Hardware Podcasts

High-Speed Interconnects for AI & Physical AI with Samtec

OnTrack · 28 Apr 2026 · 39m · Episode 340

What this episode covers

Matt Burns, Director of Technical Marketing at Samtec, discusses the evolution of high-speed interconnects for AI data centers and embedded systems. He explains how connector selection has shifted from an afterthought to a critical early-stage architectural decision to support data rates of 112G, 224G, and 448G. The conversation covers specific product families like Sci-Flex LP, Accelerated HP, and Sci-Flex HD, and details the move toward co-packaged copper and optics to reduce signal loss. Burns also explores how these high-speed technologies are trickling down to 'physical AI' applications in robotics and edge computing.

Most relevant to

large enterprises

Topics

Mentioned

Companies
Samtec
Products
Sci-Flex LP, Accelerated HP, Sci-Flex HD, Broadcom Tomahawk, Marvell Terlinks, Com Express, PCIe 6

Related episodes from other shows

Other shows on the same ground, closest first.

  • The Circuit · 49m

    EP 146: The State of AI Networking with Austin Lyons

    Austin Lyons, writing as Chip Strat, joins Ben Bajarin and Jay Goldberg to discuss the evolution of AI networking, defining the critical distinctions between scale-up, scale-out, and scale-across topologies. The conversation details the technical trade-offs between copper and optical interconnects, explaining how SerDes technology enables higher speeds over shorter distances and why optical is necessary for longer ranges. They highlight the strategic importance of SerDes capabilities for companies like Broadcom and Marvell, and touch on emerging trends like Celestial's photonic fabric and the acquisition of Alpha Wave by Qualcomm.

    Wireless & RFChips, FPGAs & semiconductors
    4 chapters

  • The Amp Hour · 1h 09m

    Interconnectorama

    Chris Gammell of Contextual Electronics and Dave Jones of EEVblog discuss the complexities of board-to-board interconnects, with Jones advocating for direct headers or Samtech connectors to avoid custom cabling hassles. They review the release of KiCad 4.0, noting its stability and community growth, while contrasting it with the high cost of Altium. The conversation also covers industry consolidation, such as Microsemi's acquisition of PMC Sierra, and the rising cost of labor in China driving automation.

    PCB design & layoutSourcing & supply chain
    10 chapters

  • EMS@C-LEVEL · 10m

    BONUS - IPC's CTO & VP Technology Solutions Matt Kelly at APEX 2023 - EMSNOW & SCOOP On Location

    Philip Stoten interviews Matt Kelly, IPC's first CTO and VP of Technology Solutions, about the strategic creation of the CTO role and IPC's evolving focus. Kelly explains that the role was established to provide internal technical horsepower and align standards with member needs, a process accelerated by his tenure during the pandemic lockdowns. He outlines IPC's four main technical pillars: advanced packaging, the factory of the future, electrification, and design, emphasizing the convergence of PCB manufacturing with semiconductor technologies like IC substrates.

    Scaling productionAI & machine learning
    4 chapters

  • The Circuit · 48m

    EP 180: HPE Reflections on AI Compute Racks, Analog Analog Analog Semis.

    Ben Bajarin and Jay Goldberg discuss findings from HPE Discover and Computex, focusing on how Dell and HPE are differentiating their AI infrastructure through custom rack engineering, hybrid cooling, and specialized networking strategies. They analyze the shift toward on-premises 'private AI factories' for enterprises and the growing importance of analog components and passive parts like MLCCs driven by the power demands of NVIDIA's Vera Rubin GPUs.

    Mechanical engineeringAnalog & power electronics
    9 chapters

  • EE Times Current · 41m

    When AI Gets a Body: Physical AI, Humanoids and the Future of Silicon

    Hezi Saar, Executive Director of Product Marketing at Synopsys, discusses the rise of Physical AI, focusing on the semiconductor demands of humanoid robots and autonomous systems. He explains the shift from cloud-only AI to hybrid inference architectures that balance latency, privacy, and cost, highlighting the 'memory wall' bottleneck in edge devices. Saar also details how open standards like MIPI CSE 2.0 and multi-die packaging are critical for reducing risk and enabling secure, scalable physical AI hardware.

    Chips, FPGAs & semiconductorsEmbedded firmware
    8 chapters

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