#semiconductor
Semiconductor: 43 AI articles covering semiconductor news, analysis, and research
Articles
Microsoft's New Maia 300 AI Chip Reduces Reliance on Nvidia GPUsβ8
Microsoft's Maia 300 AI chip, launching in 2027, aims to cut reliance on Nvidia GPUs and reshape the competitive AI hardware landscape.
Thermal Complexity Grows With AI Chips And Photonicsβ9
AI chips exceeding 1000W and co-packaged photonics create complex thermal challenges, demanding advanced liquid cooling, thermal isolation, and precise temperat...
Lola Vision Systems Wants to Make Running AI Models on Chips Easierβ9
Lola Vision Systems builds software and chips to simplify running AI models on devices, cutting setup time and offering an alternative to Nvidia.
Extreme Environments Push Chips to Their Breaking Pointβ10
Extreme environments like automotive heat and space radiation are pushing semiconductor chips to their limits, reshaping design, materials, and testing by 2026.
HBF for High-Throughput LLM Serving: UC Berkeley and FuriosaAI'sβ9
UC Berkeley and FuriosaAI use Hybrid Bonding Foundation (HBF) tech to boost LLM inference throughput with higher memory bandwidth and lower latency.
The Proof Economy: How Verifiable Computation Is Reshaping theβ9
Verifiable computation is fueling semiconductor growth, driving demand for proof accelerators as zero-knowledge proofs and AI attestation reshape silicon design...
Moore's Law AI: Applying Agentic AI Across Chip Designβ9
Agentic AI moves into production across chip design in 2026, automating design space exploration, physical layout, verification, and cross-domain optimization.
AMD to Acquire World Labs in an $8B+ Deal, Co-Founder Namedβ7
AMD agrees to acquire World Labs in an $8B+ deal, with co-founder Fei-Fei Li joining as chief scientist, boosting AMD's AI push into spatial intelligence.
When AI Agents Cross Chip Design Silosβ9
AI agents are breaking down chip design silos, bridging architecture, RTL, verification, and physical implementation to resolve cross-domain trade-offs and redu...
Concurrent HBM and Host Memory Access Boosts LLM Inferenceβ9
Georgia Tech, Nvidia, and Stanford show that concurrent HBM and host memory access boosts LLM inference throughput by hiding latency and scaling beyond HBM capa...
