Author's Latest Posts

Unlocking The Power Of Edge Computing With Large Language Models

In recent years, Large Language Models (LLMs) have revolutionized the field of artificial intelligence, transforming how we interact with devices and the possibilities of what machines can achieve. These models have demonstrated remarkable natural language understanding and generation abilities, making them indispensable for various applications. However, LLMs are incredibly resource-intensi... » read more

Generative AI: Transforming Inference At The Edge

The world is witnessing a revolutionary advancement in artificial intelligence with the emergence of generative AI. Generative AI generates text, images, or other media responding to prompts. We are in the early stages of this new technology; still, the depth and accuracy of its results are impressive, and its potential is mind-blowing. Generative AI uses transformers, a class of neural network... » read more

A Buyers Guide To An NPU

Choosing the right AI inference NPU (Neural Processing Unit) is a critical decision for a chip architect. There’s a lot at stake because as the AI landscape constantly changes, the choices will impact overall product cost, performance, and long-term viability. There are myriad options regarding system architecture and IP suppliers, and this can be daunting for even the most seasoned semicondu... » read more

An Ideal Always-Sensing Subsystem Architecture

Always-sensing cameras are a relatively new method for users to interact with their smartphones, home appliances, and other consumer devices. Like always-listening audio-based Siri and Alexa, always-sensing cameras enable a seamless, more natural user experience. Through continuous sampling and analyzing visual data, always-sensing enables use cases such as: “Find a face” detection for... » read more

Can Compute-In-Memory Bring New Benefits To Artificial Intelligence Inference?

Compute-in-memory (CIM) is not necessarily an Artificial Intelligence (AI) solution; rather, it is a memory management solution. CIM could bring advantages to AI processing by speeding up the multiplication operation at the heart of AI model execution. However, for that to be successful, an AI processing system would need to be explicitly architected to use CIM. The change would entail a shift ... » read more

Looking Beyond TOPS/W: How To Really Compare NPU Performance

There is a lot more to understanding the true capabilities of an AI engine beyond TOPS per watt. A rather arbitrary measure of the number of operations of an engine per unit of power, the TOPS/W metric completely misses the point that a single operation on one engine may accomplish more useful work than a multitude of operations on another engine. In any case, TOPS/W is by no means the only spe... » read more

Latency Considerations Of IDE Deployment On CXL Interconnects

Certain applications and hardware types – emerging memory, artificial intelligence/machine learning (AI/ML), and cloud servers, to name a few – can realize significant performance advantages when a low latency interface is employed. However, traditional interconnects like PCI Express (PCIe) often do not offer low enough latencies required to optimize these applications. In response, the Com... » read more

Washington Sets IoT Cybersecurity Standards

On December 4th, 2020, the “IoT Cybersecurity Improvement Act of 2020” became law. The bipartisan legislation sets a minimum security standard for IoT devices that the US government procures. In an increasingly rare act of bipartisanship, the bill was “passed by unanimous consent” in both the House of Representatives and the Senate, demonstrating the importance of IoT security. The l... » read more

Achieving Security Goals With A Hardware Root Of Trust

In an environment of growing threats, meeting a fundamental set of security goals is imperative for safeguarding devices and data from attack. The most robust means of meeting these goals is a root of trust anchored in hardware. In Microsoft’s “The Seven Properties of Highly Secured Devices” white paper, property #1 is implementation of a hardware root of trust. As Microsoft explains: ... » read more

Choosing The Right Hardware Root Of Trust

A Root of Trust is broadly defined as the security foundation for a semiconductor or electronic system. Any secure function performed by the device or system relies in whole or in part on that Root of Trust. The Root of Trust typically handles chip and device identities, cryptographic functions, stores and manages cryptographic keys, and handles one or more secure processes that provides the fo... » read more

← Older posts