xeon febby 2 x INTEL XEON PLATINUM 8592+ testing with a Quanta Cloud QuantaGrid D54Q-2U S6Q-MB-MPS (3B05.TEL4P1 BIOS) and ASPEED on Ubuntu 23.10 via the Phoronix Test Suite. a: Processor: 2 x INTEL XEON PLATINUM 8592+ @ 3.90GHz (128 Cores / 256 Threads), Motherboard: Quanta Cloud QuantaGrid D54Q-2U S6Q-MB-MPS (3B05.TEL4P1 BIOS), Chipset: Intel Device 1bce, Memory: 1008GB, Disk: 3201GB Micron_7450_MTFDKCB3T2TFS, Graphics: ASPEED, Network: 2 x Intel X710 for 10GBASE-T OS: Ubuntu 23.10, Kernel: 6.6.0-060600-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1024x768 b: Processor: 2 x INTEL XEON PLATINUM 8592+ @ 3.90GHz (128 Cores / 256 Threads), Motherboard: Quanta Cloud QuantaGrid D54Q-2U S6Q-MB-MPS (3B05.TEL4P1 BIOS), Chipset: Intel Device 1bce, Memory: 1008GB, Disk: 3201GB Micron_7450_MTFDKCB3T2TFS, Graphics: ASPEED, Network: 2 x Intel X710 for 10GBASE-T OS: Ubuntu 23.10, Kernel: 6.6.0-060600-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1024x768 Quicksilver 20230818 Input: CTS2 Figure Of Merit > Higher Is Better a . 9556000 |================================================================== b . 9354000 |================================================================= Quicksilver 20230818 Input: CORAL2 P1 Figure Of Merit > Higher Is Better a . 8625000 |================================================================= b . 8820000 |================================================================== Quicksilver 20230818 Input: CORAL2 P2 Figure Of Merit > Higher Is Better a . 8000000 |=============================================================== b . 8418000 |================================================================== NAMD 3.0b6 Input: ATPase with 327,506 Atoms ns/day > Higher Is Better a . 5.98308 |================================================================== b . 4.02029 |============================================ NAMD 3.0b6 Input: STMV with 1,066,628 Atoms ns/day > Higher Is Better a . 1.74622 |=============================================================== b . 1.81638 |================================================================== dav1d 1.4 Video Input: Chimera 1080p FPS > Higher Is Better a . 204.38 |=================================================================== b . 202.83 |================================================================== dav1d 1.4 Video Input: Summer Nature 4K FPS > Higher Is Better a . 68.43 |==================================================================== b . 68.36 |==================================================================== dav1d 1.4 Video Input: Summer Nature 1080p FPS > Higher Is Better a . 87.78 |==================================================================== b . 86.79 |=================================================================== dav1d 1.4 Video Input: Chimera 1080p 10-bit FPS > Higher Is Better a . 235.42 |================================================================== b . 239.01 |=================================================================== Intel Open Image Denoise 2.2 Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-Only Images / Sec > Higher Is Better a . 5.10 |==================================================================== b . 5.16 |===================================================================== Intel Open Image Denoise 2.2 Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-Only Images / Sec > Higher Is Better a . 5.14 |===================================================================== b . 5.00 |=================================================================== Intel Open Image Denoise 2.2 Run: RTLightmap.hdr.4096x4096 - Device: CPU-Only Images / Sec > Higher Is Better a . 2.46 |===================================================================== b . 2.47 |===================================================================== Y-Cruncher 0.8.3 Pi Digits To Calculate: 1B Seconds < Lower Is Better a . 5.107 |================================================================== b . 5.249 |==================================================================== Y-Cruncher 0.8.3 Pi Digits To Calculate: 500M Seconds < Lower Is Better a . 2.723 |=================================================================== b . 2.761 |==================================================================== GROMACS 2024 Implementation: MPI CPU - Input: water_GMX50_bare Ns Per Day > Higher Is Better a . 17.92 |================================================================== b . 18.40 |==================================================================== PyTorch 2.1 Device: CPU - Batch Size: 1 - Model: ResNet-50 batches/sec > Higher Is Better a . 51.66 |==================================================================== b . 51.00 |=================================================================== PyTorch 2.1 Device: CPU - Batch Size: 1 - Model: ResNet-152 batches/sec > Higher Is Better a . 19.08 |==================================================================== b . 19.21 |==================================================================== PyTorch 2.1 Device: CPU - Batch Size: 1 - Model: Efficientnet_v2_l batches/sec > Higher Is Better a . 0.42 |===================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 1 - Model: VGG-16 images/sec > Higher Is Better a . 12.25 |==================================================================== b . 11.89 |================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 1 - Model: AlexNet images/sec > Higher Is Better a . 39.98 |==================================================================== b . 37.70 |================================================================ TensorFlow 2.12 Device: CPU - Batch Size: 1 - Model: GoogLeNet images/sec > Higher Is Better a . 18.23 |==================================================================== b . 17.62 |================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 1 - Model: ResNet-50 images/sec > Higher Is Better a . 7.28 |===================================================================== b . 7.01 |================================================================== Speedb 2.7 Test: Random Read Op/s > Higher Is Better a . 613257745 |================================================================ b . 490533153 |=================================================== Speedb 2.7 Test: Update Random Op/s > Higher Is Better a . 157060 |=================================================================== b . 156458 |=================================================================== Speedb 2.7 Test: Read While Writing Op/s > Higher Is Better a . 16943739 |============================================================= b . 18187110 |================================================================= Speedb 2.7 Test: Read Random Write Random Op/s > Higher Is Better a . 1520436 |================================================================== b . 1514331 |================================================================== ONNX Runtime 1.17 Model: GPT-2 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 205.56 |================================================================== b . 208.99 |=================================================================== ONNX Runtime 1.17 Model: GPT-2 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 4.86151 |================================================================== b . 4.78113 |================================================================= ONNX Runtime 1.17 Model: yolov4 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 15.38 |============================================================= b . 17.17 |==================================================================== ONNX Runtime 1.17 Model: yolov4 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 65.01 |==================================================================== b . 58.24 |============================================================= ONNX Runtime 1.17 Model: T5 Encoder - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 465.65 |=================================================================== b . 360.78 |==================================================== ONNX Runtime 1.17 Model: T5 Encoder - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 2.14695 |=================================================== b . 2.77091 |================================================================== ONNX Runtime 1.17 Model: bertsquad-12 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 15.96 |================================================ b . 22.66 |==================================================================== ONNX Runtime 1.17 Model: bertsquad-12 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 62.64 |==================================================================== b . 44.13 |================================================ ONNX Runtime 1.17 Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 786.26 |=================================================================== b . 789.31 |=================================================================== ONNX Runtime 1.17 Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 1.27117 |================================================================== b . 1.26631 |================================================================== ONNX Runtime 1.17 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 9.90267 |================================================================== b . 9.43170 |=============================================================== ONNX Runtime 1.17 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 100.98 |================================================================ b . 106.02 |=================================================================== ONNX Runtime 1.17 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 35.92 |=============================================================== b . 38.56 |==================================================================== ONNX Runtime 1.17 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 27.84 |==================================================================== b . 25.93 |=============================================================== ONNX Runtime 1.17 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 170.02 |=================================================================== b . 170.24 |=================================================================== ONNX Runtime 1.17 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 5.88091 |================================================================== b . 5.87369 |================================================================== ONNX Runtime 1.17 Model: super-resolution-10 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 257.00 |=================================================================== b . 247.67 |================================================================= ONNX Runtime 1.17 Model: super-resolution-10 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 3.89053 |================================================================ b . 4.03712 |================================================================== ONNX Runtime 1.17 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 38.33 |==================================================================== b . 37.88 |=================================================================== ONNX Runtime 1.17 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 26.09 |=================================================================== b . 26.40 |==================================================================== Llama.cpp b1808 Model: llama-2-7b.Q4_0.gguf Tokens Per Second > Higher Is Better a . 0.69 |===================================================================== b . 0.58 |========================================================== Llama.cpp b1808 Model: llama-2-13b.Q4_0.gguf Tokens Per Second > Higher Is Better a . 0.55 |===================================================================== b . 0.45 |======================================================== Llama.cpp b1808 Model: llama-2-70b-chat.Q5_0.gguf Tokens Per Second > Higher Is Better a . 0.43 |===================================================================== b . 0.34 |======================================================= Llamafile 0.6 Test: llava-v1.5-7b-q4 - Acceleration: CPU Tokens Per Second > Higher Is Better a . 0.53 |===================================================================== b . 0.53 |===================================================================== Llamafile 0.6 Test: mistral-7b-instruct-v0.2.Q8_0 - Acceleration: CPU Tokens Per Second > Higher Is Better a . 8.57 |=================================================================== b . 8.81 |===================================================================== Llamafile 0.6 Test: wizardcoder-python-34b-v1.0.Q6_K - Acceleration: CPU Tokens Per Second > Higher Is Better a . 3.74 |=================================================================== b . 3.86 |=====================================================================