Challenges Of Heterogeneous Integration


Heterogeneous integration opens the door to an almost unlimited number of features in a single package, but it also adds system-level challenges into a small space filled with a whole spectrum of possible interactions. Mike Kelly, vice president of chiplets/FCBGA integration at Amkor Technology, talks about a variety of issues ranging from uneven aging, warpage, and different mechanical stresse... » read more

Changes In Memory Design


An explosion of data in automotive, cloud, and AI are altering the fundamentals of memory design. One size no longer fits all, as memory is used for a broader set of applications, from automotive and cloud to consumer devices. Anand Theruvengadam, director of product management at Synopsys, talks about the impact of big data applications on density, memory stacking, and growing concerns about r... » read more

Striking A Balance In Acoustic Inspection


Sound energy is a quick way to to spot voids, delamination, cracks, and other possible defects that are accessible from outside the chip or package, as well as some defects that are inside of chips. But acoustic inspection also is highly sensitive to different materials with different polarities, which can change the reflection of sound waves. Bill Zuckerman, product marketing manager at Nordso... » read more

Improving Image Resolution At The Edge


How much cameras see depends on how accurately the images are rendered and classified. The higher the resolution, the greater the accuracy. But higher resolution also requires significantly more computation, and it requires flexibility in the design to be able to adapt to new algorithms and network models. Jeremy Roberson, technical director and software architect for AI/ML at Flex Logix, talks... » read more

The Impact Of ML On Chip Design


Node scaling and rising complexity are increasing the time it takes to get chips out the door. At the same time, design teams are not getting larger. What is needed is a way to automate the creative process, and to not have to start every design from scratch. This is where reinforcement learning fits in, with its ability to centralize and store “tribal knowledge. Thomas Andersen, vice preside... » read more

Challenges In Packaging 5G And 6G


Millimeter wave frequencies are essential for transferring more data more quickly, but they also require different packaging technology to minimize loss and drift. That opens up a number of tradeoffs around antenna in package, antenna on package, flexible circuits, and different substrates. Curtis Zwenger, vice president of R&D at Amkor Technology, talks about a host of new challenges rangi... » read more

LPDDR Flash In Automotive


New automotive architectures are raising challenges for how to utilize memory effectively and efficiently. An LPDDR interface for flash allows different processors to utilize multiple banks of flash memory, which in turn reduces latency and interference. Sandeep Krishnegawda, vice president of marketing and applications at Infineon, talks about the new zonal controllers in automotive design and... » read more

Challenges In Writing SDC Constraints


Writing design constraints is becoming more difficult as chips become more heterogeneous, and as they are expected to function longer in the field. Timing and power can change over time, and constraints need to be adjusted to that changing context. Synopsys’ Ajay Daga, group director for R&D at Synopsys, talks about the challenges in pushing constraints down to different hierarchical portions... » read more

Programmable General-Purpose I/O


Talking to many different kinds of chips is becoming more complicated. There are new types of transistors, new protocols, and all of this is limited by the number of pins. Geoff Tate, CEO of Flex Logix, talks about adding programmability into the general-purpose I/O to enable more flexibility, lower inventory, and reduced obsolescence. » read more

100G Ethernet At The Edge


The amount of data is growing, and so is the need to process it closer to the source. The edge is a middle ground between the cloud and the end point, close enough to where data is generated to reduce the time it takes to process that data, yet still powerful enough to analyze that data quickly and send it wherever it is needed. But to make this all work requires faster conduits for that data i... » read more

← Older posts Newer posts →