Author's Latest Posts


Will Markets For ML Models Materialize?


Developers are spending increasing amounts of time and effort in creating machine-learning (ML) models for use in a wide variety of applications. While this will continue as the market matures, at some point some of these efforts might be seen as reinventing models over and over. Will developers of successful models ever have a marketplace in which they can sell those models as IP to other d... » read more

AI/ML Workloads Need Extra Security


The need for security is pervading all electronic systems. But given the growth in data-center machine-learning computing, which deals with extremely valuable data, some companies are paying particular attention to handling that data securely. All of the usual data-center security solutions must be brought to bear, but extra effort is needed to ensure that models and data sets are protected ... » read more

Changing Server Architectures In The Data Center


Data centers are undergoing a fundamental shift to boost server utilization and improve efficiency, optimizing architectures so available compute resources can be leveraged wherever they are needed. Traditionally, data centers were built with racks of servers, each server providing computing, memory, interconnect, and possibly acceleration resources. But when a server is selected, some of th... » read more

More Errors, More Correction in Memories


As memory bit cells of any type become smaller, bit error rates increase due to lower margins and process variation. This can be dealt with using error correction to account for and correct bit errors, but as more sophisticated error-correction codes (ECC) are used, it requires more silicon area, which in turn drives up the cost. Given this trend, the looming question is whether the cost of ... » read more

Easier And Faster Ways To Train AI


Training an AI model takes an extraordinary amount of effort and data. Leveraging existing training can save time and money, accelerating the release of new products that use the model. But there are a few ways this can be done, most notably through transfer and incremental learning, and each of them has its applications and tradeoffs. Transfer learning and incremental learning both take pre... » read more

Improving Accuracy In Satellite Navigation Systems


Increasing dependency on the global navigation satellite system (GNSS) constellations is raising concerns about what happens when signals are unavailable, even for short periods of time. GNSS systems affect our daily lives in ways we often don’t see, from location services to cell phone timing. In fact, these satellites have become a necessary part of critical infrastructure, and higher ac... » read more

Will Co-Packaged Optics Replace Pluggables?


As optical connections work their way deeper into the data center, a debate is underway. Is it better to use pluggable optical modules or to embed lasers deep into advanced packages? There are issues of convenience, power, and reliability driving the discussion, and an eventual winner isn’t clear yet. “The industry is definitely embracing co-packaged optics,” said James Pond, principal... » read more

PCB And IC Technologies Meet In The Middle


Surface-mount technology (SMT) is evolving far beyond its roots as a way of assembling packaged chips onto printed circuit boards without through-holes. It is now moving inside packages that will themselves be mounted on PCBs. But SMT for advanced packages isn’t the same as the SMT we’ve been used to. “Many systems include multiple ASICs, a lot of memory, and that's all integrated i... » read more

Competing Auto Sensor Fusion Approaches


As today’s internal-combustion engines are replaced by electric/electronic vehicles, mechanical-system sensors will be supplanted by numerous electronic sensors both for efficient operation and for achieving various levels of autonomy. Some of these new sensors will operate alone, but many prominent ones will need their outputs combined — or “fused” — with the outputs of other sensor... » read more

Will Monolithic 3D DRAM Happen?


As DRAM scaling slows, the industry will need to look for other ways to keep pushing for more and cheaper bits of memory. The most common way of escaping the limits of planar scaling is to add the third dimension to the architecture. There are two ways to accomplish that. One is in a package, which is already happening. The second is to sale the die into the Z axis, which which has been a to... » read more

← Older posts Newer posts →