9684x-ne 2 x AMD EPYC 9684X 96-Core testing with a AMD Titanite_4G (RTI1007B BIOS) and ASPEED on Ubuntu 23.10 via the Phoronix Test Suite. a: Processor: 2 x AMD EPYC 9684X 96-Core @ 2.55GHz (192 Cores / 384 Threads), Motherboard: AMD Titanite_4G (RTI1007B BIOS), Chipset: AMD Device 14a4, Memory: 1520GB, Disk: 3201GB Micron_7450_MTFDKCB3T2TFS, Graphics: ASPEED, Network: Broadcom NetXtreme BCM5720 PCIe OS: Ubuntu 23.10, Kernel: 6.6.0-060600-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 800x600 b: Processor: 2 x AMD EPYC 9684X 96-Core @ 2.55GHz (192 Cores / 384 Threads), Motherboard: AMD Titanite_4G (RTI1007B BIOS), Chipset: AMD Device 14a4, Memory: 1520GB, Disk: 3201GB Micron_7450_MTFDKCB3T2TFS, Graphics: ASPEED, Network: Broadcom NetXtreme BCM5720 PCIe OS: Ubuntu 23.10, Kernel: 6.6.0-060600-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 800x600 c: Processor: 2 x AMD EPYC 9684X 96-Core @ 2.55GHz (192 Cores / 384 Threads), Motherboard: AMD Titanite_4G (RTI1007B BIOS), Chipset: AMD Device 14a4, Memory: 1520GB, Disk: 3201GB Micron_7450_MTFDKCB3T2TFS, Graphics: ASPEED, Network: Broadcom NetXtreme BCM5720 PCIe OS: Ubuntu 23.10, Kernel: 6.6.0-060600-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 800x600 NAMD 3.0b6 Input: ATPase with 327,506 Atoms ns/day > Higher Is Better a . 20.90 |==================================================================== b . 20.89 |==================================================================== c . 20.88 |==================================================================== NAMD 3.0b6 Input: STMV with 1,066,628 Atoms ns/day > Higher Is Better a . 6.36963 |================================================================= b . 6.49427 |================================================================== c . 6.47040 |================================================================== Intel Open Image Denoise 2.2 Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-Only Images / Sec > Higher Is Better a . 3.49 |===================================================================== b . 3.49 |===================================================================== c . 3.49 |===================================================================== Intel Open Image Denoise 2.2 Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-Only Images / Sec > Higher Is Better a . 3.49 |===================================================================== b . 3.49 |===================================================================== c . 3.49 |===================================================================== Intel Open Image Denoise 2.2 Run: RTLightmap.hdr.4096x4096 - Device: CPU-Only Images / Sec > Higher Is Better a . 1.68 |===================================================================== b . 1.65 |==================================================================== c . 1.67 |===================================================================== GROMACS 2024 Implementation: MPI CPU - Input: water_GMX50_bare Ns Per Day > Higher Is Better a . 24.06 |==================================================================== b . 24.16 |==================================================================== c . 24.07 |==================================================================== ONNX Runtime 1.17 Model: GPT-2 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 110.69 |================================================================== b . 111.54 |=================================================================== ONNX Runtime 1.17 Model: GPT-2 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 9.02332 |================================================================== b . 8.95470 |================================================================= ONNX Runtime 1.17 Model: GPT-2 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 159.72 |=================================================================== b . 122.04 |=================================================== c . 122.15 |=================================================== ONNX Runtime 1.17 Model: GPT-2 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 6.25834 |================================================== b . 8.19077 |================================================================== c . 8.18389 |================================================================== ONNX Runtime 1.17 Model: yolov4 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 6.36075 |================================================================== b . 6.37602 |================================================================== ONNX Runtime 1.17 Model: yolov4 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 157.21 |=================================================================== b . 156.83 |=================================================================== ONNX Runtime 1.17 Model: yolov4 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 7.03904 |================================================================== b . 7.04966 |================================================================== c . 7.07340 |================================================================== ONNX Runtime 1.17 Model: yolov4 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 142.06 |=================================================================== b . 141.85 |=================================================================== c . 141.37 |=================================================================== ONNX Runtime 1.17 Model: T5 Encoder - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 284.32 |=================================================================== b . 281.89 |================================================================== ONNX Runtime 1.17 Model: T5 Encoder - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 3.51487 |================================================================= b . 3.54536 |================================================================== ONNX Runtime 1.17 Model: T5 Encoder - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 235.26 |================================================================== b . 237.89 |=================================================================== c . 235.81 |================================================================== ONNX Runtime 1.17 Model: T5 Encoder - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 4.24980 |================================================================== b . 4.20289 |================================================================= c . 4.23992 |================================================================== ONNX Runtime 1.17 Model: bertsquad-12 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 8.72812 |================================================================== b . 8.73027 |================================================================== ONNX Runtime 1.17 Model: bertsquad-12 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 114.57 |=================================================================== b . 114.54 |=================================================================== ONNX Runtime 1.17 Model: bertsquad-12 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 10.73 |=================================================================== b . 10.66 |=================================================================== c . 10.87 |==================================================================== ONNX Runtime 1.17 Model: bertsquad-12 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 93.21 |==================================================================== b . 93.83 |==================================================================== c . 91.95 |=================================================================== ONNX Runtime 1.17 Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 331.60 |=================================================================== b . 314.57 |================================================================ ONNX Runtime 1.17 Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 3.01302 |=============================================================== b . 3.17604 |================================================================== ONNX Runtime 1.17 Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 446.93 |============================================================== b . 430.57 |============================================================ c . 479.84 |=================================================================== ONNX Runtime 1.17 Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 2.23695 |================================================================ b . 2.32191 |================================================================== c . 2.08344 |=========================================================== ONNX Runtime 1.17 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 0.880576 |================================================================= b . 0.881007 |================================================================= ONNX Runtime 1.17 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 1135.61 |================================================================== b . 1135.06 |================================================================== ONNX Runtime 1.17 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 5.05401 |=========================================================== b . 5.64928 |================================================================== c . 5.03581 |=========================================================== ONNX Runtime 1.17 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 197.86 |=================================================================== b . 177.01 |============================================================ c . 198.57 |=================================================================== ONNX Runtime 1.17 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 15.58 |==================================================================== b . 15.46 |=================================================================== ONNX Runtime 1.17 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 64.19 |=================================================================== b . 64.69 |==================================================================== ONNX Runtime 1.17 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 23.41 |================================================================== c . 24.03 |==================================================================== ONNX Runtime 1.17 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 42.71 |==================================================================== c . 41.62 |================================================================== ONNX Runtime 1.17 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 101.63 |=================================================================== ONNX Runtime 1.17 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 9.8368 |=================================================================== ONNX Runtime 1.17 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 147.31 |=================================================================== ONNX Runtime 1.17 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 6.78768 |================================================================== ONNX Runtime 1.17 Model: super-resolution-10 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 91.86 |==================================================================== ONNX Runtime 1.17 Model: super-resolution-10 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 10.88 |==================================================================== ONNX Runtime 1.17 Model: super-resolution-10 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 97.38 |==================================================================== ONNX Runtime 1.17 Model: super-resolution-10 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 10.27 |==================================================================== ONNX Runtime 1.17 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 22.90 |==================================================================== ONNX Runtime 1.17 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 43.66 |==================================================================== ONNX Runtime 1.17 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 44.54 |==================================================================== ONNX Runtime 1.17 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 22.45 |====================================================================