Chiplets, Faster Interconnects, More Efficiency

By Ed Sperling - 22 Aug, 2019 - Comments: 1

Big chipmakers are turning to architectural improvements such as chiplets, faster throughput both on-chip and off-chip, and concentrating more work per operation or cycle, in order to ramp up processing speeds and efficiency. Taken as a whole, this represents a significant shift in direction for the major chip companies. All of them are wrestling with massive increases in processing demands ... » read more

Chiplets: Open Market or Joint Venture?

By eSilicon - 21 Aug, 2019 - Comments: 1

By Dr. Carlos Macián, senior director AI Strategy & Products, eSilicon Corporation “It may prove to be more economical to build large systems out of smaller functions, which are separately packaged and interconnected.” — Gordon Moore, 1965 “Chiplet” has become a buzzword and like most of its kind, the success of the buzzword predates the widespread availability of the produ... » read more

Optimizing Power For Learning At The Edge

By Brian Bailey - 08 Aug, 2019 - Comments: 0

Learning on the edge is seen as one of the Holy Grails of machine learning, but today even the cloud is struggling to get computation done using reasonable amounts of power. Power is the great enabler—or limiter—of the technology, and the industry is beginning to respond. "Power is like an inverse pyramid problem," says Johannes Stahl, senior director of product marketing at Synopsys. "T... » read more

HBM2E: The E Stands for Evolutionary

By Andy Patrizio - 08 Aug, 2019 - Comments: 2

Samsung introduced the first memory products in March that conform to JEDEC’s HBM2E specification, but so far nothing has come to market—a reflection of just how difficult it is to manufacture this memory in volume. Samsung’s new HBM2E (sold under the Flashbolt brand name, versus the older Aquabolt and Flarebolt brands), offers 33% better performance over HBM2 thanks to doubling the de... » read more

Are Digital Twins Something For EDA To Pursue?

By Ann Mutschler - 07 Aug, 2019 - Comments: 0

‘Digital Twins’ are one of the new, fashionable key concepts for system developers, but do they fit with EDA? How many different types of engines do these twins run on – abstract simulation, signal-based RTL simulation, emulation, prototyping, actual silicon? What should the use models be called for digital twinning – like reproduction of bugs from silicon in emulation? Or optimizing th... » read more

More Semiconductor Data Moving To Cloud

By Ed Sperling - 06 Aug, 2019 - Comments: 0

The cloud is booming. After years of steady growth it has begun to spike, creating new options for design, test, analytics and AI, all of which have an impact on every segment of the semiconductor industry. The initial idea behind the cloud is that it would supplement processing done on premises, adding extra processing power wherever necessary, such as in the verification and debug stages o... » read more

Power Is Limiting Machine Learning Deployments

By Brian Bailey - 25 Jul, 2019 - Comments: 3

The total amount of power consumed for machine learning tasks is staggering. Until a few years ago we did not have computers powerful enough to run many of the algorithms, but the repurposing of the GPU gave the industry the horsepower that it needed. The problem is that the GPU is not well suited to the task, and most of the power consumed is waste. While machine learning has provided many ... » read more

Memory IP: From Cobblestone To Cornerstone

By Mike Gianfagna - 25 Jul, 2019 - Comments: 0

Embedded, on-chip SRAM has been a fundamental building block for custom and standard chips for quite a while. When all this began, there were typically small SRAM blocks of on-chip memory supplemented by off-chip DRAM devices. Those off-chip devices became more sophisticated, with higher performance interfaces (e.g., GDDR6) or new form factors (e.g., HBM2 3D memory stacks). The on-chip memory p... » read more

Node Within A Node

By Ed Sperling - 24 Jul, 2019 - Comments: 0

Enough margin exists in manufacturing processes to carve out the equivalent of a full node of scaling, but shrinking that margin will require a collective push across the entire semiconductor manufacturing supply chain. Margin is built into manufacturing at various stages to ensure that chips are manufacturable and yield sufficiently. It can include everything from variation in how lines are... » read more

Meeting The Demands Of PAM4 Systems At 56Gbps And Beyond

By eSilicon - 24 Jul, 2019 - Comments: 0

According to an IDC white paper sponsored by Seagate the global datasphere will grow from 33 zettabytes (one zettabye = one trillion gigabytes) in 2018 to 175 zettabytes by 2025. This white paper also reports that today, more than 5 billion consumers interact with data every day. By 2025, that number will be 6 billion, or 75 percent of the world’s population. Figure 1 depicts this exponential... » read more

← Older posts Newer posts →

Knowledge Centers
Entities, people and technologies explored

Shift Left Is The Tip Of The Iceberg

A transformative change is underway for semiconductor design and EDA. New languages, models, and abstractions will need to be created.

by Brian Bailey

Partitioning In The Chiplet Era

Understanding how chiplets interact under different workloads is critical to ensuring signal integrity and optimal performance in heterogeneous designs.

by Ann Mutschler

3.5D: The Great Compromise

Pros and cons of a middle-ground chiplet assembly that combines 2.5D and 3D-IC.

by Ed Sperling

AI’s Role In Chip Design Widens, Drawing In New Startups

Focus is on letting engineers do much more with the same or fewer resources — and less drudgery.

by Karen Heyman

Key Technologies To Extend EUV To 14 Angstroms

Alongside high-NA EUV will be better-performing photoresists, reduced roughness using passivation and etch, and lateral etching to reduce tip-to-tip dimensions.

by Laura Peters

Memory Fundamentals For Engineers

eBook: Nearly everything you need to know about memory, including detailed explanations of the different types of memory; how and where these are used today; what's changing, which memories are successful and which ones might be in the future; and the limitations of each memory type.

by The SE Staff

What Comes After HBM For Chiplets

The standard for high-bandwidth memory limits design freedom at many levels, but that is required for interoperability. What freedoms can be taken from other functions to make chiplets possible?