AI & Energy: Bending The Curve


By Pushkar P. Apte and Melissa Grupen-Shemansky Artificial intelligence (AI) is scaling at a pace that is reshaping semiconductor roadmaps, data center design, and long-term infrastructure strategy. AI promises many economic and social benefits, but the growth comes with an escalating demand for power, and energy has emerged as a major challenge. The AI & energy challenge AI training c... » read more

Enabling Production-Ready AI For Semiconductor Manufacturing


Semiconductor inspection has always been a scalability problem. Inspection teams are buried in manual reviews because the machines on the line throw false rejects, miss real defects, and can't learn from the data they're already producing. The job hasn't really changed in decades. Find defects faster. Find them with higher sensitivity. Keep cost down. And whatever you do, don't bury the review ... » read more

HW-Native, GPU Compiler for Large-scale ML Production Systems (UC San Diego, Meta)


A new technical paper, "TLX: Hardware-Native, Evolvable MIMW GPU Compiler for Large-scale Production Environments," was published by researchers at UC San Diego and Meta. Abstract "Modern GPUs increasingly rely on specialized hardware units and asynchronous coordination mechanisms, so performance depends on orchestrating data movement, tensor-core computation, and synchronization rather t... » read more

Why Vision LLMs Force A Rethink Of Edge AI Hardware


As vision-centric large language models move on-device, performance measured in raw TOPS is no longer enough. Architectures need to be built around real workloads, memory behavior, and sustained utilization, especially at the edge. Vision LLMs are changing the edge AI equation For the last decade, most edge AI silicon has been built to do one job extremely well: run convolutional networks for... » read more

SOCAMM2: Bringing LPDDR5X Benefits To AI Servers


The rapid scaling of artificial intelligence is reshaping nearly every dimension of data center design. While much of the focus has been on GPUs, accelerators and advanced packaging, another constraint is emerging as equally critical: power. As AI models grow larger and more complex, power consumption, not raw compute, is increasingly the limiting factor in system scalability. Modern AI work... » read more

Vision-Language-Action Models Arrive


The AI model type capturing the most attention across robotics and autonomous vehicles right now is the vision-language-action model, or VLA. At embedded AI conferences this year, particularly the recently held Embedded Vision Summit, VLAs were a main topic of discussion – not as a research curiosity, but as the architecture that teams building autonomous systems are actively targeting. If yo... » read more

Introducing “The Architecture Speaks”


What are specifications used for? How do you use them? Are they intelligible? These questions are at the heart of the project that produces a new tool called "The Architecture Speaks". This is an experimental chatbot tool built on generative AI that aims to provide quick answers to complex questions about the Arm architecture. It also provides links to the Arm Architecture Reference Manual. Th... » read more

Harnessing Artificial Intelligence For Trusted IC Signoff


After years of behind-the-scenes work, artificial intelligence (AI) is now embedded throughout the technology world—from space exploration to everyday apps on our smartphones. There is a circular feedback loop in which we design more powerful computer chips to train AI models and use them; and then use those AI models to design even more powerful chips. The use of AI in the software used for ... » read more

What’s Really Needed For Advanced Test?


By Greg Prewitt and Marc Jacobs Advanced test has become one of the semiconductor industry's most promising frontiers: adaptive binning, feed-forward models, and real-time analytics pulling signals from mountains of measurement data. But there is a problem hiding underneath all that ambition, and it is neither compute nor algorithm; it is data. More specifically, it is the unglamorous, found... » read more

Test Distribution Evolves To Meet AI Challenges


The proliferation of artificial intelligence (AI) is driving rapid acceleration of the semiconductor market, which analysts now predict will reach $1 trillion this year. Many semiconductor devices will be the GPUs that populate the data centers that run AI workloads. Driven by strong, sustained investments from hyperscaler operators, high-performance computing (HPC)/AI data centers are expected... » read more

← Older posts Newer posts →