MinervaTensorFlow 2 x Intel Xeon Silver 4314 testing with a Intel M20NTP2SB (SE5C620.86B.0021.D02.2204261106 BIOS) and ASPEED on Ubuntu 22.04 via the Phoronix Test Suite. MinervaTFRunAbril: Processor: 2 x Intel Xeon Silver 4314 @ 3.40GHz (32 Cores / 64 Threads), Motherboard: Intel M20NTP2SB (SE5C620.86B.0021.D02.2204261106 BIOS), Chipset: Intel Device 0998, Memory: 128GB, Disk: 2 x 1920GB KINGSTON SEDC1500M1920G + 2 x 6001GB Western Digital WD6003FFBX-6, Graphics: ASPEED, Monitor: Smart Cable, Network: 2 x Intel I210 OS: Ubuntu 22.04, Kernel: 5.15.0-70-generic (x86_64), Compiler: GCC 11.3.0, File-System: ext4, Screen Resolution: 1024x768 TensorFlow 2.12 Device: CPU - Batch Size: 16 - Model: VGG-16 images/sec > Higher Is Better MinervaTFRunAbril . 9.94 |===================================================== TensorFlow 2.12 Device: CPU - Batch Size: 32 - Model: VGG-16 images/sec > Higher Is Better MinervaTFRunAbril . 11.49 |==================================================== TensorFlow 2.12 Device: CPU - Batch Size: 64 - Model: VGG-16 images/sec > Higher Is Better MinervaTFRunAbril . 12.72 |==================================================== TensorFlow 2.12 Device: CPU - Batch Size: 16 - Model: AlexNet images/sec > Higher Is Better MinervaTFRunAbril . 97.03 |==================================================== TensorFlow 2.12 Device: CPU - Batch Size: 256 - Model: VGG-16 images/sec > Higher Is Better MinervaTFRunAbril . 15.87 |==================================================== TensorFlow 2.12 Device: CPU - Batch Size: 32 - Model: AlexNet images/sec > Higher Is Better MinervaTFRunAbril . 118.45 |=================================================== TensorFlow 2.12 Device: CPU - Batch Size: 512 - Model: VGG-16 images/sec > Higher Is Better MinervaTFRunAbril . 18.08 |==================================================== TensorFlow 2.12 Device: CPU - Batch Size: 64 - Model: AlexNet images/sec > Higher Is Better MinervaTFRunAbril . 147.59 |=================================================== TensorFlow 2.12 Device: CPU - Batch Size: 256 - Model: AlexNet images/sec > Higher Is Better MinervaTFRunAbril . 230.57 |=================================================== TensorFlow 2.12 Device: CPU - Batch Size: 512 - Model: AlexNet images/sec > Higher Is Better MinervaTFRunAbril . 259.35 |=================================================== TensorFlow 2.12 Device: CPU - Batch Size: 16 - Model: GoogLeNet images/sec > Higher Is Better MinervaTFRunAbril . 49.97 |==================================================== TensorFlow 2.12 Device: CPU - Batch Size: 16 - Model: ResNet-50 images/sec > Higher Is Better MinervaTFRunAbril . 14.57 |==================================================== TensorFlow 2.12 Device: CPU - Batch Size: 32 - Model: GoogLeNet images/sec > Higher Is Better MinervaTFRunAbril . 62.15 |==================================================== TensorFlow 2.12 Device: CPU - Batch Size: 32 - Model: ResNet-50 images/sec > Higher Is Better MinervaTFRunAbril . 17.38 |==================================================== TensorFlow 2.12 Device: CPU - Batch Size: 64 - Model: GoogLeNet images/sec > Higher Is Better MinervaTFRunAbril . 78.05 |==================================================== TensorFlow 2.12 Device: CPU - Batch Size: 64 - Model: ResNet-50 images/sec > Higher Is Better MinervaTFRunAbril . 20.50 |==================================================== TensorFlow 2.12 Device: CPU - Batch Size: 256 - Model: GoogLeNet images/sec > Higher Is Better MinervaTFRunAbril . 99.24 |==================================================== TensorFlow 2.12 Device: CPU - Batch Size: 256 - Model: ResNet-50 images/sec > Higher Is Better MinervaTFRunAbril . 25.44 |==================================================== TensorFlow 2.12 Device: CPU - Batch Size: 512 - Model: GoogLeNet images/sec > Higher Is Better MinervaTFRunAbril . 101.69 |=================================================== TensorFlow 2.12 Device: CPU - Batch Size: 512 - Model: ResNet-50 images/sec > Higher Is Better MinervaTFRunAbril . 25.82 |====================================================