ryz-5800X-orig-water-build AMD Ryzen 7 5800X 8-Core testing with a ASRock X570 Phantom Gaming-ITX/TB3 (P5.01 BIOS) and Gigabyte NVIDIA GeForce RTX 3080 10GB on Ubuntu 22.04 via the Phoronix Test Suite. water cooled build of 5800X: Processor: AMD Ryzen 7 5800X 8-Core @ 3.80GHz (8 Cores / 16 Threads), Motherboard: ASRock X570 Phantom Gaming-ITX/TB3 (P5.01 BIOS), Chipset: AMD Starship/Matisse, Memory: 64GB, Disk: 2000GB Samsung SSD 970 EVO Plus 2TB + 4001GB Samsung SSD 870, Graphics: Gigabyte NVIDIA GeForce RTX 3080 10GB, Audio: NVIDIA GA102 HD Audio, Monitor: HP Z27, Network: Intel I211 + Intel Wi-Fi 6 AX200 OS: Ubuntu 22.04, Kernel: 5.19.0-45-generic (x86_64), Desktop: GNOME Shell 42.5, Display Server: X Server 1.21.1.3, Display Driver: NVIDIA 530.30.02, OpenGL: 4.6.0, OpenCL: OpenCL 3.0 CUDA 12.1.68, Vulkan: 1.3.236, Compiler: GCC 11.3.0 + CUDA 12.0, File-System: ext4, Screen Resolution: 3840x2160 TensorFlow 2.12 Device: CPU - Batch Size: 512 - Model: VGG-16 images/sec > Higher Is Better water cooled build of 5800X . 5.87 |=========================================== TensorFlow 2.12 Device: CPU - Batch Size: 256 - Model: VGG-16 images/sec > Higher Is Better water cooled build of 5800X . 5.87 |=========================================== TensorFlow 2.12 Device: CPU - Batch Size: 512 - Model: ResNet-50 images/sec > Higher Is Better water cooled build of 5800X . 11.87 |========================================== TensorFlow 2.12 Device: CPU - Batch Size: 256 - Model: ResNet-50 images/sec > Higher Is Better water cooled build of 5800X . 11.81 |========================================== Scikit-Learn 1.2.2 Benchmark: Isotonic / Perturbed Logarithm Seconds < Lower Is Better water cooled build of 5800X . 1587.49 |======================================== Scikit-Learn 1.2.2 Benchmark: Isotonic / Logistic Seconds < Lower Is Better water cooled build of 5800X . 1293.71 |======================================== TensorFlow 2.12 Device: CPU - Batch Size: 512 - Model: GoogLeNet images/sec > Higher Is Better water cooled build of 5800X . 34.34 |========================================== TensorFlow 2.12 Device: CPU - Batch Size: 64 - Model: VGG-16 images/sec > Higher Is Better water cooled build of 5800X . 5.91 |=========================================== LeelaChessZero 0.28 Backend: BLAS Nodes Per Second > Higher Is Better water cooled build of 5800X . 1052 |=========================================== Scikit-Learn 1.2.2 Benchmark: SAGA Seconds < Lower Is Better water cooled build of 5800X . 704.29 |========================================= Caffe 2020-02-13 Model: GoogleNet - Acceleration: CPU - Iterations: 1000 Milli-Seconds < Lower Is Better water cooled build of 5800X . 897866 |========================================= TensorFlow 2.12 Device: CPU - Batch Size: 256 - Model: GoogLeNet images/sec > Higher Is Better water cooled build of 5800X . 34.10 |========================================== Scikit-Learn 1.2.2 Benchmark: Sparse Random Projections / 100 Iterations Seconds < Lower Is Better water cooled build of 5800X . 520.69 |========================================= NCNN 20220729 Target: Vulkan GPU - Model: regnety_400m ms < Lower Is Better water cooled build of 5800X . 2.02 |=========================================== NCNN 20220729 Target: Vulkan GPU - Model: FastestDet ms < Lower Is Better water cooled build of 5800X . 2.70 |=========================================== NCNN 20220729 Target: Vulkan GPU - Model: vision_transformer ms < Lower Is Better water cooled build of 5800X . 236.24 |========================================= NCNN 20220729 Target: Vulkan GPU - Model: squeezenet_ssd ms < Lower Is Better water cooled build of 5800X . 40.68 |========================================== NCNN 20220729 Target: Vulkan GPU - Model: yolov4-tiny ms < Lower Is Better water cooled build of 5800X . 34.89 |========================================== NCNN 20220729 Target: Vulkan GPU - Model: resnet50 ms < Lower Is Better water cooled build of 5800X . 3.79 |=========================================== NCNN 20220729 Target: Vulkan GPU - Model: alexnet ms < Lower Is Better water cooled build of 5800X . 2.15 |=========================================== NCNN 20220729 Target: Vulkan GPU - Model: resnet18 ms < Lower Is Better water cooled build of 5800X . 10.13 |========================================== NCNN 20220729 Target: Vulkan GPU - Model: vgg16 ms < Lower Is Better water cooled build of 5800X . 6.11 |=========================================== NCNN 20220729 Target: Vulkan GPU - Model: googlenet ms < Lower Is Better water cooled build of 5800X . 15.53 |========================================== NCNN 20220729 Target: Vulkan GPU - Model: blazeface ms < Lower Is Better water cooled build of 5800X . 0.95 |=========================================== NCNN 20220729 Target: Vulkan GPU - Model: efficientnet-b0 ms < Lower Is Better water cooled build of 5800X . 11.16 |========================================== NCNN 20220729 Target: Vulkan GPU - Model: mnasnet ms < Lower Is Better water cooled build of 5800X . 1.56 |=========================================== NCNN 20220729 Target: Vulkan GPU - Model: shufflenet-v2 ms < Lower Is Better water cooled build of 5800X . 1.64 |=========================================== NCNN 20220729 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 ms < Lower Is Better water cooled build of 5800X . 2.69 |=========================================== NCNN 20220729 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 ms < Lower Is Better water cooled build of 5800X . 1.84 |=========================================== NCNN 20220729 Target: Vulkan GPU - Model: mobilenet ms < Lower Is Better water cooled build of 5800X . 4.01 |=========================================== TensorFlow 2.12 Device: CPU - Batch Size: 32 - Model: VGG-16 images/sec > Higher Is Better water cooled build of 5800X . 5.79 |=========================================== TensorFlow 2.12 Device: CPU - Batch Size: 64 - Model: ResNet-50 images/sec > Higher Is Better water cooled build of 5800X . 11.80 |========================================== Numenta Anomaly Benchmark 1.1 Detector: Earthgecko Skyline Seconds < Lower Is Better water cooled build of 5800X . 94.48 |========================================== TensorFlow 2.12 Device: CPU - Batch Size: 512 - Model: AlexNet images/sec > Higher Is Better water cooled build of 5800X . 126.25 |========================================= Scikit-Learn 1.2.2 Benchmark: Covertype Dataset Benchmark Seconds < Lower Is Better water cooled build of 5800X . 310.45 |========================================= AI Benchmark Alpha 0.1.2 Device AI Score Score > Higher Is Better water cooled build of 5800X . 2560 |=========================================== AI Benchmark Alpha 0.1.2 Device Training Score Score > Higher Is Better water cooled build of 5800X . 1247 |=========================================== AI Benchmark Alpha 0.1.2 Device Inference Score Score > Higher Is Better water cooled build of 5800X . 1313 |=========================================== Scikit-Learn 1.2.2 Benchmark: Lasso Seconds < Lower Is Better water cooled build of 5800X . 291.78 |========================================= Scikit-Learn 1.2.2 Benchmark: Isotonic / Pathological Seconds < Lower Is Better Scikit-Learn 1.2.2 Benchmark: Kernel PCA Solvers / Time vs. N Samples Seconds < Lower Is Better water cooled build of 5800X . 140.84 |========================================= Scikit-Learn 1.2.2 Benchmark: SGDOneClassSVM Seconds < Lower Is Better water cooled build of 5800X . 254.50 |========================================= Caffe 2020-02-13 Model: AlexNet - Acceleration: CPU - Iterations: 1000 Milli-Seconds < Lower Is Better water cooled build of 5800X . 339063 |========================================= TensorFlow 2.12 Device: CPU - Batch Size: 16 - Model: VGG-16 images/sec > Higher Is Better water cooled build of 5800X . 5.57 |=========================================== Scikit-Learn 1.2.2 Benchmark: Isolation Forest Seconds < Lower Is Better water cooled build of 5800X . 224.62 |========================================= Scikit-Learn 1.2.2 Benchmark: TSNE MNIST Dataset Seconds < Lower Is Better water cooled build of 5800X . 234.68 |========================================= Scikit-Learn 1.2.2 Benchmark: GLM Seconds < Lower Is Better water cooled build of 5800X . 223.17 |========================================= TensorFlow 2.12 Device: CPU - Batch Size: 32 - Model: ResNet-50 images/sec > Higher Is Better water cooled build of 5800X . 12.14 |========================================== Scikit-Learn 1.2.2 Benchmark: Plot Fast KMeans Seconds < Lower Is Better water cooled build of 5800X . 200.75 |========================================= Scikit-Learn 1.2.2 Benchmark: Plot Lasso Path Seconds < Lower Is Better water cooled build of 5800X . 179.09 |========================================= OpenCV 4.7 Test: DNN - Deep Neural Network ms < Lower Is Better water cooled build of 5800X . 46491 |========================================== TensorFlow 2.12 Device: CPU - Batch Size: 256 - Model: AlexNet images/sec > Higher Is Better water cooled build of 5800X . 123.61 |========================================= Scikit-Learn 1.2.2 Benchmark: Plot Hierarchical Seconds < Lower Is Better water cooled build of 5800X . 169.25 |========================================= Scikit-Learn 1.2.2 Benchmark: Kernel PCA Solvers / Time vs. N Components Seconds < Lower Is Better water cooled build of 5800X . 41.79 |========================================== Scikit-Learn 1.2.2 Benchmark: Plot Incremental PCA Seconds < Lower Is Better water cooled build of 5800X . 40.09 |========================================== TensorFlow 2.12 Device: CPU - Batch Size: 64 - Model: GoogLeNet images/sec > Higher Is Better water cooled build of 5800X . 35.33 |========================================== Scikit-Learn 1.2.2 Benchmark: Hist Gradient Boosting Threading Seconds < Lower Is Better water cooled build of 5800X . 144.78 |========================================= Numenta Anomaly Benchmark 1.1 Detector: KNN CAD Seconds < Lower Is Better water cooled build of 5800X . 191.58 |========================================= TNN 0.3 Target: CPU - Model: DenseNet ms < Lower Is Better water cooled build of 5800X . 2599.27 |======================================== Caffe 2020-02-13 Model: GoogleNet - Acceleration: CPU - Iterations: 200 Milli-Seconds < Lower Is Better water cooled build of 5800X . 178392 |========================================= Scikit-Learn 1.2.2 Benchmark: Plot Neighbors Seconds < Lower Is Better water cooled build of 5800X . 133.11 |========================================= Numenta Anomaly Benchmark 1.1 Detector: Bayesian Changepoint Seconds < Lower Is Better water cooled build of 5800X . 34.99 |========================================== Scikit-Learn 1.2.2 Benchmark: Plot Polynomial Kernel Approximation Seconds < Lower Is Better water cooled build of 5800X . 116.85 |========================================= Scikit-Learn 1.2.2 Benchmark: Sample Without Replacement Seconds < Lower Is Better water cooled build of 5800X . 111.70 |========================================= Numpy Benchmark Score > Higher Is Better water cooled build of 5800X . 580.78 |========================================= oneDNN 3.1 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better water cooled build of 5800X . 3219.95 |======================================== Scikit-Learn 1.2.2 Benchmark: Feature Expansions Seconds < Lower Is Better water cooled build of 5800X . 108.54 |========================================= TensorFlow 2.12 Device: CPU - Batch Size: 16 - Model: ResNet-50 images/sec > Higher Is Better water cooled build of 5800X . 12.60 |========================================== Mobile Neural Network 2.1 Model: inception-v3 ms < Lower Is Better water cooled build of 5800X . 25.57 |========================================== Mobile Neural Network 2.1 Model: mobilenet-v1-1.0 ms < Lower Is Better water cooled build of 5800X . 1.921 |========================================== Mobile Neural Network 2.1 Model: MobileNetV2_224 ms < Lower Is Better water cooled build of 5800X . 2.006 |========================================== Mobile Neural Network 2.1 Model: SqueezeNetV1.0 ms < Lower Is Better water cooled build of 5800X . 4.888 |========================================== Mobile Neural Network 2.1 Model: resnet-v2-50 ms < Lower Is Better water cooled build of 5800X . 19.25 |========================================== Mobile Neural Network 2.1 Model: squeezenetv1.1 ms < Lower Is Better water cooled build of 5800X . 2.436 |========================================== Mobile Neural Network 2.1 Model: mobilenetV3 ms < Lower Is Better water cooled build of 5800X . 1.025 |========================================== Mobile Neural Network 2.1 Model: nasnet ms < Lower Is Better water cooled build of 5800X . 7.876 |========================================== Scikit-Learn 1.2.2 Benchmark: Plot Singular Value Decomposition Seconds < Lower Is Better water cooled build of 5800X . 95.23 |========================================== Scikit-Learn 1.2.2 Benchmark: Hist Gradient Boosting Seconds < Lower Is Better water cooled build of 5800X . 91.59 |========================================== Scikit-Learn 1.2.2 Benchmark: Hist Gradient Boosting Higgs Boson Seconds < Lower Is Better water cooled build of 5800X . 58.17 |========================================== NCNN 20220729 Target: CPU - Model: shufflenet-v2 ms < Lower Is Better water cooled build of 5800X . 2.15 |=========================================== NCNN 20220729 Target: CPU - Model: FastestDet ms < Lower Is Better water cooled build of 5800X . 2.57 |=========================================== NCNN 20220729 Target: CPU - Model: vision_transformer ms < Lower Is Better water cooled build of 5800X . 198.97 |========================================= NCNN 20220729 Target: CPU - Model: regnety_400m ms < Lower Is Better water cooled build of 5800X . 6.95 |=========================================== NCNN 20220729 Target: CPU - Model: squeezenet_ssd ms < Lower Is Better water cooled build of 5800X . 14.61 |========================================== NCNN 20220729 Target: CPU - Model: yolov4-tiny ms < Lower Is Better water cooled build of 5800X . 19.17 |========================================== NCNN 20220729 Target: CPU - Model: resnet50 ms < Lower Is Better water cooled build of 5800X . 18.39 |========================================== NCNN 20220729 Target: CPU - Model: alexnet ms < Lower Is Better water cooled build of 5800X . 8.62 |=========================================== NCNN 20220729 Target: CPU - Model: resnet18 ms < Lower Is Better water cooled build of 5800X . 10.54 |========================================== NCNN 20220729 Target: CPU - Model: vgg16 ms < Lower Is Better water cooled build of 5800X . 47.30 |========================================== NCNN 20220729 Target: CPU - Model: googlenet ms < Lower Is Better water cooled build of 5800X . 9.91 |=========================================== NCNN 20220729 Target: CPU - Model: blazeface ms < Lower Is Better water cooled build of 5800X . 0.80 |=========================================== NCNN 20220729 Target: CPU - Model: efficientnet-b0 ms < Lower Is Better water cooled build of 5800X . 4.72 |=========================================== NCNN 20220729 Target: CPU - Model: mnasnet ms < Lower Is Better water cooled build of 5800X . 2.60 |=========================================== NCNN 20220729 Target: CPU-v3-v3 - Model: mobilenet-v3 ms < Lower Is Better water cooled build of 5800X . 2.16 |=========================================== NCNN 20220729 Target: CPU-v2-v2 - Model: mobilenet-v2 ms < Lower Is Better water cooled build of 5800X . 2.80 |=========================================== NCNN 20220729 Target: CPU - Model: mobilenet ms < Lower Is Better water cooled build of 5800X . 10.81 |========================================== Scikit-Learn 1.2.2 Benchmark: Sparsify Seconds < Lower Is Better water cooled build of 5800X . 80.63 |========================================== oneDNN 3.1 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better water cooled build of 5800X . 7.07805 |======================================== Scikit-Learn 1.2.2 Benchmark: Hist Gradient Boosting Adult Seconds < Lower Is Better water cooled build of 5800X . 75.39 |========================================== TensorFlow 2.12 Device: CPU - Batch Size: 32 - Model: GoogLeNet images/sec > Higher Is Better water cooled build of 5800X . 36.35 |========================================== Scikit-Learn 1.2.2 Benchmark: SGD Regression Seconds < Lower Is Better water cooled build of 5800X . 73.50 |========================================== Caffe 2020-02-13 Model: GoogleNet - Acceleration: CPU - Iterations: 100 Milli-Seconds < Lower Is Better water cooled build of 5800X . 89939 |========================================== oneDNN 3.1 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better water cooled build of 5800X . 3195.17 |======================================== oneDNN 3.1 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better water cooled build of 5800X . 3208.11 |======================================== Scikit-Learn 1.2.2 Benchmark: Plot OMP vs. LARS Seconds < Lower Is Better water cooled build of 5800X . 61.65 |========================================== oneDNN 3.1 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better water cooled build of 5800X . 1862.51 |======================================== oneDNN 3.1 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better water cooled build of 5800X . 1866.37 |======================================== oneDNN 3.1 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better water cooled build of 5800X . 1857.48 |======================================== Scikit-Learn 1.2.2 Benchmark: MNIST Dataset Seconds < Lower Is Better water cooled build of 5800X . 54.74 |========================================== Scikit-Learn 1.2.2 Benchmark: Text Vectorizers Seconds < Lower Is Better water cooled build of 5800X . 50.42 |========================================== Caffe 2020-02-13 Model: AlexNet - Acceleration: CPU - Iterations: 200 Milli-Seconds < Lower Is Better water cooled build of 5800X . 68197 |========================================== Scikit-Learn 1.2.2 Benchmark: Tree Seconds < Lower Is Better water cooled build of 5800X . 41.30 |========================================== Scikit-Learn 1.2.2 Benchmark: LocalOutlierFactor Seconds < Lower Is Better water cooled build of 5800X . 48.56 |========================================== TensorFlow 2.12 Device: CPU - Batch Size: 64 - Model: AlexNet images/sec > Higher Is Better water cooled build of 5800X . 108.11 |========================================= Scikit-Learn 1.2.2 Benchmark: Plot Ward Seconds < Lower Is Better water cooled build of 5800X . 47.38 |========================================== TensorFlow Lite 2022-05-18 Model: Inception V4 Microseconds < Lower Is Better water cooled build of 5800X . 44873.4 |======================================== TensorFlow Lite 2022-05-18 Model: Inception ResNet V2 Microseconds < Lower Is Better water cooled build of 5800X . 41004.4 |======================================== TensorFlow Lite 2022-05-18 Model: NASNet Mobile Microseconds < Lower Is Better water cooled build of 5800X . 8458.27 |======================================== TensorFlow Lite 2022-05-18 Model: Mobilenet Quant Microseconds < Lower Is Better water cooled build of 5800X . 3837.99 |======================================== TensorFlow Lite 2022-05-18 Model: Mobilenet Float Microseconds < Lower Is Better water cooled build of 5800X . 2122.82 |======================================== TensorFlow Lite 2022-05-18 Model: SqueezeNet Microseconds < Lower Is Better water cooled build of 5800X . 2994.52 |======================================== spaCy 3.4.1 Model: en_core_web_trf tokens/sec > Higher Is Better water cooled build of 5800X . 1500 |=========================================== spaCy 3.4.1 Model: en_core_web_lg tokens/sec > Higher Is Better water cooled build of 5800X . 15204 |========================================== TensorFlow 2.12 Device: CPU - Batch Size: 16 - Model: GoogLeNet images/sec > Higher Is Better water cooled build of 5800X . 36.89 |========================================== Scikit-Learn 1.2.2 Benchmark: 20 Newsgroups / Logistic Regression Seconds < Lower Is Better water cooled build of 5800X . 35.32 |========================================== Scikit-Learn 1.2.2 Benchmark: Plot Non-Negative Matrix Factorization Seconds < Lower Is Better Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better water cooled build of 5800X . 139.17 |========================================= Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better water cooled build of 5800X . 28.71 |========================================== Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better water cooled build of 5800X . 40.61 |========================================== Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better water cooled build of 5800X . 98.46 |========================================== oneDNN 3.1 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU ms < Lower Is Better water cooled build of 5800X . 8.44050 |======================================== Neural Magic DeepSparse 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better water cooled build of 5800X . 471.62 |========================================= Neural Magic DeepSparse 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better water cooled build of 5800X . 8.4566 |========================================= Neural Magic DeepSparse 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better water cooled build of 5800X . 472.22 |========================================= Neural Magic DeepSparse 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better water cooled build of 5800X . 8.4386 |========================================= Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better water cooled build of 5800X . 106.04 |========================================= Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better water cooled build of 5800X . 37.67 |========================================== Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better water cooled build of 5800X . 381.41 |========================================= Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better water cooled build of 5800X . 10.47 |========================================== Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better water cooled build of 5800X . 36.07 |========================================== Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better water cooled build of 5800X . 27.72 |========================================== Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better water cooled build of 5800X . 14.47 |========================================== Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream items/sec > Higher Is Better water cooled build of 5800X . 69.05 |========================================== Neural Magic DeepSparse 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better water cooled build of 5800X . 123.59 |========================================= Neural Magic DeepSparse 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream items/sec > Higher Is Better water cooled build of 5800X . 8.0906 |========================================= Neural Magic DeepSparse 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better water cooled build of 5800X . 123.14 |========================================= Neural Magic DeepSparse 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better water cooled build of 5800X . 8.1206 |========================================= Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better water cooled build of 5800X . 32.49 |========================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better water cooled build of 5800X . 30.77 |========================================== Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better water cooled build of 5800X . 97.53 |========================================== Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream items/sec > Higher Is Better water cooled build of 5800X . 10.25 |========================================== DeepSpeech 0.6 Acceleration: CPU Seconds < Lower Is Better water cooled build of 5800X . 54.51 |========================================== TensorFlow 2.12 Device: CPU - Batch Size: 32 - Model: AlexNet images/sec > Higher Is Better water cooled build of 5800X . 91.11 |========================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better water cooled build of 5800X . 52.39 |========================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better water cooled build of 5800X . 76.32 |========================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better water cooled build of 5800X . 16.22 |========================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream items/sec > Higher Is Better water cooled build of 5800X . 61.63 |========================================== Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better water cooled build of 5800X . 80.57 |========================================== Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better water cooled build of 5800X . 49.59 |========================================== Numenta Anomaly Benchmark 1.1 Detector: Contextual Anomaly Detector OSE Seconds < Lower Is Better water cooled build of 5800X . 37.64 |========================================== Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better water cooled build of 5800X . 36.92 |========================================== Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better water cooled build of 5800X . 108.28 |========================================= Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better water cooled build of 5800X . 22.12 |========================================== Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream items/sec > Higher Is Better water cooled build of 5800X . 45.18 |========================================== Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better water cooled build of 5800X . 11.11 |========================================== Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream items/sec > Higher Is Better water cooled build of 5800X . 89.92 |========================================== Caffe 2020-02-13 Model: AlexNet - Acceleration: CPU - Iterations: 100 Milli-Seconds < Lower Is Better water cooled build of 5800X . 33917 |========================================== TensorFlow 2.12 Device: CPU - Batch Size: 16 - Model: AlexNet images/sec > Higher Is Better water cooled build of 5800X . 68.68 |========================================== Scikit-Learn 1.2.2 Benchmark: Hist Gradient Boosting Categorical Only Seconds < Lower Is Better water cooled build of 5800X . 16.44 |========================================== oneDNN 3.1 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better water cooled build of 5800X . 2.01682 |======================================== R Benchmark Seconds < Lower Is Better water cooled build of 5800X . 0.1092 |========================================= Numenta Anomaly Benchmark 1.1 Detector: Relative Entropy Seconds < Lower Is Better water cooled build of 5800X . 16.88 |========================================== TNN 0.3 Target: CPU - Model: MobileNet v2 ms < Lower Is Better water cooled build of 5800X . 230.65 |========================================= RNNoise 2020-06-28 Seconds < Lower Is Better water cooled build of 5800X . 15.65 |========================================== oneDNN 3.1 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better water cooled build of 5800X . 3.41565 |======================================== oneDNN 3.1 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better water cooled build of 5800X . 1.42899 |======================================== TNN 0.3 Target: CPU - Model: SqueezeNet v1.1 ms < Lower Is Better water cooled build of 5800X . 212.96 |========================================= Numenta Anomaly Benchmark 1.1 Detector: Windowed Gaussian Seconds < Lower Is Better water cooled build of 5800X . 9.389 |========================================== Scikit-Learn 1.2.2 Benchmark: RCV1 Logreg Convergencet Seconds < Lower Is Better oneDNN 3.1 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better water cooled build of 5800X . 1.63297 |======================================== oneDNN 3.1 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU ms < Lower Is Better water cooled build of 5800X . 15.00 |========================================== oneDNN 3.1 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better water cooled build of 5800X . 14.42 |========================================== TNN 0.3 Target: CPU - Model: SqueezeNet v2 ms < Lower Is Better water cooled build of 5800X . 50.97 |========================================== oneDNN 3.1 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better water cooled build of 5800X . 6.11078 |======================================== oneDNN 3.1 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better water cooled build of 5800X . 2.87855 |======================================== Scikit-Learn 1.2.2 Benchmark: Plot Parallel Pairwise Seconds < Lower Is Better ECP-CANDLE 0.4 Benchmark: P1B2 Seconds < Lower Is Better ECP-CANDLE 0.4 Benchmark: P3B2 Seconds < Lower Is Better ECP-CANDLE 0.4 Benchmark: P3B1 Seconds < Lower Is Better PlaidML FP16: No - Mode: Inference - Network: VGG16 - Device: CPU Examples Per Second > Higher Is Better Scikit-Learn 1.2.2 Benchmark: Glmnet Seconds < Lower Is Better PlaidML FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU Examples Per Second > Higher Is Better Mlpack Benchmark Benchmark: scikit_svm Seconds < Lower Is Better Mlpack Benchmark Benchmark: scikit_ica Seconds < Lower Is Better Mlpack Benchmark Benchmark: scikit_linearridgeregression Seconds < Lower Is Better Mlpack Benchmark Benchmark: scikit_qda Seconds < Lower Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: S3D oneDNN 3.1 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 3.1 Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 3.1 Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better ONNX Runtime 1.14 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better ONNX Runtime 1.14 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better ONNX Runtime 1.14 Model: super-resolution-10 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better ONNX Runtime 1.14 Model: super-resolution-10 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better ONNX Runtime 1.14 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better ONNX Runtime 1.14 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better ONNX Runtime 1.14 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better ONNX Runtime 1.14 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better ONNX Runtime 1.14 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better ONNX Runtime 1.14 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better ONNX Runtime 1.14 Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better ONNX Runtime 1.14 Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better ONNX Runtime 1.14 Model: bertsquad-12 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better ONNX Runtime 1.14 Model: bertsquad-12 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better ONNX Runtime 1.14 Model: yolov4 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better ONNX Runtime 1.14 Model: yolov4 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better ONNX Runtime 1.14 Model: GPT-2 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better ONNX Runtime 1.14 Model: GPT-2 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better oneDNN 3.1 Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 3.1 Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Texture Read Bandwidth SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Bus Speed Readback SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Bus Speed Download SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Max SP Flops SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: GEMM SGEMM_N SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Reduction SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: MD5 Hash SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: FFT SP SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Triad