amd-genoa-onednn-31 2 x AMD EPYC 9654 96-Core testing with a AMD Titanite_4G (RTI1004D BIOS) and ASPEED on Clear Linux OS 38660 via the Phoronix Test Suite. a: Processor: 2 x AMD EPYC 9654 96-Core @ 2.40GHz (192 Cores / 384 Threads), Motherboard: AMD Titanite_4G (RTI1004D BIOS), Chipset: AMD Device 14a4, Memory: 1520GB, Disk: 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007, Graphics: ASPEED, Network: Broadcom NetXtreme BCM5720 PCIe OS: Clear Linux OS 38660, Kernel: 6.2.8-1293.native (x86_64), Display Server: X Server, Compiler: GCC 12.2.1 20230323 releases/gcc-12.2.0-616-g1b6b7f214c + Clang 15.0.7 + LLVM 15.0.7, File-System: ext4, Screen Resolution: 800x600 b: Processor: 2 x AMD EPYC 9654 96-Core @ 2.40GHz (192 Cores / 384 Threads), Motherboard: AMD Titanite_4G (RTI1004D BIOS), Chipset: AMD Device 14a4, Memory: 1520GB, Disk: 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007, Graphics: ASPEED, Network: Broadcom NetXtreme BCM5720 PCIe OS: Clear Linux OS 38660, Kernel: 6.2.8-1293.native (x86_64), Display Server: X Server, Compiler: GCC 12.2.1 20230323 releases/gcc-12.2.0-616-g1b6b7f214c + Clang 15.0.7 + LLVM 15.0.7, File-System: ext4, Screen Resolution: 800x600 c: Processor: 2 x AMD EPYC 9654 96-Core @ 2.40GHz (192 Cores / 384 Threads), Motherboard: AMD Titanite_4G (RTI1004D BIOS), Chipset: AMD Device 14a4, Memory: 1520GB, Disk: 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007, Graphics: ASPEED, Network: Broadcom NetXtreme BCM5720 PCIe OS: Clear Linux OS 38660, Kernel: 6.2.8-1293.native (x86_64), Display Server: X Server, Compiler: GCC 12.2.1 20230323 releases/gcc-12.2.0-616-g1b6b7f214c + Clang 15.0.7 + LLVM 15.0.7, File-System: ext4, Screen Resolution: 800x600 oneDNN 3.1 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 5.16295 |============================================================= b . 5.56995 |================================================================== c . 5.13421 |============================================================= oneDNN 3.1 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 1.81517 |================================================================== b . 1.75887 |================================================================ c . 1.72273 |=============================================================== oneDNN 3.1 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 3.81667 |============================================================= b . 4.12976 |================================================================== c . 3.98273 |================================================================ oneDNN 3.1 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 0.753564 |=========================================================== b . 0.816992 |================================================================ c . 0.824101 |================================================================= oneDNN 3.1 Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 3.80454 |====================================================== b . 3.87903 |======================================================== c . 4.61093 |================================================================== oneDNN 3.1 Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 1.54627 |============================================================= b . 1.64919 |================================================================== c . 1.66125 |================================================================== oneDNN 3.1 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 0.521813 |============================================================== b . 0.547057 |================================================================= c . 0.530342 |=============================================================== oneDNN 3.1 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 20.84 |==================================================================== b . 20.69 |==================================================================== c . 20.68 |=================================================================== oneDNN 3.1 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 0.946786 |================================================================ b . 0.952539 |================================================================= c . 0.954284 |================================================================= oneDNN 3.1 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 0.362781 |================================================================= b . 0.363114 |================================================================= c . 0.360127 |================================================================ oneDNN 3.1 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 0.923951 |=============================================================== b . 0.946937 |================================================================= c . 0.911944 |=============================================================== oneDNN 3.1 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 0.282128 |=============================================================== b . 0.292579 |================================================================= c . 0.277235 |============================================================== oneDNN 3.1 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 999.38 |================================================================== b . 1001.27 |================================================================== c . 974.37 |================================================================ oneDNN 3.1 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 1297.60 |============================================================ b . 1317.63 |============================================================= c . 1424.56 |================================================================== oneDNN 3.1 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 1007.48 |================================================================= b . 1016.04 |================================================================== c . 968.29 |=============================================================== oneDNN 3.1 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 0.414999 |================================================================= b . 0.408003 |================================================================ c . 0.406869 |================================================================ oneDNN 3.1 Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 2.23356 |================================================================== b . 2.22682 |================================================================== c . 2.21262 |================================================================= oneDNN 3.1 Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 0.643195 |================================================================ b . 0.640364 |================================================================ c . 0.653813 |================================================================= oneDNN 3.1 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 1302.83 |=============================================================== b . 1323.12 |================================================================ c . 1357.36 |================================================================== oneDNN 3.1 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 998.04 |================================================================ b . 1022.78 |================================================================== c . 985.50 |================================================================ oneDNN 3.1 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better b . 1373.66 |================================================================== c . 1347.87 |=================================================================