3700x-deepsparse AMD Ryzen 7 3700X 8-Core testing with a ASUS PRIME B450M-A (3211 BIOS) and AMD Radeon RX 6600 8GB on Linuxmint 21.2 via the Phoronix Test Suite. Ryzen 7 3700X: Processor: AMD Ryzen 7 3700X 8-Core @ 3.60GHz (8 Cores / 16 Threads), Motherboard: ASUS PRIME B450M-A (3211 BIOS), Chipset: AMD Starship/Matisse, Memory: 32GB, Disk: 1000GB KINGSTON SA2000M81000G + 4001GB Western Digital WD40EZRZ-00G + 3001GB Western Digital WD30EZRX-00S + 480GB KINGSTON SA400S3, Graphics: AMD Radeon RX 6600 8GB (2750/875MHz), Audio: AMD Navi 21 HDMI Audio, Monitor: GM27-FQ ARGB, Network: Realtek RTL8111/8168/8411 OS: Linuxmint 21.2, Kernel: 6.2.0-34-generic (x86_64), Desktop: MATE 1.26.0, Display Server: X Server 1.21.1.4, OpenGL: 4.6 Mesa 23.0.4-0ubuntu1~22.04.1 (LLVM 15.0.7 DRM 3.49), Vulkan: 1.3.238, Compiler: GCC 11.4.0, File-System: ext4, Screen Resolution: 2560x1440 Neural Magic DeepSparse 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better Ryzen 7 3700X . 7.3683 |======================================================= Neural Magic DeepSparse 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better Ryzen 7 3700X . 540.91 |======================================================= Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better Ryzen 7 3700X . 157.89 |======================================================= Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better Ryzen 7 3700X . 25.31 |======================================================== Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better Ryzen 7 3700X . 67.78 |======================================================== Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better Ryzen 7 3700X . 58.99 |======================================================== Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better Ryzen 7 3700X . 23.71 |======================================================== Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better Ryzen 7 3700X . 168.55 |======================================================= Neural Magic DeepSparse 1.5 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better Ryzen 7 3700X . 84.73 |======================================================== Neural Magic DeepSparse 1.5 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better Ryzen 7 3700X . 47.19 |======================================================== Neural Magic DeepSparse 1.5 Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better Ryzen 7 3700X . 501.49 |======================================================= Neural Magic DeepSparse 1.5 Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better Ryzen 7 3700X . 7.9595 |======================================================= Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better Ryzen 7 3700X . 38.86 |======================================================== Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better Ryzen 7 3700X . 102.91 |======================================================= Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better Ryzen 7 3700X . 84.99 |======================================================== Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better Ryzen 7 3700X . 47.05 |======================================================== Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better Ryzen 7 3700X . 39.53 |======================================================== Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better Ryzen 7 3700X . 101.16 |======================================================= Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better Ryzen 7 3700X . 61.71 |======================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better Ryzen 7 3700X . 64.78 |======================================================== Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better Ryzen 7 3700X . 8.5741 |======================================================= Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better Ryzen 7 3700X . 465.39 |======================================================= Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better Ryzen 7 3700X . 84.53 |======================================================== Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better Ryzen 7 3700X . 47.30 |======================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better Ryzen 7 3700X . 31.20 |======================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better Ryzen 7 3700X . 128.15 |======================================================= Neural Magic DeepSparse 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better Ryzen 7 3700X . 7.4076 |======================================================= Neural Magic DeepSparse 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better Ryzen 7 3700X . 539.31 |=======================================================