Chip Industry Week In Review


By Jesse Allen, Gregory Haley, and Liz Allan Bosch, Infineon, and NXP were cleared in Germany to each acquire 10% of the European Semiconductor Manufacturing Co. (ESMC), established by TSMC, solidifying the supply chain against future shortages, particularly for automotive chips. “ESMC intends to build and operate another large semiconductor factory in Dresden, in which the three Europ... » read more

Flipping Processor Design On Its Head


AI is changing processor design in fundamental ways, combining customized processing elements for specific AI workloads with more traditional processors for other tasks. But the tradeoffs are increasingly confusing, complex, and challenging to manage. For example, workloads can change faster than the time it takes to churn out customized designs. In addition, the AI-specific processes may ex... » read more

The Power Of HBM3 Memory For AI Training Hardware


AI training data sets are constantly growing, driving the need for hardware accelerators capable of handling terabyte-scale bandwidth. Among the array of memory technologies available, High Bandwidth Memory (HBM) has emerged as the memory of choice for AI training hardware, with the most recent generation, HBM3, delivering unrivaled memory bandwidth. Let’s take a closer look at this important... » read more

A Novel Approach To Mitigating RowHammer Attacks And Improving Server Memory System Reliability


A technical paper titled “RAMPART: RowHammer Mitigation and Repair for Server Memory Systems” was published by researchers at Rambus. Abstract: "RowHammer attacks are a growing security and reliability concern for DRAMs and computer systems as they can induce many bit errors that overwhelm error detection and correction capabilities. System-level solutions are needed as process technology... » read more

Securing AI/ML Training And Inference Workloads


AI/ML can be thought about in two distinct and essential functions: training and inference. Both are vulnerable to different types of security attacks and this blog will look at some of the ways in which hardware-level security can protect sensitive data and devices across the different AI workflows and pipelines. The security challenges encountered with AI/ML workloads can be addressed by i... » read more

Bug, Flaw, Or Cyberattack?


The lines between counterfeiting, security, and design flaws are becoming increasingly difficult to determine in advanced packages and process nodes, where the number of possible causes of unusual behavior grow exponentially with the complexity of a device. Strange behavior may be due to a counterfeit part, including one that contains a trojan. Or it may be the result of a cyberattack. It al... » read more

Chip Industry Week In Review


By Susan Rambo, Karen Heyman, and Liz Allan The Biden-Harris administration designated 31 Tech Hubs across the U.S. this week, focused on industries including autonomous systems, quantum computing, biotechnology, precision medicine, clean energy advancement, and semiconductor manufacturing. The Department of Commerce (DOC) also launched its second Tech Hubs Notice of Funding Opportunity. ... » read more

Chip Industry Week In Review


By Susan Rambo, Gregory Haley, and Liz Allan SRC unfurled its Microelectronics and Advanced Packaging (MAPT) industry-wide 3D semiconductor roadmap, addressing such topics as advanced packaging, heterogeneous integration, analog and mixed-signal semiconductors, energy efficiency, security, the related foundational ecosystem, and more. The guidance is the collective effort of 300 individuals ... » read more

Memory Technologies Key To Advancing AI Applications


Memory is an integral component in every computer system, from the smartphones in our pockets to the giant data centers powering the world’s leading-edge AI applications. As AI continues to rise in reach and complexity, the demand for more memory from data center to endpoints is reshaping the industry’s requirements and traditional approaches to memory architectures. According to OpenAI,... » read more

Partitioning Processors For AI Workloads


Partitioning in complex chips is beginning to resemble a high-stakes guessing game, where choices need to extrapolate from what is known today to what is expected by the time a chip finally ships. Partitioning of workloads used to be a straightforward task, although not necessarily a simple one. It depended on how a device was expected to be used, the various compute, storage and data paths ... » read more

← Older posts Newer posts →