Author's Latest Posts


What Exactly Are Chiplets And Heterogeneous Integration?


The terms “chiplet” and “heterogeneous integration” fill news pages, conference papers, and marketing presentations, and for the most part engineers understand what they're reading. But speakers sometimes stumble during a presentation trying to figure out whether a particular die qualifies as a chiplet, and heterogeneous integration comes in different guises for different people. Both t... » read more

New Data Center Protocols Tackle AI


Compute nodes in AI and HPC data centers increasingly need to reach out beyond the chip or package for additional resources to process growing workloads. They may commandeer other nodes in a rack (scale-up) or employ resources in other racks (scale-out). The problem is there currently is no open scale-up protocol. So far this task has been dominated by proprietary protocols, because much of ... » read more

Linear Pluggable Optics Save Energy In Data Centers


Linear pluggable optics (LPO) is garnering more attention as a way to quickly and efficiently move data in and out of server racks, but a lack of standards for connecting the optical modules is slowing adoption at a time when there is growing pressure to reduce power in data centers. LPO is the newest of two approaches to solving the power wall problem in data centers. Co-packaged optics (CP... » read more

Normalization Keeps AI Numbers In Check


AI training and inference are all about running data through models — typically to make some kind of decision. But the paths that the calculations take aren’t always straightforward, and as a model processes its inputs, those calculations may go astray. Normalization is a process that can keep data in bounds, improving both training and inference. Foregoing normalization can result in at... » read more

Assembly Design Rules Slowly Emerge


Process design kits (PDKs) play an essential in ensuring that silicon technology can proceed from one generation to the next in a manner that design tools can keep up with. No such infrastructure has been needed for packaging in the past, but that's beginning to change with advanced packages. Heterogeneous assemblies are still ramping up, but their benefits are attracting new designs. “Chi... » read more

What’s The Best Way To Sell An Inference Engine?


The burgeoning AI market has seen innumerable startups funded on the strength of their ideas about building faster, lower-power, and/or lower-cost AI inference engines. Part of the go-to-market dynamic has involved deciding whether to offer a chip or IP — with some newcomers pivoting between chip and IP implementations of their ideas. The fact that some companies choose to sell chips while... » read more

Baby Steps Toward 3D DRAM


Flash memory has made incredible capacity strides thanks to monolithic 3D processing enabled by the stacking of more than 200 layers, which is on its way to 1.000 layers in future generations.[1] But the equally important DRAM has achieved a similar manufacturable 3D architecture. The need for a sufficiently large means of storing charge — such as a capacitor — has proved elusive. Severa... » read more

Is In-Memory Compute Still Alive?


In-memory computing (IMC) has had a rough go, with the most visible attempt at commercialization falling short. And while some companies have pivoted to digital and others have outright abandoned the technology, developers are still trying to make analog IMC a success. There is disagreement regarding the benefits of IMC (also called compute-in-memory, or CIM). Some say it’s all about reduc... » read more

NAND Flash Targets 1,000 Layers


The chip industry is pushing to quadruple the stack height of 3D NAND flash from 200 layers to 800 layers or more over the next few years, using the additional capacity will help to feed the unending need for more memory of all types. Those additional layers will add new reliability issues a number of incremental reliability challenges, but the NAND flash industry has been steadily increasin... » read more

New AI Data Types Emerge


AI is all about data, and the representation of the data matters strongly. But after focusing primarily on 8-bit integers and 32‑bit floating-point numbers, the industry is now looking at new formats. There is no single best type for every situation, because the choice depends on the type of AI model, whether accuracy, performance, or power is prioritized, and where the computing happens, ... » read more

← Older posts