aaa AMD Ryzen 7 5800X3D 8-Core testing with a ASUS ROG CROSSHAIR VIII HERO (4201 BIOS) and Intel DG2 8GB on Ubuntu 22.04 via the Phoronix Test Suite. A: Processor: AMD Ryzen 7 5800X3D 8-Core @ 3.40GHz (8 Cores / 16 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (4201 BIOS), Chipset: AMD Starship/Matisse, Memory: 32GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0 + 2000GB, Graphics: Intel DG2 8GB (2400MHz), Audio: Intel Device 4f90, Monitor: ASUS MG28U, Network: Realtek RTL8125 2.5GbE + Intel I211 OS: Ubuntu 22.04, Kernel: 5.17.0-1019-oem (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.2.0-devel (git-44289c46d9), Vulkan: 1.3.219, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160 B: Processor: AMD Ryzen 7 5800X3D 8-Core @ 3.40GHz (8 Cores / 16 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (4201 BIOS), Chipset: AMD Starship/Matisse, Memory: 32GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0 + 2000GB, Graphics: Intel DG2 8GB (2400MHz), Audio: Intel Device 4f90, Monitor: ASUS MG28U, Network: Realtek RTL8125 2.5GbE + Intel I211 OS: Ubuntu 22.04, Kernel: 5.17.0-1019-oem (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.2.0-devel (git-44289c46d9), Vulkan: 1.3.219, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160 C: Processor: AMD Ryzen 7 5800X3D 8-Core @ 3.40GHz (8 Cores / 16 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (4201 BIOS), Chipset: AMD Starship/Matisse, Memory: 32GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0 + 2000GB, Graphics: Intel DG2 8GB (2400MHz), Audio: Intel Device 4f90, Monitor: ASUS MG28U, Network: Realtek RTL8125 2.5GbE + Intel I211 OS: Ubuntu 22.04, Kernel: 5.17.0-1019-oem (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.2.0-devel (git-44289c46d9), Vulkan: 1.3.219, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160 D: Processor: AMD Ryzen 7 5800X3D 8-Core @ 3.40GHz (8 Cores / 16 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (4201 BIOS), Chipset: AMD Starship/Matisse, Memory: 32GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0 + 2000GB, Graphics: Intel DG2 8GB (2400MHz), Audio: Intel Device 4f90, Monitor: ASUS MG28U, Network: Realtek RTL8125 2.5GbE + Intel I211 OS: Ubuntu 22.04, Kernel: 5.17.0-1019-oem (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.2.0-devel (git-44289c46d9), Vulkan: 1.3.219, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160 Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better A . 8.3037 |=================================================================== B . 8.3029 |=================================================================== C . 8.2832 |=================================================================== D . 8.3062 |=================================================================== Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream items/sec > Higher Is Better A . 8.0337 |=================================================================== B . 8.0756 |=================================================================== C . 8.0410 |=================================================================== D . 8.0672 |=================================================================== Neural Magic DeepSparse 1.1 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better A . 34.14 |==================================================================== B . 34.13 |==================================================================== C . 34.25 |==================================================================== D . 34.25 |==================================================================== Neural Magic DeepSparse 1.1 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better A . 30.09 |==================================================================== B . 30.13 |==================================================================== C . 30.04 |==================================================================== D . 29.92 |==================================================================== Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better A . 45.82 |=================================================================== B . 46.17 |==================================================================== C . 45.60 |=================================================================== D . 45.81 |=================================================================== Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-Stream items/sec > Higher Is Better A . 44.87 |==================================================================== B . 44.80 |==================================================================== C . 44.79 |==================================================================== D . 44.85 |==================================================================== Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better A . 94.40 |==================================================================== B . 94.81 |==================================================================== C . 94.80 |==================================================================== D . 94.59 |==================================================================== Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream items/sec > Higher Is Better A . 84.39 |==================================================================== B . 84.42 |==================================================================== C . 84.36 |==================================================================== D . 84.67 |==================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better A . 71.41 |==================================================================== B . 71.71 |==================================================================== C . 71.11 |=================================================================== D . 71.51 |==================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream items/sec > Higher Is Better A . 60.45 |==================================================================== B . 60.25 |==================================================================== C . 60.35 |==================================================================== D . 60.14 |==================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better A . 35.21 |==================================================================== B . 35.19 |==================================================================== C . 35.22 |==================================================================== D . 35.15 |==================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better A . 30.06 |==================================================================== B . 30.06 |==================================================================== C . 29.99 |==================================================================== D . 30.01 |==================================================================== Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better A . 8.3000 |=================================================================== B . 8.2893 |=================================================================== C . 8.2834 |=================================================================== D . 8.2812 |=================================================================== Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better A . 8.0471 |=================================================================== B . 8.0297 |=================================================================== C . 8.0528 |=================================================================== D . 8.0718 |=================================================================== JPEG XL libjxl 0.7 Input: PNG - Quality: 80 MP/s > Higher Is Better A . 10.08 |==================================================================== B . 10.06 |==================================================================== C . 10.02 |==================================================================== D . 10.02 |==================================================================== JPEG XL libjxl 0.7 Input: PNG - Quality: 90 MP/s > Higher Is Better A . 9.91 |===================================================================== B . 9.90 |===================================================================== C . 9.86 |===================================================================== D . 9.87 |===================================================================== JPEG XL libjxl 0.7 Input: JPEG - Quality: 80 MP/s > Higher Is Better A . 9.74 |===================================================================== B . 9.75 |===================================================================== C . 9.67 |==================================================================== D . 9.73 |===================================================================== JPEG XL libjxl 0.7 Input: JPEG - Quality: 90 MP/s > Higher Is Better A . 9.58 |===================================================================== B . 9.58 |===================================================================== C . 9.55 |===================================================================== D . 9.61 |===================================================================== JPEG XL libjxl 0.7 Input: PNG - Quality: 100 MP/s > Higher Is Better A . 0.81 |===================================================================== B . 0.81 |===================================================================== C . 0.81 |===================================================================== D . 0.80 |==================================================================== JPEG XL libjxl 0.7 Input: JPEG - Quality: 100 MP/s > Higher Is Better A . 0.77 |==================================================================== B . 0.78 |===================================================================== C . 0.75 |================================================================== D . 0.75 |================================================================== JPEG XL Decoding libjxl 0.7 CPU Threads: 1 MP/s > Higher Is Better A . 53.00 |==================================================================== B . 52.01 |=================================================================== C . 51.39 |================================================================== D . 51.97 |=================================================================== JPEG XL Decoding libjxl 0.7 CPU Threads: All MP/s > Higher Is Better A . 277.10 |=================================================================== B . 274.67 |================================================================== C . 271.63 |================================================================== D . 268.33 |================================================================= Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better A . 481.69 |=================================================================== B . 481.74 |=================================================================== C . 479.36 |=================================================================== D . 479.29 |=================================================================== Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better A . 124.47 |=================================================================== B . 123.82 |=================================================================== C . 124.36 |=================================================================== D . 123.95 |=================================================================== Neural Magic DeepSparse 1.1 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better A . 117.13 |=================================================================== B . 117.17 |=================================================================== C . 116.77 |=================================================================== D . 116.77 |=================================================================== Neural Magic DeepSparse 1.1 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better A . 33.23 |==================================================================== B . 33.19 |==================================================================== C . 33.28 |==================================================================== D . 33.41 |==================================================================== Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better A . 87.28 |==================================================================== B . 86.61 |=================================================================== C . 87.69 |==================================================================== D . 87.28 |==================================================================== Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better A . 22.28 |==================================================================== B . 22.31 |==================================================================== C . 22.32 |==================================================================== D . 22.29 |==================================================================== Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better A . 42.35 |==================================================================== B . 42.17 |==================================================================== C . 42.18 |==================================================================== D . 42.27 |==================================================================== Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better A . 11.84 |==================================================================== B . 11.84 |==================================================================== C . 11.85 |==================================================================== D . 11.81 |==================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better A . 56.00 |==================================================================== B . 55.77 |=================================================================== C . 56.24 |==================================================================== D . 55.92 |==================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better A . 16.54 |==================================================================== B . 16.59 |==================================================================== C . 16.56 |==================================================================== D . 16.62 |==================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better A . 113.58 |=================================================================== B . 113.64 |=================================================================== C . 113.54 |=================================================================== D . 113.79 |=================================================================== Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better A . 33.27 |==================================================================== B . 33.26 |==================================================================== C . 33.34 |==================================================================== D . 33.32 |==================================================================== Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better A . 481.76 |=================================================================== B . 482.53 |=================================================================== C . 481.99 |=================================================================== D . 483.00 |=================================================================== Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better A . 124.26 |=================================================================== B . 124.53 |=================================================================== C . 124.18 |=================================================================== D . 123.88 |=================================================================== OpenRadioss 2022.10.13 Model: Bumper Beam Seconds < Lower Is Better A . 145.34 |=================================================================== B . 144.48 |=================================================================== C . 145.25 |=================================================================== D . 144.57 |=================================================================== OpenRadioss 2022.10.13 Model: Cell Phone Drop Test Seconds < Lower Is Better A . 100.58 |================================================================== B . 100.31 |================================================================== C . 101.57 |=================================================================== D . 100.53 |================================================================== OpenRadioss 2022.10.13 Model: Bird Strike on Windshield Seconds < Lower Is Better A . 280.19 |=================================================================== B . 278.67 |=================================================================== C . 278.67 |=================================================================== D . 280.12 |=================================================================== OpenRadioss 2022.10.13 Model: Rubber O-Ring Seal Installation Seconds < Lower Is Better A . 145.95 |================================================================== B . 146.28 |================================================================== C . 146.07 |================================================================== D . 147.86 |=================================================================== OpenRadioss 2022.10.13 Model: INIVOL and Fluid Structure Interaction Drop Container Seconds < Lower Is Better A . 571.14 |================================================================== B . 571.21 |================================================================== C . 571.27 |================================================================== D . 577.26 |=================================================================== libavif avifenc 0.11 Encoder Speed: 0 Seconds < Lower Is Better A . 152.37 |=================================================================== B . 152.67 |=================================================================== C . 152.32 |=================================================================== D . 152.47 |=================================================================== libavif avifenc 0.11 Encoder Speed: 2 Seconds < Lower Is Better A . 72.04 |==================================================================== B . 71.69 |==================================================================== C . 71.87 |==================================================================== D . 72.19 |==================================================================== libavif avifenc 0.11 Encoder Speed: 6 Seconds < Lower Is Better A . 7.168 |=================================================================== B . 7.151 |=================================================================== C . 7.170 |=================================================================== D . 7.240 |==================================================================== libavif avifenc 0.11 Encoder Speed: 6, Lossless Seconds < Lower Is Better A . 10.78 |=================================================================== B . 10.83 |=================================================================== C . 10.91 |==================================================================== D . 10.93 |==================================================================== libavif avifenc 0.11 Encoder Speed: 10, Lossless Seconds < Lower Is Better A . 5.302 |==================================================================== B . 5.317 |==================================================================== C . 5.289 |=================================================================== D . 5.335 |====================================================================