Tagged articles
chip design
52 articles · Page 1 of 1
Based on a CNCC roundtable, this article argues AI can execute complex tasks like chip design but humans must define problems, verify outputs, and make value judgments. It outlines eight meta-capabilities — problem definition, verification, ethical judgment, systems thinking, human-AI collaboration, empathy, self-drive, and aesthetics — and advocates task-driven learning to cultivate these, shifting education from knowledge transmission to judgment incubation.
AI in educationCNCCHuman-AI Collaboration
0 likes · 20 min read

Hong Kong University researchers open-sourced CKTLean and CktFormalizer, a two-layer infrastructure that uses large language models to generate hardware designs in Lean 4, applies type checking and interactive theorem proving for formal verification, then exports to SystemVerilog for synthesis and physical implementation, achieving 99.4% compilation pass rate on VerilogEval and over 95% success in place-and-route, DRC, and LVS.
AI agentLean 4PPA optimization
0 likes · 16 min read

Alibaba revealed Qwen4 is in training at Yunqi Conference, detailing a four-tier lineup (Max, Flash, Plus, 27B), a new ultra-sparse MoE architecture, 33 rounds of recursive self-improvement boosting intelligence 12.5%, and a 5–10 trillion parameter roadmap through Qwen5.
AI ArchitectureAlibabaLLM
0 likes · 13 min read

Architect Labs’ Redwood chip, designed and verified entirely by AI from a natural‑language spec written by just two engineers, was fabricated on an FPGA in two weeks, delivering 3.4× the energy efficiency of Nvidia’s Jetson and demonstrating that AI‑generated hardware can now outpace traditional semiconductor design cycles.
AI hardwareArchitect LabsCUDA
0 likes · 8 min read

Anthropic has hired former Google TPU chief Amir Salek to lead its in‑house chip effort, signaling a shift from relying on external accelerators to building custom hardware as AI companies intensify competition over compute efficiency and cost.
AI hardwareAmir SalekAnthropic
0 likes · 5 min read

This article walks through the entire chip design process—from silicon material and doping, through logic gates and processor building blocks, to hierarchical design flow, layout planning, multi‑metal interconnects, and the impact of photolithography on yield—while offering a downloadable PDF reference.
chip designdesign flowintegrated circuits
0 likes · 5 min read

Although most Python developers overlook Tkinter, the underlying Tcl/Tk engine has quietly powered EDA tools for decades, evolving from a simple GUI library into the de‑facto scripting language that drives modern chip‑design workflows.
EDAPythonScripting Language
0 likes · 10 min read

DeepSeek is quietly developing its own AI inference chip to cut reliance on Nvidia and domestic silicon, a strategic shift that mirrors OpenAI and Anthropic’s hardware moves, but faces technical, manufacturing and ecosystem hurdles amid a rapidly growing inference market.
AI hardwareAI inferenceDeepSeek
0 likes · 7 min read

The article argues that AI infrastructure faces an impossible triangle of rapid expansion, gigawatt‑scale capacity, and heterogeneous DAG orchestration, and shows that only recursive self‑optimization—compressing chip design, software development, and model creation cycles—can simultaneously satisfy speed, scale, and complexity constraints.
AI infrastructurechip designheterogeneous DAG
0 likes · 20 min read


ITPUBJun 18, 2026 · Industry Insights
The article recounts how a big‑data software veteran leveraged AI‑assisted coding, the open‑source RISC‑V ISA, BitNet ternary quantization and open‑source EDA/PDK to design and tape‑out the "Pi Dan 1" AI accelerator, illustrating the technical, cost and ecosystem factors that make chip prototyping feasible for software engineers.
AI acceleratorBitNetHarmonyOS
0 likes · 14 min read

The article analyzes Huawei’s ternary‑logic chip and the τ (tau) law, tracing their historical roots, technical claims, patent details, performance numbers, ecosystem challenges, market reactions, and the intense industry debate over whether they represent genuine breakthroughs or elaborate marketing narratives.
AI accelerationHuaweichip design
0 likes · 26 min read

The article examines Huawei’s newly announced τ (Tau) Law, which proposes scaling semiconductor performance by reducing signal‑propagation delay rather than shrinking transistor geometry, explains its RC‑delay model, logical‑folding technique, multi‑layer optimization framework, and compares it with existing 3D‑stacking approaches, while assessing its practical challenges and industry implications.
RC delaySTCOchip design
0 likes · 11 min read

Huawei introduced the “τ (Tau) Law” at ISCAS 2026, proposing a shift from geometric scaling to time‑constant reduction to overcome the physical limits of Moore’s Law, and outlines how signal‑propagation delay can be compressed through system‑level innovations such as logical folding and advanced packaging.
HuaweiMoore's LawSignal Propagation
0 likes · 8 min read


ZhiKe AIMay 26, 2026 · Industry Insights
At ISCAS 2026, Huawei’s He Tingbo unveiled the “τ Law,” a time‑scaling theory that replaces geometric miniaturization with LogicFolding to cut signal‑travel time, delivering up to 55% higher transistor density, 41% better SoC efficiency, and a portfolio of 381 chips over six years.
HuaweiISCAS2026chip design
0 likes · 9 min read

Huawei introduced the “τ (Tau) Law” at the 2026 ISC conference, proposing a shift from geometric scaling of Moore’s law to “time miniaturization” that reduces signal propagation delay through logical folding and interconnect redesign, aiming to sustain semiconductor performance as transistor sizes near physical limits.
HuaweiMoore's Lawchip design
0 likes · 8 min read

Huawei’s new τ (Tao) scaling theory shifts chip optimisation from shrinking dimensions to compressing time, offering a post‑Moore roadmap that boosts mobile SoC density by 55%, AI data‑center latency by 500×, and promises continued performance growth without relying on advanced EUV lithography.
AI data centerHuaweiLogicFolding
0 likes · 8 min read

Huawei’s He Tingbo announced at ISCAS 2026 that Moore’s geometric scaling has reached a physical ceiling and introduced the “Tau Law,” a time‑scaling strategy that leverages multi‑layer optimization, logic folding, and the Lingqu bus to achieve 1.4 nm‑equivalent performance without EUV, outlining a roadmap to 2026 and 2031.
EUVHuaweiMoore's Law
0 likes · 7 min read

The article introduces Huawei’s “τ Law”, which shifts chip advancement from geometric scaling to time‑constant reduction, explains its four‑layer optimization (device, circuit, chip, system), showcases logic‑folding technology, and outlines a roadmap that could match 1.4 nm performance by 2031 without relying on EUV lithography.
HuaweiMoore's LawSystem Optimization
0 likes · 9 min read

SpaceX is planning a multibillion‑dollar effort to design and manufacture a custom AI GPU that can survive the extreme temperature, radiation, and power constraints of space while also serving Tesla’s edge‑computing needs, confronting severe technical, ecosystem, and capital challenges.
AIGPUSpace Computing
0 likes · 9 min read

Arm has shifted from pure IP licensing to launching its own Neoverse processor, securing Meta as the first customer, a move that could reshape semiconductor power dynamics by compressing the value chain and intensifying competition among chip designers and server manufacturers.
AI computeARMMeta
0 likes · 7 min read

This article provides a comprehensive, step‑by‑step overview of digital chip design, covering specification definition, system architecture, front‑end logic design, back‑end physical implementation, verification, sign‑off, and tape‑out, complete with diagrams and practical insights into each stage.
Digital ICEDATape-out
0 likes · 21 min read

Huawei is developing a new AI‑focused GPU‑style chip that mirrors Nvidia and AMD architectures, aiming to ease Chinese developers’ shift from Nvidia hardware, but still faces software compatibility hurdles due to reliance on CUDA and ongoing U.S. export restrictions.
AI chipCUDAGPU
0 likes · 3 min read

This article explains what ASIC chips are, how they differ from CPUs, GPUs and FPGAs, classifies them by customization level and function, outlines their performance and cost advantages, discusses their drawbacks, and reviews current products and market trends driving AI hardware adoption.
AI hardwareASICFPGA
0 likes · 11 min read


21CTOJun 20, 2025 · Artificial Intelligence
US CTO David Sachs warned that China’s AI and semiconductor capabilities are merely one to two years behind the United States, highlighting Huawei’s rapid progress in GPU design, the potential impact of export controls, and the broader implications for global tech competition.
AI hardwareHuaweiUS-China tech rivalry
0 likes · 5 min read

Broadcom’s market‑cap breakthrough past $1 trillion highlights its strategic push into AI ASICs, revealing how ASIC‑FPGA trade‑offs, collaborations with Google, and competition with Nvidia’s GPU ecosystem are reshaping the high‑performance computing landscape.
AI ASICBroadcomFPGA
0 likes · 13 min read

This article provides a comprehensive overview of Ethernet switches, covering their definitions, multiple classification dimensions, architectural roles in campus, enterprise, and data‑center scenarios, component makeup, market dynamics between black‑box and white‑box solutions, and future trends in switch chip development.
Ethernet SwitchWhite-box Switchchip design
0 likes · 11 min read

In just two weeks, engineer Adam Majmudar designed and implemented a minimalist GPU called tiny‑gpu—complete with a custom 11‑instruction ISA, Verilog RTL, and verified via OpenLane—sharing the open‑source project on GitHub, earning thousands of stars, and preparing it for fabrication through Tiny Tapeout 7, showcasing how modern tools make DIY chip design increasingly accessible.
EDAGPUSIMD
0 likes · 8 min read

This article provides a comprehensive overview of ASIC chips, covering their definition, material composition, classification by customization level and application, key advantages and drawbacks, notable product examples, and emerging market opportunities across AI, edge computing, and consumer electronics.
ASICchip designcustom silicon
0 likes · 11 min read

AMD’s new Versal Premium VP1902 FPGA, the world’s largest adaptive SoC, doubles logic capacity over its predecessor, adds extensive high‑speed transceivers, NoC and PCIe upgrades, and promises faster debugging and AI‑driven chip validation, marking a significant shift in semiconductor prototyping.
AMDAdaptive SoCFPGA
0 likes · 8 min read


21CTOJun 30, 2023 · Artificial Intelligence
Chinese researchers used generative AI to design Qǐ Méng 1, the first completely self‑generated CPU chip that runs Linux and rivals early Intel 486 performance, showcasing the rapid rise of AI‑driven semiconductor design.
AICPURISC-V
0 likes · 4 min read


21CTOAug 16, 2022 · Fundamentals
The U.S. added cutting‑edge electronic design automation (EDA) software and related semiconductor technologies to its export control list, prompting concerns about short‑term disruptions and long‑term constraints on China's advanced chip design while also spurring domestic EDA development.
ChinaEDAchip design
0 likes · 9 min read

This article provides a detailed, line‑by‑line analysis of a chart comparing FPGA and ASIC across dimensions such as upfront costs, unit cost, time‑to‑market, performance, power consumption, field updates, density, design flow, granularity, verification needs, upgrade paths, and additional features, helping engineers decide which technology best fits their high‑performance AI workloads.
AI AcceleratorsASICFPGA
0 likes · 12 min read

The article presents a detailed technical review of Kunlun Chip's XPU‑R AI accelerator, covering its evolution from early FPGA prototypes to the current 7nm, 256 TOPS chip, the architectural choices that address AI workload demands, performance advantages over CPUs/GPUs, and the product ecosystem supporting diverse AI scenarios.
AI accelerationAI hardwareKunlun Chip
0 likes · 20 min read

The 2022 Beijing Zhiyuan Conference report by Kunlun Core’s chip R&D director outlines AI chip market opportunities and challenges, describes the company’s shift from FPGA clusters to a programmable XPU‑R architecture with 7nm, 256 TOPS INT8 performance, GDDR6 memory and PCIe 4.0, and details current deployments and plans for third‑ and fourth‑generation chips.
AI acceleratorAI chipGDDR6
0 likes · 12 min read

Tencent’s hardware teams evolved from a lack of verification tools in 2019 to building AI inference chips, video‑encoding silicon, and intelligent NICs, overcoming FPGA challenges, scaling cloud infrastructure, and delivering high‑performance, low‑cost solutions for massive multimedia and AI workloads.
AI inferenceFPGASmart NIC
0 likes · 16 min read

Chinese domestic GPU development has accelerated rapidly, driven by fast‑track product launches, strategic IP licensing from firms like Imagination Technologies, and supportive policies, while industry players navigate challenges of patents, design complexity, and market competition to bring full‑function GPUs to market.
ChinaGPUIP licensing
0 likes · 12 min read

The article traces Apple’s four‑decade struggle with thermal challenges in its Mac lineup, recounting the legacy of the 2013 “trash‑can” Mac Pro, the evolution of chip architecture, and how the company’s shift to self‑designed silicon like the M1 series finally broke the heat‑constraint cycle.
AppleM1Mac
0 likes · 13 min read

The article explains how RISC‑V’s open, customizable ISA, the shift toward free and unrestricted hardware design, and market pressures such as Moore’s law slowdown and AI‑driven compute demand together fuel its rapid adoption, ecosystem growth, and competitive edge over proprietary architectures.
Hardware InnovationOpen ISARISC-V
0 likes · 11 min read

This article outlines the methodology, key decision factors, and practical scenarios for moving electronic design automation (EDA) environments to the cloud, comparing hybrid and full‑cloud solutions for large design firms and start‑ups, and presents case studies such as STA migration.
EDAFull Cloudchip design
0 likes · 15 min read

This article provides a comprehensive overview of ASIC chips, covering their definition, hardware composition, classification by customization and function, key advantages and drawbacks, notable product examples, and emerging market trends driving growth across AI, security, and consumer electronics.
ASICchip designfull-custom
0 likes · 11 min read


21CTOAug 10, 2021 · Fundamentals
Amid global chip shortages and shifting market dynamics, Chinese internet powerhouses like ByteDance, Tencent, and Xiaomi, alongside global players such as Google, Intel, and Nvidia, are accelerating their own semiconductor initiatives, reshaping the industry from smartphone SoCs to AI‑focused cloud processors.
AI chipsARM Architecturechip design
0 likes · 14 min read

The article explains how artificial intelligence relies on algorithms, compute and data, compares engineering and simulation methods, and details the roles, architectures, performance and energy characteristics of GPUs, FPGAs, and ASICs as the primary hardware accelerators for modern deep‑learning applications.
ASICFPGAGPU
0 likes · 14 min read

The article outlines Wave Computing’s 2018 decision to open the MIPS Release 6 instruction set, describes the evolution and product lines of MIPS, compares the open‑source licensing and ecosystem of MIPS with RISC‑V, and discusses market adoption, commercial models, and future challenges.
Instruction Set ArchitectureMIPSOpen ISA
0 likes · 9 min read

The article analyzes RISC‑V’s open, modular ISA, its technical advantages over legacy architectures, the rapidly maturing global and Chinese ecosystems, real‑world applications, and strategic recommendations for China to build an independent, competitive semiconductor industry amid trade tensions and policy drives.
AI hardwareChina technology policyIoT
0 likes · 10 min read

The article provides a comprehensive overview of RISC‑V, covering its origins amid trade‑war pressures, open‑source technical characteristics, growing global and Chinese ecosystem, comparisons with ARM and x86, and its emerging role in low‑power, customizable chips for IoT and AI applications.
AIInstruction Set ArchitectureIoT
0 likes · 10 min read

The article provides a comprehensive overview of the open‑source RISC‑V instruction set, its historical development, technical benefits such as modularity and a minimal instruction set, and its growing relevance across IoT, mobile, server, storage, AI, and security domains, while also discussing ecosystem challenges and industry initiatives.
CPU architectureIoTRISC-V
0 likes · 12 min read

This article offers a comprehensive overview of Huawei's three‑decade chip development, detailing the evolution of its AI, computing, mobile SoC, 5G communication, IoT, and video chips, their technical specifications, market impact, and future roadmap within China's semiconductor landscape.
5GAIHuawei
0 likes · 15 min read

This article traces Huawei’s three‑decade journey from its modest 1991 chip beginnings to a diversified portfolio of five major series—Kirin, Kunpeng, Ascend, Balong/Tiangang, Boudica/Lingxiao, and Honghu—detailing their technical evolution, market impact, and future roadmap across mobile, compute, AI, 5G, IoT, and video domains.
5GAIHuawei
0 likes · 18 min read


ITPUBAug 9, 2020 · Fundamentals
Five 2016‑class undergraduates from the University of Chinese Academy of Sciences completed a 64‑bit RISC‑V SoC chip named "NutShell," successfully fabricated it in 110 nm, ran Linux and a custom teaching OS, and presented the open‑source design at the RISC‑V Global Forum, showcasing a novel "One Life One Chip" education model.
RISC-VSOCchip design
0 likes · 19 min read

Alibaba's DAMO Academy outlines ten disruptive technology trends for 2020—including AI’s shift to cognitive intelligence, compute‑storage integration, industrial‑Internet hyper‑convergence, massive machine collaboration, modular chip design, mass‑scale blockchain, quantum computing breakthroughs, new semiconductor materials, privacy‑preserving AI, and cloud‑centric innovation—offering a comprehensive outlook on the next wave of digital transformation.
AIBlockchainTechnology Forecast
0 likes · 11 min read

The 2020 DAMO Academy report outlines ten transformative technology trends—including the shift from perceptual to cognitive AI, compute‑storage integration, industrial‑internet hyper‑convergence, large‑scale multi‑agent collaboration, modular chip design, mass‑market blockchain, quantum‑computing breakthroughs, new semiconductor materials, privacy‑preserving AI, and cloud as the core of IT innovation—highlighting their potential impact on the next decade of tech development.
AIBlockchainchip design
0 likes · 10 min read

The article provides a detailed, English-language overview of the entire integrated circuit design flow—from architecture and algorithm selection through RTL coding, verification, synthesis, layout, and sign‑off—highlighting the roles, tools, and challenges faced by engineers in modern ASIC and FPGA development.
ASICEDAFPGA
0 likes · 29 min read
