ASUS showcases NVIDIA GB300 NVL72 for Artificial Intelligence at SC25

ASUS will showcase a full spectrum of Artificial Intelligence infrastructure at Supercomputing 2025, highlighting the XA GB721-E2 Artificial Intelligence POD built on NVIDIA GB300 NVL72 equipped with 72 Blackwell Ultra GPUs and 36 Grace CPUs.

ASUS announced a showcase of its end-to-end Artificial Intelligence infrastructure portfolio at Supercomputing 2025. The company framed the effort under the strategy “Ubiquitous Artificial Intelligence. Incredible Possibilities.” and positioned itself as a total infrastructure solution provider offering cloud and on-premise systems aimed at accelerating customers’ time to market with higher computing performance.

The portfolio emphasizes integration of the latest NVIDIA compute platforms with supporting system technologies such as advanced cooling, network orchestration, and large-scale deployment capabilities. ASUS said it can deliver a full spectrum of Artificial Intelligence solutions that span from personal workstations to national supercomputing systems, reflecting a focus on scalable, deployment-ready architectures intended to democratize access to powerful Artificial Intelligence technologies.

At the top of the portfolio is the XA GB721-E2, described as an ASUS Artificial Intelligence POD built on the NVIDIA GB300 NVL72 rack-scale architecture. That system pairs 72 NVIDIA Blackwell Ultra GPUs with 36 NVIDIA Grace CPUs and uses a 100% liquid-cooling system combined with integrated switch trays. ASUS presents the design as offering deployment-ready scalability and energy-efficient performance, delivering roughly 10-petaflops-class computing power for enterprise Artificial Intelligence and national-cloud workloads.

55

Impact Score

Marvell unveils ultra low power 2 nm dense sram with major efficiency gains

Marvell is detailing performance data for its 2 nm custom sram ip, showing sharp gains in power, area, and bandwidth density over standard dense sram offerings. The company positions the architecture as a strategic edge as logic scaling continues to outpace memory in leading semiconductor nodes.

Contact Us

Got questions? Use the form to contact us.

Contact Form

Clicking next sends a verification code to your email. After verifying, you can enter your message.