Advanced Micro Devices (AMD) has introduced its newest artificial intelligence (AI) processor, the MI325X. This advanced version of the MI300 series is expected to be available in the fourth quarter.
At the Computex technology trade show in Taipei, AMD also announced that it will develop AI chips over the next two years to challenge Nvidia’s dominance.
It should be noted that Nvidia has an almost 80% share in the market of AI semiconductors.
AMD has announced a new series of AI chips named MI350, which is expected to be available in 2025. According to the company, it expects the MI350 chip to perform 35 times better in inference than the currently existing MI300 series.
Further, the company announced that the MI400 series of chips will arrive in 2026 and be based on a new type of architecture called ‘Next.’
Competition between AMD and Nvidia
“AI is our number one priority and we’re at the beginning of an incredibly exciting time for the industry as AI transforms virtually every business, improves our quality of life, and reshapes every part of the computing market,” AMD CEO Lisa Su said during the Computex tech conference in Taipei.
The releases and announcements from AMD came just a day after Nvidia released its next-gen AI chip, ‘Rubin.’ Rubin is a successor to Nvidia’s ‘Blackwell’ model, which was announced earlier this year.
Nvidia CEO Jensen Huang has announced that his company will release new AI chips yearly. AMD also plans to do the same and hopes to challenge the current market leader.
The Ryzen AI 300 series for AI laptops will compete with Intel’s Lunar Lake and Qualcomm’s Snapdragon X. AMD is also partnering with Microsoft to allow these chips to power its laptops with its AI chatbot Copilot.
More announcements from AMD
At the event on Monday, AMD also introduced its next-generation Zen 5 CPU architecture and XDNA 2 GPU NPU architecture, powering the new AMD Ryzen 9000 series processors for gaming PCs and the company’s third-generation Ryzen AI processors for ultrabooks.
According to the company, the third-gen processors will allow up to 50 trillion operations per second (TOPs) to enable on-device AI experiences like recall, live caption, and more.
The Ryzen AI 300 series has the new XDNA 2 neural processing unit (NPU) with up to 50 TOPs of performance, a 12-core central processing unit (CPU), and a new graphics processing unit (GPU) based on RDNA 3.5 architecture with up to 16 compute units on the flagship AMD Ryzen AI 9 HX 370.
Su also said that the new Ryzen 9000 series for desktops will be the “world’s fastest consumer PC processors” for gaming and content creation.
Both the series are expected to launch in July.
The CEO also revealed that Ryzen AI 300, Ryzen 9000, and 5th-gen EPYC chips will be built on the latest “Zen 5” architecture.
ABOUT THE EDITOR
Abhishek Bhardwaj Abhishek brings a wealth of experience in covering diverse stories across different beats. Having contributed to renowned wire agencies and Indian media outlets like ANI and NDTV, he is keenly interested in Tech, Business and Defense coverage.
