onnx sapphire rapids 2 x Intel Xeon Platinum 8490H testing with a Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS) and ASPEED on Ubuntu 23.04 via the Phoronix Test Suite. a: Processor: 2 x Intel Xeon Platinum 8490H @ 3.50GHz (120 Cores / 240 Threads), Motherboard: Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS), Chipset: Intel Device 1bce, Memory: 1008GB, Disk: 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007 + 960GB INTEL SSDSC2KG96, Graphics: ASPEED, Monitor: VGA HDMI, Network: 4 x Intel E810-C for QSFP + 2 x Intel X710 for 10GBASE-T OS: Ubuntu 23.04, Kernel: 5.19.0-21-generic (x86_64), Desktop: GNOME Shell 43.2, Display Server: X Server 1.21.1.6, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 1920x1080 b: Processor: 2 x Intel Xeon Platinum 8490H @ 3.50GHz (120 Cores / 240 Threads), Motherboard: Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS), Chipset: Intel Device 1bce, Memory: 1008GB, Disk: 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007 + 960GB INTEL SSDSC2KG96, Graphics: ASPEED, Monitor: VGA HDMI, Network: 4 x Intel E810-C for QSFP + 2 x Intel X710 for 10GBASE-T OS: Ubuntu 23.04, Kernel: 5.19.0-21-generic (x86_64), Desktop: GNOME Shell 43.2, Display Server: X Server 1.21.1.6, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 1920x1080 c: Processor: 2 x Intel Xeon Platinum 8490H @ 3.50GHz (120 Cores / 240 Threads), Motherboard: Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS), Chipset: Intel Device 1bce, Memory: 1008GB, Disk: 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007 + 960GB INTEL SSDSC2KG96, Graphics: ASPEED, Monitor: VGA HDMI, Network: 4 x Intel E810-C for QSFP + 2 x Intel X710 for 10GBASE-T OS: Ubuntu 23.04, Kernel: 5.19.0-21-generic (x86_64), Desktop: GNOME Shell 43.2, Display Server: X Server 1.21.1.6, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 1920x1080 ONNX Runtime 1.14 Model: GPT-2 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 148.35 |================================================================== b . 150.97 |=================================================================== c . 149.85 |=================================================================== ONNX Runtime 1.14 Model: GPT-2 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 6.73420 |================================================================== b . 6.61718 |================================================================= c . 6.66703 |================================================================= ONNX Runtime 1.14 Model: GPT-2 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 191.15 |=================================================================== b . 189.29 |================================================================== c . 190.18 |=================================================================== ONNX Runtime 1.14 Model: GPT-2 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 5.22926 |================================================================= b . 5.28042 |================================================================== c . 5.25596 |================================================================== ONNX Runtime 1.14 Model: yolov4 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 9.26590 |================================================================= b . 9.43283 |================================================================== c . 9.33290 |================================================================= ONNX Runtime 1.14 Model: yolov4 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 107.92 |=================================================================== b . 106.01 |================================================================== c . 107.14 |=================================================================== ONNX Runtime 1.14 Model: yolov4 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 11.41 |==================================================================== b . 10.91 |================================================================= c . 11.40 |==================================================================== ONNX Runtime 1.14 Model: yolov4 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 87.66 |================================================================= b . 91.68 |==================================================================== c . 87.69 |================================================================= ONNX Runtime 1.14 Model: bertsquad-12 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 15.40 |==================================================================== b . 15.12 |=================================================================== c . 14.93 |================================================================== ONNX Runtime 1.14 Model: bertsquad-12 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 64.95 |================================================================== b . 66.15 |=================================================================== c . 66.99 |==================================================================== ONNX Runtime 1.14 Model: bertsquad-12 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 15.14 |=================================================================== b . 15.38 |==================================================================== c . 15.31 |==================================================================== ONNX Runtime 1.14 Model: bertsquad-12 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 66.03 |==================================================================== b . 65.04 |=================================================================== c . 65.30 |=================================================================== ONNX Runtime 1.14 Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 584.39 |=================================================================== b . 577.16 |================================================================== c . 588.00 |=================================================================== ONNX Runtime 1.14 Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 1.70895 |================================================================= b . 1.73032 |================================================================== c . 1.69842 |================================================================= ONNX Runtime 1.14 Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 686.86 |=================================================================== b . 685.14 |================================================================== c . 691.63 |=================================================================== ONNX Runtime 1.14 Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 1.45525 |================================================================== b . 1.45885 |================================================================== c . 1.44521 |================================================================= ONNX Runtime 1.14 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 3.01627 |================================================================ b . 3.10708 |================================================================== c . 2.99560 |================================================================ ONNX Runtime 1.14 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 331.53 |=================================================================== b . 321.84 |================================================================= c . 333.82 |=================================================================== ONNX Runtime 1.14 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 10.40070 |================================================================ b . 10.55470 |================================================================= c . 9.10379 |======================================================== ONNX Runtime 1.14 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 96.14 |=========================================================== b . 94.74 |========================================================== c . 109.84 |=================================================================== ONNX Runtime 1.14 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 27.17 |==================================================================== b . 27.01 |=================================================================== c . 27.30 |==================================================================== ONNX Runtime 1.14 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 36.80 |==================================================================== b . 37.03 |==================================================================== c . 36.62 |=================================================================== ONNX Runtime 1.14 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 34.51 |==================================================================== b . 34.48 |==================================================================== c . 32.08 |=============================================================== ONNX Runtime 1.14 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 28.98 |=============================================================== b . 29.00 |=============================================================== c . 31.17 |==================================================================== ONNX Runtime 1.14 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 161.31 |=================================================================== b . 162.38 |=================================================================== c . 162.33 |=================================================================== ONNX Runtime 1.14 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 6.19737 |================================================================== b . 6.15705 |================================================================== c . 6.15868 |================================================================== ONNX Runtime 1.14 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 176.19 |=================================================================== b . 174.68 |================================================================== c . 176.93 |=================================================================== ONNX Runtime 1.14 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 5.67502 |================================================================= b . 5.72410 |================================================================== c . 5.65135 |================================================================= ONNX Runtime 1.14 Model: super-resolution-10 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 176.86 |=================================================================== b . 177.26 |=================================================================== c . 178.18 |=================================================================== ONNX Runtime 1.14 Model: super-resolution-10 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 5.65264 |================================================================== b . 5.64013 |================================================================== c . 5.61077 |================================================================== ONNX Runtime 1.14 Model: super-resolution-10 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 214.78 |=================================================================== b . 164.61 |=================================================== c . 212.01 |================================================================== ONNX Runtime 1.14 Model: super-resolution-10 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 4.65541 |=================================================== b . 6.07432 |================================================================== c . 4.71628 |=================================================== ONNX Runtime 1.14 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 32.56 |================================================================== b . 33.48 |==================================================================== c . 33.39 |==================================================================== ONNX Runtime 1.14 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 30.71 |==================================================================== b . 29.86 |================================================================== c . 29.94 |================================================================== ONNX Runtime 1.14 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 37.69 |================================================================ b . 39.82 |==================================================================== c . 39.90 |==================================================================== ONNX Runtime 1.14 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 26.53 |==================================================================== b . 25.11 |================================================================ c . 25.06 |================================================================