ai 2 x Intel Xeon Max 9468 testing with a Supermicro X13DEM v1.10 (1.3 BIOS) and ASPEED on Ubuntu 23.04 via the Phoronix Test Suite. a: Processor: 2 x Intel Xeon Max 9468 @ 3.50GHz (96 Cores / 192 Threads), Motherboard: Supermicro X13DEM v1.10 (1.3 BIOS), Chipset: Intel Device 1bce, Memory: 512GB, Disk: 7682GB INTEL SSDPF2KX076TZ, Graphics: ASPEED, Monitor: VE228, Network: 2 x Broadcom BCM57508 NetXtreme-E 10Gb/25Gb/40Gb/50Gb/100Gb/200Gb OS: Ubuntu 23.04, Kernel: 6.2.0-20-generic (x86_64), Desktop: GNOME Shell 44.0, Display Server: X Server 1.21.1.7, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 1920x1080 b: Processor: 2 x Intel Xeon Max 9468 @ 3.50GHz (96 Cores / 192 Threads), Motherboard: Supermicro X13DEM v1.10 (1.3 BIOS), Chipset: Intel Device 1bce, Memory: 512GB, Disk: 7682GB INTEL SSDPF2KX076TZ, Graphics: ASPEED, Monitor: VE228, Network: 2 x Broadcom BCM57508 NetXtreme-E 10Gb/25Gb/40Gb/50Gb/100Gb/200Gb OS: Ubuntu 23.04, Kernel: 6.2.0-20-generic (x86_64), Desktop: GNOME Shell 44.0, Display Server: X Server 1.21.1.7, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 1920x1080 c: Processor: 2 x Intel Xeon Max 9468 @ 3.50GHz (96 Cores / 192 Threads), Motherboard: Supermicro X13DEM v1.10 (1.3 BIOS), Chipset: Intel Device 1bce, Memory: 512GB, Disk: 7682GB INTEL SSDPF2KX076TZ, Graphics: ASPEED, Monitor: VE228, Network: 2 x Broadcom BCM57508 NetXtreme-E 10Gb/25Gb/40Gb/50Gb/100Gb/200Gb OS: Ubuntu 23.04, Kernel: 6.2.0-20-generic (x86_64), Desktop: GNOME Shell 44.0, Display Server: X Server 1.21.1.7, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 1920x1080 d: Processor: 2 x Intel Xeon Max 9468 @ 3.50GHz (96 Cores / 192 Threads), Motherboard: Supermicro X13DEM v1.10 (1.3 BIOS), Chipset: Intel Device 1bce, Memory: 512GB, Disk: 7682GB INTEL SSDPF2KX076TZ, Graphics: ASPEED, Monitor: VE228, Network: 2 x Broadcom BCM57508 NetXtreme-E 10Gb/25Gb/40Gb/50Gb/100Gb/200Gb OS: Ubuntu 23.04, Kernel: 6.2.0-20-generic (x86_64), Desktop: GNOME Shell 44.0, Display Server: X Server 1.21.1.7, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 1920x1080 TensorFlow 2.12 Device: CPU - Batch Size: 512 - Model: ResNet-50 images/sec > Higher Is Better a . 72.60 |=============================================================== b . 76.96 |=================================================================== c . 77.77 |==================================================================== d . 77.76 |==================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 256 - Model: ResNet-50 images/sec > Higher Is Better a . 70.97 |==================================================================== b . 69.57 |================================================================== c . 70.31 |=================================================================== d . 71.32 |==================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 512 - Model: GoogLeNet images/sec > Higher Is Better a . 232.36 |================================================================== b . 234.35 |================================================================== c . 237.48 |=================================================================== d . 235.21 |================================================================== OpenVINO 2022.3 Model: Face Detection FP16 - Device: CPU ms < Lower Is Better a . 149.92 |=============================================================== b . 151.35 |================================================================ c . 158.88 |=================================================================== d . 150.66 |================================================================ OpenVINO 2022.3 Model: Face Detection FP16 - Device: CPU FPS > Higher Is Better a . 159.92 |=================================================================== b . 158.39 |================================================================== c . 151.47 |=============================================================== d . 159.12 |=================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 256 - Model: GoogLeNet images/sec > Higher Is Better a . 209.53 |=================================================================== b . 200.60 |================================================================ c . 206.53 |================================================================== d . 206.70 |================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 64 - Model: GoogLeNet images/sec > Higher Is Better a . 159.05 |=================================================================== b . 154.89 |================================================================= c . 157.31 |================================================================== d . 152.92 |================================================================ TensorFlow 2.12 Device: CPU - Batch Size: 64 - Model: ResNet-50 images/sec > Higher Is Better a . 57.69 |================================================================== b . 59.23 |==================================================================== c . 57.17 |================================================================== d . 57.12 |================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 32 - Model: ResNet-50 images/sec > Higher Is Better a . 50.86 |==================================================================== b . 47.79 |================================================================ c . 50.61 |==================================================================== d . 50.58 |==================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 512 - Model: AlexNet images/sec > Higher Is Better a . 685.25 |=================================================================== b . 671.22 |================================================================== c . 666.10 |================================================================= d . 679.84 |================================================================== OpenVINO 2022.3 Model: Face Detection FP16-INT8 - Device: CPU ms < Lower Is Better a . 294.46 |=================================================================== b . 294.87 |=================================================================== c . 293.86 |=================================================================== d . 293.13 |=================================================================== OpenVINO 2022.3 Model: Face Detection FP16-INT8 - Device: CPU FPS > Higher Is Better a . 325.25 |=================================================================== b . 324.86 |=================================================================== c . 325.91 |=================================================================== d . 326.61 |=================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 256 - Model: AlexNet images/sec > Higher Is Better a . 585.76 |================================================================ b . 593.27 |================================================================= c . 609.80 |=================================================================== d . 599.68 |================================================================== OpenVINO 2022.3 Model: Person Vehicle Bike Detection FP16 - Device: CPU ms < Lower Is Better a . 15.25 |==================================================================== b . 15.19 |=================================================================== c . 15.27 |==================================================================== d . 15.34 |==================================================================== OpenVINO 2022.3 Model: Person Vehicle Bike Detection FP16 - Device: CPU FPS > Higher Is Better a . 6280.34 |================================================================== b . 6303.60 |================================================================== c . 6270.57 |================================================================== d . 6240.17 |================================================================= OpenVINO 2022.3 Model: Person Detection FP16 - Device: CPU ms < Lower Is Better a . 700.16 |=================================================================== b . 703.85 |=================================================================== c . 699.38 |=================================================================== d . 693.14 |================================================================== OpenVINO 2022.3 Model: Person Detection FP16 - Device: CPU FPS > Higher Is Better a . 34.12 |=================================================================== b . 33.97 |=================================================================== c . 34.20 |=================================================================== d . 34.48 |==================================================================== OpenVINO 2022.3 Model: Person Detection FP32 - Device: CPU ms < Lower Is Better a . 696.17 |================================================================= b . 696.77 |================================================================= c . 709.07 |================================================================== d . 715.44 |=================================================================== OpenVINO 2022.3 Model: Person Detection FP32 - Device: CPU FPS > Higher Is Better a . 34.32 |==================================================================== b . 34.35 |==================================================================== c . 33.70 |=================================================================== d . 33.40 |================================================================== OpenVINO 2022.3 Model: Vehicle Detection FP16-INT8 - Device: CPU ms < Lower Is Better a . 17.02 |==================================================================== b . 17.00 |==================================================================== c . 17.03 |==================================================================== d . 16.93 |==================================================================== OpenVINO 2022.3 Model: Vehicle Detection FP16-INT8 - Device: CPU FPS > Higher Is Better a . 5630.29 |================================================================== b . 5637.81 |================================================================== c . 5628.20 |================================================================== d . 5661.26 |================================================================== OpenVINO 2022.3 Model: Machine Translation EN To DE FP16 - Device: CPU ms < Lower Is Better a . 37.24 |==================================================================== b . 37.36 |==================================================================== c . 37.41 |==================================================================== d . 37.37 |==================================================================== OpenVINO 2022.3 Model: Machine Translation EN To DE FP16 - Device: CPU FPS > Higher Is Better a . 643.45 |=================================================================== b . 641.21 |=================================================================== c . 640.39 |=================================================================== d . 641.23 |=================================================================== OpenVINO 2022.3 Model: Weld Porosity Detection FP16 - Device: CPU ms < Lower Is Better a . 5.97 |===================================================================== b . 5.94 |===================================================================== c . 5.94 |===================================================================== d . 5.94 |===================================================================== OpenVINO 2022.3 Model: Weld Porosity Detection FP16 - Device: CPU FPS > Higher Is Better a . 15718.16 |================================================================= b . 15755.63 |================================================================= c . 15763.43 |================================================================= d . 15797.20 |================================================================= OpenVINO 2022.3 Model: Weld Porosity Detection FP16-INT8 - Device: CPU ms < Lower Is Better a . 2.96 |===================================================================== b . 2.95 |===================================================================== c . 2.96 |===================================================================== d . 2.95 |===================================================================== OpenVINO 2022.3 Model: Weld Porosity Detection FP16-INT8 - Device: CPU FPS > Higher Is Better a . 31933.23 |================================================================ b . 32169.37 |================================================================= c . 32075.69 |================================================================= d . 32249.87 |================================================================= TensorFlow 2.12 Device: CPU - Batch Size: 16 - Model: GoogLeNet images/sec > Higher Is Better a . 104.39 |================================================================== b . 105.39 |=================================================================== c . 104.26 |================================================================== d . 101.54 |================================================================= OpenVINO 2022.3 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU ms < Lower Is Better a . 1.12 |==================================================================== b . 1.13 |===================================================================== c . 1.13 |===================================================================== d . 1.13 |===================================================================== OpenVINO 2022.3 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU FPS > Higher Is Better a . 68911.42 |================================================================ b . 69578.86 |================================================================= c . 69611.40 |================================================================= d . 66799.28 |============================================================== OpenVINO 2022.3 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU ms < Lower Is Better a . 0.4 |====================================================================== b . 0.4 |====================================================================== c . 0.4 |====================================================================== d . 0.4 |====================================================================== OpenVINO 2022.3 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU FPS > Higher Is Better a . 110460.51 |=============================================================== b . 111897.59 |================================================================ c . 112093.02 |================================================================ d . 112095.52 |================================================================ OpenVINO 2022.3 Model: Vehicle Detection FP16 - Device: CPU ms < Lower Is Better a . 8.19 |===================================================================== b . 8.18 |===================================================================== c . 8.19 |===================================================================== d . 8.16 |===================================================================== OpenVINO 2022.3 Model: Vehicle Detection FP16 - Device: CPU FPS > Higher Is Better a . 2922.38 |================================================================== b . 2926.31 |================================================================== c . 2920.10 |================================================================== d . 2931.83 |================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 16 - Model: ResNet-50 images/sec > Higher Is Better a . 40.35 |==================================================================== b . 40.64 |==================================================================== c . 40.35 |==================================================================== d . 40.50 |==================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 32 - Model: GoogLeNet images/sec > Higher Is Better a . 129.13 |============================================================== b . 138.10 |================================================================== c . 136.99 |================================================================= d . 140.15 |=================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 16 - Model: AlexNet images/sec > Higher Is Better a . 240.00 |=================================================================== b . 229.08 |================================================================ c . 240.69 |=================================================================== d . 229.92 |================================================================ TensorFlow 2.12 Device: CPU - Batch Size: 64 - Model: AlexNet images/sec > Higher Is Better a . 431.07 |================================================================ b . 450.94 |=================================================================== c . 445.77 |================================================================== d . 453.77 |=================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 32 - Model: AlexNet images/sec > Higher Is Better a . 373.54 |=================================================================== b . 361.25 |================================================================= c . 356.69 |================================================================ d . 347.60 |==============================================================