Taipei— At Computex 2025, Qualcomm announced its re-entry into the data center CPU market, unveiling plans to develop custom processors that integrate seamlessly with Nvidia's GPUs. This strategic move aims to enhance AI computing capabilities by combining Qualcomm's energy-efficient CPUs with Nvidia's high-performance GPUs.
Key Facts:
-
Collaboration: Qualcomm's new CPUs will support Nvidia's NVLink Fusion technology, enabling high-speed communication between CPUs and GPUs.
-
Market Re-entry: This marks Qualcomm's return to the data center CPU market since its previous venture with the Centriq 2400 series in 2017.
-
Partnerships: Qualcomm has secured a deal with Saudi AI company Humain to co-develop custom data center CPUs.
Qualcomm's initiative to develop data center CPUs is part of a broader strategy to diversify its product offerings beyond mobile devices. The new processors are designed to work in tandem with Nvidia's NVLink Fusion, a technology that allows for efficient integration of CPUs and GPUs, facilitating faster data processing and improved AI performance.
The collaboration with Nvidia is expected to bolster Qualcomm's position in the data center market, providing solutions that cater to the growing demand for AI-driven computing. By leveraging Nvidia's established GPU technology and Qualcomm's expertise in energy-efficient CPU design, the partnership aims to deliver high-performance computing solutions for data centers worldwide.
Qualcomm's previous attempt to enter the data center CPU market with the Centriq 2400 series faced challenges, including legal disputes and market competition. However, the current collaboration with Nvidia and renewed focus on AI applications signal a strategic shift aimed at capturing a share of the expanding data center market.
"With the ability to connect our custom processors to Nvidia's rack-scale architecture, we're advancing a shared vision of high-performance, energy-efficient computing to the data center," said Cristiano Amon, Qualcomm president and CEO.
Do You Know? Nvidia's NVLink Fusion technology enables a bandwidth of up to 1.8 TB/s per GPU, significantly surpassing the capabilities of PCIe Gen5 and enhancing data transfer speeds between CPUs and GPUs.
Key Terms:
-
NVLink Fusion: A technology developed by Nvidia that allows for high-speed communication between CPUs and GPUs, facilitating efficient data processing in AI applications.
-
Data Center CPU: A central processing unit designed specifically for use in data centers, optimized for handling large-scale computing tasks and workloads.
-
AI Computing: The use of specialized hardware and software to perform tasks associated with artificial intelligence, such as machine learning and data analysis.