AI Requires Tailored DRAM Solutions: Part 4
October 15, 2020
Frank Ferro, Senior Director Product Management at Rambus, and Shane Rau, Senior Research Executive at IDC, recently hosted a webinar that explores the role of tailored DRAM solutions in advancing artificial intelligence. Part three of this four-part series touched on a wide range of topics including the impact of AI on specific hardware systems, training versus inference, and selecting the most appropriate memory for AI/ML. This blog post (part four) takes a closer look at the evolution of HBM and GDDR6, as well as the design tradeoffs and challenges of the two memory types.
To read the full article, click here
Related Semiconductor IP
Related Blogs
- AI Requires Tailored DRAM Solutions: Part 1
- AI Requires Tailored DRAM Solutions: Part 2
- AI Requires Tailored DRAM Solutions: Part 3
- Intel vs. ARM: In the Smartphone Era (Part 4)
Latest Blogs
- Rivian’s autonomy breakthrough built with Arm: the compute foundation for the rise of physical AI
- AV1 Image File Format Specification Gets an Upgrade with AVIF v1.2.0
- Industry’s First End-to-End eUSB2V2 Demo for Edge AI and AI PCs at CES
- Integrating Post-Quantum Cryptography (PQC) on Arty-Z7
- UA Link PCS customizations from 800GBASE-R Ethernet PCS Clause 172