onednn 3.1 tigerlake Intel Core i7-1165G7 testing with a Dell 0GG9PT (3.11.0 BIOS) and Intel Xe TGL GT2 15GB on Ubuntu 22.10 via the Phoronix Test Suite. a: Processor: Intel Core i7-1165G7 @ 4.70GHz (4 Cores / 8 Threads), Motherboard: Dell 0GG9PT (3.11.0 BIOS), Chipset: Intel Tiger Lake-LP, Memory: 16GB, Disk: Kioxia KBG40ZNS256G NVMe 256GB, Graphics: Intel Xe TGL GT2 15GB (1300MHz), Audio: Realtek ALC289, Network: Intel Wi-Fi 6 AX201 OS: Ubuntu 22.10, Kernel: 5.19.0-38-generic (x86_64), Desktop: GNOME Shell 43.0, Display Server: X Server 1.21.1.4 + Wayland, OpenGL: 4.6 Mesa 22.2.5, OpenCL: OpenCL 3.0, Vulkan: 1.3.224, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 1920x1200 b: Processor: Intel Core i7-1165G7 @ 4.70GHz (4 Cores / 8 Threads), Motherboard: Dell 0GG9PT (3.11.0 BIOS), Chipset: Intel Tiger Lake-LP, Memory: 16GB, Disk: Kioxia KBG40ZNS256G NVMe 256GB, Graphics: Intel Xe TGL GT2 15GB (1300MHz), Audio: Realtek ALC289, Network: Intel Wi-Fi 6 AX201 OS: Ubuntu 22.10, Kernel: 5.19.0-38-generic (x86_64), Desktop: GNOME Shell 43.0, Display Server: X Server 1.21.1.4 + Wayland, OpenGL: 4.6 Mesa 22.2.5, OpenCL: OpenCL 3.0, Vulkan: 1.3.224, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 1920x1200 c: Processor: Intel Core i7-1165G7 @ 4.70GHz (4 Cores / 8 Threads), Motherboard: Dell 0GG9PT (3.11.0 BIOS), Chipset: Intel Tiger Lake-LP, Memory: 16GB, Disk: Kioxia KBG40ZNS256G NVMe 256GB, Graphics: Intel Xe TGL GT2 15GB (1300MHz), Audio: Realtek ALC289, Network: Intel Wi-Fi 6 AX201 OS: Ubuntu 22.10, Kernel: 5.19.0-38-generic (x86_64), Desktop: GNOME Shell 43.0, Display Server: X Server 1.21.1.4 + Wayland, OpenGL: 4.6 Mesa 22.2.5, OpenCL: OpenCL 3.0, Vulkan: 1.3.224, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 1920x1200 oneDNN 3.1 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 7629.39 |================================================================== b . 7626.55 |================================================================== c . 7631.13 |================================================================== oneDNN 3.1 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 8260.44 |================================================================== b . 7604.92 |============================================================= c . 7194.33 |========================================================= oneDNN 3.1 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 7448.89 |================================================================== b . 7499.70 |================================================================== c . 7479.15 |================================================================== oneDNN 3.1 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 3859.67 |================================================================== b . 3858.62 |================================================================== c . 3851.35 |================================================================== oneDNN 3.1 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 3849.51 |================================================================== b . 3857.97 |================================================================== c . 3848.60 |================================================================== oneDNN 3.1 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 3852.88 |================================================================== b . 3850.94 |================================================================== c . 3857.92 |================================================================== oneDNN 3.1 Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 84.73 |==================================================================== b . 46.88 |====================================== c . 52.22 |========================================== oneDNN 3.1 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 12.98 |==================================================================== b . 11.95 |============================================================== c . 13.06 |==================================================================== oneDNN 3.1 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 2.15004 |================================================================== b . 2.16516 |================================================================== c . 2.16487 |================================================================== oneDNN 3.1 Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 19.09 |==================================================================== b . 19.13 |==================================================================== c . 18.26 |================================================================= oneDNN 3.1 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 7.43755 |================================================================= b . 7.52319 |================================================================== c . 6.70311 |=========================================================== oneDNN 3.1 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 1.58645 |================================================================= b . 1.59346 |================================================================== c . 1.60082 |================================================================== oneDNN 3.1 Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 5.83118 |=============================================================== b . 6.12705 |================================================================== c . 5.80452 |=============================================================== oneDNN 3.1 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 5.72636 |================================================================= b . 5.80411 |================================================================== c . 5.68653 |================================================================= oneDNN 3.1 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 2.20666 |================================================================ b . 2.28981 |================================================================== c . 2.20832 |================================================================ oneDNN 3.1 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 38.60 |========================================================== b . 39.11 |=========================================================== c . 45.12 |==================================================================== oneDNN 3.1 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 8.79583 |================================================================== b . 8.84187 |================================================================== c . 8.56588 |================================================================ oneDNN 3.1 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 7.96507 |================================================================== b . 7.97341 |================================================================== c . 7.76888 |================================================================ oneDNN 3.1 Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 39.28 |==================================================================== b . 37.49 |================================================================= c . 37.51 |================================================================= oneDNN 3.1 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 10.60 |==================================================================== b . 10.65 |==================================================================== c . 10.27 |================================================================== oneDNN 3.1 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 2.53561 |================================================================== b . 2.54368 |================================================================== c . 2.51699 |=================================================================