Podcast cover
Semi Doped · Technology

Semi Doped

Semiconductor business and engineering with Vikram Sekar and Austin Lyons.

Episodes

Episode cover

Synopsys Will Take a Royalty on Amazon's Chips and Sell GPT-Synopsys: Ravi Subramanian

08 Oct 2026AI processed

Synopsys is transforming semiconductor development through application-optimized IP and agentic AI integration. The recent $1 billion-plus deal with Amazon exemplifies a shift toward workload-specific silicon, where custom IP interfaces are engineered for precise metrics like latency and power efficiency rather than re...

Episode cover

Grok Bots and How CPUs are used in Agentic AI

24 Aug 2026AI processed

Agentic AI is shifting from local, hardware-intensive setups toward simplified, cloud-based virtual machine environments. This transition creates significant demand for specialized "agentic CPUs" designed to handle non-inference tasks—such as data retrieval and file management—that would otherwise bottleneck the GPU "g...

Episode cover

GlobalFoundries Thomas Barber: CPO, Silicon Photonics, 300mm, SiGe, OCI, NRZ

07 Aug 2026AI processed

Silicon photonics serves as a critical foundation for modern data center infrastructure, enabling the transition from copper to optical communication as bandwidth demands for AI scale-up networks surge. GlobalFoundries, leveraging its history with IBM Microelectronics and 300mm wafer manufacturing, provides the essenti...

Episode cover

Qualcomm's HBC Memory, Alphawave, Modular, and more

29 Jun 2026AI processed

Qualcomm is aggressively pivoting from its legacy as a communications-focused company toward a diversified strategy centered on data centers, automotive technology, and edge AI. This shift relies on the integration of new technical capabilities, specifically High Bandwidth Compute (HBC), which aims to optimize inferenc...

Episode cover

Huawei's Tau Scaling Law: Is the "EUV Killer" Real?

29 May 2026AI processed

Huawei’s recent announcement regarding "tau scaling" proposes a shift from traditional transistor-level geometric shrinking to system-level delay reduction, aiming to bypass the need for EUV lithography. By utilizing hybrid bonding to stack logic chips, Huawei seeks to increase transistor density and performance withou...

Episode cover

Reiner Pope (MatX): Designing AI Chips From First Principles for LLMs

09 Apr 2026AI processed

Reiner Pope, co-founder and CEO of MatX, discusses the company's mission to create advanced chips for large language models (LLMs). Pope details his and his co-founder's departure from Google to address the economic challenges of running increasingly large and expensive models like GPT-3. He addresses initial investor ...

Follow this podcast in Podwise

Sign in to get AI summaries, transcripts and mind maps for any episode, including new ones.

Open in Podwise