rt gh200 ARMv8 Neoverse-V2 testing with a Pegatron JIMBO P4352 (00022432 BIOS) and NVIDIA GH200 144G HBM3e 143GB on Ubuntu 24.04 via the Phoronix Test Suite. a: Processor: ARMv8 Neoverse-V2 @ 3.47GHz (72 Cores), Motherboard: Pegatron JIMBO P4352 (00022432 BIOS), Memory: 1 x 480GB LPDDR5-6400MT/s NVIDIA 699-2G530-0236-RC1, Disk: 1000GB CT1000T700SSD3, Graphics: NVIDIA GH200 144G HBM3e 143GB, Network: 2 x Intel X550 OS: Ubuntu 24.04, Kernel: 6.8.0-45-generic-64k (aarch64), Display Driver: NVIDIA, OpenCL: OpenCL 3.0 CUDA 12.6.65, Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200 b: Processor: ARMv8 Neoverse-V2 @ 3.47GHz (72 Cores), Motherboard: Pegatron JIMBO P4352 (00022432 BIOS), Memory: 1 x 480GB LPDDR5-6400MT/s NVIDIA 699-2G530-0236-RC1, Disk: 1000GB CT1000T700SSD3, Graphics: NVIDIA GH200 144G HBM3e 143GB, Network: 2 x Intel X550 OS: Ubuntu 24.04, Kernel: 6.8.0-45-generic-64k (aarch64), Display Driver: NVIDIA, OpenCL: OpenCL 3.0 CUDA 12.6.65, Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200 c: Processor: ARMv8 Neoverse-V2 @ 3.47GHz (72 Cores), Motherboard: Pegatron JIMBO P4352 (00022432 BIOS), Memory: 1 x 480GB LPDDR5-6400MT/s NVIDIA 699-2G530-0236-RC1, Disk: 1000GB CT1000T700SSD3, Graphics: NVIDIA GH200 144G HBM3e 143GB, Network: 2 x Intel X550 OS: Ubuntu 24.04, Kernel: 6.8.0-45-generic-64k (aarch64), Display Driver: NVIDIA, OpenCL: OpenCL 3.0 CUDA 12.6.65, Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200 wd: Processor: ARMv8 Neoverse-V2 @ 3.47GHz (72 Cores), Motherboard: Pegatron JIMBO P4352 (00022432 BIOS), Memory: 1 x 480GB LPDDR5-6400MT/s NVIDIA 699-2G530-0236-RC1, Disk: 1000GB CT1000T700SSD3, Graphics: NVIDIA GH200 144G HBM3e 143GB, Network: 2 x Intel X550 OS: Ubuntu 24.04, Kernel: 6.8.0-45-generic-64k (aarch64), Display Driver: NVIDIA, OpenCL: OpenCL 3.0 CUDA 12.6.65, Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200 LiteRT 2024-10-15 Model: DeepLab V3 Microseconds < Lower Is Better a .. 1554.91 |================================================================ b .. 1560.02 |================================================================ c .. 1587.52 |================================================================= wd . 1584.85 |================================================================= LiteRT 2024-10-15 Model: SqueezeNet Microseconds < Lower Is Better a .. 974.49 |================================================================== b .. 976.67 |================================================================== c .. 971.85 |================================================================= wd . 980.63 |================================================================== LiteRT 2024-10-15 Model: Inception V4 Microseconds < Lower Is Better a .. 8385.10 |================================================================ b .. 8417.11 |================================================================= c .. 8472.32 |================================================================= wd . 8378.40 |================================================================ LiteRT 2024-10-15 Model: NASNet Mobile Microseconds < Lower Is Better a .. 12144.3 |================================================================= b .. 11628.0 |============================================================== c .. 11446.3 |============================================================= wd . 12010.2 |================================================================ LiteRT 2024-10-15 Model: Mobilenet Float Microseconds < Lower Is Better a .. 582.53 |================================================================== b .. 586.66 |================================================================== c .. 584.00 |================================================================== wd . 585.48 |================================================================== LiteRT 2024-10-15 Model: Mobilenet Quant Microseconds < Lower Is Better a .. 885.31 |================================================================= b .. 878.92 |================================================================= c .. 892.21 |================================================================== wd . 896.03 |================================================================== LiteRT 2024-10-15 Model: Inception ResNet V2 Microseconds < Lower Is Better a .. 9751.92 |================================================================= b .. 9364.56 |============================================================== c .. 9731.31 |================================================================= wd . 9626.92 |================================================================ LiteRT 2024-10-15 Model: Quantized COCO SSD MobileNet v1 Microseconds < Lower Is Better a .. 1509.54 |================================================================= b .. 1493.54 |================================================================ c .. 1506.16 |================================================================= wd . 1508.69 |================================================================= oneDNN 3.6 Harness: IP Shapes 1D - Engine: CPU ms < Lower Is Better a .. 37.21 |=================================================================== b .. 36.45 |================================================================== c .. 36.87 |================================================================== wd . 36.84 |================================================================== oneDNN 3.6 Harness: IP Shapes 3D - Engine: CPU ms < Lower Is Better a .. 21.75 |================================================================== b .. 21.43 |================================================================= c .. 21.82 |=================================================================== wd . 21.94 |=================================================================== oneDNN 3.6 Harness: Convolution Batch Shapes Auto - Engine: CPU ms < Lower Is Better a .. 33.63 |=================================================================== b .. 33.27 |================================================================== c .. 33.49 |=================================================================== wd . 33.64 |=================================================================== oneDNN 3.6 Harness: Deconvolution Batch shapes_1d - Engine: CPU ms < Lower Is Better a .. 64.04 |================================================================== b .. 64.79 |=================================================================== c .. 63.01 |================================================================= wd . 63.49 |================================================================== oneDNN 3.6 Harness: Deconvolution Batch shapes_3d - Engine: CPU ms < Lower Is Better a .. 64.90 |================================================================== b .. 65.40 |=================================================================== c .. 64.90 |================================================================== wd . 64.38 |================================================================== oneDNN 3.6 Harness: Recurrent Neural Network Training - Engine: CPU ms < Lower Is Better a .. 33136.4 |================================================================= b .. 33108.0 |================================================================= c .. 32626.6 |================================================================ wd . 33137.9 |================================================================= oneDNN 3.6 Harness: Recurrent Neural Network Inference - Engine: CPU ms < Lower Is Better a .. 12605.2 |================================================================ b .. 12820.2 |================================================================= c .. 12756.3 |================================================================= wd . 12676.2 |================================================================ XNNPACK b7b048 Model: FP32MobileNetV1 us < Lower Is Better a .. 639 |===================================================================== b .. 641 |===================================================================== c .. 633 |==================================================================== wd . 639 |===================================================================== XNNPACK b7b048 Model: FP32MobileNetV2 us < Lower Is Better a .. 945 |===================================================================== b .. 937 |==================================================================== c .. 934 |==================================================================== wd . 946 |===================================================================== XNNPACK b7b048 Model: FP32MobileNetV3Large us < Lower Is Better a .. 1513 |==================================================================== b .. 1495 |=================================================================== c .. 1493 |=================================================================== wd . 1503 |==================================================================== XNNPACK b7b048 Model: FP32MobileNetV3Small us < Lower Is Better a .. 1042 |==================================================================== b .. 1029 |=================================================================== c .. 1045 |==================================================================== wd . 1049 |==================================================================== XNNPACK b7b048 Model: FP16MobileNetV1 us < Lower Is Better a .. 470 |===================================================================== b .. 464 |==================================================================== c .. 470 |===================================================================== wd . 470 |===================================================================== XNNPACK b7b048 Model: FP16MobileNetV2 us < Lower Is Better a .. 849 |===================================================================== b .. 836 |==================================================================== c .. 853 |===================================================================== wd . 853 |===================================================================== XNNPACK b7b048 Model: FP16MobileNetV3Large us < Lower Is Better a .. 1326 |==================================================================== b .. 1316 |=================================================================== c .. 1309 |=================================================================== wd . 1325 |==================================================================== XNNPACK b7b048 Model: FP16MobileNetV3Small us < Lower Is Better a .. 1005 |==================================================================== b .. 993 |=================================================================== c .. 985 |=================================================================== wd . 1004 |==================================================================== XNNPACK b7b048 Model: QS8MobileNetV2 us < Lower Is Better a .. 949 |===================================================================== b .. 943 |===================================================================== c .. 933 |==================================================================== wd . 945 |=====================================================================