Multi-Physics At 5/3nm


Joao Geada, chief technologist at ANSYS, talks about why timing, process, voltage, and temperature no longer can be considered independently of each other at the most advanced nodes, and why it becomes more critical as designs shrink from 7nm to 5nm and eventually to 3nm. In addition, more chips are being customized, and more of those chips are part of broader systems that may involve an AI com... » read more

GDDR6 – HBM2 Tradeoffs


Steven Woo, Rambus fellow and distinguished inventor, talks about why designers choose one memory type over another. Applications for each were clearly delineated in the past, but the lines are starting to blur. Nevertheless, tradeoffs remain around complexity, cost, performance, and power efficiency.   Related Video Latency Under Load: HBM2 vs. GDDR6 Why data traffic and bandw... » read more

Safety Critical Design In Automotive


Shiv Chonnad, hardware engineer at Synopsys, examines how to design chips for safety-critical applications such as automotive and ensure they work as planned and in accordance with ISO 26262 and the various ASIL levels. This includes how to find faults at both a chip and a system level. https://youtu.be/3dL4ZuSe5Ls » read more

Billion-Gate Design Connectivity


Sasa Stamenkovic, senior field application engineer at OneSpin Solutions, explains how to find and resolve connectivity issues in integrating large numbers of components in very big designs, often at the leading edge nodes and in markets such as AI. » read more

Debug Changes At Advanced Nodes


Ribhu Mittal, emulation applications director at Synopsys, zeroes in on what’s changing in debug, including why traditional verification methods are failing in designs with 1 billion gates and a commensurate amount of software complexity. The key is how to maintain or reduce time to market, and that requires a different way of approaching the problem. » read more

2.5D, 3D Power Integrity


Chris Ortiz, principal applications engineer at ANSYS, zeroes in on some common issues that are showing up in 2.5D and 3D packaging, which were not obvious in the initial implementations of these packaging technologies. This includes everything from how to build a power delivery network to minimize the coupling between chips to dealing with variability and power integrity and placement of diffe... » read more

Designing An AI SoC


Susheel Tadikonda, vice president of networking and storage at Synopsys, looks at how to achieve economies of scale in AI chips and where the common elements are across all the different architectures. https://youtu.be/fm0kxnj3DuM » read more

The Winograd Transformation


Cheng Wang, senior vice president of engineering at Flex Logix, explains how the Winograd Transformation applies to convolutional neural networks. https://youtu.be/E7QJUby9x-I » read more

New Memory Options


Carlos Macián, eSilicon’s senior director of AI strategy and products, talks about how to utilize memory differently and reduce the movement of data in AI chips, and what impact that has on power and performance. https://youtu.be/wItp6wReVts » read more

Reverse Debug


Chun Chan, product applications engineering director at Synopsys, talks with Semiconductor Engineering about testbench debug and how adding time markers can speed time to signoff. https://youtu.be/tx_89M1bq3Q » read more

← Older posts Newer posts →