zz AMD Ryzen 7 5700G testing with a ASUS TUF GAMING B550M-PLUS (WI-FI) (2423 BIOS) and ASUS AMD Cezanne 512MB on Ubuntu 21.10 via the Phoronix Test Suite. A: Processor: AMD Ryzen 7 5700G @ 3.80GHz (8 Cores / 16 Threads), Motherboard: ASUS TUF GAMING B550M-PLUS (WI-FI) (2423 BIOS), Chipset: AMD Renoir/Cezanne, Memory: 16GB, Disk: 1000GB Samsung SSD 980 PRO 1TB, Graphics: ASUS AMD Cezanne 512MB (2000/1800MHz), Audio: AMD Renoir Radeon HD Audio, Monitor: MX279, Network: Realtek RTL8125 2.5GbE + Intel Wi-Fi 6 AX200 OS: Ubuntu 21.10, Kernel: 5.16.0-051600rc8daily20220108-generic (x86_64), Desktop: GNOME Shell 40.5, Display Server: X Server 1.20.11 + Wayland, OpenGL: 4.6 Mesa 22.0.0-devel (git-9cb9101 2022-01-08 impish-oibaf-ppa) (LLVM 13.0.0 DRM 3.44), Vulkan: 1.2.199, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 1920x1080 B: Processor: AMD Ryzen 7 5700G @ 3.80GHz (8 Cores / 16 Threads), Motherboard: ASUS TUF GAMING B550M-PLUS (WI-FI) (2423 BIOS), Chipset: AMD Renoir/Cezanne, Memory: 16GB, Disk: 1000GB Samsung SSD 980 PRO 1TB, Graphics: ASUS AMD Cezanne 512MB (2000/1800MHz), Audio: AMD Renoir Radeon HD Audio, Monitor: MX279, Network: Realtek RTL8125 2.5GbE + Intel Wi-Fi 6 AX200 OS: Ubuntu 21.10, Kernel: 5.16.0-051600rc8daily20220108-generic (x86_64), Desktop: GNOME Shell 40.5, Display Server: X Server 1.20.11 + Wayland, OpenGL: 4.6 Mesa 22.0.0-devel (git-9cb9101 2022-01-08 impish-oibaf-ppa) (LLVM 13.0.0 DRM 3.44), Vulkan: 1.2.199, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 1920x1080 C: Processor: AMD Ryzen 7 5700G @ 3.80GHz (8 Cores / 16 Threads), Motherboard: ASUS TUF GAMING B550M-PLUS (WI-FI) (2423 BIOS), Chipset: AMD Renoir/Cezanne, Memory: 16GB, Disk: 1000GB Samsung SSD 980 PRO 1TB, Graphics: ASUS AMD Cezanne 512MB (2000/1800MHz), Audio: AMD Renoir Radeon HD Audio, Monitor: MX279, Network: Realtek RTL8125 2.5GbE + Intel Wi-Fi 6 AX200 OS: Ubuntu 21.10, Kernel: 5.16.0-051600rc8daily20220108-generic (x86_64), Desktop: GNOME Shell 40.5, Display Server: X Server 1.20.11 + Wayland, OpenGL: 4.6 Mesa 22.0.0-devel (git-9cb9101 2022-01-08 impish-oibaf-ppa) (LLVM 13.0.0 DRM 3.44), Vulkan: 1.2.199, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 1920x1080 SVT-AV1 1.0 Encoder Mode: Preset 4 - Input: Bosphorus 4K Frames Per Second > Higher Is Better A . 1.981 |==================================================================== B . 1.984 |==================================================================== C . 1.978 |==================================================================== SVT-AV1 1.0 Encoder Mode: Preset 8 - Input: Bosphorus 4K Frames Per Second > Higher Is Better A . 26.39 |==================================================================== B . 26.32 |==================================================================== C . 26.25 |==================================================================== SVT-AV1 1.0 Encoder Mode: Preset 10 - Input: Bosphorus 4K Frames Per Second > Higher Is Better A . 65.14 |==================================================================== B . 64.92 |==================================================================== C . 65.19 |==================================================================== SVT-AV1 1.0 Encoder Mode: Preset 12 - Input: Bosphorus 4K Frames Per Second > Higher Is Better A . 89.67 |==================================================================== B . 86.97 |================================================================== C . 89.69 |==================================================================== SVT-AV1 1.0 Encoder Mode: Preset 4 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better A . 6.035 |=================================================================== B . 6.044 |=================================================================== C . 6.091 |==================================================================== SVT-AV1 1.0 Encoder Mode: Preset 8 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better A . 92.45 |=================================================================== B . 93.62 |==================================================================== C . 92.82 |=================================================================== SVT-AV1 1.0 Encoder Mode: Preset 10 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better A . 189.41 |=================================================================== B . 188.79 |=================================================================== C . 190.06 |=================================================================== SVT-AV1 1.0 Encoder Mode: Preset 12 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better A . 355.48 |=================================================================== B . 350.78 |================================================================== C . 349.10 |================================================================== libavif avifenc 0.10 Encoder Speed: 0 Seconds < Lower Is Better A . 158.84 |=================================================================== B . 158.88 |=================================================================== C . 158.15 |=================================================================== libavif avifenc 0.10 Encoder Speed: 2 Seconds < Lower Is Better A . 74.46 |==================================================================== B . 74.24 |==================================================================== C . 74.28 |==================================================================== libavif avifenc 0.10 Encoder Speed: 6 Seconds < Lower Is Better A . 10.15 |==================================================================== B . 10.17 |==================================================================== C . 10.22 |==================================================================== libavif avifenc 0.10 Encoder Speed: 6, Lossless Seconds < Lower Is Better A . 12.54 |==================================================================== B . 12.50 |==================================================================== C . 12.59 |==================================================================== libavif avifenc 0.10 Encoder Speed: 10, Lossless Seconds < Lower Is Better A . 5.733 |==================================================================== B . 5.590 |================================================================== C . 5.635 |=================================================================== oneDNN 2.6 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 3.98732 |================================================================= B . 4.05032 |================================================================== C . 4.07036 |================================================================== oneDNN 2.6 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 11.71 |=================================================================== B . 11.73 |==================================================================== C . 11.80 |==================================================================== oneDNN 2.6 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 1.39092 |================================================================== B . 1.39030 |================================================================== C . 1.39934 |================================================================== oneDNN 2.6 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 2.84523 |================================================================== B . 2.60928 |============================================================= C . 2.60520 |============================================================ oneDNN 2.6 Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 2.6 Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 22.35 |==================================================================== B . 22.40 |==================================================================== C . 22.45 |==================================================================== oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 8.14632 |================================================================ B . 8.36734 |================================================================== C . 8.25826 |================================================================= oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 7.03558 |================================================================= B . 7.02718 |================================================================= C . 7.12334 |================================================================== oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 23.47 |==================================================================== B . 23.56 |==================================================================== C . 23.46 |==================================================================== oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 1.95484 |================================================================== B . 1.95319 |================================================================== C . 1.95551 |================================================================== oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 2.91606 |================================================================ B . 3.01126 |================================================================== C . 2.86797 |=============================================================== oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 3583.10 |================================================================== B . 3580.17 |================================================================== C . 3585.22 |================================================================== oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 2213.99 |================================================================= B . 2219.82 |================================================================== C . 2232.66 |================================================================== oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 3580.24 |============================================================= B . 3577.41 |============================================================= C . 3850.32 |================================================================== oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 2210.71 |================================================================ B . 2214.51 |================================================================= C . 2265.57 |================================================================== oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 4.48476 |================================================================== B . 4.48147 |================================================================== C . 4.50371 |================================================================== oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 3584.64 |================================================================== B . 3577.26 |================================================================== C . 3591.14 |================================================================== oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 2213.88 |================================================================== B . 2225.46 |================================================================== C . 2214.16 |================================================================== oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 1.70968 |================================================================== B . 1.68982 |================================================================= C . 1.70049 |================================================================== oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better Java JMH Ops/s > Higher Is Better ONNX Runtime 1.11 Model: GPT-2 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better A . 6063 |================================================================ B . 6062 |================================================================ C . 6545 |===================================================================== ONNX Runtime 1.11 Model: yolov4 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better A . 299 |====================================================================== B . 298 |====================================================================== C . 299 |====================================================================== ONNX Runtime 1.11 Model: bertsquad-12 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better A . 496 |============================================ B . 495 |============================================ C . 788 |====================================================================== ONNX Runtime 1.11 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better A . 47 |======================================================================= B . 47 |======================================================================= C . 47 |======================================================================= ONNX Runtime 1.11 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better A . 1040 |==================================================================== B . 1036 |==================================================================== C . 1056 |===================================================================== ONNX Runtime 1.11 Model: super-resolution-10 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better A . 3273 |==================================================================== B . 3309 |===================================================================== C . 3263 |====================================================================