Thinking Small to Think Big: AMD Modular Architecture is Advancing Sustainability
Tackling macro technology challenges often entails devising micro solutions that scale. At AMD, we have embraced this approach for 55 years as we design high performance and adaptive computing solutions. In my role to advance sustainability at AMD, I have seen incredible innovations where AMDers think small to think big and in doing so, create major co-benefits for technology users and the planet.
A powerful example is AMD developing “chiplets” - a revolutionary semiconductor design approach that embraces modular architecture. The innovation addresses several technology and sustainability challenges simultaneously such as cutting manufacturing environmental impacts and costs while increasing compute performance and energy efficiency. Instead of one large monolithic chip, AMD engineers reconfigured the component IP building blocks using a flexible, scalable connectivity we designed known as Infinity Fabric. This laid the foundation for our Infinity Architecture configuring multiple individual chiplets to scale compute cores in countless designs that further optimize energy efficiency.
AMD recently measured the sustainability benefits of chiplets in the wafer manufacturing process for one product line, and the results are compelling. Producing 4th Gen EPYC CPUs with 8 separate compute chiplets instead of one monolithic die saved ~50K metric tons of CO2e in 2023 through avoidance of wafers manufactured, approximately the same as the annual operational CO2e footprint of AMD in 2022.[i]
Related Chiplet
- Direct Chiplet Interface
- HBM3e Advanced-packaging chiplet for all workloads
- UCIe AP based 8-bit 170-Gsps Chiplet Transceiver
- UCIe based 8-bit 48-Gsps Transceiver
- UCIe based 12-bit 12-Gsps Transceiver
Related Blogs
- Revolutionizing Automotive Design with Chiplet-Based Architecture
- Avoiding Multi-Die System Re-spins with New Early Architecture Exploration Technology
Latest Blogs
- Scaling AI Data Centers: The Role of Chiplets and Connectivity
- Is a GPU, ASIC or chiplet-based SoC better for AI as we switch from training to inference?
- Siemens EDA intros next-gen ESD; focus on chiplet-design kits (CDK)
- Accelerating the AI Economy through Heterogeneous Integration
- Outlook 2025: Embracing Chiplets