Photonics Speeds Up Data Center AI


Photonics is playing an increasingly vital role in the acceleration of AI within data centers. The global market for optical components is already substantial, accounting for $17 billion in revenue last year. Historically, telecommunications — such as undersea cables and fiber-to-the-home — dominated demand. However, the datacom sector, especially AI-driven data centers, now accounts for... » read more

Chip Industry Week in Review


To listen to the podcast version, click here. TSMC unveiled an unusually detailed roadmap at this week's North America Technology Symposium, including future architectures for 3D-ICs for high-performance computing and small, extremely low-power chips for AR/VR glasses, and two implementations of system-on-wafer. Fig. 1: TSMC's future packaging and stacking roadmap. Source: TSMC The ... » read more

Chip Industry Week In Review


ASML and imec signed a five-year strategic partnership to advance semiconductor innovation and sustainable technology. The collaboration will leverage ASML’s full product portfolio, including high-NA EUV, DUV immersion, and advanced metrology tools, within imec’s pilot line for sub-2nm R&D. Supported by EU and national funding, it will also drive research in silicon photonics, memory, a... » read more

Chip Industry Week In Review


Chinese startup DeepSeek rattled the tech world and U.S. stock market with claims it spent just $5.6 million on compute power for its AI model compared to its billion-dollar rivals in the U.S. The announcement raised questions about U.S. investment strategies in AI infrastructure and led to an initial $600 billion selloff of NVIDIA stock. Since its launch, DeepSeek reportedly was hit by malicio... » read more

Fast Monte Carlo Simulations For Timing Variation Analysis


Process variations and device mismatches profoundly affect the latest ultra-small geometrical processes. Complexity creates additional factors that impact device manufacturing variability, which in turn impact overall yield. Monte Carlo (MC) simulations use repeated random sampling to relate process variations to circuit performance and functionality, thus determining how they impact yield. How... » read more

Chip Industry Week In Review


The 2024 IEEE International Electron Devices Meeting (IEDM) was held this week, prompting a number of announcements from: imec: Proposed a new CFET-based standard cell architecture for the A7 node containing two rows of CFETs with a shared signal routing wall in between, allowing standard cell heights to be reduced from 4 to 3.5T, compared to single-row CFETs. Integrated indium pho... » read more

Data Center Thermal Management Improves


Thermal issues are plaguing semiconductor design at every level, from chips developed with single-digit nanometer processes to 100,000-square-foot data centers. The underlying cause is too many devices or services that require increasing amounts of power, and too few opportunities for the resulting heat to dissipate. “Everybody wants to try to do more in a small volume of space,” said St... » read more

Chip Industry Week In Review


The Design Automation Conference morphed into the Chips to Systems Conference, reflecting an industry shift from monolithic SoCs to assemblies of chiplets in various flavors of advanced packaging. The change drew a slew of students and a resurgent buzz, fueled by discussions about heterogeneous integration, reliability, and ways to leverage AI/ML to speed up design and verification processes. ... » read more

Chip Industry Week In Review


JEDEC and the Open Compute Project rolled out a new set of guidelines for standardizing chiplet characterization details, such as thermal properties, physical and mechanical requirements, and behavior specs. Those details have been a sticking point for commercial chiplets, because without them it's not possible to choose the best chiplet for a particular application or workload. The guidelines ... » read more

Linear Drive Optics May Reduce Data Latency


Optical and electrical are starting to cross paths at a much deeper level, particularly with the growing focus on 3D-ICs and AI/ML training in data centers, driving changes both in how chips are designed and how these very different technologies are integrated together. At the root of this shift are the power and performance demands of AI/ML. It can now take several buildings of a data cente... » read more

← Older posts