HDVR4-A8.9600-1 AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C+6G testing with a ASRock A320M-HDV R4.0 (P2.00 BIOS) and llvmpipe on Ubuntu 20.04 via the Phoronix Test Suite. llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C: Processor: AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C+6G @ 3.10GHz (2 Cores / 4 Threads), Motherboard: ASRock A320M-HDV R4.0 (P2.00 BIOS), Chipset: AMD 15h, Memory: 3584MB, Disk: 1000GB Western Digital WDS100T2B0A, Graphics: llvmpipe, Audio: AMD Kabini HDMI/DP, Network: Realtek RTL8111/8168/8411 OS: Ubuntu 20.04, Kernel: 5.15.0-89-generic (x86_64), Desktop: GNOME Shell 3.36.9, Display Server: X Server 1.20.13, OpenGL: 4.5 Mesa 21.2.6 (LLVM 12.0.0 256 bits), Vulkan: 1.1.182, Compiler: GCC 9.4.0, File-System: ext4, Screen Resolution: 1368x768 PyTorch 2.1 Device: CPU - Batch Size: 1 - Model: ResNet-50 batches/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 3.85 |================== PyTorch 2.1 Device: CPU - Batch Size: 1 - Model: ResNet-152 batches/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 1.62 |================== PyTorch 2.1 Device: CPU - Batch Size: 16 - Model: ResNet-50 batches/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 2.24 |================== PyTorch 2.1 Device: CPU - Batch Size: 32 - Model: ResNet-50 batches/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 2.21 |================== PyTorch 2.1 Device: CPU - Batch Size: 64 - Model: ResNet-50 batches/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 2.21 |================== PyTorch 2.1 Device: CPU - Batch Size: 16 - Model: ResNet-152 batches/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 0.91 |================== PyTorch 2.1 Device: CPU - Batch Size: 256 - Model: ResNet-50 batches/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 2.17 |================== PyTorch 2.1 Device: CPU - Batch Size: 32 - Model: ResNet-152 batches/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 0.93 |================== PyTorch 2.1 Device: CPU - Batch Size: 512 - Model: ResNet-50 batches/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 2.23 |================== PyTorch 2.1 Device: CPU - Batch Size: 64 - Model: ResNet-152 batches/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 0.92 |================== PyTorch 2.1 Device: CPU - Batch Size: 256 - Model: ResNet-152 batches/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 0.92 |================== PyTorch 2.1 Device: CPU - Batch Size: 512 - Model: ResNet-152 batches/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 0.93 |================== PyTorch 2.1 Device: CPU - Batch Size: 1 - Model: Efficientnet_v2_l batches/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 1.10 |================== PyTorch 2.1 Device: CPU - Batch Size: 16 - Model: Efficientnet_v2_l batches/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 0.59 |================== PyTorch 2.1 Device: CPU - Batch Size: 32 - Model: Efficientnet_v2_l batches/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 0.59 |================== PyTorch 2.1 Device: CPU - Batch Size: 64 - Model: Efficientnet_v2_l batches/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 0.60 |================== PyTorch 2.1 Device: CPU - Batch Size: 256 - Model: Efficientnet_v2_l batches/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 0.60 |================== PyTorch 2.1 Device: CPU - Batch Size: 512 - Model: Efficientnet_v2_l batches/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 0.60 |================== PlaidML FP16: No - Mode: Inference - Network: VGG16 - Device: CPU FPS > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 1.33 |================== PlaidML FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU FPS > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 1.60 |================== OpenVINO 2023.2.dev Model: Face Detection FP16 - Device: CPU FPS > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 0.23 |================== OpenVINO 2023.2.dev Model: Person Detection FP16 - Device: CPU FPS > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 1.92 |================== OpenVINO 2023.2.dev Model: Person Detection FP32 - Device: CPU FPS > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 1.91 |================== OpenVINO 2023.2.dev Model: Vehicle Detection FP16 - Device: CPU FPS > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 11.85 |================= OpenVINO 2023.2.dev Model: Face Detection FP16-INT8 - Device: CPU FPS > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 0.3 |=================== OpenVINO 2023.2.dev Model: Face Detection Retail FP16 - Device: CPU FPS > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 46.80 |================= OpenVINO 2023.2.dev Model: Road Segmentation ADAS FP16 - Device: CPU FPS > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 4.69 |================== OpenVINO 2023.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU FPS > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 20.20 |================= OpenVINO 2023.2.dev Model: Weld Porosity Detection FP16 - Device: CPU FPS > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 21.55 |================= OpenVINO 2023.2.dev Model: Face Detection Retail FP16-INT8 - Device: CPU FPS > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 65.08 |================= OpenVINO 2023.2.dev Model: Road Segmentation ADAS FP16-INT8 - Device: CPU FPS > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 9.86 |================== OpenVINO 2023.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU FPS > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 2.79 |================== OpenVINO 2023.2.dev Model: Weld Porosity Detection FP16-INT8 - Device: CPU FPS > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 29.49 |================= OpenVINO 2023.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU FPS > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 23.78 |================= OpenVINO 2023.2.dev Model: Handwritten English Recognition FP16 - Device: CPU FPS > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 3.40 |================== OpenVINO 2023.2.dev Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU FPS > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 438.38 |================ OpenVINO 2023.2.dev Model: Handwritten English Recognition FP16-INT8 - Device: CPU FPS > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 3.41 |================== OpenVINO 2023.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU FPS > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 681.70 |================ TensorFlow 2.12 Device: CPU - Batch Size: 16 - Model: VGG-16 images/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 0.61 |================== TensorFlow 2.12 Device: CPU - Batch Size: 32 - Model: VGG-16 images/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 0.53 |================== TensorFlow 2.12 Device: CPU - Batch Size: 64 - Model: VGG-16 images/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 0.45 |================== TensorFlow 2.12 Device: CPU - Batch Size: 16 - Model: AlexNet images/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 7.02 |================== TensorFlow 2.12 Device: CPU - Batch Size: 256 - Model: VGG-16 images/sec > Higher Is Better TensorFlow 2.12 Device: CPU - Batch Size: 32 - Model: AlexNet images/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 9.07 |================== TensorFlow 2.12 Device: CPU - Batch Size: 512 - Model: VGG-16 images/sec > Higher Is Better TensorFlow 2.12 Device: CPU - Batch Size: 64 - Model: AlexNet images/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 10.54 |================= TensorFlow 2.12 Device: CPU - Batch Size: 256 - Model: AlexNet images/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 12.02 |================= TensorFlow 2.12 Device: CPU - Batch Size: 512 - Model: AlexNet images/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 12.23 |================= TensorFlow 2.12 Device: CPU - Batch Size: 16 - Model: GoogLeNet images/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 4.48 |================== TensorFlow 2.12 Device: CPU - Batch Size: 16 - Model: ResNet-50 images/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 1.47 |================== TensorFlow 2.12 Device: CPU - Batch Size: 32 - Model: GoogLeNet images/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 4.53 |================== TensorFlow 2.12 Device: CPU - Batch Size: 32 - Model: ResNet-50 images/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 1.50 |================== TensorFlow 2.12 Device: CPU - Batch Size: 64 - Model: GoogLeNet images/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 4.58 |================== TensorFlow 2.12 Device: CPU - Batch Size: 64 - Model: ResNet-50 images/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 1.02 |================== TensorFlow 2.12 Device: CPU - Batch Size: 256 - Model: GoogLeNet images/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 3.02 |================== TensorFlow 2.12 Device: CPU - Batch Size: 256 - Model: ResNet-50 images/sec > Higher Is Better TensorFlow 2.12 Device: CPU - Batch Size: 512 - Model: GoogLeNet images/sec > Higher Is Better TensorFlow 2.12 Device: CPU - Batch Size: 512 - Model: ResNet-50 images/sec > Higher Is Better ONNX Runtime 1.14 Model: GPT-2 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 11.72 |================= ONNX Runtime 1.14 Model: GPT-2 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 21.62 |================= ONNX Runtime 1.14 Model: yolov4 - 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: bertsquad-12 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 0.758124 |============== ONNX Runtime 1.14 Model: bertsquad-12 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 1.22825 |=============== ONNX Runtime 1.14 Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 26.25 |================= ONNX Runtime 1.14 Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 44.58 |================= ONNX Runtime 1.14 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 0.0745773 |============= ONNX Runtime 1.14 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 0.106443 |============== ONNX Runtime 1.14 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 1.94502 |=============== ONNX Runtime 1.14 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 3.54808 |=============== ONNX Runtime 1.14 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 6.48329 |=============== ONNX Runtime 1.14 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 11.82 |================= ONNX Runtime 1.14 Model: super-resolution-10 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 8.32539 |=============== ONNX Runtime 1.14 Model: super-resolution-10 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 11.40 |================= ONNX Runtime 1.14 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 0.901280 |============== ONNX Runtime 1.14 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 1.11900 |=============== Neural Magic DeepSparse 1.6 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 0.7139 |================ Neural Magic DeepSparse 1.6 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream items/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 0.7398 |================ Neural Magic DeepSparse 1.6 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 14.56 |================= Neural Magic DeepSparse 1.6 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 13.48 |================= Neural Magic DeepSparse 1.6 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 7.6144 |================ Neural Magic DeepSparse 1.6 Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream items/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 8.3342 |================ Neural Magic DeepSparse 1.6 Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 46.77 |================= Neural Magic DeepSparse 1.6 Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 42.68 |================= Neural Magic DeepSparse 1.6 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 3.6022 |================ Neural Magic DeepSparse 1.6 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream items/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 3.9464 |================ Neural Magic DeepSparse 1.6 Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 0.8881 |================ Neural Magic DeepSparse 1.6 Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream items/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 0.9181 |================ Neural Magic DeepSparse 1.6 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 7.6267 |================ Neural Magic DeepSparse 1.6 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream items/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 8.3171 |================ Neural Magic DeepSparse 1.6 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 3.5275 |================ Neural Magic DeepSparse 1.6 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 3.9896 |================ Neural Magic DeepSparse 1.6 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 6.1356 |================ Neural Magic DeepSparse 1.6 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream items/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 5.5004 |================ Neural Magic DeepSparse 1.6 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 0.9012 |================ Neural Magic DeepSparse 1.6 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream items/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 0.9604 |================ Neural Magic DeepSparse 1.6 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 6.3146 |================ Neural Magic DeepSparse 1.6 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 6.3561 |================ Neural Magic DeepSparse 1.6 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 0.7168 |================ Neural Magic DeepSparse 1.6 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 0.7380 |================ LeelaChessZero 0.28 Backend: BLAS Nodes Per Second > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 124 |=================== Numpy Benchmark Score > Higher Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 122.42 |================ AI Benchmark Alpha 0.1.2 Score > Higher Is Better spaCy 3.4.1 tokens/sec > Higher Is Better ONNX Runtime 1.14 Model: GPT-2 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 85.33 |================= ONNX Runtime 1.14 Model: GPT-2 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 46.24 |================= ONNX Runtime 1.14 Model: bertsquad-12 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 1319.06 |=============== ONNX Runtime 1.14 Model: bertsquad-12 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 814.17 |================ ONNX Runtime 1.14 Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 38.09 |================= ONNX Runtime 1.14 Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 22.43 |================= ONNX Runtime 1.14 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 13409.4 |=============== ONNX Runtime 1.14 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 9394.74 |=============== ONNX Runtime 1.14 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 514.17 |================ ONNX Runtime 1.14 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 281.84 |================ ONNX Runtime 1.14 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 154.24 |================ ONNX Runtime 1.14 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 84.58 |================= ONNX Runtime 1.14 Model: super-resolution-10 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 120.16 |================ ONNX Runtime 1.14 Model: super-resolution-10 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 87.78 |================= ONNX Runtime 1.14 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 1109.54 |=============== ONNX Runtime 1.14 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 893.65 |================ TensorFlow Lite 2022-05-18 Model: SqueezeNet Microseconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 34007.2 |=============== TensorFlow Lite 2022-05-18 Model: Inception V4 Microseconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 547885 |================ TensorFlow Lite 2022-05-18 Model: NASNet Mobile Microseconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 66075.7 |=============== TensorFlow Lite 2022-05-18 Model: Mobilenet Float Microseconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 26921.0 |=============== TensorFlow Lite 2022-05-18 Model: Mobilenet Quant Microseconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 28341.7 |=============== TensorFlow Lite 2022-05-18 Model: Inception ResNet V2 Microseconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 419892 |================ Caffe 2020-02-13 Model: AlexNet - Acceleration: CPU - Iterations: 100 Milli-Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 107310 |================ Caffe 2020-02-13 Model: AlexNet - Acceleration: CPU - Iterations: 200 Milli-Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 216588 |================ Caffe 2020-02-13 Model: AlexNet - Acceleration: CPU - Iterations: 1000 Milli-Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 1079113 |=============== Caffe 2020-02-13 Model: GoogleNet - Acceleration: CPU - Iterations: 100 Milli-Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 231503 |================ Caffe 2020-02-13 Model: GoogleNet - Acceleration: CPU - Iterations: 200 Milli-Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 457100 |================ Caffe 2020-02-13 Model: GoogleNet - Acceleration: CPU - Iterations: 1000 Milli-Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 2318550 |=============== oneDNN 3.3 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 42.23 |================= oneDNN 3.3 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 45.54 |================= oneDNN 3.3 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 23.79 |================= oneDNN 3.3 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 12.00 |================= oneDNN 3.3 Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 3.3 Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 3.3 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 90.59 |================= oneDNN 3.3 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 53.30 |================= oneDNN 3.3 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 54.13 |================= oneDNN 3.3 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 70.48 |================= oneDNN 3.3 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 32.51 |================= oneDNN 3.3 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 60.62 |================= oneDNN 3.3 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 38466.3 |=============== oneDNN 3.3 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 21158.0 |=============== oneDNN 3.3 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 38464.9 |=============== oneDNN 3.3 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 3.3 Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 3.3 Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 3.3 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 21148.2 |=============== oneDNN 3.3 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 38767.3 |=============== oneDNN 3.3 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 21318.6 |=============== Mobile Neural Network 2.1 Model: nasnet ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 46.61 |================= Mobile Neural Network 2.1 Model: mobilenetV3 ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 6.958 |================= Mobile Neural Network 2.1 Model: squeezenetv1.1 ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 17.63 |================= Mobile Neural Network 2.1 Model: resnet-v2-50 ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 130.58 |================ Mobile Neural Network 2.1 Model: SqueezeNetV1.0 ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 32.41 |================= Mobile Neural Network 2.1 Model: MobileNetV2_224 ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 17.25 |================= Mobile Neural Network 2.1 Model: mobilenet-v1-1.0 ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 20.46 |================= Mobile Neural Network 2.1 Model: inception-v3 ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 163.10 |================ NCNN 20230517 Target: CPU - Model: mobilenet ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 100.21 |================ NCNN 20230517 Target: CPU-v2-v2 - Model: mobilenet-v2 ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 31.61 |================= NCNN 20230517 Target: CPU-v3-v3 - Model: mobilenet-v3 ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 22.58 |================= NCNN 20230517 Target: CPU - Model: shufflenet-v2 ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 16.32 |================= NCNN 20230517 Target: CPU - Model: mnasnet ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 25.63 |================= NCNN 20230517 Target: CPU - Model: efficientnet-b0 ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 39.50 |================= NCNN 20230517 Target: CPU - Model: blazeface ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 5.33 |================== NCNN 20230517 Target: CPU - Model: googlenet ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 75.15 |================= NCNN 20230517 Target: CPU - Model: vgg16 ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 333.56 |================ NCNN 20230517 Target: CPU - Model: resnet18 ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 60.75 |================= NCNN 20230517 Target: CPU - Model: alexnet ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 42.29 |================= NCNN 20230517 Target: CPU - Model: resnet50 ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 135.48 |================ NCNN 20230517 Target: CPU - Model: yolov4-tiny ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 139.59 |================ NCNN 20230517 Target: CPU - Model: squeezenet_ssd ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 68.66 |================= NCNN 20230517 Target: CPU - Model: regnety_400m ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 33.68 |================= NCNN 20230517 Target: CPU - Model: vision_transformer ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 1141.93 |=============== NCNN 20230517 Target: CPU - Model: FastestDet ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 22.26 |================= NCNN 20230517 Target: Vulkan GPU - Model: mobilenet ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 100.53 |================ NCNN 20230517 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 31.44 |================= NCNN 20230517 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 22.45 |================= NCNN 20230517 Target: Vulkan GPU - Model: shufflenet-v2 ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 16.53 |================= NCNN 20230517 Target: Vulkan GPU - Model: mnasnet ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 25.62 |================= NCNN 20230517 Target: Vulkan GPU - Model: efficientnet-b0 ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 39.25 |================= NCNN 20230517 Target: Vulkan GPU - Model: blazeface ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 5.32 |================== NCNN 20230517 Target: Vulkan GPU - Model: googlenet ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 75.41 |================= NCNN 20230517 Target: Vulkan GPU - Model: vgg16 ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 335.23 |================ NCNN 20230517 Target: Vulkan GPU - Model: resnet18 ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 61.47 |================= NCNN 20230517 Target: Vulkan GPU - Model: alexnet ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 42.25 |================= NCNN 20230517 Target: Vulkan GPU - Model: resnet50 ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 135.98 |================ NCNN 20230517 Target: Vulkan GPU - Model: yolov4-tiny ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 139.80 |================ NCNN 20230517 Target: Vulkan GPU - Model: squeezenet_ssd ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 68.80 |================= NCNN 20230517 Target: Vulkan GPU - Model: regnety_400m ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 33.20 |================= NCNN 20230517 Target: Vulkan GPU - Model: vision_transformer ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 1140.71 |=============== NCNN 20230517 Target: Vulkan GPU - Model: FastestDet ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 22.62 |================= TNN 0.3 Target: CPU - Model: DenseNet ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 8874.35 |=============== TNN 0.3 Target: CPU - Model: MobileNet v2 ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 656.29 |================ TNN 0.3 Target: CPU - Model: SqueezeNet v2 ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 135.31 |================ TNN 0.3 Target: CPU - Model: SqueezeNet v1.1 ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 557.95 |================ OpenVINO 2023.2.dev Model: Face Detection FP16 - Device: CPU ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 8841.25 |=============== OpenVINO 2023.2.dev Model: Person Detection FP16 - Device: CPU ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 1042.19 |=============== OpenVINO 2023.2.dev Model: Person Detection FP32 - Device: CPU ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 1044.45 |=============== OpenVINO 2023.2.dev Model: Vehicle Detection FP16 - Device: CPU ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 168.71 |================ OpenVINO 2023.2.dev Model: Face Detection FP16-INT8 - Device: CPU ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 6728.06 |=============== OpenVINO 2023.2.dev Model: Face Detection Retail FP16 - Device: CPU ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 42.70 |================= OpenVINO 2023.2.dev Model: Road Segmentation ADAS FP16 - Device: CPU ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 426.61 |================ OpenVINO 2023.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 98.95 |================= OpenVINO 2023.2.dev Model: Weld Porosity Detection FP16 - Device: CPU ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 92.76 |================= OpenVINO 2023.2.dev Model: Face Detection Retail FP16-INT8 - Device: CPU ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 30.73 |================= OpenVINO 2023.2.dev Model: Road Segmentation ADAS FP16-INT8 - Device: CPU ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 202.73 |================ OpenVINO 2023.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 716.36 |================ OpenVINO 2023.2.dev Model: Weld Porosity Detection FP16-INT8 - Device: CPU ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 67.76 |================= OpenVINO 2023.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 84.09 |================= OpenVINO 2023.2.dev Model: Handwritten English Recognition FP16 - Device: CPU ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 593.05 |================ OpenVINO 2023.2.dev Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 4.54 |================== OpenVINO 2023.2.dev Model: Handwritten English Recognition FP16-INT8 - Device: CPU ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 587.13 |================ OpenVINO 2023.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 2.90 |================== OpenCV 4.7 Test: DNN - Deep Neural Network ms < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 106960 |================ Neural Magic DeepSparse 1.6 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 2785.40 |=============== Neural Magic DeepSparse 1.6 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 1351.89 |=============== Neural Magic DeepSparse 1.6 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 137.27 |================ Neural Magic DeepSparse 1.6 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 74.18 |================= Neural Magic DeepSparse 1.6 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 262.34 |================ Neural Magic DeepSparse 1.6 Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 119.97 |================ Neural Magic DeepSparse 1.6 Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 42.69 |================= Neural Magic DeepSparse 1.6 Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 23.41 |================= Neural Magic DeepSparse 1.6 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 554.86 |================ Neural Magic DeepSparse 1.6 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 253.36 |================ Neural Magic DeepSparse 1.6 Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 2245.61 |=============== Neural Magic DeepSparse 1.6 Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 1089.99 |=============== Neural Magic DeepSparse 1.6 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 261.94 |================ Neural Magic DeepSparse 1.6 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 120.21 |================ Neural Magic DeepSparse 1.6 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 565.80 |================ Neural Magic DeepSparse 1.6 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 250.61 |================ Neural Magic DeepSparse 1.6 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 325.30 |================ Neural Magic DeepSparse 1.6 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 181.79 |================ Neural Magic DeepSparse 1.6 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 2218.22 |=============== Neural Magic DeepSparse 1.6 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 1041.22 |=============== Neural Magic DeepSparse 1.6 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 316.59 |================ Neural Magic DeepSparse 1.6 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 157.31 |================ Neural Magic DeepSparse 1.6 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 2788.65 |=============== Neural Magic DeepSparse 1.6 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 1354.91 |=============== DeepSpeech 0.6 Acceleration: CPU Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 378.78 |================ R Benchmark Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 0.6143 |================ RNNoise 2020-06-28 Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 36.44 |================= 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: KNN CAD Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 1009.02 |=============== Numenta Anomaly Benchmark 1.1 Detector: Relative Entropy Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 119.86 |================ Numenta Anomaly Benchmark 1.1 Detector: Windowed Gaussian Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 57.32 |================= Numenta Anomaly Benchmark 1.1 Detector: Earthgecko Skyline Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 953.65 |================ Numenta Anomaly Benchmark 1.1 Detector: Bayesian Changepoint Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 325.85 |================ Numenta Anomaly Benchmark 1.1 Detector: Contextual Anomaly Detector OSE Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 272.34 |================ Mlpack Benchmark Benchmark: scikit_ica Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 223.37 |================ Mlpack Benchmark Benchmark: scikit_qda Seconds < Lower Is Better Mlpack Benchmark Benchmark: scikit_svm Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 44.60 |================= Mlpack Benchmark Benchmark: scikit_linearridgeregression Seconds < Lower Is Better Scikit-Learn 1.2.2 Benchmark: GLM Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 1877.54 |=============== Scikit-Learn 1.2.2 Benchmark: SAGA Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 1919.81 |=============== Scikit-Learn 1.2.2 Benchmark: Tree Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 103.79 |================ Scikit-Learn 1.2.2 Benchmark: Lasso Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 1312.06 |=============== Scikit-Learn 1.2.2 Benchmark: Glmnet Seconds < Lower Is Better Scikit-Learn 1.2.2 Benchmark: Sparsify Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 226.79 |================ Scikit-Learn 1.2.2 Benchmark: Plot Ward Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 202.93 |================ Scikit-Learn 1.2.2 Benchmark: MNIST Dataset Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 177.39 |================ Scikit-Learn 1.2.2 Benchmark: Plot Neighbors Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 599.88 |================ Scikit-Learn 1.2.2 Benchmark: SGD Regression Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 358.67 |================ Scikit-Learn 1.2.2 Benchmark: SGDOneClassSVM Seconds < Lower Is Better Scikit-Learn 1.2.2 Benchmark: Plot Lasso Path Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 835.04 |================ Scikit-Learn 1.2.2 Benchmark: Isolation Forest Seconds < Lower Is Better Scikit-Learn 1.2.2 Benchmark: Plot Fast KMeans Seconds < Lower Is Better Scikit-Learn 1.2.2 Benchmark: Text Vectorizers Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 171.50 |================ Scikit-Learn 1.2.2 Benchmark: Plot Hierarchical Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 722.27 |================ Scikit-Learn 1.2.2 Benchmark: Plot OMP vs. LARS Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 355.35 |================ Scikit-Learn 1.2.2 Benchmark: Feature Expansions Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 491.63 |================ Scikit-Learn 1.2.2 Benchmark: LocalOutlierFactor Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 559.54 |================ Scikit-Learn 1.2.2 Benchmark: TSNE MNIST Dataset Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 1425.79 |=============== Scikit-Learn 1.2.2 Benchmark: Isotonic / Logistic Seconds < Lower Is Better Scikit-Learn 1.2.2 Benchmark: Plot Incremental PCA Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 110.29 |================ Scikit-Learn 1.2.2 Benchmark: Hist Gradient Boosting Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 414.92 |================ Scikit-Learn 1.2.2 Benchmark: Plot Parallel Pairwise Seconds < Lower Is Better Scikit-Learn 1.2.2 Benchmark: Isotonic / Pathological Seconds < Lower Is Better Scikit-Learn 1.2.2 Benchmark: RCV1 Logreg Convergencet Seconds < Lower Is Better Scikit-Learn 1.2.2 Benchmark: Sample Without Replacement Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 338.63 |================ Scikit-Learn 1.2.2 Benchmark: Covertype Dataset Benchmark Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 965.03 |================ Scikit-Learn 1.2.2 Benchmark: Hist Gradient Boosting Adult Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 202.00 |================ Scikit-Learn 1.2.2 Benchmark: Isotonic / Perturbed Logarithm Seconds < Lower Is Better Scikit-Learn 1.2.2 Benchmark: Hist Gradient Boosting Threading Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 838.41 |================ Scikit-Learn 1.2.2 Benchmark: Plot Singular Value Decomposition Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 692.64 |================ Scikit-Learn 1.2.2 Benchmark: Hist Gradient Boosting Higgs Boson Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 309.51 |================ Scikit-Learn 1.2.2 Benchmark: 20 Newsgroups / Logistic Regression Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 126.69 |================ Scikit-Learn 1.2.2 Benchmark: Plot Polynomial Kernel Approximation Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 761.96 |================ Scikit-Learn 1.2.2 Benchmark: Plot Non-Negative Matrix Factorization Seconds < Lower Is Better Scikit-Learn 1.2.2 Benchmark: Hist Gradient Boosting Categorical Only Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 61.35 |================= Scikit-Learn 1.2.2 Benchmark: Kernel PCA Solvers / Time vs. N Samples Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 720.17 |================ Scikit-Learn 1.2.2 Benchmark: Kernel PCA Solvers / Time vs. N Components Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 329.19 |================ Scikit-Learn 1.2.2 Benchmark: Sparse Random Projections / 100 Iterations Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 8668.53 |=============== Whisper.cpp 1.4 Model: ggml-base.en - Input: 2016 State of the Union Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 2498.67 |=============== Whisper.cpp 1.4 Model: ggml-small.en - Input: 2016 State of the Union Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 8252.81 |=============== Whisper.cpp 1.4 Model: ggml-medium.en - Input: 2016 State of the Union Seconds < Lower Is Better llvmpipe - AMD A8-9600 RADEON R7 10 COMPUTE CORES 4C . 29217.40 |==============