onednn 5500U AMD Ryzen 5 5500U testing with a LENOVO LNVNB161216 (GLCN22WW BIOS) and AMD Lucienne 2GB on Ubuntu 21.10 via the Phoronix Test Suite. A: Processor: AMD Ryzen 5 5500U @ 4.06GHz (6 Cores / 12 Threads), Motherboard: LENOVO LNVNB161216 (GLCN22WW BIOS), Chipset: AMD Renoir/Cezanne, Memory: 6GB, Disk: 256GB SAMSUNG MZALQ256HBJD-00BL2, Graphics: AMD Lucienne 2GB (1800/400MHz), Audio: AMD Renoir Radeon HD Audio, Network: Qualcomm Atheros QCA6174 802.11ac OS: Ubuntu 21.10, Kernel: 5.17.0-051700-generic (x86_64), Desktop: GNOME Shell 40.5, Display Server: X Server 1.20.13 + Wayland, OpenGL: 4.6 Mesa 22.1.0-devel (git-729f95a 2022-03-24 impish-oibaf-ppa) (LLVM 13.0.1 DRM 3.44), Vulkan: 1.3.207, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 1920x1080 B: Processor: AMD Ryzen 5 5500U @ 4.06GHz (6 Cores / 12 Threads), Motherboard: LENOVO LNVNB161216 (GLCN22WW BIOS), Chipset: AMD Renoir/Cezanne, Memory: 6GB, Disk: 256GB SAMSUNG MZALQ256HBJD-00BL2, Graphics: AMD Lucienne 2GB (1800/400MHz), Audio: AMD Renoir Radeon HD Audio, Network: Qualcomm Atheros QCA6174 802.11ac OS: Ubuntu 21.10, Kernel: 5.17.0-051700-generic (x86_64), Desktop: GNOME Shell 40.5, Display Server: X Server 1.20.13 + Wayland, OpenGL: 4.6 Mesa 22.1.0-devel (git-729f95a 2022-03-24 impish-oibaf-ppa) (LLVM 13.0.1 DRM 3.44), Vulkan: 1.3.207, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 1920x1080 C: Processor: AMD Ryzen 5 5500U @ 4.06GHz (6 Cores / 12 Threads), Motherboard: LENOVO LNVNB161216 (GLCN22WW BIOS), Chipset: AMD Renoir/Cezanne, Memory: 6GB, Disk: 256GB SAMSUNG MZALQ256HBJD-00BL2, Graphics: AMD Lucienne 2GB (1800/400MHz), Audio: AMD Renoir Radeon HD Audio, Network: Qualcomm Atheros QCA6174 802.11ac OS: Ubuntu 21.10, Kernel: 5.17.0-051700-generic (x86_64), Desktop: GNOME Shell 40.5, Display Server: X Server 1.20.13 + Wayland, OpenGL: 4.6 Mesa 22.1.0-devel (git-729f95a 2022-03-24 impish-oibaf-ppa) (LLVM 13.0.1 DRM 3.44), Vulkan: 1.3.207, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 1920x1080 oneDNN 2.6 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 12.11 |==================================================================== B . 12.09 |==================================================================== C . 12.09 |==================================================================== oneDNN 2.6 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 14.50 |==================================================================== B . 11.33 |===================================================== C . 11.39 |===================================================== oneDNN 2.6 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 3.72999 |================================================================= B . 3.79690 |================================================================== C . 3.79445 |================================================================== oneDNN 2.6 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 4.55304 |================================================================== B . 3.75469 |====================================================== C . 3.76327 |======================================================= oneDNN 2.6 Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 2.6 Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 34.45 |==================================================================== B . 34.12 |=================================================================== C . 34.16 |=================================================================== oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 13.62 |==================================================================== B . 13.64 |==================================================================== C . 13.33 |================================================================== oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 11.76 |==================================================================== B . 11.72 |==================================================================== C . 11.72 |==================================================================== oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 37.77 |==================================================================== B . 33.74 |============================================================= C . 33.72 |============================================================= oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 5.62842 |================================================================= B . 5.61911 |================================================================= C . 5.70647 |================================================================== oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 8.03215 |================================================================== B . 8.02814 |================================================================== C . 8.03124 |================================================================== oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 7127.16 |================================================================== B . 7087.03 |================================================================== C . 7043.60 |================================================================= oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 4688.21 |================================================================== B . 4690.55 |================================================================== C . 4690.50 |================================================================== oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 7099.28 |================================================================== B . 7098.27 |================================================================== C . 7066.77 |================================================================== oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 4694.72 |================================================================== B . 4701.50 |================================================================== C . 4676.62 |================================================================== oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 7.90632 |================================================================== B . 7.89074 |================================================================== C . 7.85276 |================================================================== oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 7073.68 |================================================================== B . 7067.16 |================================================================== C . 7094.51 |================================================================== oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 4687.06 |================================================================== B . 4683.43 |================================================================== C . 4662.02 |================================================================== oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 5.11790 |================================================================== B . 5.11311 |================================================================== C . 5.11709 |================================================================== oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better