3990X sysbench onednn AMD Ryzen Threadripper 3990X 64-Core testing with a System76 Thelio Major (F4c Z5 BIOS) and AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB on Pop 20.10 via the Phoronix Test Suite. 1: Processor: AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads), Motherboard: System76 Thelio Major (F4c Z5 BIOS), Chipset: AMD Starship/Matisse, Memory: 126GB, Disk: Samsung SSD 970 EVO Plus 500GB, Graphics: AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB (1750/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: DELL P2415Q, Network: Intel I211 + Intel Wi-Fi 6 AX200 OS: Pop 20.10, Kernel: 5.8.0-7630-generic (x86_64), Desktop: GNOME Shell 3.38.2, Display Server: X Server 1.20.8, OpenGL: 4.6 Mesa 21.1.0-devel (git-96d7555 2021-01-22 groovy-oibaf-ppa) (LLVM 11.0.1), Vulkan: 1.2.145, Compiler: GCC 10.2.0 + Clang 11.0.1-1~oibaf~g, File-System: ext4, Screen Resolution: 3840x2160 2: Processor: AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads), Motherboard: System76 Thelio Major (F4c Z5 BIOS), Chipset: AMD Starship/Matisse, Memory: 126GB, Disk: Samsung SSD 970 EVO Plus 500GB, Graphics: AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB (1750/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: DELL P2415Q, Network: Intel I211 + Intel Wi-Fi 6 AX200 OS: Pop 20.10, Kernel: 5.8.0-7630-generic (x86_64), Desktop: GNOME Shell 3.38.2, Display Server: X Server 1.20.8, OpenGL: 4.6 Mesa 21.1.0-devel (git-96d7555 2021-01-22 groovy-oibaf-ppa) (LLVM 11.0.1), Vulkan: 1.2.145, Compiler: GCC 10.2.0 + Clang 11.0.1-1~oibaf~g, File-System: ext4, Screen Resolution: 3840x2160 3: Processor: AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads), Motherboard: System76 Thelio Major (F4c Z5 BIOS), Chipset: AMD Starship/Matisse, Memory: 126GB, Disk: Samsung SSD 970 EVO Plus 500GB, Graphics: AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB (1750/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: DELL P2415Q, Network: Intel I211 + Intel Wi-Fi 6 AX200 OS: Pop 20.10, Kernel: 5.8.0-7630-generic (x86_64), Desktop: GNOME Shell 3.38.2, Display Server: X Server 1.20.8, OpenGL: 4.6 Mesa 21.1.0-devel (git-96d7555 2021-01-22 groovy-oibaf-ppa) (LLVM 11.0.1), Vulkan: 1.2.145, Compiler: GCC 10.2.0 + Clang 11.0.1-1~oibaf~g, File-System: ext4, Screen Resolution: 3840x2160 4: Processor: AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads), Motherboard: System76 Thelio Major (F4c Z5 BIOS), Chipset: AMD Starship/Matisse, Memory: 126GB, Disk: Samsung SSD 970 EVO Plus 500GB, Graphics: AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB (1750/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: DELL P2415Q, Network: Intel I211 + Intel Wi-Fi 6 AX200 OS: Pop 20.10, Kernel: 5.8.0-7630-generic (x86_64), Desktop: GNOME Shell 3.38.2, Display Server: X Server 1.20.8, OpenGL: 4.6 Mesa 21.1.0-devel (git-96d7555 2021-01-22 groovy-oibaf-ppa) (LLVM 11.0.1), Vulkan: 1.2.145, Compiler: GCC 10.2.0 + Clang 11.0.1-1~oibaf~g, File-System: ext4, Screen Resolution: 3840x2160 Sysbench 1.0.20 Test: CPU Events Per Second > Higher Is Better 1 . 124312.60 |================================================================ 2 . 123807.73 |================================================================ 3 . 123768.96 |================================================================ 4 . 123660.73 |================================================================ oneDNN 2.1.2 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 . 3780.64 |================================================================== 2 . 3750.45 |================================================================= 3 . 3760.17 |================================================================== 4 . 3721.68 |================================================================= oneDNN 2.1.2 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 . 3741.53 |================================================================= 2 . 3770.99 |================================================================== 3 . 3747.70 |================================================================== 4 . 3730.17 |================================================================= oneDNN 2.1.2 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better 1 . 3750.35 |================================================================== 2 . 3759.67 |================================================================== 3 . 3747.38 |================================================================== 4 . 3733.74 |================================================================== oneDNN 2.1.2 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better 1 . 742.79 |=================================================================== 2 . 744.79 |=================================================================== 3 . 743.58 |=================================================================== 4 . 746.70 |=================================================================== oneDNN 2.1.2 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 . 743.20 |=================================================================== 2 . 747.63 |=================================================================== 3 . 745.82 |=================================================================== 4 . 747.81 |=================================================================== oneDNN 2.1.2 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 . 743.97 |=================================================================== 2 . 744.47 |=================================================================== 3 . 746.45 |=================================================================== 4 . 744.35 |=================================================================== oneDNN 2.1.2 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 . 7.56650 |================================================================= 2 . 7.62499 |================================================================= 3 . 7.59192 |================================================================= 4 . 7.70634 |================================================================== oneDNN 2.1.2 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 . 0.890976 |================================================================= 2 . 0.896707 |================================================================= 3 . 0.895418 |================================================================= 4 . 0.889403 |================================================================ oneDNN 2.1.2 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 . 1.23508 |================================================================= 2 . 1.25724 |================================================================== 3 . 1.24953 |================================================================== 4 . 1.23832 |================================================================= oneDNN 2.1.2 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 . 1.47243 |================================================================= 2 . 1.48945 |================================================================= 3 . 1.50143 |================================================================== 4 . 1.46291 |================================================================ Sysbench 1.0.20 Test: RAM / Memory MiB/sec > Higher Is Better 1 . 7515.51 |================================================================== 2 . 7520.15 |================================================================== 3 . 7511.92 |================================================================== 4 . 7484.70 |================================================================== oneDNN 2.1.2 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 . 0.411915 |================================================================ 2 . 0.415420 |================================================================= 3 . 0.411918 |================================================================ 4 . 0.417122 |================================================================= oneDNN 2.1.2 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 . 0.667705 |================================================================= 2 . 0.668714 |================================================================= 3 . 0.667192 |================================================================= 4 . 0.670735 |================================================================= oneDNN 2.1.2 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 . 5.37221 |========================================= 2 . 8.44270 |================================================================= 3 . 8.57665 |================================================================== 4 . 8.11946 |============================================================== oneDNN 2.1.2 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 . 1.002151 |=============================================================== 2 . 1.026890 |================================================================ 3 . 1.032520 |================================================================= 4 . 1.035480 |================================================================= oneDNN 2.1.2 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 . 0.946125 |========================================================= 2 . 1.025490 |============================================================== 3 . 1.081290 |================================================================= 4 . 1.082800 |================================================================= oneDNN 2.1.2 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 . 6.52783 |================================================================= 2 . 6.63625 |================================================================== 3 . 6.58848 |================================================================= 4 . 6.65608 |================================================================== oneDNN 2.1.2 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 . 2.02131 |================================================================= 2 . 2.03585 |================================================================== 3 . 2.04302 |================================================================== 4 . 2.02647 |================================================================= oneDNN 2.1.2 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 . 0.947941 |================================================================= 2 . 0.954759 |================================================================= 3 . 0.953820 |================================================================= 4 . 0.954016 |=================================================================