Thermal Slip Length at a L/S Interface: Power Law Relations From Spatial and Frequency Attributes of the Contact Layer (Caltech)


A new technical paper titled "Thermal Slip Length at a Liquid/Solid Interface: Power Law Relations From Spatial and Frequency Attributes of the Contact Layer" was published by researchers at California Institute of Technology, , T. J. Watson Sr. Laboratories of Applied Physics. Abstract "Specialty integrated chips for power intensive tasks like artificial intelligence generate so much heat ... » read more

Photonic-SRAM Bitcell for High-Speed On-Chip Photonic Memory and Compute Systems (UW, USC, GF)


A new technical paper titled "Design of Energy-Efficient Cross-coupled Differential Photonic-SRAM (pSRAM) Bitcell for High-Speed On-Chip Photonic Memory and Compute Systems" was published by researchers at University of Wisconsin–Madison, USC and GlobalFoundries. Abstract "In this work, we propose a novel differential photonic static random access memory (pSRAM) bitcell design using fabri... » read more

Adaptive RISC-V Cache Architecture for Near-Memory Extensions (Politecnico di Torino, EPFL)


A new technical paper titled "ARCANE: Adaptive RISC-V Cache Architecture for Near-memory Extensions" was published by researchers at Politecnico di Torino and EPFL. Abstract "Modern data-driven applications expose limitations of von Neumann architectures - extensive data movement, low throughput, and poor energy efficiency. Accelerators improve performance but lack flexibility and require... » read more

Chip Industry Week In Review


Check out our new Inside Chips podcast. President Trump’s ‘Liberation Day’ tariffs were announced this week. The executive order stated that semiconductors and copper imports are not directly subject to the reciprocal tariff, although the exemption may be short-lived. Semiconductor equipment and tools were not mentioned, leaving the industry searching for clarification. Regardless, hig... » read more

AI For The Edge: Why Open-Weight Models Matter


The rapid advancements in AI have brought powerful large language models (LLMs) to the forefront. However, most high-performing models are massive, compute-heavy, and require cloud-based inference, making them impractical for edge computing. The recent release of DeepSeek-R1 is an early, but unlikely to be the only, example of how open-weight AI models, combined with efficient distillation t... » read more

The Rise Of Generative AI On The Edge


Artificial intelligence (AI) and machine learning (ML) have undergone significant transformations over the past decade. The revolution of convolutional neural networks (CNNs) and recurrent neural networks (RNNs) is evolving toward the adoption of transformers and generative AI (GenAI), marking a pivotal shift in the field. This transition is driven by the need for more accurate, efficient, and ... » read more

Tailoring Root Of Trust Security Capabilities To Specific Customer Needs


The cybersecurity threat landscape is dynamic and rapidly evolving. Indeed, attackers are constantly finding new ways to exploit critical vulnerabilities across a wide range of applications and devices. Protecting data and devices requires secure processes running on systems and networks. A Root of Trust is the foundation on which all secure operations of a computing system depend. It contai... » read more

2024 Security IP Year In Review: Innovations And Best Practices


This booklet offers six insightful articles on advanced security IP technologies, helping to fortify digital systems against emerging threats. Learn about: DDR Interface Security: Defend against DRAM attacks. IoT Security: Safeguard IoT devices with SIM and Root of Trust. SRAM PUF Technology: Secure device authentication. Post-Quantum Cryptography: Protect against quantum threa... » read more

Considerations And Guidelines For Using High-Voltage CoolGaN Switches In Power Systems


The design of an electronic switched-mode power system has always been a complex task, requiring both knowledge and experience. With the appearance of gallium nitride (GaN), this task has even become more complex, because the electrical properties of GaN expand the room for possible system solutions. Particularly the lack of a physical body diode and the lateral device operation enable complete... » read more

Accelerating The Shift To Software-Defined Vehicles


The automotive E/E architecture is undergoing a significant transformation, driven by the vision of a software-defined vehicle (SDV). This shift is leading to a change from traditional distributed and domain-based architectures to more centralized and mixed domain-zone architectures. Central Electronic Control Units (ECUs) are now powered by sophisticated system-on-chips (SoCs) that combine com... » read more

← Older posts Newer posts →