onednn onnx alderlake Intel Core i9-12900K testing with a ASUS ROG STRIX Z690-E GAMING WIFI (1003 BIOS) and Gigabyte AMD Radeon RX 6800 XT 16GB on Ubuntu 21.10 via the Phoronix Test Suite. A: Processor: Intel Core i9-12900K @ 5.20GHz (16 Cores / 24 Threads), Motherboard: ASUS ROG STRIX Z690-E GAMING WIFI (1003 BIOS), Chipset: Intel Device 7aa7, Memory: 32GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0 + 2000GB, Graphics: Gigabyte AMD Radeon RX 6800 XT 16GB (2575/1000MHz), Audio: Intel Device 7ad0, Monitor: ASUS VP28U, Network: Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411 OS: Ubuntu 21.10, Kernel: 5.17.0-phx (x86_64), Desktop: GNOME Shell 40.5, Display Server: X Server 1.20.13 + Wayland, OpenGL: 4.6 Mesa 22.1.0-devel (git-ae710f3 2022-03-26 impish-oibaf-ppa) (LLVM 13.0.1 DRM 3.46), Vulkan: 1.3.207, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160 B: Processor: Intel Core i9-12900K @ 5.20GHz (16 Cores / 24 Threads), Motherboard: ASUS ROG STRIX Z690-E GAMING WIFI (1003 BIOS), Chipset: Intel Device 7aa7, Memory: 32GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0 + 2000GB, Graphics: Gigabyte AMD Radeon RX 6800 XT 16GB (2575/1000MHz), Audio: Intel Device 7ad0, Monitor: ASUS VP28U, Network: Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411 OS: Ubuntu 21.10, Kernel: 5.17.0-phx (x86_64), Desktop: GNOME Shell 40.5, Display Server: X Server 1.20.13 + Wayland, OpenGL: 4.6 Mesa 22.1.0-devel (git-ae710f3 2022-03-26 impish-oibaf-ppa) (LLVM 13.0.1 DRM 3.46), Vulkan: 1.3.207, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160 C: Processor: Intel Core i9-12900K @ 5.20GHz (16 Cores / 24 Threads), Motherboard: ASUS ROG STRIX Z690-E GAMING WIFI (1003 BIOS), Chipset: Intel Device 7aa7, Memory: 32GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0 + 2000GB, Graphics: Gigabyte AMD Radeon RX 6800 XT 16GB (2575/1000MHz), Audio: Intel Device 7ad0, Monitor: ASUS VP28U, Network: Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411 OS: Ubuntu 21.10, Kernel: 5.17.0-phx (x86_64), Desktop: GNOME Shell 40.5, Display Server: X Server 1.20.13 + Wayland, OpenGL: 4.6 Mesa 22.1.0-devel (git-ae710f3 2022-03-26 impish-oibaf-ppa) (LLVM 13.0.1 DRM 3.46), Vulkan: 1.3.207, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160 D: Processor: Intel Core i9-12900K @ 5.20GHz (16 Cores / 24 Threads), Motherboard: ASUS ROG STRIX Z690-E GAMING WIFI (1003 BIOS), Chipset: Intel Device 7aa7, Memory: 32GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0 + 2000GB, Graphics: Gigabyte AMD Radeon RX 6800 XT 16GB (2575/1000MHz), Audio: Intel Device 7ad0, Monitor: ASUS VP28U, Network: Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411 OS: Ubuntu 21.10, Kernel: 5.17.0-phx (x86_64), Desktop: GNOME Shell 40.5, Display Server: X Server 1.20.13 + Wayland, OpenGL: 4.6 Mesa 22.1.0-devel (git-ae710f3 2022-03-26 impish-oibaf-ppa) (LLVM 13.0.1 DRM 3.46), Vulkan: 1.3.207, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160 ONNX Runtime 1.11 Model: GPT-2 - Device: CPU - Executor: Parallel Inferences Per Minute > Higher Is Better A . 7989 |==================================================================== B . 8110 |===================================================================== C . 8046 |==================================================================== D . 8095 |===================================================================== ONNX Runtime 1.11 Model: GPT-2 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better A . 11035 |=================================================================== B . 11077 |==================================================================== C . 11079 |==================================================================== D . 11123 |==================================================================== ONNX Runtime 1.11 Model: yolov4 - Device: CPU - Executor: Parallel Inferences Per Minute > Higher Is Better A . 628 |===================================================================== B . 632 |====================================================================== C . 631 |====================================================================== D . 633 |====================================================================== ONNX Runtime 1.11 Model: yolov4 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better A . 670 |====================================================================== B . 664 |===================================================================== C . 666 |====================================================================== D . 669 |====================================================================== ONNX Runtime 1.11 Model: bertsquad-12 - Device: CPU - Executor: Parallel Inferences Per Minute > Higher Is Better A . 925 |=================================================================== B . 937 |==================================================================== C . 933 |==================================================================== D . 964 |====================================================================== ONNX Runtime 1.11 Model: bertsquad-12 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better A . 931 |====================================================================== B . 916 |===================================================================== C . 918 |===================================================================== D . 926 |====================================================================== ONNX Runtime 1.11 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel Inferences Per Minute > Higher Is Better A . 111 |====================================================================== B . 111 |====================================================================== C . 111 |====================================================================== D . 111 |====================================================================== ONNX Runtime 1.11 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better A . 96 |======================================================================= B . 95 |====================================================================== C . 95 |====================================================================== D . 95 |====================================================================== ONNX Runtime 1.11 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel Inferences Per Minute > Higher Is Better A . 363 |====================================================================== B . 364 |====================================================================== C . 362 |====================================================================== D . 364 |====================================================================== ONNX Runtime 1.11 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better A . 1908 |===================================================================== B . 1913 |===================================================================== C . 1896 |==================================================================== D . 1893 |==================================================================== ONNX Runtime 1.11 Model: super-resolution-10 - Device: CPU - Executor: Parallel Inferences Per Minute > Higher Is Better A . 4518 |===================================================================== B . 4504 |===================================================================== C . 4444 |==================================================================== D . 4506 |===================================================================== ONNX Runtime 1.11 Model: super-resolution-10 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better A . 5332 |==================================================================== B . 5349 |===================================================================== C . 5328 |==================================================================== D . 5384 |===================================================================== oneDNN 2.6 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 2.63724 |================================================================== B . 2.65135 |================================================================== C . 2.63180 |================================================================== D . 2.63287 |================================================================== oneDNN 2.6 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 3.91213 |================================================================== B . 3.81887 |================================================================ C . 3.88487 |================================================================== D . 3.88717 |================================================================== oneDNN 2.6 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 1.08279 |================================================================== B . 1.05578 |================================================================ C . 1.05754 |================================================================ D . 1.05923 |================================================================= oneDNN 2.6 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 0.882082 |================================================================= B . 0.851627 |=============================================================== C . 0.881799 |================================================================= D . 0.885057 |================================================================= 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 . 5.90865 |================================================================== B . 5.90320 |================================================================== C . 5.90578 |================================================================== D . 5.90930 |================================================================== oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 8.27680 |================================================================= B . 8.38411 |================================================================== C . 8.21415 |================================================================= D . 8.05084 |=============================================================== oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 5.24536 |================================================================== B . 5.24601 |================================================================== C . 5.24648 |================================================================== D . 5.24826 |================================================================== oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 6.05436 |================================================================== B . 6.04615 |================================================================== C . 6.05662 |================================================================== D . 6.04798 |================================================================== oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 1.35376 |================================================================== B . 1.35332 |================================================================== C . 1.34061 |================================================================= D . 1.34296 |================================================================= oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 2.21737 |================================================================== B . 2.22008 |================================================================== C . 2.22075 |================================================================== D . 2.21930 |================================================================== oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 2883.12 |================================================================== B . 2875.93 |================================================================== C . 2881.76 |================================================================== D . 2879.92 |================================================================== oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 1614.54 |================================================================== B . 1611.80 |================================================================== C . 1612.97 |================================================================== D . 1614.78 |================================================================== oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 2881.96 |================================================================== B . 2885.96 |================================================================== C . 2882.62 |================================================================== D . 2880.35 |================================================================== 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 . 1617.55 |================================================================== B . 1612.80 |================================================================== C . 1611.27 |================================================================== D . 1614.27 |================================================================== oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 1.24567 |=============================================================== B . 1.25510 |=============================================================== C . 1.28432 |================================================================= D . 1.31081 |================================================================== oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 2884.94 |================================================================== B . 2881.54 |================================================================== C . 2879.53 |================================================================== D . 2882.22 |================================================================== oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 1615.08 |================================================================= B . 1630.53 |================================================================== C . 1618.78 |================================================================== D . 1616.11 |================================================================= oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 1.033654 |================================================================= B . 0.826339 |==================================================== C . 0.842998 |===================================================== D . 1.011141 |================================================================ oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better