xeon r gold onednn 3.0 2 x Intel Xeon Gold 5220R testing with a TYAN S7106 (V2.01.B40 BIOS) and ASPEED on Ubuntu 20.04 via the Phoronix Test Suite. a: Processor: 2 x Intel Xeon Gold 5220R @ 3.90GHz (36 Cores / 72 Threads), Motherboard: TYAN S7106 (V2.01.B40 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 94GB, Disk: 500GB Samsung SSD 860, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel I210 + 2 x QLogic cLOM8214 1/10GbE OS: Ubuntu 20.04, Kernel: 6.1.0-phx (x86_64), Desktop: GNOME Shell 3.36.9, Display Server: X Server 1.20.13, Compiler: GCC 9.4.0, File-System: ext4, Screen Resolution: 1920x1080 b: Processor: 2 x Intel Xeon Gold 5220R @ 3.90GHz (36 Cores / 72 Threads), Motherboard: TYAN S7106 (V2.01.B40 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 94GB, Disk: 500GB Samsung SSD 860, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel I210 + 2 x QLogic cLOM8214 1/10GbE OS: Ubuntu 20.04, Kernel: 6.1.0-phx (x86_64), Desktop: GNOME Shell 3.36.9, Display Server: X Server 1.20.13, Compiler: GCC 9.4.0, File-System: ext4, Screen Resolution: 1920x1080 c: Processor: 2 x Intel Xeon Gold 5220R @ 3.90GHz (36 Cores / 72 Threads), Motherboard: TYAN S7106 (V2.01.B40 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 94GB, Disk: 500GB Samsung SSD 860, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel I210 + 2 x QLogic cLOM8214 1/10GbE OS: Ubuntu 20.04, Kernel: 6.1.0-phx (x86_64), Desktop: GNOME Shell 3.36.9, Display Server: X Server 1.20.13, Compiler: GCC 9.4.0, File-System: ext4, Screen Resolution: 1920x1080 oneDNN 3.0 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 1.75250 |================================================================== b . 1.74919 |================================================================= c . 1.76469 |================================================================== oneDNN 3.0 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 3.81228 |================================================================ b . 3.77586 |=============================================================== c . 3.94714 |================================================================== oneDNN 3.0 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 1.73090 |=============================================================== b . 1.67674 |============================================================= c . 1.80903 |================================================================== oneDNN 3.0 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 1.29656 |================================================================== b . 1.27572 |================================================================= c . 1.26769 |================================================================= oneDNN 3.0 Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 5.78540 |================================================================ b . 5.80604 |================================================================ c . 5.97953 |================================================================== oneDNN 3.0 Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 3.11322 |================================================================== b . 3.04360 |================================================================= c . 3.06163 |================================================================= oneDNN 3.0 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 7.59329 |================================================================== b . 7.58018 |================================================================== c . 7.51633 |================================================================= oneDNN 3.0 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 8.14539 |================================================================== b . 7.93565 |================================================================ c . 8.11243 |================================================================== oneDNN 3.0 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 2.76971 |================================================================== b . 2.76176 |================================================================== c . 2.75773 |================================================================== oneDNN 3.0 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 7.07070 |================================================================== b . 7.10229 |================================================================== c . 7.04447 |================================================================= oneDNN 3.0 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 0.583986 |================================================================= b . 0.581283 |================================================================= c . 0.576626 |================================================================ oneDNN 3.0 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 0.696550 |================================================================= b . 0.693376 |================================================================= c . 0.695969 |================================================================= oneDNN 3.0 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 1400.64 |================================================================== b . 1397.35 |================================================================== c . 1397.94 |================================================================== oneDNN 3.0 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 800.12 |=================================================================== b . 799.43 |=================================================================== c . 797.84 |=================================================================== oneDNN 3.0 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 1409.74 |================================================================== b . 1392.36 |================================================================= c . 1401.03 |================================================================== oneDNN 3.0 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 6.41676 |================================================================== b . 6.42421 |================================================================== c . 6.43035 |================================================================== oneDNN 3.0 Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 9.21597 |================================================================== b . 9.06402 |================================================================= c . 9.14855 |================================================================== oneDNN 3.0 Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 9.59277 |================================================================ b . 9.61333 |================================================================ c . 9.86147 |================================================================== oneDNN 3.0 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 796.63 |================================================================== b . 805.57 |=================================================================== c . 798.11 |================================================================== oneDNN 3.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 0.517990 |================================================================= b . 0.510599 |================================================================ c . 0.507931 |================================================================ oneDNN 3.0 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 1400.41 |================================================================== b . 1399.00 |================================================================== c . 1404.71 |================================================================== oneDNN 3.0 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 802.64 |================================================================== b . 802.95 |================================================================== c . 811.32 |=================================================================== oneDNN 3.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 0.215615 |=============================================================== b . 0.221767 |================================================================= c . 0.219184 |================================================================ oneDNN 3.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 2.34752 |================================================================ b . 2.41696 |================================================================== c . 2.35576 |================================================================