2022-12-22-0913 2 x Intel Xeon Silver 4208 testing with a Dell 06WXJT (2.13.3 BIOS) and Matrox G200eW3 on Ubuntu 20.04 via the Phoronix Test Suite. 2022-12-22 09:13: Processor: 2 x Intel Xeon Silver 4208 @ 3.20GHz (16 Cores / 32 Threads), Motherboard: Dell 06WXJT (2.13.3 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 64GB, Disk: 6000GB PERC H750 Adp + 299GB PERC H750 Adp, Graphics: Matrox G200eW3, Network: 4 x Broadcom NetXtreme BCM5720 2-port PCIe OS: Ubuntu 20.04, Kernel: 5.4.0-135-generic (x86_64), Desktop: GNOME Shell 3.36.9, Display Server: X Server, Compiler: GCC 9.4.0, File-System: ext4, Screen Resolution: 1024x768 Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better 2022-12-22 09:13 . 5.2342 |==================================================== Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream items/sec > Higher Is Better 2022-12-22 09:13 . 2.5743 |==================================================== Neural Magic DeepSparse 1.1 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better 2022-12-22 09:13 . 32.13 |===================================================== Neural Magic DeepSparse 1.1 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better 2022-12-22 09:13 . 15.44 |===================================================== Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better 2022-12-22 09:13 . 39.99 |===================================================== Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-Stream items/sec > Higher Is Better 2022-12-22 09:13 . 17.59 |===================================================== Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better 2022-12-22 09:13 . 101.39 |==================================================== Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream items/sec > Higher Is Better 2022-12-22 09:13 . 44.84 |===================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better 2022-12-22 09:13 . 51.70 |===================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream items/sec > Higher Is Better 2022-12-22 09:13 . 22.86 |===================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better 2022-12-22 09:13 . 26.12 |===================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better 2022-12-22 09:13 . 11.45 |===================================================== Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better 2022-12-22 09:13 . 5.2337 |==================================================== Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better 2022-12-22 09:13 . 2.5776 |==================================================== Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better 2022-12-22 09:13 . 1518.09 |=================================================== Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better 2022-12-22 09:13 . 388.44 |==================================================== Neural Magic DeepSparse 1.1 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better 2022-12-22 09:13 . 248.12 |==================================================== Neural Magic DeepSparse 1.1 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better 2022-12-22 09:13 . 64.74 |===================================================== Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better 2022-12-22 09:13 . 199.58 |==================================================== Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better 2022-12-22 09:13 . 56.82 |===================================================== Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better 2022-12-22 09:13 . 78.83 |===================================================== Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better 2022-12-22 09:13 . 22.29 |===================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better 2022-12-22 09:13 . 154.60 |==================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better 2022-12-22 09:13 . 43.72 |===================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better 2022-12-22 09:13 . 305.92 |==================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better 2022-12-22 09:13 . 87.32 |===================================================== Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better 2022-12-22 09:13 . 1515.44 |=================================================== Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better 2022-12-22 09:13 . 387.96 |====================================================