AMD has detailed new CPU, NPU and GPU architectures powering end-to-end AI infrastructure from the data centre to PCs.
At Computex, the company unveiled an expanded AMD Instinct accelerator roadmap, introducing an annual cadence of leadership AI accelerators including the new AMD Instinct MI325X accelerator with industry-leading memory capacity planned to be available in Q4 2024.
AMD also previewed 5th Gen AMD EPYC server processors, on track to launch in 2H 2024, with leadership performance and efficiency. AMD announced AMD Ryzen AI 300 Series, the third generation of AMD AI-enabled mobile processors, and AMD Ryzen 9000 Series processors for laptop and desktop PCs, respectively.
“This is an incredibly exciting time for AMD as the rapid and accelerating adoption of AI is driving increased demand for our high-performance computing platforms,” says Dr Lisa Su, chair and CEO.
AI and Enterprise Compute for the Data Centre
AMD detailed its expanded multi-generational accelerator roadmap, showing how it plans to deliver performance and memory leadership on an annual cadence for generative AI. The expanded roadmap includes the AMD Instinct MI325X accelerators, with planned availability in Q4 2024, delivering industry leading memory capacity with 288GB of ultra-fast HBM3E memory that extends AMD generative AI performance leadership.
The next-generation AMD CDNA 4 architecture, expected in 2025, will power the AMD Instinct MI350 Series and is expected to drive up to 35x better AI inference performance compared to AMD Instinct MI300 Series with AMD CDNA 33. Continuing performance and feature improvements, the CDNA “Next” architecture will power MI400 series accelerators planned for 2026.
5th Gen AMD EPYC processors (codenamed “Turin”) will leverage the “Zen 5” core and continue the leadership performance and efficiency of the AMD EPYC processor family. 5th Gen AMD EPYC processors are targeted for availability in 2H of 2024.
Reimagining the PC
AMD detailed its next generation “Zen 5” CPU core, built from the ground up for leadership performance and energy efficiency spanning from supercomputers and the cloud to PCs. It also unveiled the AMD XDNA 2 NPU core architecture that delivers 50 TOPs of AI processing performance4 and up to 2x projected power efficiency for generative AI workloads compared to the prior generation.
The AMD XDNA 2 architecture-based NPU is the industry’s first and only NPU supporting advanced Block FP16 data type6, delivering increased accuracy compared to lower precision data types used by competitive NPUs without sacrificing performance. Together, “Zen 5,” AMD XDNA 2 and AMD RDNA 3.5 graphics enable next-gen AI experiences in laptops powered by AMD Ryzen AI 300 Series processors.
AMD has also unveiled the AMD Ryzen 9000 Series desktop processors based on the “Zen 5” architecture, delivering leadership performance in gaming, productivity and content creation. AMD Ryzen 9 9950X processors are the world’s fastest consumer desktop processors7.
Separately, AMD announced the AMD Radeon PRO W7900 Dual Slot workstation graphics card, optimised to deliver scalable AI performance for platforms supporting multiple GPUs. AMD also unveiled AMD ROCm 6.1 for AMD Radeon GPUs, designed to make AI development and deployment with AMD Radeon desktop GPUs more compatible, accessible and scalable.
Powering the Next Wave of Edge AI
AMD has showcased how its AI and adaptive computing technology is powering the next wave of AI innovation at the edge. The new AMD Versal AI Edge Series Gen 2 brings together FPGA programmable logic for real-time pre-processing, next-gen AI Engines powered by XDNA technology for efficient AI inference, and embedded CPUs for post-processing to deliver the highest performing single chip adaptive solution for edge AI. AMD Versal AI Edge Gen 2 devices are available now for early access with over 30 key partners currently in development.