Home » Newsroom » Blog » Semiconductor Engineering: Tech Talk – Changes In AI SoCs

Semiconductor Engineering: Tech Talk – Changes In AI SoCs

Mar 16, 2020
Madelyn Miller
< 1 min read

Tech Talk Video: Changes In AI SoCs

March 16, 2020 – By Ed Sperling

Ed Sperling of Semiconductor Engineering interviews Kurt Shuler at Arteris headquarters in this new video.

Arteris’ Kurt Shuler talks about the tradeoffs in AI SoCs, which range from power and performance to flexibility, depending on whether processing elements are highly specific or more general, and the need for more modeling.

To see the video on the SemiEngineering page, please click HERE.

See other SemiEngineering tech talk videos here.

Blogs

Latest Blogs

Blog

Power Electronics Magazine: How Network-on-Chip Architectures Are Powering the Future of Microcontroller Design

Network-on-Chip (NoC) technology is redefining how microcontrollers (MCUs) handle performance, power efficiency, and scalability. As MCUs take on more complex, AI-driven, and safety-critical tasks, NoC architectures provide the structured, high-speed interconnects needed to keep pace. Learn more about how Arteris

Learn more about this

Blog

Semiconductor Engineering: Efficiency Defines The Future Of Data Movement

As AI workloads expand and chiplet architectures evolve, data movement now consumes more energy than computation itself. Achieving higher performance within fixed power budgets demands efficient, intelligent interconnects and automation across multi-die SoC designs. Learn more in the article.

Learn more about this

Blog

EE Times: A Guide to Building Chiplets Today While Shaping Tomorrow’s Standards

Chiplet standards like UCIe, AIB, and BoW are still evolving, but design teams can start building with chiplets today by adopting packaging automation, structured IP metadata, and scalable interconnect fabrics that enable flexibility and future-proof integration. Learn how to design

Learn more about this

Blog

EDN: A Logically Correct SoC Design Isn’t an Optimized Design

Automation in SoC design is evolving beyond correctness toward true optimization. Just as modern GPS systems account for real-world traffic, AI-driven, physically aware automation for NoC design minimizes wire length, manages congestion, and adapts dynamically to design changes — closing

Learn more about this

Blog

Semiconductor Engineering: The Future Of SoC Design Is Data Movement

The semiconductor industry is shifting from focusing on raw compute to tackling the growing challenge of data movement in complex SoCs. With advances in chiplets, high-bandwidth memory, CXL fabrics, and automotive zonal architectures, predictable performance now depends on layered, automated,

Learn more about this

Blog

Electronic Design: Speeding the Process of Building IPs, Chiplets, and SoCs

Designing modern SoCs and multi-die systems requires faster integration of thousands of IP blocks and chiplets while minimizing errors. Structured metadata standards like IP-XACT, combined with automation, are transforming this process by ensuring consistency, tool interoperability, and accurate hardware/software alignment

Learn more about this