new we AMD Ryzen 9 5900HX testing with a ASUS G513QY v1.0 (G513QY.318 BIOS) and ASUS AMD Cezanne 512MB on Ubuntu 22.10 via the Phoronix Test Suite. a: Processor: AMD Ryzen 9 5900HX @ 3.30GHz (8 Cores / 16 Threads), Motherboard: ASUS G513QY v1.0 (G513QY.318 BIOS), Chipset: AMD Renoir/Cezanne, Memory: 16GB, Disk: 512GB SAMSUNG MZVLQ512HBLU-00B00, Graphics: ASUS AMD Cezanne 512MB (2500/1000MHz), Audio: AMD Navi 21/23, Monitor: LQ156M1JW25, Network: Realtek RTL8111/8168/8411 + MEDIATEK MT7921 802.11ax PCI OS: Ubuntu 22.10, Kernel: 5.19.0-43-generic (x86_64), Desktop: GNOME Shell 43.0, Display Server: X Server 1.21.1.4 + Wayland, OpenGL: 4.6 Mesa 22.2.5 (LLVM 15.0.2 DRM 3.47), Vulkan: 1.3.224, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 1920x1080 b: Processor: AMD Ryzen 9 5900HX @ 3.30GHz (8 Cores / 16 Threads), Motherboard: ASUS G513QY v1.0 (G513QY.318 BIOS), Chipset: AMD Renoir/Cezanne, Memory: 16GB, Disk: 512GB SAMSUNG MZVLQ512HBLU-00B00, Graphics: ASUS AMD Cezanne 512MB, Audio: AMD Navi 21/23, Monitor: LQ156M1JW25, Network: Realtek RTL8111/8168/8411 + MEDIATEK MT7921 802.11ax PCI OS: Ubuntu 22.10, Kernel: 5.19.0-43-generic (x86_64), Desktop: GNOME Shell 43.0, Display Server: X Server 1.21.1.4 + Wayland, OpenGL: 4.6 Mesa 22.2.5 (LLVM 15.0.2 DRM 3.47), Vulkan: 1.3.224, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 1920x1080 c: Processor: AMD Ryzen 9 5900HX @ 3.30GHz (8 Cores / 16 Threads), Motherboard: ASUS G513QY v1.0 (G513QY.318 BIOS), Chipset: AMD Renoir/Cezanne, Memory: 16GB, Disk: 512GB SAMSUNG MZVLQ512HBLU-00B00, Graphics: ASUS AMD Cezanne 512MB (2500/1000MHz), Audio: AMD Navi 21/23, Monitor: LQ156M1JW25, Network: Realtek RTL8111/8168/8411 + MEDIATEK MT7921 802.11ax PCI OS: Ubuntu 22.10, Kernel: 5.19.0-43-generic (x86_64), Desktop: GNOME Shell 43.0, Display Server: X Server 1.21.1.4 + Wayland, OpenGL: 4.6 Mesa 22.2.5 (LLVM 15.0.2 DRM 3.47), Vulkan: 1.3.224, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 1920x1080 dav1d 1.2.1 Video Input: Chimera 1080p FPS > Higher Is Better a . 500.06 |=================================================================== b . 472.50 |=============================================================== c . 471.89 |=============================================================== dav1d 1.2.1 Video Input: Chimera 1080p 10-bit FPS > Higher Is Better a . 319.65 |=================================================================== b . 316.35 |================================================================== c . 311.92 |================================================================= Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 8.4260 |=================================================================== b . 8.3232 |================================================================== c . 8.3119 |================================================================== Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 118.67 |================================================================== b . 120.13 |=================================================================== c . 120.29 |=================================================================== Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 37.10 |==================================================================== b . 36.64 |=================================================================== c . 36.99 |==================================================================== Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 107.80 |================================================================== b . 109.11 |=================================================================== c . 108.10 |================================================================== Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 12.84 |=================================================================== b . 12.99 |==================================================================== c . 12.96 |==================================================================== Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 77.82 |==================================================================== b . 76.92 |=================================================================== c . 77.10 |=================================================================== Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 34.18 |==================================================================== b . 34.14 |==================================================================== c . 33.82 |=================================================================== Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 29.24 |=================================================================== b . 29.29 |=================================================================== c . 29.56 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 60.17 |=================================================================== b . 60.70 |==================================================================== c . 60.45 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 66.47 |==================================================================== b . 65.88 |=================================================================== c . 66.16 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 61.19 |=================================================================== b . 61.52 |==================================================================== c . 61.68 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 65.36 |==================================================================== b . 65.01 |==================================================================== c . 64.84 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 128.69 |=================================================================== b . 128.08 |=================================================================== c . 128.78 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 31.08 |==================================================================== b . 31.23 |==================================================================== c . 31.06 |==================================================================== Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 83.45 |==================================================================== b . 83.91 |==================================================================== c . 83.47 |==================================================================== Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 47.92 |==================================================================== b . 47.66 |==================================================================== c . 47.90 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 18.22 |==================================================================== b . 18.15 |==================================================================== c . 18.18 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 54.86 |==================================================================== b . 55.07 |==================================================================== c . 54.98 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 6.2943 |=================================================================== b . 6.3179 |=================================================================== c . 6.3091 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 158.86 |=================================================================== b . 158.27 |=================================================================== c . 158.49 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 214.56 |=================================================================== b . 214.52 |=================================================================== c . 215.32 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 6.6588 |=================================================================== b . 6.6656 |=================================================================== c . 6.6825 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 600.70 |=================================================================== b . 600.08 |=================================================================== c . 598.57 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 18.64 |==================================================================== b . 18.63 |==================================================================== c . 18.57 |==================================================================== dav1d 1.2.1 Video Input: Summer Nature 4K FPS > Higher Is Better a . 136.41 |=================================================================== b . 136.00 |=================================================================== c . 136.02 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 53.32 |==================================================================== b . 53.26 |==================================================================== c . 53.41 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 18.75 |==================================================================== b . 18.77 |==================================================================== c . 18.72 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 25.54 |==================================================================== b . 25.47 |==================================================================== c . 25.51 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 39.15 |==================================================================== b . 39.26 |==================================================================== c . 39.19 |==================================================================== dav1d 1.2.1 Video Input: Summer Nature 1080p FPS > Higher Is Better a . 693.94 |=================================================================== b . 692.20 |=================================================================== c . 692.80 |=================================================================== Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 8.6348 |=================================================================== b . 8.6172 |=================================================================== c . 8.6145 |=================================================================== Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 463.22 |=================================================================== b . 464.16 |=================================================================== c . 464.31 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 6.6571 |=================================================================== b . 6.6707 |=================================================================== c . 6.6559 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 600.85 |=================================================================== b . 599.62 |=================================================================== c . 600.95 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 20.01 |==================================================================== b . 20.04 |==================================================================== c . 20.00 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 49.96 |==================================================================== b . 49.88 |==================================================================== c . 49.99 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 6.3094 |=================================================================== b . 6.3166 |=================================================================== c . 6.3057 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 158.48 |=================================================================== b . 158.31 |=================================================================== c . 158.58 |===================================================================