Hardware Podcasts

Beyond PPA: How Foundation IP Enables Predictable Execution and Lower TCO for AI-Era SoCs

EE Times Current · 7 Oct 2026 · 24m

What this episode covers

Ravi Todi, Executive Director of Product Management at Synopsys, explains that competitive power, performance, and area (PPA) are no longer sufficient for AI-era SoCs, as design complexity and execution risk at advanced nodes require a focus on predictable execution and total cost of ownership (TCO). He details how Synopsys' Foundation IP platform—integrating embedded memory, logic libraries, and I/O—reduces integration risks and avoids expensive re-spins, which can cost $20–$40 million in mask sets and delay tape-outs by 6–9 months. Todi highlights that this holistic approach enables first-pass silicon success, cross-foundry portability, and optimized PPA for both high-performance compute (HPC) and edge AI (HAI) designs, shifting the buying decision from lowest IP license price to lowest total cost of silicon on time.

Most relevant to

large enterprises

Topics

Mentioned

Companies
Synopsys
Also
Ravi Todi

Related episodes from other shows

Other shows on the same ground, closest first.

  • The Amp Hour · 1h 09m

    The RP1 and beyond with the Raspberry Pi Hardware team

    James Adams (CTO) and Liam Fraser (Hardware/Software Engineer) from Raspberry Pi discuss the development of the RP1 custom silicon, the success of the RP2040 microcontroller, and the architecture of the Raspberry Pi 5. They explain how RP1 acts as a Southbridge/chiplet to offload I/O functions from the main Broadcom SoC, allowing for cost and complexity reductions as process nodes shrink. The conversation covers their internal chip design tooling, sourcing strategies during the chip shortage, and the rationale for sticking with ARM over RISC-V.

    Chips, FPGAs & semiconductorsMicrocontrollers & dev platforms
    6 chapters

  • Moore's Lobby · 1h 01m

    Synopsys' Stelios Diamantidis Is Bringing the Magic of AI To Chip Design

    Stelios Diamantidis, Distinguished Architect at Synopsys, discusses the evolution of chip design from manual processes to AI-driven optimization. He recounts his career journey, including founding two EDA startups focused on verification and Silicon Lifecycle Management (SLM), before joining Synopsys to lead the development of DSO.ai. Diamantidis explains how reinforcement learning is used to solve intractable physical design problems, optimizing power, performance, and area (PPA) for diverse verticals like CPUs, GPUs, and automotive chips.

    AI & machine learningEDA & CAD tools
    8 chapters

  • The Circuit · 55m

    Episode 111: Talking Chips and Wafers with Chips and Wafers

    Simi Sherman and Chaim Eisenberg, founders of the semiconductor data analytics firm Chips and Wafers, explain how they aggregate granular, timely data to help investors predict company performance and industry trends. They discuss specific methodologies, such as tracking memory IC exports from Korea to Taiwan to model TSMC's CoWoS capacity, and using Besi's Malaysia-to-China shipments to forecast quarterly misses. The conversation also covers the industry's shift from monolithic SoCs to disaggregated chiplets, highlighting the increasing complexity and cost of ABF substrates and the rising importance of backend packaging.

    Sourcing & supply chainChips, FPGAs & semiconductors
    7 chapters

  • Embedded.fm · 48m

    105: Some Paths Are More Suicidal

    Manny Wright, Senior FAE Manager at Cortus, explains the process of designing custom processor IP, from RTL to silicon fabrication. He details the high costs and long timelines (1.5+ years, millions of dollars) involved in tape-out, the role of FPGAs like the Xilinx Spartan in early development, and the importance of configurable cores for power and cost efficiency. Wright also discusses security features, debugging methods like JTAG and trace, and the challenges of protecting intellectual property from reverse engineering.

    Chips, FPGAs & semiconductorsMicrocontrollers & dev platforms
    6 chapters

The summary, chapters and topics are generated from the episode’s audio by this directory, not written by EE Times Current. The episode itself belongs to its publisher.