Tagged articles
hardware design
40 articles · Page 1 of 1
Anthropic's Claude Fable 5.2 and Mythos 5.2 top FrontierCode and Intelligence Index benchmarks, coordinate 1000 agents to build a bootable OS in 8 days, formalize Fermat's Last Theorem in 30 hours, design hardware, and control robots, with Fable for complex engineering and Mythos for high-risk security and biology tasks.
AI benchmarksClaude Fable 5.2Mythos 5.2
0 likes · 16 min read

The article explains how MCUs focus on minimal, low‑power designs with limited resources, while SOCs integrate powerful CPUs, GPUs, and peripherals for full operating systems, and it guides selection based on performance, power, and cost with concrete product examples.
LinuxMCUReal-time
0 likes · 7 min read

DeepSeek is quietly developing a custom AI inference chip—started a year ago and recruited for without public postings—to cut reliance on Nvidia, a move reflected in a broader industry shift toward self‑designed chips and backed by a 51‑billion‑RMB funding round for compute infrastructure and talent expansion.
AI chipAI industryDeepSeek
0 likes · 6 min read

On June 10, ACM announced the 2025 Doctoral Dissertation Award, granting the prize to Allen Liu of NYU for his thesis on learning‑theoretic foundations of quantum systems, while honoring Gal Arnon and MIT’s Rachit Nigam for advances in interactive oracle proofs and efficient hardware abstractions.
ACM AwardInteractive Oracle ProofsQuantum Systems
0 likes · 9 min read

The article argues that AI chip performance is shifting from transistor scaling to minimizing data movement time and energy, explaining the τ (tau) law, Bill Dally's energy model, and how data‑centric architecture, short communication paths, and tight software‑hardware co‑design are essential for efficient large‑model inference.
AI chipscompiler stackdata flow
0 likes · 13 min read

The article examines how Balmuda, together with design studio LoveFrom, transformed the overlooked bedside clock into a carefully crafted, screen‑free device that solves the disruptive phone‑on‑the‑nightstand problem through minimalist lighting, curated soundscapes, and nuanced interaction, illustrating the power of deep design insight.
BalmudaProduct DesignUser Experience
0 likes · 7 min read

This guide walks through the essential steps of STM32 development—from reading schematics and configuring CubeMX to structuring code, debugging with tools like J‑Link RTT, and optimizing performance, providing practical tips to avoid common pitfalls and build reliable embedded systems.
CubeMXDebuggingEmbedded
0 likes · 6 min read

This article explains the open‑drain nature of I2C, why pull‑up resistors are essential for providing a high level, ensuring signal integrity and enabling wired‑AND logic, and offers practical formulas, recommended resistor ranges for different speeds, STM32 configuration examples, and debugging tips.
I2CSTM32bus communication
0 likes · 13 min read

Engineers training large AI models often see noticeable FP16/BF16 result differences between GPUs and NPUs, and even between generations of the same chip, due to floating‑point representation limits, hardware design choices, software library implementations, compiler optimizations, and parallel execution nondeterminism.
AIGPUNPU
0 likes · 10 min read

This article explains what a MAC address is, its structure and role in networking, and why many embedded devices must assign their own MAC addresses due to cost, industry practices, and the need for on‑demand configuration rather than universal uniqueness.
Cost OptimizationEthernetMAC address
0 likes · 8 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

Meituan’s first smart‑helmet article details hardware innovations that tackle delivery riders’ safety, comfort, and efficiency, covering stricter safety standards, sensor‑driven alerts, lightweight structures, advanced ventilation, three‑times longer battery life, noise‑cancelling audio, IPX6 waterproofing, and a data‑driven production line.
AI safetydelivery efficiencyhardware design
0 likes · 24 min read

This article provides a comprehensive overview of ASIC technology, covering its definition, origins, design process, key parameters, core techniques, and major application domains such as data centers, AI, automotive, and more, while also comparing it to general‑purpose ICs and highlighting leading industry players.
ASICchip architecturehardware design
0 likes · 21 min read

The article provides a detailed technical overview of the Loongson 3A5000 processor, covering its multi‑core architecture, cache coherence protocol, AXI interconnect, performance specs, and four CPU‑GPU‑display communication modes, while omitting promotional content.
AXI interconnectLoongsoncache coherence
0 likes · 8 min read

A YouTuber known as MINT documented the creation of EPROMINT, a complete 8‑bit CPU built from discarded memory chips and simple logic components, detailing its ALU design, modular architecture, custom instruction set, interrupt handling, video output, open‑source release, and plans for a C compiler.
DIY CPUassembly languagehardware design
0 likes · 9 min read

Steve Wozniak single‑handedly designed and built the Apple I in 1976, creating both the hardware using a Motorola 6800 CPU and 4 KB RAM and the software including a BASIC interpreter and a machine‑language monitor, demonstrating how one person could assemble a complete computer system before the era of modern development tools.
Apple ISteve Wozniakcomputer history
0 likes · 5 min read

This article provides a comprehensive technical overview of AI chips, focusing on ASIC technology—including its classifications, design trade‑offs, performance advantages, drawbacks, real‑world examples, and emerging market trends—while also summarizing related GPU, FPGA, and neuromorphic developments.
AI chipsASICTechnology Analysis
0 likes · 11 min read

This article analyzes the factors influencing optical‑module requirements for AI GPU clusters, compares four typical network configurations for A100 and H100 SuperPODs, and provides step‑by‑step calculations that reveal the projected market demand for 200G, 400G, and 800G modules in 2023‑2024.
AIGPUSuperPod
0 likes · 14 min read

This article details the design, engineering, and user‑experience innovations behind a lightweight, AI‑enabled self‑service kiosk that streamlines on‑site health examinations, reduces costs, and earned the 2021 IAI International Creative Award.
AIIndustry Case StudyUI/UX
0 likes · 6 min read

Apple’s Vision Pro, a head‑mounted display launched in early 2024, combines a curved 3‑D glass front, dual‑eye micro‑OLED screens, M2 and R1 chips, extensive cameras and sensors, and a breathable headband to deliver low‑latency mixed reality via VisionOS’s windows, volumes and spaces, while emphasizing familiar UI, ergonomics, privacy through on‑device Optic ID, and enabling novel experiences such as immersive music‑app environments.
Apple Vision ProMixed RealityUser Experience
0 likes · 20 min read

A NYU Tandon study shows that GPT‑4, using plain‑language dialogue, can generate Verilog code for a novel 8‑bit accumulator microprocessor, which was tape‑out on Skywater 130 nm, demonstrating AI’s emerging ability to perform hardware design tasks at near‑human level.
AGIAI chip designGPT-4
0 likes · 5 min read

This article explores why the x86 architecture adopted an 8‑bit byte, examining historical decisions, character‑encoding needs, binary‑coded decimal compatibility, power‑of‑two advantages, and legacy compatibility, while clarifying the distinction between bytes and words in computer design.
binary representationbyte sizehardware design
0 likes · 14 min read

This article provides a comprehensive technical review of Tesla's D1 AI processor and Dojo super‑computer architecture, covering its data‑flow near‑memory design, RISC‑V‑like instruction set, matrix compute units, chiplet packaging, power‑management, cooling solutions, and the associated software compilation ecosystem.
AI chipCompilation EcosystemDojo Architecture
0 likes · 23 min read

The article recounts how Steve Wozniak, inspired by the Homebrew Computer Club in 1975, single‑handedly designed and built the Apple I computer using a Motorola 6800 CPU, 4 KB memory, a BASIC interpreter and a machine‑language monitor, illustrating the challenges of creating a complete system in the 1970s.
Apple ISteve Wozniakcomputer history
0 likes · 6 min read

This article provides a comprehensive comparison between FPGA and ASIC, covering their architectures, design processes, speed, area, power consumption, cost factors, typical use cases, and emerging integration trends to help engineers decide which technology best fits their project requirements.
ASICFPGATechnology Comparison
0 likes · 9 min read

The HiPChips workshop at ISCA 2022 gathered leading academia and industry experts to discuss the motivations, recent research breakthroughs, technical challenges, and ecosystem efforts surrounding high‑performance chiplet and interconnect architectures for future computing systems.
Chipletcomputer architecturehardware design
0 likes · 10 min read

The article explains how 3D chip stacking—illustrated by AMD's Zen 3 3D V‑Cache, Graphcore's Bow AI accelerator, and Intel's Ponte Vecchio—overcomes physical limits of transistor scaling, boosts performance, and reshapes high‑performance and AI computing architectures.
3D stackingAI acceleratorCPU architecture
0 likes · 10 min read

This article provides a detailed, line‑by‑line comparison of FPGA and ASIC across pre‑fabrication cost, unit cost, time‑to‑market, performance, power consumption, field update capability, density, design flow, verification, upgrade paths, and the role of structured ASICs, helping engineers decide the optimal solution for complex, high‑performance, non‑standard IC designs.
ASICFPGAcost analysis
0 likes · 11 min read

The article reviews the accelerating data explosion and its impact on computing hardware, analyzes the limits of traditional scaling in logic, memory, and interconnect, and proposes specialized ICs, design reuse, 3‑D integration, new memory technologies, and optical interconnects as viable paths to sustain performance growth.
computinghardware designinterconnect
0 likes · 30 min read

This article reviews the historical evolution of computer architecture, analyzes the end of Dennard scaling and Moore's Law, discusses domain‑specific architectures, open ISAs like RISC‑V, security vulnerabilities, and emerging opportunities such as agile hardware development and specialized accelerators.
Performance ScalingRISC-VSecurity Vulnerabilities
0 likes · 41 min read

The article provides a comprehensive overview of FPGA technology, detailing its architecture, advantages over ASICs, current global market size, growth drivers such as 5G and AI, and the challenges and opportunities faced by domestic Chinese manufacturers in a market dominated by Xilinx and Intel.
5GAIFPGA
0 likes · 19 min read

The article explains how SmartNICs offload networking, storage, and compute tasks from CPUs to improve server performance and reduce power consumption, outlines three SmartNIC architectures—multicore ASIC, FPGA‑based, and FPGA‑enhanced—and details design methods and functional extensions illustrated with thirteen practical examples.
ASICFPGANetwork Acceleration
0 likes · 14 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

The article examines autonomous vehicle hardware, covering aesthetic design, sensor placement for full 360° vision, weather impacts on perception, performance versus power consumption, cooling solutions, and environmental robustness such as vibration, temperature, humidity, salt corrosion, and electromagnetic interference, while highlighting modular sensor modules and innovative concepts like Zoox's direction‑free chassis.
Autonomous Vehicleshardware designperformance
0 likes · 12 min read

This article presents a step‑by‑step guide to designing and building a Gongfu tea‑making robot, covering embedded development basics, hardware modularization, controller design, platform comparisons, power supply considerations, and complete Python code for servo control and action sequencing.
ArduinoPythonRaspberry Pi
0 likes · 15 min read

This article provides a detailed introduction to Field‑Programmable Gate Arrays (FPGA), covering their definition, evolution, major vendors, internal architecture, design and programming workflow, usage in data‑center and telecom, and typical application scenarios such as AI and high‑performance computing.
ASICFPGAdata center acceleration
0 likes · 13 min read

This guide outlines the key components, step‑by‑step process, and quality‑assurance measures for evaluating software and hardware system architectures to ensure reliability, scalability, security, and cost‑effectiveness while reducing risk and guiding future design decisions.
architecture evaluationhardware designrisk-management
0 likes · 11 min read

The article explains why data‑center cabinets, though often overlooked, are critical infrastructure, detailing required dimensions, load and power capacities, cooling and ventilation needs, relevant IEC and EIA standards, material and safety features, and best practices for installation and management.
CoolingRack Cabinetdata center
0 likes · 8 min read


21CTOAug 26, 2015 · Fundamentals
Registers outrun main memory because they sit closer to the CPU, employ high‑performance hardware designs, and involve far fewer access steps, a distinction illustrated with examples from iPhone 5s architecture and detailed step‑by‑step memory access processes.
CPU architectureRegistershardware design
0 likes · 6 min read

This article examines Facebook's cold storage system, detailing how the company redesigned hardware and software to slash power consumption, improve reliability with Reed‑Solomon coding, mitigate bit‑rot, and balance loads while supporting massive photo archives in energy‑constrained data centers.
FacebookReed-Solomoncold storage
0 likes · 8 min read
