < Lower Is Better Mlpack Benchmark Benchmark: scikit_svm Seconds < Lower Is Better Mlpack Benchmark Benchmark: scikit_linearridgeregression Seconds < Lower Is Better Scikit-Learn 0.22.1 Seconds < Lower Is Better rtx3080_12900K . 5.364 |======================================================= OpenCV 4.6 Test: DNN - Deep Neural Network ms < Lower Is Better