Tag
We present TACS-RF, a framework where an LLM coding agent (Claude Opus 4.8) semi-autonomously drives industry-standard EDA tools to design a 240-251 GHz sub-THz transmitter in 90 nm SiGe BiCMOS, marking a step toward a 'text-to-ASIC' future for RF/mmWave hardware design.
Anthropic宣布其STEM Fellows Program新成果:Claude Mythos 5根据自然语言指令设计出量子电路,在八个化学、优化、物理模拟和数论案例中超越已发表的最优设计,部分情况提升一个数量级以上,有望加速实用量子计算机的到来。
A researcher built software that speeds up quantum circuit design by roughly 10,000×, and GPT-6 Astra further optimized the already-optimized code for an additional ~10× speedup overnight.
This paper presents TARGet, a topology-aware fusion-based method using graph neural networks for radio frequency circuit functional modeling, demonstrating improved prediction accuracy and data efficiency over state-of-the-art approaches.
This article provides a solution to Jane Street's ASIC reverse engineering puzzle, detailing the process of analyzing GDS files and inferring the circuit using the SkyWater 130 nm standard-cell library documentation.
A user shares that they are assembling a kit designed by Cherry Takuan-san for a DIY CPU, with original designs licensed under CC BY 4.0. The CPU is similar in complexity to early-1980s 16-bit home computers.
A game that lets players build a computer from scratch using logic gates, design circuits, construct a CPU, and run programs.
MorphoHDL is a minimalistic domain-specific language for designing and growing circuits, offering a simple syntax for hardware description.
An educational blog post explaining the capacitance multiplier circuit using op-amps, part of a series on 'cursed circuits'.
This paper presents SINA, an open-source AI pipeline that automatically converts circuit schematic images into netlists with 96.67% accuracy, significantly improving over prior methods by integrating deep learning, OCR, and vision-language models.
Huawei discusses LogicFolding, a technique that compresses propagation time between adjacent flip-flops in circuit design, tightening critical paths and enabling faster chips. The company expects its high-end chips to achieve transistor density equivalent to 14 Å (1.4 nm) processes by 2031.
Researchers from the University of Innsbruck and NVIDIA developed an AI method using multimodal diffusion models to automatically generate efficient quantum circuits, significantly reducing circuit length and rediscovering textbook circuits like the Quantum Fourier Transform.