onednn tgl Intel Core i5-1135G7 testing with a Dell 08642J (3.3.0 BIOS) and Intel Xe TGL GT2 3GB on Ubuntu 20.04 via the Phoronix Test Suite. A: Processor: Intel Core i5-1135G7 @ 4.20GHz (4 Cores / 8 Threads), Motherboard: Dell 08642J (3.3.0 BIOS), Chipset: Intel Device a0ef, Memory: 8GB, Disk: PC SN530 NVMe WDC 256GB, Graphics: Intel Xe TGL GT2 3GB (1300MHz), Audio: Realtek ALC289, Network: Intel Device a0f0 OS: Ubuntu 20.04, Kernel: 5.14.0-1029-oem (x86_64), Desktop: GNOME Shell 3.36.9, Display Server: X Server 1.20.9, OpenGL: 4.6 Mesa 21.2.6, Vulkan: 1.2.182, Compiler: GCC 9.4.0, File-System: ext4, Screen Resolution: 3456x2160 V: Processor: Intel Core i5-1135G7 @ 4.20GHz (4 Cores / 8 Threads), Motherboard: Dell 08642J (3.3.0 BIOS), Chipset: Intel Device a0ef, Memory: 8GB, Disk: PC SN530 NVMe WDC 256GB, Graphics: Intel Xe TGL GT2 3GB (1300MHz), Audio: Realtek ALC289, Network: Intel Device a0f0 OS: Ubuntu 20.04, Kernel: 5.14.0-1029-oem (x86_64), Desktop: GNOME Shell 3.36.9, Display Server: X Server 1.20.9, OpenGL: 4.6 Mesa 21.2.6, Vulkan: 1.2.182, Compiler: GCC 9.4.0, File-System: ext4, Screen Resolution: 3456x2160 C: Processor: Intel Core i5-1135G7 @ 4.20GHz (4 Cores / 8 Threads), Motherboard: Dell 08642J (3.3.0 BIOS), Chipset: Intel Device a0ef, Memory: 8GB, Disk: PC SN530 NVMe WDC 256GB, Graphics: Intel Xe TGL GT2 3GB (1300MHz), Audio: Realtek ALC289, Network: Intel Device a0f0 OS: Ubuntu 20.04, Kernel: 5.14.0-1029-oem (x86_64), Desktop: GNOME Shell 3.36.9, Display Server: X Server 1.20.9, OpenGL: 4.6 Mesa 21.2.6, Vulkan: 1.2.182, Compiler: GCC 9.4.0, File-System: ext4, Screen Resolution: 3456x2160 oneDNN 2.6 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 10.21 |==================================================================== V . 10.22 |==================================================================== C . 10.21 |==================================================================== oneDNN 2.6 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 6.61640 |================================================================= V . 6.72230 |================================================================== C . 6.54558 |================================================================ oneDNN 2.6 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 2.10994 |================================================================== V . 2.11645 |================================================================== C . 2.10776 |================================================================== oneDNN 2.6 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 2.70766 |================================================================== V . 2.71662 |================================================================== C . 2.69766 |================================================================== oneDNN 2.6 Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 25.65 |==================================================================== V . 25.64 |==================================================================== C . 25.64 |==================================================================== oneDNN 2.6 Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 6.44962 |================================================================= V . 6.52050 |================================================================== C . 6.51208 |================================================================== oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 10.35 |==================================================================== V . 10.34 |==================================================================== C . 10.31 |==================================================================== oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 16.57 |================================================================== V . 17.18 |==================================================================== C . 17.12 |==================================================================== oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 13.53 |==================================================================== V . 13.56 |==================================================================== C . 13.59 |==================================================================== oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 8.51257 |================================================================== V . 8.49301 |================================================================== C . 8.50841 |================================================================== oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 2.63798 |================================================================== V . 2.63758 |================================================================== C . 2.64240 |================================================================== oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 3.14203 |================================================================== V . 3.15049 |================================================================== C . 3.14523 |================================================================== oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 7561.25 |========================================================= V . 8754.58 |================================================================== C . 7565.21 |========================================================= oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 4465.24 |================================================================= V . 4565.49 |================================================================== C . 4553.79 |================================================================== oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 8685.42 |============================================================= V . 8986.95 |=============================================================== C . 9364.40 |================================================================== oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 52.54 |==================================================================== V . 52.54 |==================================================================== C . 52.55 |==================================================================== oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 60.14 |==================================================================== V . 60.19 |==================================================================== C . 60.24 |==================================================================== oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 52.94 |==================================================================== V . 52.94 |==================================================================== C . 52.78 |==================================================================== oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 3840.02 |========================================================= V . 4396.18 |================================================================= C . 4467.07 |================================================================== oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 3.15249 |================================================================== V . 3.15675 |================================================================== C . 3.15390 |================================================================== oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 8798.47 |================================================================== V . 8805.12 |================================================================== C . 8811.18 |================================================================== oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 4543.09 |================================================================== V . 4563.71 |================================================================== C . 4558.69 |================================================================== oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 1.50550 |================================================================= V . 1.52166 |================================================================== C . 1.50861 |================================================================= oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 10.90 |==================================================================== V . 10.89 |==================================================================== C . 10.88 |====================================================================