AMD unveiled its next-generation Ryzen AI 300 series processors on Monday, announcing that these chips will be integrated into over 100 upcoming personal computers equipped with advanced Artificial Intelligence capabilities. The Santa Clara, California-based company is pioneering a new category of Windows-based AI PCs, featuring a neural processing unit (NPU) capable of at least 50 Tera Operations Per Second (TOPS), all-day battery life, and access to the most advanced AI models.
AMD’s event in Los Angeles was geared towards sparking renewed interest in PCs, emphasizing the importance of AI. While the senior leadership highlighted the company’s new AI chips for laptops and desktops, they also reinforced the ongoing relevance of computer performance in the era of NPUs, which surpass traditional central processing units (CPUs) in handling AI tasks.
At the event, AMD shared technical details about the new Ryzen AI 300 Series chips and the Ryzen 9000 Series processors that will power the next generation of laptops and desktops. The company announced two Ryzen AI 300 mobile APUs, both featuring the same NPU with 50 TOPS but differing in other specifications. The flagship chip, the Ryzen AI 9 HX 370, boasts 12 cores and 24 threads. Additionally, AMD introduced the Ryzen 9000 desktop CPU, claiming the Ryzen 9 9950X is the “fastest consumer desktop processor.” This significant move positions AMD to compete fiercely with Intel, Qualcomm, and Apple. The new processors will be used in PCs from brands such as Asus, MSI, and HP, available later this month.
Jack Huynh, Senior Vice President and General Manager of Computing and Graphics at AMD, stated, “As we think about building the next AI PC, we did not want to build yet another PC. Of course, AI can make things faster, but that’s not what we’re here to do. We are here to create new experiences; we want to build disruptive form factors.”
First introduced at the Computex trade show in Taiwan last month, these processors, manufactured using a mix of 4 nm and 3 nm processes, are touted as the “world’s most powerful NPU” with 50 TOPS of local AI acceleration. In comparison, Qualcomm’s Snapdragon X Elite and X Plus chips reach 45 TOPS, and Intel’s upcoming “Lunar Lake” chips are expected to have a 45 TOPS ceiling. This high processing power is essential for Copilot Plus features in Windows 11, which require an NPU with at least 40 TOPS.
Vamsi Boppana, Senior Vice President of the Artificial Intelligence Group at AMD, explained, “The XDNA 2 architecture, unlike other NPUs on the market, is built on a spatial data flow architecture. It is a two-dimensional array of AI compute with a smart interconnect that can be programmed dynamically at runtime and reconfigured to create custom compute hierarchies. This is unlike any other NPU out there.”
The introduction of AI PCs aims to revive the market, which has seen a steep decline in recent years. AMD, Intel, and Qualcomm are all focusing on AI chips, and original equipment manufacturers (OEMs) like Dell, HP, Asus, and Lenovo are heavily relying on these processors to attract consumers. Apple also plans to integrate AI into its Mac products later this year, aiming to enhance user interaction with these AI-enabled devices.
AMD’s gradual gains over its larger competitor, Intel, are noteworthy, and the company believes its next-generation AI processors could give it an edge in the market. AMD is committed to delivering performance improvements along with better battery life in thinner and lighter laptops. Despite Intel’s dominance, AMD emphasized openness and provided compelling reasons for consumers to consider AMD-powered computers.
 capable of at least 50 Tera Operations Per Second (TOPS), all-day battery life, and access to the most advanced AI models.){kind=link}