tr onednn 3.1 AMD Ryzen Threadripper 3990X 64-Core testing with a Gigabyte TRX40 AORUS PRO WIFI (F6 BIOS) and AMD Radeon RX 5700 8GB on Ubuntu 23.04 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 (F6 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 23.04, Kernel: 6.2.0-18-generic (x86_64), Desktop: GNOME Shell 44.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 22.3.6 (LLVM 15.0.7 DRM 3.49), Compiler: GCC 12.2.0, 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 (F6 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 23.04, Kernel: 6.2.0-18-generic (x86_64), Desktop: GNOME Shell 44.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 23.0.1 (LLVM 15.0.7 DRM 3.49), Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 3840x2160 c: Processor: AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads), Motherboard: Gigabyte TRX40 AORUS PRO WIFI (F6 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 23.04, Kernel: 6.2.0-18-generic (x86_64), Desktop: GNOME Shell 44.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 23.0.1 (LLVM 15.0.7 DRM 3.49), Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 3840x2160 d: Processor: AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads), Motherboard: Gigabyte TRX40 AORUS PRO WIFI (F6 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 23.04, Kernel: 6.2.0-18-generic (x86_64), Desktop: GNOME Shell 44.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 23.0.1 (LLVM 15.0.7 DRM 3.49), Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 3840x2160 oneDNN 3.1 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 3.69076 |================================================================== b . 2.43237 |=========================================== c . 2.42598 |=========================================== d . 1.57043 |============================ oneDNN 3.1 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 6.47745 |=================================================== b . 6.37674 |================================================== c . 8.33405 |================================================================= d . 8.41506 |================================================================== oneDNN 3.1 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 11.59889 |================================================================= b . 3.60412 |==================== c . 2.60751 |=============== d . 2.33334 |============= oneDNN 3.1 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 3.48600 |================================================================== b . 1.09122 |===================== c . 1.13827 |====================== d . 1.14615 |====================== oneDNN 3.1 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 0.919370 |========================================================== b . 0.923333 |========================================================== c . 1.027830 |================================================================= d . 0.967448 |============================================================= oneDNN 3.1 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 10.48951 |=============================================================== b . 10.90270 |================================================================= c . 10.23840 |============================================================= d . 9.81509 |=========================================================== oneDNN 3.1 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 2.08690 |================================================================= b . 2.07202 |================================================================= c . 2.10876 |================================================================== d . 2.08485 |================================================================= oneDNN 3.1 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 6.48493 |================================================================ b . 6.54503 |================================================================= c . 6.62890 |================================================================== d . 6.66997 |================================================================== oneDNN 3.1 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 1.78620 |================================================================= b . 1.76202 |================================================================ c . 1.82592 |================================================================== d . 1.74741 |=============================================================== oneDNN 3.1 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 0.989134 |================================================================= b . 0.978770 |================================================================ c . 0.964088 |=============================================================== d . 0.978819 |================================================================ oneDNN 3.1 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 4011.41 |================================================================== b . 3998.12 |================================================================== c . 4018.10 |================================================================== d . 4017.57 |================================================================== oneDNN 3.1 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 859.10 |=================================================================== b . 844.46 |================================================================== c . 857.91 |=================================================================== d . 839.18 |================================================================= oneDNN 3.1 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 4024.21 |================================================================== b . 4014.98 |================================================================== c . 4008.56 |================================================================== d . 4001.77 |================================================================== oneDNN 3.1 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 3.1 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 856.72 |=================================================================== b . 858.40 |=================================================================== c . 850.40 |================================================================== d . 862.30 |=================================================================== oneDNN 3.1 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 4042.59 |================================================================== b . 4007.14 |================================================================= c . 4027.35 |================================================================== d . 4010.35 |================================================================= oneDNN 3.1 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 844.98 |================================================================== b . 864.21 |=================================================================== c . 858.76 |=================================================================== d . 841.92 |=================================================================