Intel’s next-generation 14A manufacturing process is showing unusually strong early progress, with defect density falling faster than the company expected. The improvement gives Intel a technical boost as it attempts to restore confidence in its manufacturing operation, win foundry customers and demonstrate that years… Read More
TSMC’s Overseas Fabs Are Paying Off
TSMC’s overseas fabrication strategy is beginning to deliver its intended return: not immediate cost parity with Taiwan, but manufacturable geographic redundancy, closer integration with major customers and access to subsidized capacity in strategically important markets. Arizona and Kumamoto are already producing … Read More
Crescent Island: Turning Memory Capacity into Agentic AI Throughput
Intel’s Crescent Island is a discrete data-center GPU designed for agentic AI inference, where performance is constrained by more than matrix arithmetic. Multi-step agents impose latency through repeated model calls and tool interactions, consume large memory capacity for weights and long-context key-value caches, and… Read More
AI-designed Chip Points Toward a Faster Future for Custom Silicon
Architect Labs says it has created Redwood, an AI accelerator designed and verified almost entirely by artificial intelligence in less than two weeks. If independently validated and successfully translated from a programmable prototype into manufactured silicon, the project could represent a major change in how computer… Read More
Huawei Can’t Shrink Its Chips, So It’s Folding Them
On May 25, Huawei semiconductor chief He Tingbo unveiled LogicFolding, an architecture intended to advance chip performance without relying on ever-smaller transistors. Presented alongside Huawei’s “Tau Scaling Law,” the approach prioritizes signal speed over transistor dimensions. It is a genuine engineering response… Read More
Intel Diamond Rapids: Building Xeon Up, Out, and Through Silicon
Akhilesh Kumar & Krishnakanth Sistla, Intel
Diamond Rapids is Intel’s next-generation Xeon processor, designed around the proposition that hyperscale performance increasingly depends on moving, processing, and protecting data as efficiently as executing instructions. The architecture replaces the conventional… Read More
Intel Wildcat Lake: Right-Sizing Silicon Without Sinking Performance
Lance Hacking, Intel
Intel Core Series 3, code-named Wildcat Lake, is a mainstream client system-on-chip derived from the Panther Lake-based Core Ultra Series 3 architecture. Its design objective is not maximum feature density, but broad deployment of current-generation CPU, graphics, AI, memory, security, and connectivity… Read More
Hot Chips: Evolving Memory Architectures for Artificial Intelligence
Artificial intelligence performance is increasingly constrained by memory rather than arithmetic throughput. Scaling laws show that model quality improves when parameter count, training data, and compute grow together, but this balance fails when processors cannot obtain operands quickly enough. Contemporary accelerators… Read More
Podcast EP362: An atomic layer in compute. A discussion of what can be built as graphene photonics scales with Cedric Huyghebaert
Daniel is joined by Dr. Cedric Huyghebaert, CTO of Black Semiconductor. Cedric is one of the world’s leading experts in the development and integration of 2D materials, particularly graphene, into industrial semiconductor manufacturing. With a PhD in Physics from KU Leuven and over 25 years at imec, Cedric built and led… Read More
How TSMC Is Wiring the AI Era With Light
TSMC’s photonics strategy is centered on integrating optical input-output with advanced logic, rather than selling conventional optical transceivers as standalone products. The company is developing a silicon-photonics foundry platform and a packaging architecture called TSMC-COUPE, or Compact Universal Photonic … Read More


Intel’s Tiny Bridges Could Lead to Very Big Paychecks