tgl onnx onednn Intel Core i7-1185G7 testing with a Dell 0DXP1F (3.4.0 BIOS) and Intel Xe TGL GT2 3GB on Ubuntu 22.04 via the Phoronix Test Suite. A: Processor: Intel Core i7-1185G7 @ 4.80GHz (4 Cores / 8 Threads), Motherboard: Dell 0DXP1F (3.4.0 BIOS), Chipset: Intel Tiger Lake-LP, Memory: 16GB, Disk: Micron 2300 NVMe 512GB, Graphics: Intel Xe TGL GT2 3GB (1350MHz), Audio: Realtek ALC289, Network: Intel Wi-Fi 6 AX201 OS: Ubuntu 22.04, Kernel: 5.17.0-051700rc7daily20220309-generic (x86_64), Desktop: GNOME Shell 41.3, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 21.3.5, Vulkan: 1.2.195, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 1920x1200 B: Processor: Intel Core i7-1185G7 @ 4.80GHz (4 Cores / 8 Threads), Motherboard: Dell 0DXP1F (3.4.0 BIOS), Chipset: Intel Tiger Lake-LP, Memory: 16GB, Disk: Micron 2300 NVMe 512GB, Graphics: Intel Xe TGL GT2 3GB (1350MHz), Audio: Realtek ALC289, Network: Intel Wi-Fi 6 AX201 OS: Ubuntu 22.04, Kernel: 5.17.0-051700rc7daily20220309-generic (x86_64), Desktop: GNOME Shell 41.3, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 21.3.5, Vulkan: 1.2.195, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 1920x1200 C: Processor: Intel Core i7-1185G7 @ 4.80GHz (4 Cores / 8 Threads), Motherboard: Dell 0DXP1F (3.4.0 BIOS), Chipset: Intel Tiger Lake-LP, Memory: 16GB, Disk: Micron 2300 NVMe 512GB, Graphics: Intel Xe TGL GT2 3GB (1350MHz), Audio: Realtek ALC289, Network: Intel Wi-Fi 6 AX201 OS: Ubuntu 22.04, Kernel: 5.17.0-051700rc7daily20220309-generic (x86_64), Desktop: GNOME Shell 41.3, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 21.3.5, Vulkan: 1.2.195, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 1920x1200 oneDNN 2.6 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 6.73638 |====================================================== B . 8.20647 |================================================================== C . 7.33232 |=========================================================== oneDNN 2.6 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 5.92686 |================================================================ B . 5.98301 |================================================================= C . 6.12000 |================================================================== oneDNN 2.6 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 1.60833 |======================================================= B . 1.91706 |================================================================== C . 1.61437 |======================================================== oneDNN 2.6 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 2.45760 |================================================================= B . 2.44323 |================================================================= C . 2.49809 |================================================================== oneDNN 2.6 Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 24.35 |==================================================================== B . 22.59 |=============================================================== C . 20.85 |========================================================== oneDNN 2.6 Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 6.31954 |=========================================================== B . 6.48728 |============================================================= C . 7.07477 |================================================================== oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 8.75990 |======================================================== B . 10.17321 |================================================================= C . 10.24478 |================================================================= oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 16.25 |==================================================================== B . 16.15 |==================================================================== C . 15.06 |=============================================================== oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 9.99564 |============================================================ B . 10.81977 |================================================================= C . 10.58500 |================================================================ oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 7.85365 |=========================================================== B . 8.68295 |================================================================== C . 8.72272 |================================================================== oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 2.06617 |======================================================= B . 2.46720 |================================================================== C . 2.41235 |================================================================= oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 2.42655 |================================================================ B . 2.46736 |================================================================= C . 2.52091 |================================================================== oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 7179.62 |============================================================ B . 7833.65 |================================================================== C . 7177.77 |============================================================ oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 3708.31 |================================================================== B . 3706.01 |================================================================== C . 3708.62 |================================================================== oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 7183.16 |================================================================== B . 7189.33 |================================================================== C . 7195.10 |================================================================== oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 50.93 |==================================================================== B . 50.95 |==================================================================== C . 50.89 |==================================================================== oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 58.21 |==================================================================== B . 58.45 |==================================================================== C . 57.26 |=================================================================== oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 41.63 |==================================================================== B . 38.95 |================================================================ C . 39.25 |================================================================ oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 3703.27 |================================================================== B . 3706.43 |================================================================== C . 3702.64 |================================================================== oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 3.20134 |================================================================== B . 3.20291 |================================================================== C . 3.20418 |================================================================== oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 7180.81 |================================================================== B . 7188.55 |================================================================== C . 7189.06 |================================================================== oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 3702.70 |================================================================== B . 3708.52 |================================================================== C . 3711.78 |================================================================== oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 1.43080 |================================================================== B . 1.43371 |================================================================== C . 1.42532 |================================================================== oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 10.81 |==================================================================== B . 10.79 |==================================================================== C . 10.29 |================================================================= ONNX Runtime 1.11 Model: GPT-2 - Device: CPU - Executor: Parallel Inferences Per Minute > Higher Is Better A . 4466 |==================================================================== B . 4513 |===================================================================== C . 4470 |==================================================================== ONNX Runtime 1.11 Model: GPT-2 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better A . 6388 |===================================================================== B . 6376 |===================================================================== C . 6373 |===================================================================== ONNX Runtime 1.11 Model: yolov4 - Device: CPU - Executor: Parallel Inferences Per Minute > Higher Is Better A . 181 |====================================================================== B . 182 |====================================================================== C . 182 |====================================================================== ONNX Runtime 1.11 Model: yolov4 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better A . 262 |====================================================================== B . 261 |====================================================================== C . 261 |====================================================================== ONNX Runtime 1.11 Model: bertsquad-12 - Device: CPU - Executor: Parallel Inferences Per Minute > Higher Is Better A . 222 |==================================================================== B . 227 |====================================================================== C . 221 |==================================================================== ONNX Runtime 1.11 Model: bertsquad-12 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better A . 369 |===================================================================== B . 372 |====================================================================== C . 278 |==================================================== ONNX Runtime 1.11 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel Inferences Per Minute > Higher Is Better A . 33 |======================================================================= B . 32 |===================================================================== C . 25 |====================================================== ONNX Runtime 1.11 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better A . 40 |======================================================================= B . 37 |================================================================== C . 30 |===================================================== ONNX Runtime 1.11 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel Inferences Per Minute > Higher Is Better A . 550 |===================================================================== B . 554 |====================================================================== C . 465 |=========================================================== ONNX Runtime 1.11 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better A . 761 |==================================================================== B . 778 |====================================================================== C . 721 |================================================================= ONNX Runtime 1.11 Model: super-resolution-10 - Device: CPU - Executor: Parallel Inferences Per Minute > Higher Is Better A . 1879 |===================================================================== B . 1888 |===================================================================== C . 1646 |============================================================ ONNX Runtime 1.11 Model: super-resolution-10 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better A . 2488 |===================================================================== B . 2208 |============================================================= C . 1756 |=================================================