ASUS Demonstrates AI and Immersion-Cooling Solutions at SC23

At SC23, ASUS will showcase the latest NVIDIA-qualified ESC N8A-E12 HGX H100 eight-GPU server empowered by dual-socket AMD EPYC 9004 processors and is designed for enterprise-level generative AI with market-leading integrated capabilities. Related to NVIDIA® announcement on the latest NVIDIA H200 Tensor Core GPU at SC23, which is the first GPU to offer HBM3E for faster, larger memory to fuel the acceleration of generative AI and large language models, ASUS will offer an update of H100-based system with an H200-based drop-in replacement in 2024.

Another demonstration at SC23 is the Arm-based 2U4N server — ASUS RS720QN-E11. This is designed around the NVIDIA Grace CPU Superchip and NVIDIA NVLink®-C2C technology, with power-efficient dense infrastructure and D2C cooling solutions. ASUS will also launch a server powered by the latest NVIDIA GH200 Grace Hopper Superchip to enable scientists and researchers to tackle the world’s most challenging problems by accelerating complex AI and HPC applications running terabytes of data. In addition to the hardware showcase, ASUS will host a series of session talks at SC23, inviting speakers from leading industries and domains, along with demos, related content and more.

As an AI-supercomputing domain expert, ASUS offers optimized server design and rack integration to meet the needs for AI/HPC workloads and delivers a no-code AI platform with a complete in-house AI software stack that helps any business to accelerate AI development on LLM pre-training, fine-tuning and inference with lower risk and faster catch-up — minimizing or even eliminating the need to start from scratch. In addition, ASUS has experience of running as a supercomputer operator in Taiwan with both operations and business support systems (OSS and BSS), working with customers to realize data-center-infrastructure strategies that optimize operating expense (OpEx).