onednn 3.0 threadripper AMD Ryzen Threadripper 3990X 64-Core testing with a Gigabyte TRX40 AORUS PRO WIFI (F4p BIOS) and AMD Radeon RX 5700 8GB on Ubuntu 22.10 via the Phoronix Test Suite. a: Processor: AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads), Motherboard: Gigabyte TRX40 AORUS PRO WIFI (F4p BIOS), Chipset: AMD Starship/Matisse, Memory: 128GB, Disk: Samsung SSD 970 EVO Plus 500GB, Graphics: AMD Radeon RX 5700 8GB (1750/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: DELL P2415Q, Network: Intel I211 + Intel Wi-Fi 6 AX200 OS: Ubuntu 22.10, Kernel: 6.1.0-rc8-phx-mglru (x86_64), Desktop: GNOME Shell 43.0, Display Server: X Server 1.21.1.4 + Wayland, OpenGL: 4.6 Mesa 22.2.1 (LLVM 15.0.2 DRM 3.49), Vulkan: 1.3.224, Compiler: GCC 12.2.0 + LLVM 15.0.2, File-System: ext4, Screen Resolution: 3840x2160 b: Processor: AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads), Motherboard: Gigabyte TRX40 AORUS PRO WIFI (F4p BIOS), Chipset: AMD Starship/Matisse, Memory: 128GB, Disk: Samsung SSD 970 EVO Plus 500GB, Graphics: AMD Radeon RX 5700 8GB (1750/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: DELL P2415Q, Network: Intel I211 + Intel Wi-Fi 6 AX200 OS: Ubuntu 22.10, Kernel: 6.1.0-rc8-phx-mglru (x86_64), Desktop: GNOME Shell 43.0, Display Server: X Server 1.21.1.4 + Wayland, OpenGL: 4.6 Mesa 22.2.1 (LLVM 15.0.2 DRM 3.49), Vulkan: 1.3.224, Compiler: GCC 12.2.0 + LLVM 15.0.2, File-System: ext4, Screen Resolution: 3840x2160 cc: Processor: AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads), Motherboard: Gigabyte TRX40 AORUS PRO WIFI (F4p BIOS), Chipset: AMD Starship/Matisse, Memory: 128GB, Disk: Samsung SSD 970 EVO Plus 500GB, Graphics: AMD Radeon RX 5700 8GB (1750/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: DELL P2415Q, Network: Intel I211 + Intel Wi-Fi 6 AX200 OS: Ubuntu 22.10, Kernel: 6.1.0-rc8-phx-mglru (x86_64), Desktop: GNOME Shell 43.0, Display Server: X Server 1.21.1.4 + Wayland, OpenGL: 4.6 Mesa 22.2.1 (LLVM 15.0.2 DRM 3.49), Vulkan: 1.3.224, Compiler: GCC 12.2.0 + LLVM 15.0.2, File-System: ext4, Screen Resolution: 3840x2160 oneDNN 3.0 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a .. 1358.93 |================================================================= b .. 1314.16 |=============================================================== cc . 1268.47 |============================================================= oneDNN 3.0 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better a .. 5197.15 |================================================================ b .. 5182.40 |================================================================ cc . 5246.90 |================================================================= oneDNN 3.0 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a .. 1281.82 |=============================================================== b .. 1324.29 |================================================================= cc . 1322.57 |================================================================= oneDNN 3.0 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a .. 5273.92 |================================================================= b .. 5109.34 |=============================================================== cc . 5269.95 |================================================================= oneDNN 3.0 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a .. 5182.24 |================================================================ b .. 5208.02 |================================================================= cc . 5236.44 |================================================================= oneDNN 3.0 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better a .. 1291.22 |================================================================= b .. 1291.11 |================================================================= cc . 1297.12 |================================================================= oneDNN 3.0 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a .. 1.72926 |================================================================ b .. 1.74884 |================================================================= cc . 1.60670 |============================================================ oneDNN 3.0 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a .. 2.44556 |============================================================= b .. 2.62054 |================================================================= cc . 2.42089 |============================================================ oneDNN 3.0 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better a .. 3.92526 |================================================================= b .. 2.03399 |================================== cc . 1.65081 |=========================== oneDNN 3.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU ms < Lower Is Better a .. 8.64383 |===================================================== b .. 10.28060 |=============================================================== cc . 10.41480 |================================================================ oneDNN 3.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a .. 12.76 |============================================================== b .. 10.62 |=================================================== cc . 13.90 |=================================================================== oneDNN 3.0 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a .. 1.34962 |============================================================= b .. 1.36747 |============================================================== cc . 1.42830 |================================================================= oneDNN 3.0 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better a .. 9.82269 |============================================================== b .. 9.88978 |=============================================================== cc . 10.11480 |================================================================ oneDNN 3.0 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU ms < Lower Is Better a .. 5.52121 |=============================================== b .. 7.54120 |================================================================ cc . 7.68970 |================================================================= oneDNN 3.0 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU ms < Lower Is Better a .. 1.039830 |============================================================ b .. 1.108050 |================================================================ cc . 0.941291 |====================================================== oneDNN 3.0 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a .. 6.48281 |=============================================================== b .. 6.58094 |================================================================ cc . 6.67325 |================================================================= oneDNN 3.0 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better a .. 2.08900 |================================================================= b .. 2.09561 |================================================================= cc . 2.07244 |================================================================ oneDNN 3.0 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a .. 0.995989 |================================================================ b .. 0.975595 |=============================================================== cc . 0.957802 |==============================================================