nvidia-rtx6000ada-48g 2 x Intel Xeon Platinum 8352V testing with a Supermicro X12DPG-OA6 v1.01 (1.4b BIOS) and ASPEED 48GB on Ubuntu 20.04 via the Phoronix Test Suite. ASPEED: Processor: 2 x Intel Xeon Platinum 8352V @ 2.10GHz (72 Cores / 144 Threads), Motherboard: Supermicro X12DPG-OA6 v1.01 (1.4b BIOS), Chipset: Intel Device 0998, Memory: 512GB, Disk: 280GB INTEL SSDPE21D280GA, Graphics: ASPEED 48GB, Audio: NVIDIA Device 22ba, Network: 2 x Intel I350 OS: Ubuntu 20.04, Kernel: 5.4.0-171-generic (x86_64), Desktop: GNOME Shell 3.36.9, Display Server: X Server 1.20.13, Display Driver: NVIDIA, OpenCL: OpenCL 3.0 CUDA 12.4.131, Vulkan: 1.3.277, Compiler: GCC 9.4.0 + CUDA 12.2, File-System: ext4, Screen Resolution: 1024x768 ProjectPhysX OpenCL-Benchmark 1.6 Operation: FP64 Compute TFLOPs/s > Higher Is Better ASPEED . 1.534 |=============================================================== ProjectPhysX OpenCL-Benchmark 1.6 Operation: FP32 Compute TFLOPs/s > Higher Is Better ASPEED . 93.03 |=============================================================== ProjectPhysX OpenCL-Benchmark 1.6 Operation: FP16 Compute TFLOPs/s > Higher Is Better ASPEED . 94.62 |=============================================================== ProjectPhysX OpenCL-Benchmark 1.6 Operation: INT64 Compute TIOPs/s > Higher Is Better ASPEED . 4.073 |=============================================================== ProjectPhysX OpenCL-Benchmark 1.6 Operation: INT32 Compute TIOPs/s > Higher Is Better ASPEED . 46.69 |=============================================================== ProjectPhysX OpenCL-Benchmark 1.6 Operation: INT16 Compute TIOPs/s > Higher Is Better ASPEED . 34.33 |=============================================================== ProjectPhysX OpenCL-Benchmark 1.6 Operation: INT8 Compute TIOPs/s > Higher Is Better ASPEED . 22.76 |=============================================================== ProjectPhysX OpenCL-Benchmark 1.6 Operation: Memory Bandwidth Coalesced Read GB/s > Higher Is Better ASPEED . 864.62 |============================================================== ProjectPhysX OpenCL-Benchmark 1.6 Operation: Memory Bandwidth Coalesced Write GB/s > Higher Is Better ASPEED . 860.28 |==============================================================