onnx runtime 1.14 amd ryzen 7900 AMD Ryzen 9 7900 12-Core testing with a Gigabyte B650M DS3H (F4h BIOS) and Gigabyte AMD Raphael 512MB on Ubuntu 22.10 via the Phoronix Test Suite. a: Processor: AMD Ryzen 9 7900 12-Core @ 3.70GHz (12 Cores / 24 Threads), Motherboard: Gigabyte B650M DS3H (F4h BIOS), Chipset: AMD Device 14d8, Memory: 32GB, Disk: 1000GB Sabrent Rocket 4.0 Plus, Graphics: Gigabyte AMD Raphael 512MB (2200/2400MHz), Audio: AMD Rembrandt Radeon HD Audio, Monitor: ASUS VP28U, Network: Realtek RTL8125 2.5GbE OS: Ubuntu 22.10, Kernel: 6.2.0-060200rc5daily20230129-generic (x86_64), Desktop: GNOME Shell 43.0, Display Server: X Server 1.21.1.4 + Wayland, OpenGL: 4.6 Mesa 23.0.0-devel (git-e20564c 2022-12-12 kinetic-oibaf-ppa) (LLVM 15.0.5 DRM 3.49), Vulkan: 1.3.235, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 3840x2160 b: Processor: AMD Ryzen 9 7900 12-Core @ 3.70GHz (12 Cores / 24 Threads), Motherboard: Gigabyte B650M DS3H (F4h BIOS), Chipset: AMD Device 14d8, Memory: 32GB, Disk: 1000GB Sabrent Rocket 4.0 Plus, Graphics: Gigabyte AMD Raphael 512MB (2200/2400MHz), Audio: AMD Rembrandt Radeon HD Audio, Monitor: ASUS VP28U, Network: Realtek RTL8125 2.5GbE OS: Ubuntu 22.10, Kernel: 6.2.0-060200rc5daily20230129-generic (x86_64), Desktop: GNOME Shell 43.0, Display Server: X Server 1.21.1.4 + Wayland, OpenGL: 4.6 Mesa 23.0.0-devel (git-e20564c 2022-12-12 kinetic-oibaf-ppa) (LLVM 15.0.5 DRM 3.49), Vulkan: 1.3.235, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 3840x2160 c: Processor: AMD Ryzen 9 7900 12-Core @ 3.70GHz (12 Cores / 24 Threads), Motherboard: Gigabyte B650M DS3H (F4h BIOS), Chipset: AMD Device 14d8, Memory: 32GB, Disk: 1000GB Sabrent Rocket 4.0 Plus, Graphics: Gigabyte AMD Raphael 512MB (2200/2400MHz), Audio: AMD Rembrandt Radeon HD Audio, Monitor: ASUS VP28U, Network: Realtek RTL8125 2.5GbE OS: Ubuntu 22.10, Kernel: 6.2.0-060200rc5daily20230129-generic (x86_64), Desktop: GNOME Shell 43.0, Display Server: X Server 1.21.1.4 + Wayland, OpenGL: 4.6 Mesa 23.0.0-devel (git-e20564c 2022-12-12 kinetic-oibaf-ppa) (LLVM 15.0.5 DRM 3.49), Vulkan: 1.3.235, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 3840x2160 ONNX Runtime 1.14 Model: GPT-2 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 117.62 |================================================================== b . 119.31 |=================================================================== c . 117.99 |================================================================== ONNX Runtime 1.14 Model: GPT-2 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 139.85 |=================================================================== b . 140.46 |=================================================================== c . 140.87 |=================================================================== ONNX Runtime 1.14 Model: yolov4 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 7.89231 |================================================================== b . 7.85662 |================================================================== c . 7.88522 |================================================================== ONNX Runtime 1.14 Model: yolov4 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 9.78495 |=========================================================== b . 10.70550 |================================================================= c . 10.36520 |=============================================================== ONNX Runtime 1.14 Model: bertsquad-12 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 12.72 |==================================================================== b . 12.65 |==================================================================== c . 12.57 |=================================================================== ONNX Runtime 1.14 Model: bertsquad-12 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 16.31 |============================================================= b . 18.27 |==================================================================== c . 18.06 |=================================================================== ONNX Runtime 1.14 Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 747.70 |================================================================== b . 756.21 |=================================================================== c . 747.94 |================================================================== ONNX Runtime 1.14 Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 939.15 |============================================================= b . 1014.19 |================================================================== c . 1015.49 |================================================================== ONNX Runtime 1.14 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 1.44749 |================================================================= b . 1.42497 |================================================================ c . 1.46501 |================================================================== ONNX Runtime 1.14 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 2.44468 |============================================================== b . 2.54412 |================================================================ c . 2.61293 |================================================================== ONNX Runtime 1.14 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 28.55 |==================================================================== b . 28.01 |=================================================================== c . 28.48 |==================================================================== ONNX Runtime 1.14 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 39.10 |=================================================================== b . 39.80 |==================================================================== c . 35.37 |============================================================ ONNX Runtime 1.14 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 342.11 |=================================================================== b . 343.33 |=================================================================== c . 339.56 |================================================================== ONNX Runtime 1.14 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 388.92 |=================================================================== b . 387.84 |=================================================================== c . 358.94 |============================================================== ONNX Runtime 1.14 Model: super-resolution-10 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 104.95 |=================================================================== b . 103.98 |================================================================== c . 105.14 |=================================================================== ONNX Runtime 1.14 Model: super-resolution-10 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 136.49 |======================================================== b . 162.64 |=================================================================== c . 117.15 |================================================ ONNX Runtime 1.14 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 46.16 |================================================================ b . 48.78 |==================================================================== c . 45.55 |=============================================================== ONNX Runtime 1.14 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 56.48 |==================================================================== b . 48.32 |========================================================== c . 48.24 |========================================================== ONNX Runtime 1.14 Model: GPT-2 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 8.49794 |================================================================== b . 8.37831 |================================================================= c . 8.47144 |================================================================== ONNX Runtime 1.14 Model: GPT-2 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 7.14936 |================================================================== b . 7.11735 |================================================================== c . 7.09665 |================================================================== ONNX Runtime 1.14 Model: yolov4 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 126.71 |=================================================================== b . 127.28 |=================================================================== c . 126.82 |=================================================================== ONNX Runtime 1.14 Model: yolov4 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 103.94 |=================================================================== b . 93.41 |============================================================ c . 96.47 |============================================================== ONNX Runtime 1.14 Model: bertsquad-12 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 78.60 |=================================================================== b . 79.03 |==================================================================== c . 79.57 |==================================================================== ONNX Runtime 1.14 Model: bertsquad-12 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 62.78 |==================================================================== b . 54.74 |=========================================================== c . 55.37 |============================================================ ONNX Runtime 1.14 Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 1.33643 |================================================================== b . 1.32121 |================================================================= c . 1.33605 |================================================================== ONNX Runtime 1.14 Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 1.072977 |================================================================= b . 0.985640 |============================================================ c . 0.984378 |============================================================ ONNX Runtime 1.14 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 690.92 |================================================================== b . 701.77 |=================================================================== c . 682.59 |================================================================= ONNX Runtime 1.14 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 417.42 |=================================================================== b . 393.06 |=============================================================== c . 382.71 |============================================================= ONNX Runtime 1.14 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 35.02 |=================================================================== b . 35.70 |==================================================================== c . 35.11 |=================================================================== ONNX Runtime 1.14 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 26.01 |=============================================================== b . 25.12 |============================================================ c . 28.27 |==================================================================== ONNX Runtime 1.14 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 2.92224 |================================================================== b . 2.91195 |================================================================= c . 2.94418 |================================================================== ONNX Runtime 1.14 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 2.58475 |============================================================= b . 2.57769 |============================================================= c . 2.78527 |================================================================== ONNX Runtime 1.14 Model: super-resolution-10 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 9.52804 |================================================================= b . 9.61619 |================================================================== c . 9.51022 |================================================================= ONNX Runtime 1.14 Model: super-resolution-10 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 7.57906 |=========================================================== b . 6.14844 |================================================ c . 8.53572 |================================================================== ONNX Runtime 1.14 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 21.67 |=================================================================== b . 20.50 |================================================================ c . 21.95 |==================================================================== ONNX Runtime 1.14 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 17.96 |=========================================================== b . 20.70 |==================================================================== c . 20.73 |====================================================================