The hottest Chip Design Substack posts right now

And their main takeaways
Category
Top Technology Topics

CPUs are Back: The Datacenter CPU Landscape in 2026

SemiAnalysis • 22426 implied HN points • 09 Feb 26
🕹 Technology Chip Design
  1. Datacenter CPUs are back in demand because reinforcement learning, agentic models, and RAG-style inference need lots of general-purpose compute for environments, tool use, data sharding and media decode, which is driving hyperscalers and AI labs to build large CPU clusters and straining inventories.
  2. CPU architecture is rapidly shifting to chiplet/disaggregated designs, higher core counts and mesh interconnects with advanced packaging, and vendors are diverging — AMD and hyperscale ARM designs are outperforming while Intel faces delays and questionable design choices that hurt competitiveness.
  3. The broader system ecosystem now matters as much as raw CPU cores: GPUs and specialized CPUs act as head nodes with shared memory, DPUs and context-memory platforms change how memory is used, and DRAM shortages plus packaging yields are shaping performance, supply and pricing.

Nvidia's Groq Plot Thickens

The Chip Letter • 6334 implied HN points • 04 Mar 26
🕹 Technology Chip Design
  1. Nvidia is quickly integrating Groq’s low-latency processor technology and team and is expected to unveil a Groq-derived inference chip at GTC.
  2. Groq’s dataflow architecture plus years of compiler work could deliver extremely fast, low-latency inference if Nvidia combines it with its wider IP and engineering.
  3. If Nvidia pulls this off it could narrow the field of inference accelerators and become a major, potentially game-changing shift in computer architecture for AI.

Apple-TSMC: The Partnership That Built Modern Semiconductors

SemiAnalysis • 14850 implied HN points • 08 Jan 26
🕹 Technology Chip Design
  1. Apple’s huge, predictable orders and upfront funding were the anchor that let TSMC build and scale bleeding‑edge fabs, turning TSMC into the dominant foundry.
  2. The rise of AI/HPC demand (led by Nvidia and hyperscalers) has shifted the industry to a two‑anchor model, splitting wafer and packaging demand and reducing Apple’s relative share on some nodes while creating fierce competition for advanced packaging capacity.
  3. Apple vertically integrated chip design through acquisitions and internal teams to boost margins and product differentiation, while quietly diversifying non‑core production (and managing Taiwan concentration risk) with alternatives like Intel, Samsung, and Arizona fabs.

Google TPUv7: The 900lb Gorilla In the Room

SemiAnalysis • 33539 implied HN points • 28 Nov 25
🕹 Technology Chip Design
  1. Google's TPUs are becoming a serious competitor to Nvidia's GPUs, especially with big companies like Anthropic starting to use them. This might change the game in AI hardware.
  2. The design and architecture of Google's TPU systems, especially the new TPUv7, are optimized for better performance and cost efficiency. This means companies can save money on their AI infrastructures.
  3. Google is focusing on improving its software tools for TPUs, making them more user-friendly and possibly attracting more developers. This shift might help boost the adoption of TPUs over Nvidia's GPUs.

Qualcomm's RISC-Ventana Fusion

The Chip Letter • 6770 implied HN points • 13 Jan 26
🕹 Technology Chip Design
  1. Qualcomm bought Ventana mainly to add experienced RISC-V CPU engineers and IP so it can accelerate its own CPU plans and reduce reliance on Arm.
  2. Ventana produced promising Veyron CPU designs (V1 then V2 with vector support) but appears to have struggled to convert that tech into clear customer wins.
  3. A bigger Qualcomm push into RISC-V could hurt Arm’s revenues given Qualcomm’s size, but RISC-V still faces major software and ecosystem hurdles before it can fully replace Arm for high-performance workloads.
Get a weekly roundup of the best Substack posts, by hacker news affinity:

Jensen Groks Groq

The Chip Letter • 5241 implied HN points • 31 Dec 25
🕹 Technology Chip Design
  1. Groq’s LPUs deliver much faster, low‑latency AI inference by storing model parameters in on‑chip SRAM and linking many chips together, avoiding reliance on scarce HBM.
  2. Nvidia struck a non‑exclusive licence and talent deal that moves most Groq employees to Nvidia and pays shareholders, while Groq remains operating with a new CEO and GroqCloud continuing.
  3. Bringing Groq’s processors into Nvidia’s AI platform could let real‑time, high‑speed inference scale broadly and shift the economics and architecture of AI inference.

The Sequence Opinion #819: How AI Chips are Made?

TheSequence • 238 implied HN points • 05 Mar 26
🕹 Technology Chip Design
  1. Hardware drives modern deep learning: algorithms explain maybe 40% of progress and the rest comes from the compute, memory, and system-level engineering that makes training and inference practical.
  2. GPUs were a lucky fit for neural nets because their high arithmetic density matched the workload, but custom AI chips are needed to close remaining gaps by optimizing dataflow, precision, and memory access.
  3. Designing an AI chip is a layered engineering craft from architecture to physics and tape‑out, involving RTL/Verilog work, hardware–software co‑design, and careful trade‑offs across performance, power, and manufacturability.

Roche SBX Chip Die Size Estimate Update (It's small!)

ASeq Newsletter • 21 implied HN points • 05 Mar 26
🕹 Technology Chip Design
  1. A newly found die photo lines up with the AGBT sensor module because the screw holes and exposed vias match, confirming they’re the same module.
  2. By rescaling the die image to the PCB (for which sizes are known), you can derive a size estimate for the die.
  3. The resulting estimate indicates the Roche SBX die is quite small, implying a more compact sensor/chip than many might expect.

🔮E08: Optical Computing

Let Us Face the Future • 238 implied HN points • 14 Jul 23
🕹 Technology Chip Design
  1. Optical computing uses light particles instead of electrons for computations, promising faster processing speeds and energy efficiency.
  2. Opto-electronic computing is close to commercialization, combining optical and electronic functions to leverage speed and bandwidth advantages.
  3. Optical computing faces challenges in adoption due to the need for changing components and manufacturing processes, but has potential for high-performance tasks like AI training.

Silicon Valley Generation Shift

Breaking Smart • 83 implied HN points • 25 Mar 23
🕹 Technology Chip Design
  1. Silicon Valley is experiencing a generation shift in tech with the return of silicon fabrication to the region.
  2. The passing of Gordon Moore marks a significant moment in the tech industry and highlights the renewal underway.
  3. Actual silicon manufacturing hasn't been a common practice in Silicon Valley for decades, with most fabs moving to Asia.

Vision Reasoning, Brain-Inspired Pruning, and Behavioral Simulations

HackerPulse Dispatch • 16 implied HN points • 22 Nov 24
🕹 Technology Chip Design
  1. LLaVA-o1 helps vision-language models improve their reasoning skills with clear steps, making them better at understanding complex tasks.
  2. Brain-inspired pruning makes spiking neural networks much more efficient by keeping only the important parts, leading to significant cost savings.
  3. Generative agents can simulate thousands of people's behavior accurately, which can help in studying social science and creating better policies.

The Relentless Pursuit of Moore's Law

Bits and Bytes • 5 HN points • 16 Jul 23
🕹 Technology Chip Design
  1. Moore's Law has driven progress in computing for decades by doubling transistor counts every 2 years.
  2. The management of complexity in computing has been achieved through abstraction and refactoring across multiple disciplines.
  3. Future advances in computing will likely involve raising the level of abstraction and introducing new tools to handle increasing transistor counts.

Khải Trần: công nghệ chip máy tính tiến về đâu?

Thái | Hacker | Kỹ sư tin tặc • 19 implied HN points • 19 Sep 18
🕹 Technology Chip Design
  1. The history of computer chip technology evolution highlights the shift from vacuum tubes to transistors leading to higher performance and faster clock speeds.
  2. The era of Moore's Law brought about significant advancements in chip design by increasing the number of transistors and optimizing instruction execution.
  3. With the end of Moore's Law approaching, the future of chip technology may involve domain-specific chips tailored for specific tasks, like deep learning, to overcome physical limitations and energy consumption challenges.

The PacBio Vega Chips

ASeq Newsletter • 0 implied HN points • 12 Nov 24
🕹 Technology Chip Design
  1. The PacBio Vega Chips are similar to the Revio chips, but they provide much less data. This means they might not be as powerful for certain tasks.
  2. The data from the Vega chips is available for analysis, and people can check it out for deeper understanding.
  3. This information is part of a subscription service, which means you can get more insights if you become a paid member.

The Lord of Small Things

Sector 6 | The Newsletter of AIM • 0 implied HN points • 28 Dec 22
🕹 Technology Chip Design
  1. Apple is moving to smaller 3nm chips for better efficiency in its devices. This will help iPhones and Macs perform better while saving power.
  2. The new 3nm chips promise to boost performance compared to the previous 4nm versions. This means faster and more capable devices for users.
  3. However, there's a challenge with chip production as TSMC, the manufacturer, is struggling to keep up with the high demand for these new chips.

Chip Designs Redefined

Sector 6 | The Newsletter of AIM • 0 implied HN points • 29 Mar 23
🕹 Technology Chip Design
  1. Chip technology is becoming more advanced, but making them smaller is getting harder. This means the way chips are designed needs to evolve.
  2. Moore's Law, which said chip components would double every year, is slowing down. We are reaching the limits of how many circuits can fit on a single chip.
  3. Nvidia has proposed a new way to improve chip design automation with their paper on automated placement of components. This could help overcome some of the challenges in current chip manufacturing.