AMD Ryzen 9 7950X 16-Core testing with a ASUS ProArt X670E-CREATOR WIFI (1710 BIOS) and Zotac NVIDIA GeForce RTX 4070 Ti 12GB on Pop 22.04 via the Phoronix Test Suite.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2403157-NE-240313POP28
24.03.13.Pop.2204.ML.test1
AMD Ryzen 9 7950X 16-Core testing with a ASUS ProArt X670E-CREATOR WIFI (1710 BIOS) and Zotac NVIDIA GeForce RTX 4070 Ti 12GB on Pop 22.04 via the Phoronix Test Suite.
,,"Initial test 1 No water cool"
Processor,,AMD Ryzen 9 7950X 16-Core @ 5.88GHz (16 Cores / 32 Threads)
Motherboard,,ASUS ProArt X670E-CREATOR WIFI (1710 BIOS)
Chipset,,AMD Device 14d8
Memory,,2 x 16 GB DDR5-4800MT/s G Skill F5-6000J3636F16G
Disk,,1000GB PNY CS2130 1TB SSD
Graphics,,Zotac NVIDIA GeForce RTX 4070 Ti 12GB
Audio,,NVIDIA Device 22bc
Monitor,,2 x DELL 2001FP
Network,,Intel I225-V + Aquantia AQtion AQC113CS NBase-T/IEEE + MEDIATEK MT7922 802.11ax PCI
OS,,Pop 22.04
Kernel,,6.6.10-76060610-generic (x86_64)
Desktop,,GNOME Shell 42.5
Display Server,,X Server 1.21.1.4
Display Driver,,NVIDIA 550.54.14
OpenGL,,4.6.0
OpenCL,,OpenCL 3.0 CUDA 12.4.89
Vulkan,,1.3.277
Compiler,,GCC 11.4.0
File-System,,ext4
Screen Resolution,,3200x1200
,,"Initial test 1 No water cool"
"TensorFlow - Device: GPU - Batch Size: 256 - Model: VGG-16 (images/sec)",HIB,1.77
"TensorFlow - Device: GPU - Batch Size: 256 - Model: ResNet-50 (images/sec)",HIB,5.56
"TensorFlow - Device: GPU - Batch Size: 64 - Model: VGG-16 (images/sec)",HIB,1.73
"TensorFlow - Device: GPU - Batch Size: 512 - Model: GoogLeNet (images/sec)",HIB,15.90
"TensorFlow - Device: GPU - Batch Size: 32 - Model: VGG-16 (images/sec)",HIB,1.72
"TensorFlow - Device: GPU - Batch Size: 256 - Model: GoogLeNet (images/sec)",HIB,15.76
"SHOC Scalable HeterOgeneous Computing - Target: OpenCL - Benchmark: Max SP Flops (GFLOPS)",HIB,43074.9
"TensorFlow - Device: GPU - Batch Size: 512 - Model: AlexNet (images/sec)",HIB,35.93
"TensorFlow - Device: CPU - Batch Size: 256 - Model: VGG-16 (images/sec)",HIB,18.12
"TensorFlow - Device: GPU - Batch Size: 64 - Model: ResNet-50 (images/sec)",HIB,5.51
"TensorFlow - Device: GPU - Batch Size: 16 - Model: VGG-16 (images/sec)",HIB,1.70
"TensorFlow - Device: GPU - Batch Size: 256 - Model: AlexNet (images/sec)",HIB,35.82
"TensorFlow - Device: CPU - Batch Size: 256 - Model: ResNet-50 (images/sec)",HIB,36.15
"TensorFlow - Device: GPU - Batch Size: 32 - Model: ResNet-50 (images/sec)",HIB,5.49
"TensorFlow - Device: CPU - Batch Size: 512 - Model: GoogLeNet (images/sec)",HIB,115.70
"TensorFlow - Device: GPU - Batch Size: 64 - Model: GoogLeNet (images/sec)",HIB,15.61
"TensorFlow - Device: CPU - Batch Size: 64 - Model: VGG-16 (images/sec)",HIB,17.44
"TensorFlow - Device: GPU - Batch Size: 16 - Model: ResNet-50 (images/sec)",HIB,5.42
"Numenta Anomaly Benchmark - Detector: KNN CAD (sec)",LIB,105.001
"AI Benchmark Alpha - Device AI Score (Score)",HIB,6473
"AI Benchmark Alpha - Device Training Score (Score)",HIB,3573
"AI Benchmark Alpha - Device Inference Score (Score)",HIB,2900
"TensorFlow - Device: CPU - Batch Size: 256 - Model: GoogLeNet (images/sec)",HIB,116.33
"TensorFlow - Device: GPU - Batch Size: 32 - Model: GoogLeNet (images/sec)",HIB,15.45
"TensorFlow - Device: CPU - Batch Size: 32 - Model: VGG-16 (images/sec)",HIB,16.89
"TensorFlow - Device: GPU - Batch Size: 64 - Model: AlexNet (images/sec)",HIB,34.84
"TensorFlow - Device: CPU - Batch Size: 64 - Model: ResNet-50 (images/sec)",HIB,36.36
"PyTorch - Device: CPU - Batch Size: 512 - Model: Efficientnet_v2_l (batches/sec)",HIB,10.44
"PyTorch - Device: CPU - Batch Size: 16 - Model: Efficientnet_v2_l (batches/sec)",HIB,10.46
"PyTorch - Device: CPU - Batch Size: 32 - Model: Efficientnet_v2_l (batches/sec)",HIB,10.59
"PyTorch - Device: CPU - Batch Size: 256 - Model: Efficientnet_v2_l (batches/sec)",HIB,10.63
"PyTorch - Device: CPU - Batch Size: 64 - Model: Efficientnet_v2_l (batches/sec)",HIB,10.58
"OpenCV - Test: DNN - Deep Neural Network (ms)",LIB,30277
"OpenVINO - Model: Face Detection FP16 - Device: CPU (ms)",LIB,625.66
"OpenVINO - Model: Face Detection FP16 - Device: CPU (FPS)",HIB,12.75
"TensorFlow - Device: CPU - Batch Size: 512 - Model: AlexNet (images/sec)",HIB,392.16
"TNN - Target: CPU - Model: DenseNet (ms)",LIB,2005.606
"Mobile Neural Network - Model: inception-v3 (ms)",LIB,23.421
"Mobile Neural Network - Model: mobilenet-v1-1.0 (ms)",LIB,2.456
"Mobile Neural Network - Model: MobileNetV2_224 (ms)",LIB,3.410
"Mobile Neural Network - Model: SqueezeNetV1.0 (ms)",LIB,4.141
"Mobile Neural Network - Model: resnet-v2-50 (ms)",LIB,12.123
"Mobile Neural Network - Model: squeezenetv1.1 (ms)",LIB,2.542
"Mobile Neural Network - Model: mobilenetV3 (ms)",LIB,1.638
"Mobile Neural Network - Model: nasnet (ms)",LIB,11.300
"TensorFlow - Device: GPU - Batch Size: 16 - Model: GoogLeNet (images/sec)",HIB,15.10
"Numpy Benchmark - (Score)",HIB,704.52
"TensorFlow - Device: CPU - Batch Size: 16 - Model: VGG-16 (images/sec)",HIB,16.09
"TensorFlow - Device: GPU - Batch Size: 512 - Model: VGG-16 (images/sec)",HIB,
"PyTorch - Device: CPU - Batch Size: 256 - Model: ResNet-152 (batches/sec)",HIB,17.69
"PyTorch - Device: CPU - Batch Size: 64 - Model: ResNet-152 (batches/sec)",HIB,17.66
"PyTorch - Device: CPU - Batch Size: 512 - Model: ResNet-152 (batches/sec)",HIB,17.59
"PyTorch - Device: CPU - Batch Size: 32 - Model: ResNet-152 (batches/sec)",HIB,17.64
"PyTorch - Device: CPU - Batch Size: 16 - Model: ResNet-152 (batches/sec)",HIB,17.66
"TensorFlow - Device: GPU - Batch Size: 32 - Model: AlexNet (images/sec)",HIB,33.39
"TensorFlow - Device: CPU - Batch Size: 32 - Model: ResNet-50 (images/sec)",HIB,36.74
"PyTorch - Device: CPU - Batch Size: 1 - Model: Efficientnet_v2_l (batches/sec)",HIB,14.14
"TensorFlow - Device: GPU - Batch Size: 1 - Model: VGG-16 (images/sec)",HIB,1.46
"oneDNN - Harness: Recurrent Neural Network Training - Engine: CPU (ms)",LIB,1452.96
"oneDNN - Harness: Recurrent Neural Network Inference - Engine: CPU (ms)",LIB,747.499
"TensorFlow - Device: CPU - Batch Size: 256 - Model: AlexNet (images/sec)",HIB,388.40
"Neural Magic DeepSparse - Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,303.3330
"Neural Magic DeepSparse - Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,26.3345
"Neural Magic DeepSparse - Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream (ms/batch)",LIB,54.0028
"Neural Magic DeepSparse - Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream (items/sec)",HIB,18.5143
"Mlpack Benchmark - Benchmark: scikit_qda (sec)",LIB,34.07
"OpenVINO - Model: Face Detection FP16-INT8 - Device: CPU (ms)",LIB,323.12
"OpenVINO - Model: Face Detection FP16-INT8 - Device: CPU (FPS)",HIB,24.71
"NCNN - Target: CPU - Model: FastestDet (ms)",LIB,4.69
"NCNN - Target: CPU - Model: vision_transformer (ms)",LIB,37.92
"NCNN - Target: CPU - Model: regnety_400m (ms)",LIB,9.87
"NCNN - Target: CPU - Model: squeezenet_ssd (ms)",LIB,8.49
"NCNN - Target: CPU - Model: yolov4-tiny (ms)",LIB,16.28
"NCNN - Target: CPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3 (ms)",LIB,9.80
"NCNN - Target: CPU - Model: resnet50 (ms)",LIB,13.48
"NCNN - Target: CPU - Model: alexnet (ms)",LIB,5.52
"NCNN - Target: CPU - Model: resnet18 (ms)",LIB,6.62
"NCNN - Target: CPU - Model: vgg16 (ms)",LIB,32.60
"NCNN - Target: CPU - Model: googlenet (ms)",LIB,9.56
"NCNN - Target: CPU - Model: blazeface (ms)",LIB,1.60
"NCNN - Target: CPU - Model: efficientnet-b0 (ms)",LIB,4.50
"NCNN - Target: CPU - Model: mnasnet (ms)",LIB,3.46
"NCNN - Target: CPU - Model: shufflenet-v2 (ms)",LIB,3.93
"NCNN - Target: CPU-v3-v3 - Model: mobilenet-v3 (ms)",LIB,3.69
"NCNN - Target: CPU-v2-v2 - Model: mobilenet-v2 (ms)",LIB,3.65
"NCNN - Target: CPU - Model: mobilenet (ms)",LIB,9.80
"TensorFlow - Device: CPU - Batch Size: 64 - Model: GoogLeNet (images/sec)",HIB,119.04
"NCNN - Target: Vulkan GPU - Model: FastestDet (ms)",LIB,4.30
"NCNN - Target: Vulkan GPU - Model: vision_transformer (ms)",LIB,38.12
"NCNN - Target: Vulkan GPU - Model: regnety_400m (ms)",LIB,9.83
"NCNN - Target: Vulkan GPU - Model: squeezenet_ssd (ms)",LIB,8.38
"NCNN - Target: Vulkan GPU - Model: yolov4-tiny (ms)",LIB,15.84
"NCNN - Target: Vulkan GPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3 (ms)",LIB,9.36
"NCNN - Target: Vulkan GPU - Model: resnet50 (ms)",LIB,13.16
"NCNN - Target: Vulkan GPU - Model: alexnet (ms)",LIB,5.67
"NCNN - Target: Vulkan GPU - Model: resnet18 (ms)",LIB,6.65
"NCNN - Target: Vulkan GPU - Model: vgg16 (ms)",LIB,32.31
"NCNN - Target: Vulkan GPU - Model: googlenet (ms)",LIB,9.69
"NCNN - Target: Vulkan GPU - Model: blazeface (ms)",LIB,1.62
"NCNN - Target: Vulkan GPU - Model: efficientnet-b0 (ms)",LIB,4.57
"NCNN - Target: Vulkan GPU - Model: mnasnet (ms)",LIB,3.45
"NCNN - Target: Vulkan GPU - Model: shufflenet-v2 (ms)",LIB,3.90
"NCNN - Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 (ms)",LIB,3.72
"NCNN - Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 (ms)",LIB,3.69
"NCNN - Target: Vulkan GPU - Model: mobilenet (ms)",LIB,9.36
"OpenVINO - Model: Machine Translation EN To DE FP16 - Device: CPU (ms)",LIB,65.52
"OpenVINO - Model: Machine Translation EN To DE FP16 - Device: CPU (FPS)",HIB,121.96
"OpenVINO - Model: Person Detection FP16 - Device: CPU (ms)",LIB,104.27
"OpenVINO - Model: Person Detection FP16 - Device: CPU (FPS)",HIB,76.65
"OpenVINO - Model: Person Detection FP32 - Device: CPU (ms)",LIB,103.09
"OpenVINO - Model: Person Detection FP32 - Device: CPU (FPS)",HIB,77.54
"TensorFlow Lite - Model: Inception V4 (us)",LIB,21139.4
"OpenVINO - Model: Noise Suppression Poconet-Like FP16 - Device: CPU (ms)",LIB,11.33
"OpenVINO - Model: Noise Suppression Poconet-Like FP16 - Device: CPU (FPS)",HIB,1386.93
"TensorFlow Lite - Model: Inception ResNet V2 (us)",LIB,21857.0
"OpenVINO - Model: Road Segmentation ADAS FP16-INT8 - Device: CPU (ms)",LIB,17.81
"OpenVINO - Model: Road Segmentation ADAS FP16-INT8 - Device: CPU (FPS)",HIB,448.28
"TensorFlow Lite - Model: NASNet Mobile (us)",LIB,10099.3
"TensorFlow Lite - Model: Mobilenet Float (us)",LIB,1214.11
"TensorFlow Lite - Model: SqueezeNet (us)",LIB,1716.04
"OpenVINO - Model: Person Vehicle Bike Detection FP16 - Device: CPU (ms)",LIB,5.53
"OpenVINO - Model: Person Vehicle Bike Detection FP16 - Device: CPU (FPS)",HIB,1442.07
"TensorFlow Lite - Model: Mobilenet Quant (us)",LIB,1861.53
"OpenVINO - Model: Road Segmentation ADAS FP16 - Device: CPU (ms)",LIB,29.32
"OpenVINO - Model: Road Segmentation ADAS FP16 - Device: CPU (FPS)",HIB,272.36
"OpenVINO - Model: Person Re-Identification Retail FP16 - Device: CPU (ms)",LIB,4.46
"OpenVINO - Model: Person Re-Identification Retail FP16 - Device: CPU (FPS)",HIB,1785.48
"OpenVINO - Model: Handwritten English Recognition FP16-INT8 - Device: CPU (ms)",LIB,21.88
"OpenVINO - Model: Handwritten English Recognition FP16-INT8 - Device: CPU (FPS)",HIB,729.99
"OpenVINO - Model: Vehicle Detection FP16-INT8 - Device: CPU (ms)",LIB,5.18
"OpenVINO - Model: Vehicle Detection FP16-INT8 - Device: CPU (FPS)",HIB,1538.27
"OpenVINO - Model: Face Detection Retail FP16-INT8 - Device: CPU (ms)",LIB,3.61
"OpenVINO - Model: Face Detection Retail FP16-INT8 - Device: CPU (FPS)",HIB,4335.66
"OpenVINO - Model: Handwritten English Recognition FP16 - Device: CPU (ms)",LIB,23.94
"OpenVINO - Model: Handwritten English Recognition FP16 - Device: CPU (FPS)",HIB,667.29
"OpenVINO - Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU (ms)",LIB,0.31
"OpenVINO - Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU (FPS)",HIB,46025.94
"OpenVINO - Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU (ms)",LIB,0.45
"OpenVINO - Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU (FPS)",HIB,32402.42
"OpenVINO - Model: Vehicle Detection FP16 - Device: CPU (ms)",LIB,12.91
"OpenVINO - Model: Vehicle Detection FP16 - Device: CPU (FPS)",HIB,618.41
"OpenVINO - Model: Weld Porosity Detection FP16 - Device: CPU (ms)",LIB,12.61
"OpenVINO - Model: Weld Porosity Detection FP16 - Device: CPU (FPS)",HIB,1266.85
"OpenVINO - Model: Face Detection Retail FP16 - Device: CPU (ms)",LIB,2.53
"OpenVINO - Model: Face Detection Retail FP16 - Device: CPU (FPS)",HIB,3062.63
"OpenVINO - Model: Weld Porosity Detection FP16-INT8 - Device: CPU (ms)",LIB,6.44
"OpenVINO - Model: Weld Porosity Detection FP16-INT8 - Device: CPU (FPS)",HIB,2470.86
"TensorFlow - Device: GPU - Batch Size: 512 - Model: ResNet-50 (images/sec)",HIB,
"TensorFlow - Device: GPU - Batch Size: 16 - Model: AlexNet (images/sec)",HIB,30.67
"Numenta Anomaly Benchmark - Detector: Earthgecko Skyline (sec)",LIB,55.566
"TensorFlow - Device: CPU - Batch Size: 16 - Model: ResNet-50 (images/sec)",HIB,36.43
"oneDNN - Harness: IP Shapes 1D - Engine: CPU (ms)",LIB,1.17351
"PyTorch - Device: CPU - Batch Size: 1 - Model: ResNet-152 (batches/sec)",HIB,25.64
"PyTorch - Device: CPU - Batch Size: 512 - Model: ResNet-50 (batches/sec)",HIB,42.91
"PyTorch - Device: CPU - Batch Size: 256 - Model: ResNet-50 (batches/sec)",HIB,43.49
"PyTorch - Device: CPU - Batch Size: 64 - Model: ResNet-50 (batches/sec)",HIB,43.35
"PyTorch - Device: CPU - Batch Size: 32 - Model: ResNet-50 (batches/sec)",HIB,44.08
"PyTorch - Device: CPU - Batch Size: 16 - Model: ResNet-50 (batches/sec)",HIB,44.08
"Neural Magic DeepSparse - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,397.5797
"Neural Magic DeepSparse - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,20.0852
"Neural Magic DeepSparse - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream (ms/batch)",LIB,3.5898
"Neural Magic DeepSparse - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream (items/sec)",HIB,278.3122
"spaCy - Model: en_core_web_trf (tokens/sec)",HIB,2415
"spaCy - Model: en_core_web_lg (tokens/sec)",HIB,18557
"Neural Magic DeepSparse - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,8.9714
"Neural Magic DeepSparse - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,890.1894
"Neural Magic DeepSparse - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,400.3931
"Neural Magic DeepSparse - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,19.9101
"Neural Magic DeepSparse - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,19.1612
"Neural Magic DeepSparse - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,417.1723
"Neural Magic DeepSparse - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream (ms/batch)",LIB,10.1862
"Neural Magic DeepSparse - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream (items/sec)",HIB,98.0758
"Neural Magic DeepSparse - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream (ms/batch)",LIB,57.6038
"Neural Magic DeepSparse - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream (items/sec)",HIB,17.3572
"Neural Magic DeepSparse - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream (ms/batch)",LIB,57.8304
"Neural Magic DeepSparse - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream (items/sec)",HIB,17.2893
"Neural Magic DeepSparse - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,236.3144
"Neural Magic DeepSparse - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,33.8095
"Neural Magic DeepSparse - Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,43.7801
"Neural Magic DeepSparse - Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,182.6225
"Neural Magic DeepSparse - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream (ms/batch)",LIB,36.3089
"Neural Magic DeepSparse - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream (items/sec)",HIB,27.5303
"Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream (ms/batch)",LIB,10.8023
"Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream (items/sec)",HIB,92.5135
"Neural Magic DeepSparse - Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream (ms/batch)",LIB,10.3590
"Neural Magic DeepSparse - Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream (items/sec)",HIB,96.4692
"Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,69.4409
"Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,115.1124
"Neural Magic DeepSparse - Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,30.2415
"Neural Magic DeepSparse - Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,264.3773
"Neural Magic DeepSparse - Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,30.1491
"Neural Magic DeepSparse - Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,265.2018
"Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,72.0412
"Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,110.9914
"Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream (ms/batch)",LIB,11.0556
"Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream (items/sec)",HIB,90.3558
"Neural Magic DeepSparse - Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream (ms/batch)",LIB,5.7601
"Neural Magic DeepSparse - Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream (items/sec)",HIB,173.3786
"Neural Magic DeepSparse - Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,3.9240
"Neural Magic DeepSparse - Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,2031.8775
"Neural Magic DeepSparse - Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream (ms/batch)",LIB,5.7436
"Neural Magic DeepSparse - Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream (items/sec)",HIB,173.8986
"DeepSpeech - Acceleration: CPU (sec)",LIB,47.03514
"Neural Magic DeepSparse - Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream (ms/batch)",LIB,0.8214
"Neural Magic DeepSparse - Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream (items/sec)",HIB,1214.2399
"TensorFlow - Device: CPU - Batch Size: 512 - Model: VGG-16 (images/sec)",HIB,
"oneDNN - Harness: Deconvolution Batch shapes_1d - Engine: CPU (ms)",LIB,3.06179
"PyTorch - Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: Efficientnet_v2_l (batches/sec)",HIB,69.80
"PyTorch - Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: Efficientnet_v2_l (batches/sec)",HIB,69.97
"PyTorch - Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: Efficientnet_v2_l (batches/sec)",HIB,70.52
"PyTorch - Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: Efficientnet_v2_l (batches/sec)",HIB,70.63
"PyTorch - Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: Efficientnet_v2_l (batches/sec)",HIB,70.81
"Mlpack Benchmark - Benchmark: scikit_ica (sec)",LIB,30.12
"TensorFlow - Device: CPU - Batch Size: 32 - Model: GoogLeNet (images/sec)",HIB,122.39
"TensorFlow - Device: CPU - Batch Size: 512 - Model: ResNet-50 (images/sec)",HIB,
"Mlpack Benchmark - Benchmark: scikit_linearridgeregression (sec)",LIB,1.03
"TensorFlow - Device: GPU - Batch Size: 1 - Model: ResNet-50 (images/sec)",HIB,4.25
"Numenta Anomaly Benchmark - Detector: Contextual Anomaly Detector OSE (sec)",LIB,25.400
"TensorFlow - Device: CPU - Batch Size: 1 - Model: VGG-16 (images/sec)",HIB,4.74
"Numenta Anomaly Benchmark - Detector: Windowed Gaussian (sec)",LIB,4.984
"TensorFlow - Device: CPU - Batch Size: 64 - Model: AlexNet (images/sec)",HIB,305.81
"PyTorch - Device: CPU - Batch Size: 1 - Model: ResNet-50 (batches/sec)",HIB,64.81
"PyTorch - Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: ResNet-152 (batches/sec)",HIB,138.62
"PyTorch - Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: ResNet-152 (batches/sec)",HIB,138.78
"PyTorch - Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: ResNet-152 (batches/sec)",HIB,139.41
"PyTorch - Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: ResNet-152 (batches/sec)",HIB,138.72
"PyTorch - Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: ResNet-152 (batches/sec)",HIB,140.41
"PyTorch - Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: Efficientnet_v2_l (batches/sec)",HIB,71.98
"Mlpack Benchmark - Benchmark: scikit_svm (sec)",LIB,15.12
"TensorFlow - Device: CPU - Batch Size: 32 - Model: AlexNet (images/sec)",HIB,224.56
"TensorFlow - Device: CPU - Batch Size: 16 - Model: GoogLeNet (images/sec)",HIB,125.83
"RNNoise - (sec)",LIB,13.707
"TensorFlow - Device: CPU - Batch Size: 16 - Model: AlexNet (images/sec)",HIB,148.72
"Numenta Anomaly Benchmark - Detector: Bayesian Changepoint (sec)",LIB,13.213
"TNN - Target: CPU - Model: MobileNet v2 (ms)",LIB,183.277
"TNN - Target: CPU - Model: SqueezeNet v1.1 (ms)",LIB,179.679
"TensorFlow - Device: CPU - Batch Size: 1 - Model: ResNet-50 (images/sec)",HIB,12.70
"TensorFlow - Device: GPU - Batch Size: 1 - Model: GoogLeNet (images/sec)",HIB,12.36
"Numenta Anomaly Benchmark - Detector: Relative Entropy (sec)",LIB,8.281
"PyTorch - Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: ResNet-152 (batches/sec)",HIB,137.39
"TensorFlow - Device: GPU - Batch Size: 1 - Model: AlexNet (images/sec)",HIB,12.58
"TensorFlow - Device: CPU - Batch Size: 1 - Model: AlexNet (images/sec)",HIB,13.00
"oneDNN - Harness: IP Shapes 3D - Engine: CPU (ms)",LIB,4.42170
"PyTorch - Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: ResNet-50 (batches/sec)",HIB,380.34
"PyTorch - Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: ResNet-50 (batches/sec)",HIB,379.98
"PyTorch - Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: ResNet-50 (batches/sec)",HIB,380.67
"PyTorch - Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: ResNet-50 (batches/sec)",HIB,380.74
"PyTorch - Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: ResNet-50 (batches/sec)",HIB,383.56
"SHOC Scalable HeterOgeneous Computing - Target: OpenCL - Benchmark: Texture Read Bandwidth (GB/s)",HIB,2985.70
"oneDNN - Harness: Convolution Batch Shapes Auto - Engine: CPU (ms)",LIB,7.16631
"SHOC Scalable HeterOgeneous Computing - Target: OpenCL - Benchmark: GEMM SGEMM_N (GFLOPS)",HIB,13212.0
"PyTorch - Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: ResNet-50 (batches/sec)",HIB,387.06
"Whisper.cpp - Model: ggml-medium.en - Input: 2016 State of the Union (sec)",LIB,0.86615
"TensorFlow - Device: CPU - Batch Size: 1 - Model: GoogLeNet (images/sec)",HIB,47.21
"SHOC Scalable HeterOgeneous Computing - Target: OpenCL - Benchmark: Bus Speed Readback (GB/s)",HIB,27.0723
"oneDNN - Harness: Deconvolution Batch shapes_3d - Engine: CPU (ms)",LIB,2.56519
"TNN - Target: CPU - Model: SqueezeNet v2 (ms)",LIB,42.215
"SHOC Scalable HeterOgeneous Computing - Target: OpenCL - Benchmark: S3D (GFLOPS)",HIB,299.468
"Whisper.cpp - Model: ggml-small.en - Input: 2016 State of the Union (sec)",LIB,0.34881
"SHOC Scalable HeterOgeneous Computing - Target: OpenCL - Benchmark: FFT SP (GFLOPS)",HIB,1292.53
"SHOC Scalable HeterOgeneous Computing - Target: OpenCL - Benchmark: Triad (GB/s)",HIB,25.4632
"SHOC Scalable HeterOgeneous Computing - Target: OpenCL - Benchmark: Reduction (GB/s)",HIB,388.934
"SHOC Scalable HeterOgeneous Computing - Target: OpenCL - Benchmark: Bus Speed Download (GB/s)",HIB,26.8275
"Whisper.cpp - Model: ggml-base.en - Input: 2016 State of the Union (sec)",LIB,0.15350
"Scikit-Learn - Benchmark: Tree (sec)",LIB,
"SHOC Scalable HeterOgeneous Computing - Target: OpenCL - Benchmark: MD5 Hash (GHash/s)",HIB,47.8988
"PlaidML - FP16: No - Mode: Inference - Network: VGG16 - Device: CPU (Examples/sec)",HIB,
"Scikit-Learn - Benchmark: Plot Non-Negative Matrix Factorization (sec)",LIB,
"PlaidML - FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU (Examples/sec)",HIB,
"Scikit-Learn - Benchmark: Kernel PCA Solvers / Time vs. N Samples (sec)",LIB,
"Scikit-Learn - Benchmark: Text Vectorizers (sec)",LIB,
"Scikit-Learn - Benchmark: Kernel PCA Solvers / Time vs. N Components (sec)",LIB,
"Scikit-Learn - Benchmark: Sample Without Replacement (sec)",LIB,
"Scikit-Learn - Benchmark: RCV1 Logreg Convergencet (sec)",LIB,
"Scikit-Learn - Benchmark: Plot Parallel Pairwise (sec)",LIB,
"Scikit-Learn - Benchmark: Hist Gradient Boosting (sec)",LIB,
"Scikit-Learn - Benchmark: SGD Regression (sec)",LIB,
"Scikit-Learn - Benchmark: Plot Neighbors (sec)",LIB,
"Scikit-Learn - Benchmark: Feature Expansions (sec)",LIB,
"Scikit-Learn - Benchmark: Plot Incremental PCA (sec)",LIB,
"Scikit-Learn - Benchmark: Isolation Forest (sec)",LIB,
"Scikit-Learn - Benchmark: LocalOutlierFactor (sec)",LIB,
"Scikit-Learn - Benchmark: Hist Gradient Boosting Adult (sec)",LIB,
"Scikit-Learn - Benchmark: Hist Gradient Boosting Higgs Boson (sec)",LIB,
"Scikit-Learn - Benchmark: GLM (sec)",LIB,
"Scikit-Learn - Benchmark: Sparse Random Projections / 100 Iterations (sec)",LIB,
"Scikit-Learn - Benchmark: Hist Gradient Boosting Categorical Only (sec)",LIB,
"Scikit-Learn - Benchmark: Plot Polynomial Kernel Approximation (sec)",LIB,
"Scikit-Learn - Benchmark: 20 Newsgroups / Logistic Regression (sec)",LIB,
"Scikit-Learn - Benchmark: Hist Gradient Boosting Threading (sec)",LIB,
"Scikit-Learn - Benchmark: Covertype Dataset Benchmark (sec)",LIB,
"Scikit-Learn - Benchmark: Isotonic / Logistic (sec)",LIB,
"Scikit-Learn - Benchmark: Plot OMP vs. LARS (sec)",LIB,
"Scikit-Learn - Benchmark: Plot Hierarchical (sec)",LIB,
"Scikit-Learn - Benchmark: Plot Fast KMeans (sec)",LIB,
"Scikit-Learn - Benchmark: Plot Lasso Path (sec)",LIB,
"Scikit-Learn - Benchmark: MNIST Dataset (sec)",LIB,
"Scikit-Learn - Benchmark: Sparsify (sec)",LIB,
"Scikit-Learn - Benchmark: Glmnet (sec)",LIB,
"Scikit-Learn - Benchmark: Lasso (sec)",LIB,
"Scikit-Learn - Benchmark: SAGA (sec)",LIB,
"Scikit-Learn - Benchmark: Isotonic / Perturbed Logarithm (sec)",LIB,
"Scikit-Learn - Benchmark: Isotonic / Pathological (sec)",LIB,
"Scikit-Learn - Benchmark: TSNE MNIST Dataset (sec)",LIB,
"Scikit-Learn - Benchmark: Plot Ward (sec)",LIB,
"Scikit-Learn - Benchmark: Plot Singular Value Decomposition (sec)",LIB,
"Scikit-Learn - Benchmark: SGDOneClassSVM (sec)",LIB,
"Llamafile - Test: mistral-7b-instruct-v0.2.Q8_0 - Acceleration: CPU (Tokens/sec)",HIB,
"Llamafile - Test: wizardcoder-python-34b-v1.0.Q6_K - Acceleration: CPU (Tokens/sec)",HIB,
"Llamafile - Test: llava-v1.5-7b-q4 - Acceleration: CPU (Tokens/sec)",HIB,
"Llama.cpp - Model: llama-2-70b-chat.Q5_0.gguf (Tokens/sec)",HIB,
"Llama.cpp - Model: llama-2-13b.Q4_0.gguf (Tokens/sec)",HIB,
"Llama.cpp - Model: llama-2-7b.Q4_0.gguf (Tokens/sec)",HIB,
"ONNX Runtime - Model: GPT-2 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,
"ONNX Runtime - Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,
"ONNX Runtime - Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,
"ONNX Runtime - Model: super-resolution-10 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,
"ONNX Runtime - Model: super-resolution-10 - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,
"ONNX Runtime - Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,
"ONNX Runtime - Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,
"ONNX Runtime - Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,
"ONNX Runtime - Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,
"ONNX Runtime - Model: fcn-resnet101-11 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,
"ONNX Runtime - Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,
"ONNX Runtime - Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,
"ONNX Runtime - Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,
"ONNX Runtime - Model: bertsquad-12 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,
"ONNX Runtime - Model: bertsquad-12 - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,
"ONNX Runtime - Model: T5 Encoder - Device: CPU - Executor: Standard (Inferences/sec)",HIB,
"ONNX Runtime - Model: T5 Encoder - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,
"ONNX Runtime - Model: yolov4 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,
"ONNX Runtime - Model: yolov4 - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,
"ONNX Runtime - Model: GPT-2 - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,
"Caffe - Model: GoogleNet - Acceleration: CPU - Iterations: 1000 (ms)",LIB,
"Caffe - Model: GoogleNet - Acceleration: CPU - Iterations: 200 (ms)",LIB,
"Caffe - Model: GoogleNet - Acceleration: CPU - Iterations: 100 (ms)",LIB,
"Caffe - Model: AlexNet - Acceleration: CPU - Iterations: 1000 (ms)",LIB,
"Caffe - Model: AlexNet - Acceleration: CPU - Iterations: 200 (ms)",LIB,
"Caffe - Model: AlexNet - Acceleration: CPU - Iterations: 100 (ms)",LIB,
"R Benchmark - (sec)",LIB,
"LeelaChessZero - Backend: BLAS (Nodes/s)",HIB,