onednn 3.1 raptor lake Intel Core i9-13900K testing with a ASUS PRIME Z790-P WIFI (0809 BIOS) and AMD Radeon RX 6800 16GB on Ubuntu 23.04 via the Phoronix Test Suite. a: Processor: Intel Core i9-13900K @ 4.00GHz (24 Cores / 32 Threads), Motherboard: ASUS PRIME Z790-P WIFI (0809 BIOS), Chipset: Intel Device 7a27, Memory: 32GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0, Graphics: AMD Radeon RX 6800 16GB (2475/1000MHz), Audio: Realtek ALC897, Monitor: ASUS VP28U, Network: Intel Device 7a70 OS: Ubuntu 23.04, Kernel: 5.19.0-21-generic (x86_64), Desktop: GNOME Shell 43.2, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 22.3.6 (LLVM 15.0.7 DRM 3.47), Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 3840x2160 b: Processor: Intel Core i9-13900K @ 4.00GHz (24 Cores / 32 Threads), Motherboard: ASUS PRIME Z790-P WIFI (0809 BIOS), Chipset: Intel Device 7a27, Memory: 32GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0, Graphics: AMD Radeon RX 6800 16GB (2475/1000MHz), Audio: Realtek ALC897, Monitor: ASUS VP28U, Network: Intel Device 7a70 OS: Ubuntu 23.04, Kernel: 5.19.0-21-generic (x86_64), Desktop: GNOME Shell 43.2, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 22.3.6 (LLVM 15.0.7 DRM 3.47), Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 3840x2160 c: Processor: Intel Core i9-13900K @ 4.00GHz (24 Cores / 32 Threads), Motherboard: ASUS PRIME Z790-P WIFI (0809 BIOS), Chipset: Intel Device 7a27, Memory: 32GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0, Graphics: AMD Radeon RX 6800 16GB (2475/1000MHz), Audio: Realtek ALC897, Monitor: ASUS VP28U, Network: Intel Device 7a70 OS: Ubuntu 23.04, Kernel: 5.19.0-21-generic (x86_64), Desktop: GNOME Shell 43.2, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 22.3.6 (LLVM 15.0.7 DRM 3.47), Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 3840x2160 d: Processor: Intel Core i9-13900K @ 4.00GHz (24 Cores / 32 Threads), Motherboard: ASUS PRIME Z790-P WIFI (0809 BIOS), Chipset: Intel Device 7a27, Memory: 32GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0, Graphics: AMD Radeon RX 6800 16GB (2475/1000MHz), Audio: Realtek ALC897, Monitor: ASUS VP28U, Network: Intel Device 7a70 OS: Ubuntu 23.04, Kernel: 5.19.0-21-generic (x86_64), Desktop: GNOME Shell 43.2, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 22.3.6 (LLVM 15.0.7 DRM 3.47), Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 3840x2160 oneDNN 3.1 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 1.77671 |============================================================ b . 1.76791 |=========================================================== c . 1.94834 |================================================================= d . 1.96346 |================================================================== oneDNN 3.1 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 4.30790 |================================================================== b . 3.63899 |======================================================== c . 3.65587 |======================================================== d . 3.67596 |======================================================== oneDNN 3.1 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 0.875256 |================================================================= b . 0.768990 |========================================================= c . 0.760111 |======================================================== d . 0.790233 |=========================================================== oneDNN 3.1 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 0.723845 |================================================================= b . 0.662423 |=========================================================== c . 0.667107 |============================================================ d . 0.671659 |============================================================ oneDNN 3.1 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 5.98598 |================================================================== b . 5.97718 |================================================================== c . 5.98154 |================================================================== d . 5.96883 |================================================================== oneDNN 3.1 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 2.80342 |============================================================== b . 2.84702 |=============================================================== c . 2.97854 |================================================================== d . 2.95880 |================================================================== oneDNN 3.1 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 3.52046 |================================================================= b . 3.55114 |================================================================== c . 3.52596 |================================================================== d . 3.51438 |================================================================= oneDNN 3.1 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 5.90479 |================================================================== b . 5.86230 |================================================================== c . 5.87030 |================================================================== d . 5.89599 |================================================================== oneDNN 3.1 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 1.02824 |================================================================== b . 1.03100 |================================================================== c . 1.03500 |================================================================== d . 1.03419 |================================================================== oneDNN 3.1 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 1.49421 |================================================================= b . 1.47704 |================================================================= c . 1.48198 |================================================================= d . 1.50665 |================================================================== oneDNN 3.1 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 1956.69 |================================================================ b . 2015.58 |================================================================== c . 1963.18 |================================================================ d . 2022.96 |================================================================== oneDNN 3.1 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 1060.06 |================================================================== b . 995.81 |============================================================== c . 1060.92 |================================================================== d . 1013.47 |=============================================================== oneDNN 3.1 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 2051.81 |================================================================== b . 1979.81 |=============================================================== c . 2002.91 |================================================================ d . 2064.24 |================================================================== oneDNN 3.1 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 1055.43 |================================================================= b . 1066.18 |================================================================== c . 1021.11 |=============================================================== d . 1014.72 |=============================================================== oneDNN 3.1 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 1961.50 |=============================================================== b . 2068.68 |================================================================== c . 2065.28 |================================================================== d . 2018.95 |================================================================ oneDNN 3.1 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 1056.49 |================================================================== b . 1019.23 |================================================================ d . 1052.63 |==================================================================