onednn 2.7 zen4 AMD Ryzen 7 7700X 8-Core testing with a ASUS ROG CROSSHAIR X670E HERO (0604 BIOS) and GFX1036 512MB on Ubuntu 22.04 via the Phoronix Test Suite. A: Processor: AMD Ryzen 7 7700X 8-Core @ 5.57GHz (8 Cores / 16 Threads), Motherboard: ASUS ROG CROSSHAIR X670E HERO (0604 BIOS), Chipset: AMD Device 14d8, Memory: 32GB, Disk: 2000GB Samsung SSD 980 PRO 2TB, Graphics: GFX1036 512MB (2200/3000MHz), Audio: AMD Device 1640, Monitor: ASUS MG28U, Network: Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411 OS: Ubuntu 22.04, Kernel: 6.0.0-060000rc1daily20220820-generic (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.3.0-devel (git-4685385 2022-08-23 jammy-oibaf-ppa) (LLVM 14.0.6 DRM 3.48), Vulkan: 1.3.224, Compiler: GCC 12.0.1 20220319, File-System: ext4, Screen Resolution: 3840x2160 B: Processor: AMD Ryzen 7 7700X 8-Core @ 5.57GHz (8 Cores / 16 Threads), Motherboard: ASUS ROG CROSSHAIR X670E HERO (0604 BIOS), Chipset: AMD Device 14d8, Memory: 32GB, Disk: 2000GB Samsung SSD 980 PRO 2TB, Graphics: GFX1036 512MB (2200/3000MHz), Audio: AMD Device 1640, Monitor: ASUS MG28U, Network: Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411 OS: Ubuntu 22.04, Kernel: 6.0.0-060000rc1daily20220820-generic (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.3.0-devel (git-4685385 2022-08-23 jammy-oibaf-ppa) (LLVM 14.0.6 DRM 3.48), Vulkan: 1.3.224, Compiler: GCC 12.0.1 20220319, File-System: ext4, Screen Resolution: 3840x2160 C: Processor: AMD Ryzen 7 7700X 8-Core @ 5.57GHz (8 Cores / 16 Threads), Motherboard: ASUS ROG CROSSHAIR X670E HERO (0604 BIOS), Chipset: AMD Device 14d8, Memory: 32GB, Disk: 2000GB Samsung SSD 980 PRO 2TB, Graphics: GFX1036 512MB (2200/3000MHz), Audio: AMD Device 1640, Monitor: ASUS MG28U, Network: Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411 OS: Ubuntu 22.04, Kernel: 6.0.0-060000rc1daily20220820-generic (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.3.0-devel (git-4685385 2022-08-23 jammy-oibaf-ppa) (LLVM 14.0.6 DRM 3.48), Vulkan: 1.3.224, Compiler: GCC 12.0.1 20220319, File-System: ext4, Screen Resolution: 3840x2160 oneDNN 2.7 Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 2.35347 |================================================================= B . 2.38621 |================================================================== C . 2.37762 |================================================================== oneDNN 2.7 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 2099.39 |================================================================== B . 2080.20 |================================================================= C . 2080.07 |================================================================= oneDNN 2.7 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 0.909473 |================================================================= B . 0.904431 |================================================================= C . 0.901712 |================================================================ oneDNN 2.7 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 0.401082 |================================================================= B . 0.404040 |================================================================= C . 0.402066 |================================================================= oneDNN 2.7 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 2.91480 |================================================================== B . 2.92132 |================================================================== C . 2.91229 |================================================================== oneDNN 2.7 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 7.19897 |================================================================== B . 7.17681 |================================================================== C . 7.18198 |================================================================== oneDNN 2.7 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 3.69919 |================================================================== B . 3.70507 |================================================================== C . 3.70630 |================================================================== oneDNN 2.7 Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 1.14277 |================================================================== B . 1.14493 |================================================================== C . 1.14479 |================================================================== oneDNN 2.7 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 1033.60 |================================================================== B . 1034.44 |================================================================== C . 1035.48 |================================================================== Y-Cruncher 0.7.10.9513 Pi Digits To Calculate: 500M Seconds < Lower Is Better A . 12.23 |==================================================================== B . 12.25 |==================================================================== C . 12.24 |==================================================================== oneDNN 2.7 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 1034.29 |================================================================== B . 1034.25 |================================================================== C . 1036.03 |================================================================== oneDNN 2.7 Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 7.42575 |================================================================== B . 7.43741 |================================================================== C . 7.43242 |================================================================== Y-Cruncher 0.7.10.9513 Pi Digits To Calculate: 1B Seconds < Lower Is Better A . 26.77 |==================================================================== B . 26.78 |==================================================================== C . 26.74 |==================================================================== oneDNN 2.7 Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 2.28387 |================================================================== B . 2.28673 |================================================================== C . 2.28671 |================================================================== oneDNN 2.7 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 7.38483 |================================================================== B . 7.39387 |================================================================== C . 7.39096 |================================================================== oneDNN 2.7 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 2082.27 |================================================================== B . 2082.78 |================================================================== C . 2084.71 |================================================================== oneDNN 2.7 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 0.547774 |================================================================= B . 0.548203 |================================================================= C . 0.548382 |================================================================= oneDNN 2.7 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 0.239226 |================================================================= B . 0.239225 |================================================================= C . 0.239466 |================================================================= oneDNN 2.7 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 0.922113 |================================================================= B . 0.921455 |================================================================= C . 0.922358 |================================================================= oneDNN 2.7 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 2082.16 |================================================================== B . 2083.93 |================================================================== C . 2082.78 |================================================================== oneDNN 2.7 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 4.21459 |================================================================== B . 4.21692 |================================================================== C . 4.21774 |================================================================== oneDNN 2.7 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 1033.73 |================================================================== B . 1034.46 |================================================================== C . 1034.46 |================================================================== oneDNN 2.7 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 1.22275 |================================================================== B . 1.22197 |================================================================== C . 1.22231 |================================================================== oneDNN 2.7 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 0.740658 |================================================================= B . 0.740963 |================================================================= C . 0.740801 |================================================================= oneDNN 2.7 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 3.17118 |================================================================== B . 3.17100 |================================================================== C . 3.17066 |================================================================== oneDNN 2.7 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 6.12956 |================================================================ B . 6.27580 |================================================================== C . 5.71816 |============================================================