For decades, we've focused on shrinking transistors to make chips faster. But as Moore's Law slows, a different revolution is happening in chip packaging — how chips are physically assembled and connected. In this episode, Lucas and Luna explore the 40-year history of chip packaging, from wire bonding to today's 3D stacking and hybrid bonding. They zero in on a specific breakthrough: TSMC's 3D SoIC technology, which stacks logic chips directly on top of each other, reducing signal delay and power consumption by 40% compared to traditional 2D chips. They discuss why AMD's use of chiplet packaging in its Ryzen and EPYC processors gave it a 2-year lead over Intel, and how Apple's M1 Ultra used TSMC's InFO packaging to connect two dies as if they were one. The hosts also touch on the economics: advanced packaging now accounts for 20% of semiconductor capital spending, up from 5% a decade ago. This episode shows that the next leap in computing performance won't come from smaller transistors, but from smarter ways to put them together.

#ChipPackaging #Semiconductor #AdvancedPackaging #TSMC #3DStacking #HybridBonding #MooreSLaw #AMD #AppleSilicon #InFO #SoIC #Chiplet #Technology #Engineering #Manufacturing #HardwarePodcast #FexingoBusiness #BusinessPodcast

Keep every episode free: buymeacoffee.com/fexingo

Lucas and Luna dive into the world of chiplet architecture—how semiconductor designers are breaking traditional monolithic chips into smaller, specialized dies that are then packaged together. They explore the technical challenges, cost benefits, and why industry giants like AMD and Intel are betting big on this approach. Specific examples include AMD's EPYC processors and Intel's Ponte Vecchio GPU, along with the role of die-to-die interconnects like Universal Chiplet Interconnect Express (UCIe). This episode unpacks a quiet revolution in chip design that is reshaping everything from data centers to consumer electronics.

#ChipletArchitecture #Semiconductors #AMD #Intel #UCIe #DieToDieInterconnect #EPYC #PonteVecchio #ChipDesign #MooreLaw #AdvancedPackaging #Technology #FexingoBusiness #BusinessPodcast #HardwarePodcast #SemiconductorEngineering #Chiplets #DataCenter

Keep every episode free: buymeacoffee.com/fexingo

This episode of The Hardware Podcast dives into silicon carbide (SiC) semiconductors—the material quietly transforming power electronics in electric vehicles, solar inverters, and data centers. Lucas explains why SiC chips handle higher voltages and heat than traditional silicon, using Tesla's early adoption in the Model 3 as a concrete example. Luna questions the manufacturing challenges, from wafer defects to cost per die. Together they unpack why SiC is projected to grow from $3 billion to over $10 billion by 2030, and what that means for chip suppliers like Wolfspeed and STMicroelectronics. A focused look at one material's impact on the hardware landscape.

#SiliconCarbide #SiC #PowerElectronics #ElectricVehicles #Tesla #Wolfspeed #STMicroelectronics #Semiconductors #WideBandgap #GaN #Inverters #EVCharging #EnergyEfficiency #Technology #Chips #Hardware #FexingoBusiness #BusinessPodcast

Keep every episode free: buymeacoffee.com/fexingo

Lucas and Luna explore the humble yet essential passive components that make modern electronics possible. They focus on multilayer ceramic capacitors — MLCCs — the tiny chips that outnumber active semiconductors in every smartphone, car, and data center. The conversation explains why these components are suddenly in short supply, how manufacturers like Murata and Samsung Electro-Mechanics dominate the market, and what the shortage means for gadget prices and delivery times. Lucas walks through a real supply-chain crunch from 2023 that delayed laptop shipments, and Luna connects it to the broader push for local manufacturing. A concrete look at the component you've never heard of that holds the entire electronics industry together.

#MLCC #PassiveComponents #ElectronicComponents #SupplyChain #Semiconductor #Murata #SamsungElectroMechanics #Capacitors #Manufacturing #ElectronicsEngineering #Hardware #Technology #TechSupplyChain #ComponentShortage #CeramicCapacitors #FexingoBusiness #BusinessPodcast #TheHardwarePodcast

Keep every episode free: buymeacoffee.com/fexingo

Lucas and Luna explore why chip design verification now consumes 60% of a semiconductor company's engineering budget—more than the actual design work. They trace the problem through two concrete examples: the 2023 errata in a widely used server processor that cost its manufacturer $475 million, and the rising use of formal verification tools at ARM and AMD. The conversation covers the semiconductor industry's growing 'verification tax,' the talent bottleneck in hardware verification engineering, and what it means for the next generation of AI and automotive chips. Listeners learn why a single logic bug found after tape-out can cost more than the entire verification team's annual salary, and how the industry is responding with open-source verification frameworks and AI-assisted test generation.

#ChipDesign #Verification #Semiconductor #HardwareEngineering #VLSI #EDA #ARM #AMD #FormalVerification #SystemVerilog #UVM #Technology #TechPodcast #FexingoBusiness #BusinessPodcast #Engineering #ChipDesignVerification #AI

Keep every episode free: buymeacoffee.com/fexingo

Episode 5 of The Hardware Podcast dives into the unsung hero of mobile devices: the sensor hub. Lucas and Luna unpack a specific case — the Apple M-series coprocessors that have quietly handled motion, context, and always-on sensing since the iPhone 5S. They trace the evolution from discrete chips to integrated system-on-chip blocks, explain why this matters for battery life and privacy, and look at how the same architecture is spreading into wearables and IoT. Specific numbers and design decisions anchor the conversation, including the power consumption difference between the main application processor and a dedicated sensor hub — measured in milliwatts versus hundreds of milliwatts. No broad chip overview; just one focused angle on the hardware that wakes your phone when you pick it up.

#SensorHub #AppleMSeries #M7Coprocessor #AlwaysOnSensing #LowPowerChips #SmartphoneHardware #BatteryEfficiency #IoT #Wearables #MotionProcessing #ContextAwareComputing #TechDeepDive #HardwareEngineering #ChipDesign #MobileTech #FexingoBusiness #BusinessPodcast #HardwarePodcast

Keep every episode free: buymeacoffee.com/fexingo

Episode 4 of The Hardware Podcast digs into the hidden hardware that keeps the global internet running: subsea fiber-optic cables. Lucas and Luna examine the recent damage to a critical cable in the Red Sea, the economics of cable repair, and why a single ship—the Dependable—handles most Atlantic repairs. They explore how hyperscalers like Google are now building their own private cables and what that means for the rest of us. Along the way, they reveal why you can't just patch a broken cable with duct tape and why the repair process is more like spacewalk surgery than undersea plumbing. A concrete look at the fragile physical layer of the internet.

#SubseaCables #FiberOptics #InternetInfrastructure #Hardware #Technology #Business #Telecom #Google #RedSea #CableRepair #TheDependable #Hyperscalers #Latency #Bandwidth #DigitalEconomy #Engineering #FexingoBusiness #BusinessPodcast

Keep every episode free: buymeacoffee.com/fexingo

In Episode 3 of The Hardware Podcast, Lucas and Luna dive into the unsung hero of chipmaking: the photomask. While headlines obsess over EUV lithography machines, the photomask—the master template that patterns every transistor—is quietly becoming a bottleneck as chip designs grow more complex. Lucas explains how masks are made using electron-beam lithography, why defects are catastrophic, and the growing challenge of mask write times for extreme ultraviolet (EUV) layers. Luna questions whether mask costs are inflating chip prices and whether alternative approaches like direct-write lithography or maskless patterning could disrupt the status quo. The conversation touches on key players like ASML, Toppan, Photronics, and the mask shops inside Intel and TSMC. By the end, listeners understand why the photomask—not just the wafer fab—deserves attention as semiconductor scaling gets harder.

#Photomask #SemiconductorManufacturing #EUVLithography #ASML #Intel #TSMC #ElectronBeamLithography #ChipDesign #HardwareEngineering #TechBottleneck #MaskShop #Toppan #Photronics #AdvancedLithography #Yield #Technology #FexingoBusiness #BusinessPodcast

Keep every episode free: buymeacoffee.com/fexingo

In this episode of The Hardware Podcast, Lucas and Luna tackle the semiconductor industry's most pressing challenge: the end of Moore's Law. They explore why transistor scaling has hit a physics wall at the 3-nanometer node, how TSMC and Intel are navigating this transition, and what comes next—from advanced packaging to new materials like graphene and silicon photonics. Lucas explains the concept of Dennard scaling and why power density stopped dropping years ago, while Luna questions whether the industry's obsession with nanometer labels has become marketing theater. They discuss real numbers: the 2.5x increase in design costs per node, the 23,000 watts per square centimeter problem in hot spots, and the role of chiplets and 3D stacking in keeping progress alive. The episode avoids hype, focusing on the genuine engineering trade-offs and the future of specialized hardware for AI and data centers. A grounded look at where silicon goes from here.

#MooreLaw #Semiconductors #TSMC #Intel #ChipDesign #Transistor #Nanometer #PhysicsWall #DennardScaling #AdvancedPackaging #Chiplets #SiliconPhotonics #Graphene #AIHardware #Technology #HardwarePodcast #FexingoBusiness #BusinessPodcast

Keep every episode free: buymeacoffee.com/fexingo

In the premiere episode of The Hardware Podcast, Lucas and Luna dissect Intel's troubled 10-nanometer journey—a process node that arrived three years late and cost the company an estimated $40 billion in market value and lost business. They trace how a single architectural decision (cobalt interconnects) cascaded into years of delays, handed AMD its biggest opening since 2006, and forced Intel to abandon its famous 'tick-tock' cadence. Along the way, they unpack what 'nanometer' actually means in 2026, why the chip industry's transition from planar to FinFET transistors was so brutal, and how Intel's foundry pivot under Pat Gelsinger is both a mea culpa and a high-stakes gamble. This is a conversation about the physics of transistors, the economics of fabrication plants, and the human cost of engineering hubris—told through one of the most expensive mistakes in industrial history.

#Intel #10Nanometer #CannonLake #ProcessNode #ChipManufacturing #FinFET #Semiconductors #Technology #Hardware #EngineeringFailure #TockTick #PatGelsinger #Foundry #AMD #Transistors #CobaltInterconnects #FexingoBusiness #BusinessPodcast

Keep every episode free: buymeacoffee.com/fexingo