Improving AI Productivity With AI

By Ed Sperling - 28 Nov, 2023 - Comments: 0

AI is showing up or proposed for nearly all aspects of chip design, but it also can be used to improve the performance of AI chips and to make engineers more productive earlier in the design process. Matt Graham, product management group director at Cadence, talks with Semiconductor Engineering about the role of AI in identifying patterns that are too complex for the human brain to grasp, how t... » read more

What To Do About Electrostatic Discharge

By Ed Sperling - 20 Nov, 2023 - Comments: 0

Electrostatic discharge is a well-understood phenomenon, but it’s becoming more difficult to plan for as single chips are replaced by multiple chips or chiplets in a package, and as the density of components continues to increase with each new node. In both cases, the probability for failure increases unless these sudden shocks are addressed in the design. Dermott Lynch, director of product m... » read more

Blog Review: November 15

By Jesse Allen - 15 Nov, 2023 - Comments: 0

Cadence's Neelabh Singh explores the process of lane initialization and link training in bringing up a high-speed link in USB4. Synopsys' Shela Aboud argues that TCAD should be an integral part of an EDA flow as it enhances design technology co-optimization with a way to experiment and determine what works and what doesn’t work at different process nodes using physics-based models. Siem... » read more

Blog Review: Nov. 8

By Jesse Allen - 08 Nov, 2023 - Comments: 0

Siemens' Todd Westerhoff takes a look at the three stages of power integrity analysis for PCBs, challenges to board-level signal integrity, and best practices for getting the most accurate estimate of design performance. Synopsys' William Ruby provides a brief overview of the evolution of low-power design techniques and finds opportunities to reduce power and to make chip designs more energy... » read more

Coding And Debugging RISC-V

By Ann Mutschler - 06 Nov, 2023 - Comments: 0

As monolithic device scaling continues to wind down and evolve toward increasingly heterogeneous designs, it has created an inflection point for chip architects to create customized cores that are much more energy efficient and faster than off-the-shelf processors. Zdeněk Přikryl, CTO of Codasip, talks about where RISC-V fits into this picture, using a modular ISA and custom instruction layer... » read more

Blog Review: November 1

By Jesse Allen - 01 Nov, 2023 - Comments: 0

Cadence’s Rich Chang finds that although UVM has being used for testbench creation for more than a decade, it is still challenging to debug problems that are inside of UVM testbench. Siemens’ Keith Felton suggests that early analysis in complex advanced packaging flows can enable designers to spot potential issues early to avoid built-in constructs that cause design failures and require ... » read more

What Will That Chip Cost?

By Brian Bailey - 30 Oct, 2023 - Comments: 1

In the past, analysts, consultants, and many other experts attempted to estimate the cost of a new chip implemented in the latest process technology. They concluded that by the 3nm node, only a few companies would be able to afford them — and by the time they got into the angstrom range, probably nobody would. Much has changed over the past few process nodes. Increasing numbers of startups... » read more

Unlocking The Power Of Edge Computing With Large Language Models

By Paul Karazuba - 30 Oct, 2023 - Comments: 0

In recent years, Large Language Models (LLMs) have revolutionized the field of artificial intelligence, transforming how we interact with devices and the possibilities of what machines can achieve. These models have demonstrated remarkable natural language understanding and generation abilities, making them indispensable for various applications. However, LLMs are incredibly resource-intensi... » read more

The Limits Of AI-Generated Models

By Brian Bailey - 26 Oct, 2023 - Comments: 2

In several recent stories, the subject of models has come up, and one recurrent theme is that AI may be able to help us generate models of a required abstraction. While this may be true in some cases, it is very dangerous in others. If we generalize, AI should be good for any model where the results are predominantly continuous, but discontinuities create problems. Unless those are found and... » read more

Ensuring The Health And Reliability Of Multi-Die Systems

By Yervant Zorian - 26 Oct, 2023 - Comments: 0

From generative AI tools that rapidly produce chatbot responses to high-performance computing (HPC) applications enabling financial forecasting and weather modeling, it’s clear we’re in a whole new realm of processing power demand. Given these compute-intensive workloads, monolithic SoCs are no longer capable to meet today’s processing needs. Engineering ingenuity, however, has answered t... » 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

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?

by Brian Bailey

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

Why Small Fab And Assembly Houses Are Thriving

Megafabs churning out the most advanced processors are not the only game in town.

by Bryon Moyer

New AI Processors Architectures Balance Speed With Efficiency

Hot Chips 24: Large language models ratchet up pressure for sustainable computing and heterogeneous integration; data management becomes key differentiator.