3900XT oneDNN 2.0 AMD Ryzen 9 3900XT 12-Core testing with a MSI MEG X570 GODLIKE (MS-7C34) v1.0 (1.B3 BIOS) and AMD Radeon RX 56/64 8GB on Ubuntu 20.10 via the Phoronix Test Suite. 1: Processor: AMD Ryzen 9 3900XT 12-Core @ 3.80GHz (12 Cores / 24 Threads), Motherboard: MSI MEG X570 GODLIKE (MS-7C34) v1.0 (1.B3 BIOS), Chipset: AMD Starship/Matisse, Memory: 16GB, Disk: 500GB Seagate FireCuda 520 SSD ZP500GM30002, Graphics: AMD Radeon RX 56/64 8GB (1630/945MHz), Audio: AMD Vega 10 HDMI Audio, Monitor: ASUS MG28U, Network: Realtek Device 2600 + Realtek Device 3000 + Intel Wi-Fi 6 AX200 OS: Ubuntu 20.10, Kernel: 5.8.0-31-generic (x86_64), Desktop: GNOME Shell 3.38.1, Display Server: X Server 1.20.9, Display Driver: amdgpu 19.1.0, OpenGL: 4.6 Mesa 20.2.1 (LLVM 11.0.0), Vulkan: 1.2.131, Compiler: GCC 10.2.0, File-System: ext4, Screen Resolution: 3840x2160 2: Processor: AMD Ryzen 9 3900XT 12-Core @ 3.80GHz (12 Cores / 24 Threads), Motherboard: MSI MEG X570 GODLIKE (MS-7C34) v1.0 (1.B3 BIOS), Chipset: AMD Starship/Matisse, Memory: 16GB, Disk: 500GB Seagate FireCuda 520 SSD ZP500GM30002, Graphics: AMD Radeon RX 56/64 8GB (1630/945MHz), Audio: AMD Vega 10 HDMI Audio, Monitor: ASUS MG28U, Network: Realtek Device 2600 + Realtek Device 3000 + Intel Wi-Fi 6 AX200 OS: Ubuntu 20.10, Kernel: 5.8.0-31-generic (x86_64), Desktop: GNOME Shell 3.38.1, Display Server: X Server 1.20.9, Display Driver: amdgpu 19.1.0, OpenGL: 4.6 Mesa 20.2.1 (LLVM 11.0.0), Vulkan: 1.2.131, Compiler: GCC 10.2.0, File-System: ext4, Screen Resolution: 3840x2160 3: Processor: AMD Ryzen 9 3900XT 12-Core @ 3.80GHz (12 Cores / 24 Threads), Motherboard: MSI MEG X570 GODLIKE (MS-7C34) v1.0 (1.B3 BIOS), Chipset: AMD Starship/Matisse, Memory: 16GB, Disk: 500GB Seagate FireCuda 520 SSD ZP500GM30002, Graphics: AMD Radeon RX 56/64 8GB (1630/945MHz), Audio: AMD Vega 10 HDMI Audio, Monitor: ASUS MG28U, Network: Realtek Device 2600 + Realtek Device 3000 + Intel Wi-Fi 6 AX200 OS: Ubuntu 20.10, Kernel: 5.8.0-31-generic (x86_64), Desktop: GNOME Shell 3.38.1, Display Server: X Server 1.20.9, Display Driver: amdgpu 19.1.0, OpenGL: 4.6 Mesa 20.2.1 (LLVM 11.0.0), Vulkan: 1.2.131, Compiler: GCC 10.2.0, File-System: ext4, Screen Resolution: 3840x2160 oneDNN 2.0 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 . 4.91756 |================================================================ 2 . 4.93209 |================================================================ 3 . 5.08005 |================================================================== oneDNN 2.0 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 . 10.92 |==================================================================== 2 . 10.48 |================================================================= 3 . 10.32 |================================================================ oneDNN 2.0 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 . 1.97943 |================================================================= 2 . 2.01142 |================================================================== 3 . 1.99787 |================================================================== oneDNN 2.0 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 . 0.917533 |================================================================= 2 . 0.913077 |================================================================= 3 . 0.904227 |================================================================ oneDNN 2.0 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 . 22.71 |==================================================================== 2 . 22.77 |==================================================================== 3 . 22.84 |==================================================================== oneDNN 2.0 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 . 3.60412 |============================================================== 2 . 3.80744 |================================================================== 3 . 3.69057 |================================================================ oneDNN 2.0 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 . 5.38129 |================================================================= 2 . 5.29598 |================================================================ 3 . 5.42790 |================================================================== oneDNN 2.0 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 . 25.46 |==================================================================== 2 . 25.14 |=================================================================== 3 . 25.26 |=================================================================== oneDNN 2.0 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 . 4.36389 |================================================================= 2 . 4.33763 |================================================================= 3 . 4.40262 |================================================================== oneDNN 2.0 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 . 3.54912 |================================================================ 2 . 3.58446 |================================================================= 3 . 3.63921 |================================================================== oneDNN 2.0 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 . 4173.77 |================================================================== 2 . 4164.13 |================================================================= 3 . 4198.12 |================================================================== oneDNN 2.0 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 . 2525.88 |================================================================== 2 . 2488.28 |================================================================= 3 . 2498.37 |================================================================= oneDNN 2.0 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 . 4159.19 |================================================================ 2 . 4256.15 |================================================================== 3 . 4099.21 |================================================================ oneDNN 2.0 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 . 2581.13 |================================================================== 2 . 2502.21 |================================================================ 3 . 2542.01 |================================================================= oneDNN 2.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 . 0.955569 |================================================================= 2 . 0.934456 |================================================================ 3 . 0.924557 |=============================================================== oneDNN 2.0 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better 1 . 4234.30 |================================================================== 2 . 4205.89 |================================================================== 3 . 4135.54 |================================================================ oneDNN 2.0 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better 1 . 2546.38 |================================================================== 2 . 2552.93 |================================================================== 3 . 2564.79 |================================================================== oneDNN 2.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 . 2.26033 |================================================================== 2 . 2.19307 |================================================================ 3 . 2.24168 |=================================================================