onednn 3.0 raptor lake
Intel Core i9-13900K testing with a ASUS PRIME Z790-P WIFI (0602 BIOS) and eVGA NVIDIA GeForce RTX 3060 12GB on Ubuntu 22.10 via the Phoronix Test Suite.


a: 

	Processor: Intel Core i9-13900K @ 4.00GHz (24 Cores / 32 Threads), Motherboard: ASUS PRIME Z790-P WIFI (0602 BIOS), Chipset: Intel Device 7a27, Memory: 32GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0, Graphics: eVGA NVIDIA GeForce RTX 3060 12GB, Audio: Realtek ALC897, Monitor: ASUS VP28U, Network: Realtek RTL8125 2.5GbE + Intel Device 7a70

	OS: Ubuntu 22.10, Kernel: 5.19.0-26-generic (x86_64), Desktop: GNOME Shell 43.1, Display Server: X Server 1.21.1.4, Display Driver: NVIDIA 525.60.11, OpenGL: 4.6.0, OpenCL: OpenCL 3.0 CUDA 12.0.89, Vulkan: 1.3.224, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 2560x1600

b: 

	Processor: Intel Core i9-13900K @ 4.00GHz (24 Cores / 32 Threads), Motherboard: ASUS PRIME Z790-P WIFI (0602 BIOS), Chipset: Intel Device 7a27, Memory: 32GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0, Graphics: eVGA NVIDIA GeForce RTX 3060 12GB, Audio: Realtek ALC897, Monitor: ASUS VP28U, Network: Realtek RTL8125 2.5GbE + Intel Device 7a70

	OS: Ubuntu 22.10, Kernel: 5.19.0-26-generic (x86_64), Desktop: GNOME Shell 43.1, Display Server: X Server 1.21.1.4, Display Driver: NVIDIA 525.60.11, OpenGL: 4.6.0, OpenCL: OpenCL 3.0 CUDA 12.0.89, Vulkan: 1.3.224, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 2560x1600

c: 

	Processor: Intel Core i9-13900K @ 4.00GHz (24 Cores / 32 Threads), Motherboard: ASUS PRIME Z790-P WIFI (0602 BIOS), Chipset: Intel Device 7a27, Memory: 32GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0, Graphics: eVGA NVIDIA GeForce RTX 3060 12GB, Audio: Realtek ALC897, Monitor: ASUS VP28U, Network: Realtek RTL8125 2.5GbE + Intel Device 7a70

	OS: Ubuntu 22.10, Kernel: 5.19.0-26-generic (x86_64), Desktop: GNOME Shell 43.1, Display Server: X Server 1.21.1.4, Display Driver: NVIDIA 525.60.11, OpenGL: 4.6.0, OpenCL: OpenCL 3.0 CUDA 12.0.89, Vulkan: 1.3.224, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 2560x1600


oneDNN 3.0
Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU
ms < Lower Is Better
a . 1.71588 |============================================================
b . 1.88491 |==================================================================
c . 1.86077 |=================================================================


oneDNN 3.0
Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU
ms < Lower Is Better
a . 4.15008 |==================================================================
b . 3.93573 |===============================================================
c . 3.84879 |=============================================================


oneDNN 3.0
Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU
ms < Lower Is Better
a . 0.786709 |=========================================================
b . 0.863089 |===============================================================
c . 0.891727 |=================================================================


oneDNN 3.0
Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU
ms < Lower Is Better
a . 0.629303 |=================================================================
b . 0.621966 |================================================================
c . 0.599391 |==============================================================


oneDNN 3.0
Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU
ms < Lower Is Better
a . 5.76384 |==================================================================
b . 5.75816 |==================================================================
c . 5.75127 |==================================================================


oneDNN 3.0
Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU
ms < Lower Is Better
a . 7.47730 |===============================================================
b . 7.36674 |==============================================================
c . 7.86792 |==================================================================


oneDNN 3.0
Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU
ms < Lower Is Better
a . 3.42736 |==================================================================
b . 3.42391 |==================================================================
c . 3.42519 |==================================================================


oneDNN 3.0
Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU
ms < Lower Is Better
a . 5.91006 |==================================================================
b . 5.89829 |==================================================================
c . 5.86806 |==================================================================


oneDNN 3.0
Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU
ms < Lower Is Better
a . 0.955404 |================================================================
b . 0.972727 |=================================================================
c . 0.937470 |===============================================================


oneDNN 3.0
Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU
ms < Lower Is Better
a . 1.44911 |==================================================================
b . 1.44938 |==================================================================
c . 1.44885 |==================================================================


oneDNN 3.0
Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU
ms < Lower Is Better
a . 2119.68 |==================================================================
b . 2122.24 |==================================================================
c . 2089.67 |=================================================================


oneDNN 3.0
Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU
ms < Lower Is Better
a . 1087.51 |=================================================================
b . 1073.62 |================================================================
c . 1104.46 |==================================================================


oneDNN 3.0
Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU
ms < Lower Is Better
a . 2126.29 |=================================================================
b . 2143.27 |==================================================================
c . 2097.67 |=================================================================


oneDNN 3.0
Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU
ms < Lower Is Better
a . 1098.42 |==================================================================
b . 1099.64 |==================================================================
c . 1095.20 |==================================================================


oneDNN 3.0
Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU
ms < Lower Is Better
a . 1.269326 |============================================================
b . 1.179855 |=======================================================
c . 1.382935 |=================================================================


oneDNN 3.0
Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU
ms < Lower Is Better
a . 2117.94 |=================================================================
b . 2148.96 |==================================================================
c . 2113.69 |=================================================================


oneDNN 3.0
Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU
ms < Lower Is Better
a . 1084.75 |=================================================================
b . 1095.58 |==================================================================
c . 1083.23 |=================================================================


oneDNN 3.0
Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU
ms < Lower Is Better
a . 0.783081 |=================================================================
b . 0.786177 |=================================================================
c . 0.759611 |===============================================================