oneDNN 2.0 Ryzen 3 AMD Ryzen 3 3200U testing with a MOTILE PF4PU1F (N.1.03 BIOS) and AMD Picasso 512MB on Ubuntu 20.04 via the Phoronix Test Suite. 1: Processor: AMD Ryzen 3 3200U @ 2.60GHz (2 Cores / 4 Threads), Motherboard: MOTILE PF4PU1F (N.1.03 BIOS), Chipset: AMD Raven/Raven2, Memory: 3584MB, Disk: 128GB BIWIN SSD, Graphics: AMD Picasso 512MB (1200/1200MHz), Audio: AMD Raven/Raven2/Fenghuang, Network: Realtek RTL8111/8168/8411 + Intel Dual Band-AC 3168NGW OS: Ubuntu 20.04, Kernel: 5.4.0-53-generic (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: amdgpu 19.1.0, OpenGL: 4.6 Mesa 20.0.4 (LLVM 9.0.1), Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080 2: Processor: AMD Ryzen 3 3200U @ 2.60GHz (2 Cores / 4 Threads), Motherboard: MOTILE PF4PU1F (N.1.03 BIOS), Chipset: AMD Raven/Raven2, Memory: 3584MB, Disk: 128GB BIWIN SSD, Graphics: AMD Picasso 512MB (1200/1200MHz), Audio: AMD Raven/Raven2/Fenghuang, Network: Realtek RTL8111/8168/8411 + Intel Dual Band-AC 3168NGW OS: Ubuntu 20.04, Kernel: 5.4.0-53-generic (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: amdgpu 19.1.0, OpenGL: 4.6 Mesa 20.0.4 (LLVM 9.0.1), Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080 3: Processor: AMD Ryzen 3 3200U @ 2.60GHz (2 Cores / 4 Threads), Motherboard: MOTILE PF4PU1F (N.1.03 BIOS), Chipset: AMD Raven/Raven2, Memory: 3584MB, Disk: 128GB BIWIN SSD, Graphics: AMD Picasso 512MB (1200/1200MHz), Audio: AMD Raven/Raven2/Fenghuang, Network: Realtek RTL8111/8168/8411 + Intel Dual Band-AC 3168NGW OS: Ubuntu 20.04, Kernel: 5.4.0-53-generic (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: amdgpu 19.1.0, OpenGL: 4.6 Mesa 20.0.4 (LLVM 9.0.1), Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080 oneDNN 2.0 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 . 39.46 |=================================================================== 2 . 40.08 |==================================================================== 3 . 39.60 |=================================================================== oneDNN 2.0 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 . 19.43 |==================================================================== 2 . 18.01 |=============================================================== 3 . 17.93 |=============================================================== oneDNN 2.0 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 . 28.33 |=================================================================== 2 . 28.54 |==================================================================== 3 . 28.40 |==================================================================== oneDNN 2.0 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 . 7.76345 |================================================================== 2 . 7.76679 |================================================================== 3 . 7.81460 |================================================================== oneDNN 2.0 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 . 48.79 |=================================================================== 2 . 49.55 |==================================================================== 3 . 49.42 |==================================================================== oneDNN 2.0 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 . 51.54 |=================================================================== 2 . 51.98 |==================================================================== 3 . 51.66 |==================================================================== oneDNN 2.0 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 . 62.99 |==================================================================== 2 . 63.44 |==================================================================== 3 . 63.34 |==================================================================== oneDNN 2.0 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 . 69.11 |==================================================================== 2 . 68.96 |==================================================================== 3 . 69.25 |==================================================================== oneDNN 2.0 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 . 52.34 |================================================================ 2 . 55.32 |==================================================================== 3 . 55.49 |==================================================================== oneDNN 2.0 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 . 52.78 |=================================================================== 2 . 53.35 |==================================================================== 3 . 53.33 |==================================================================== oneDNN 2.0 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 . 12605.0 |================================================================== 2 . 12549.5 |================================================================== 3 . 12602.2 |================================================================== oneDNN 2.0 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 . 12793.9 |================================================================== 2 . 12850.1 |================================================================== 3 . 12787.2 |================================================================== oneDNN 2.0 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 . 12805.4 |================================================================== 2 . 12756.2 |================================================================== 3 . 12661.5 |================================================================= oneDNN 2.0 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 . 12736.6 |================================================================== 2 . 12758.1 |================================================================== 3 . 12803.1 |================================================================== oneDNN 2.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 . 16.42 |==================================================================== 2 . 16.32 |==================================================================== 3 . 16.40 |==================================================================== oneDNN 2.0 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better 1 . 12657.9 |================================================================= 2 . 12844.7 |================================================================== 3 . 12605.4 |================================================================= oneDNN 2.0 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better 1 . 12769.6 |================================================================== 2 . 12815.7 |================================================================== 3 . 12808.8 |================================================================== oneDNN 2.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 . 27.03 |=================================================================== 2 . 27.03 |=================================================================== 3 . 27.51 |====================================================================