Hardware Podcasts

CEO Interview: Flex Logix’ Geoff Tate on AI | Open Source Hits Hardware

EE Times Current · 5 Feb 2021 · 40m

What this episode covers

Geoff Tate, CEO of Flex Logix, explains the distinction between AI training and inference, arguing that engineers must benchmark their specific neural network models on target chips rather than relying on generic metrics like TOPS, which he demonstrates can be misleading compared to real-world performance on models like YOLO V3. Industry analyst Kevin Krewell discusses the rise of open technologies in hardware, tracing the evolution from open source software like Linux to open RAN in networking and the growing ecosystem around the open-source RISC-V architecture as an alternative to proprietary instruction sets like ARM and x86.

Most relevant to

large enterprises and companies scaling up

Topics

Mentioned

Companies
Flex Logix, NVIDIA, Rambus, ARM, Intel
Products
Xavier NX, YOLO V3, ResNet 50, Nintendo 64, Linux, Open RAN
Chips
RISC-V, x86
Also
Geoff Tate, Kevin Krewell

Related episodes from other shows

Other shows on the same ground, closest first.

  • The Circuit · 41m

    Episode 85: OpenAI leaves AI Silicon in the Dust

    Ben Bajarin and Jay Goldberg discuss how OpenAI's new model, which uses reinforcement learning and multi-level reasoning, drastically increases inference compute demands, leaving current silicon architectures behind. They analyze the competitive landscape, noting that while Nvidia dominates training, the inference market is becoming more open due to high costs and the need for edge deployment. The hosts also highlight Google's recent demos, including a podcast generator and a game engine, as evidence of rapid software innovation that continues to outpace hardware development.

    AI & machine learningChips, FPGAs & semiconductors
    7 chapters

  • The Circuit · 38m

    Episode 8: AI Infrastructure and Silicon Demands

    Ben Bajarin and Jay Goldberg discuss the immense compute demands of training large foundational models like GPT-3 and GPT-4, noting that Nvidia’s A100 and H100 GPUs dominate this $300 billion infrastructure market due to CUDA’s software moat. They analyze the bottleneck in inference scalability, arguing that while training is a small fraction of the market, inference costs will drop as incumbents like Google, Amazon, and Apple leverage their own silicon, leaving little room for new AI accelerator startups. The hosts conclude that generative AI represents a powerful new category of productivity software rather than a fundamental shift in human-computer interaction, driving data center Capex through natural upgrade cycles rather than complete rebuilds.

    Chips, FPGAs & semiconductorsConnected products & IoT
    8 chapters

  • The Circuit · 41m

    Episode 105: Sanity Check on Custom ASICS?

    Ben Bajarin and Jay Goldberg discuss the debate between custom ASICs and GPUs in AI compute, arguing that GPUs retain significant value due to software flexibility and installed base. They analyze the uneven maturity of hyperscaler silicon efforts, noting Google's TPU success versus the struggles of Amazon's Trainium and Meta's MTIA. The conversation then shifts to analog semiconductors, highlighting their critical role in humanoid robotics and data center power management, with specific mentions of Infineon's inventory buildup linked to NVIDIA's Blackwell.

    Chips, FPGAs & semiconductorsPricing, margins & unit economics
    6 chapters

  • The Amp Hour · 1h 23m

    Open FPGA Toolchains and Machine Learning with Brian Faith of QuickLogic

    Brian Faith, CEO of QuickLogic, explains how the company shifted from proprietary tools to adopting SymbiFlow as its official open-source FPGA toolchain, a decision driven by persistent engagement with Google’s Tim Ansell. He details the integration of the SensiML platform to enable low-power machine learning on devices like the EOS S3, allowing software engineers to build AI models without deep hardware expertise. Faith discusses the strategic move to license embedded FPGA IP and participate in open hardware initiatives like the Open Hardware Group and Chips Alliance to support mass customization and heterogeneous computing at the edge.

    Fabrication & craftAI & machine learning
    10 chapters

  • The Amp Hour · 2h 41m

    An Interview with Claire (née 'Clifford') Wolf

    Clifford Wolf, founder of Symbiotic EDA, discusses his creation of the first open-source FPGA toolchain, Yosys, and his work in reverse-engineering bitstreams for Lattice and Xilinx devices. He explains the significance of the open RISC-V instruction set architecture, contrasting it with proprietary models like ARM and x86, and details his development of the PicoRV32 processor. Wolf also highlights the use of formal verification tools, such as RISC-V Formal, to ensure hardware correctness and security, demonstrating how open-source methods can match or exceed commercial verification standards.

    Chips, FPGAs & semiconductorsMicrocontrollers & dev platforms
    9 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.