Would You like a feature Interview?
All Interviews are 100% FREE of Charge
Microsoft’s Copilot+ initiative for supercharged AI PCs is becoming a reality at Computex 2024. AMD today announced its next major chip platforms, Ryzen AI 300 for laptops and Ryzen 9000 for desktops, which target improved AI performance on laptops and faster gaming on desktops, respectively. Notably, the Ryzen AI 300 chips feature improved Neural Processing Units (NPUs) with 50 TOPS (Tera Operations per Second) of AI performance, more than three times that of AMD’s previous laptop hardware. Meanwhile, the new desktop processors are reported to be 16% faster than their predecessors in terms of overall performance.
The key takeaway from these announcements is that Qualcomm is no longer the only one boasting fast AI hardware for Copilot+ PCs. The initiative, announced by Microsoft a few weeks ago, sets a new baseline specification standard for AI PCs. Copilot+ PCs will need an NPU with at least 40 TOPS of AI performance, 16GB of RAM, and a 256GB SSD to be certified as a Copilot+ notebook. Microsoft also tied long battery life to the initiative, but it’s unclear whether the Ryzen AI 300 chips can match the reported 20+ hours of operation of Qualcomm’s latest Snapdragon processors. (We expect Intel to also provide more details about its Lunar Lake Copilot+ chips at Computex later today.)
So far, AMD’s new laptop chips come in two models: the 12-core Ryzen AI 9 HX 370 and the 10-core AI 9 365. As always, the company is expected to round out its lineup with mid-range and low-end offerings over the next year. Both Ryzen AI 9 chips reach boost speeds of at least up to 5GHz and also feature RDNA 3.5 Radeon 890M and 880M graphics. According to AMD’s benchmarks, the Ryzen AI 9 HX 370 is 98% faster than Apple’s M3 chip in Blender and 73% faster than Intel’s Core Ultra 185H. (It’s worth noting that the company tested its hardware with 32GB of RAM against Apple and Intel systems with 16GB of RAM, according to a footnote in the test.)
Powering both the Ryzen AI 300 and Ryzen 9000 chips is AMD’s Zen 5 architecture, which Senior Processor Technical Marketing Manager Donny Woligrosky said in a media briefing is a “radical update” for the company. He claims the architecture improves branch prediction (helping to improve accuracy and latency), increases overall throughput, and boosts instruction bandwidth by up to 2x. For the average user, this means we can expect Zen 5 systems to be a bit more responsive and better equipped to handle heavy data loads.
AMD’s new AI chips are the big draw, but the company isn’t leaving desktop users behind. The new Ryzen 9000 chips top out with the 16-core Ryzen 9 9950X, which has a boost speed of 5.7GHz, pushing the 6GHz dream to the brink. But it’s a beast that requires 170 watts of power, so more reasonable hardware geeks might opt for the Ryzen 9 9900X (120W TDP) or the 8-core Ryzen 7 9700X (65W). These new chips don’t include an NPU like the Ryzen 8000G, but for now, gamers and demanding PC users can make do with the raw computing power of a desktop CPU and a powerful GPU. (NVIDIA is also Powering AI Capabilities with RTX GPUsThis eliminates the need for a standalone NPU.
In addition to these new desktop chips, AMD also announced the X870E and X870 AM5 chipsets, which include features expected in next-gen PCs, such as PCIe 5, USB4, WiFi 7, and DDR5. For older AM4 hardware, AMD also announced the 16-core Ryzen 9 5900XT and the 8-core Ryzen 7 5800XT, both of which can reach speeds of 4.8GHz.
Pricing details for AMD’s new hardware have yet to be announced, but the company said that the Ryzen AI 300 systems will be unveiled in July, along with the Ryzen 9000 chips. These new laptops include the ASUS ZenBook S 16 and Zephyrus G16, as well as the MSI Stealth A16 AI+.