Scaling AI/ML Training Performance With HBM2E Memory


In my April SemiEngineering Low Power-High Performance blog, I wrote: “Today, AI/ML neural network training models can exceed 10 billion parameters, soon it will be over 100 billion.” “Soon” didn’t take long to arrive. At the end of May, OpenAI unveiled a new 175-billion parameter GPT-3 language model. This represented a more that 100X jump over the size of GPT-2’s 1.5 billion param... » read more

Preparing For A Barrage Of Physical Effects


Advancements in 3D transistors and packaging continue to enable better power and performance in a given footprint, but they also require more attention to physical effects stemming from both increased density and vertical stacking. Even in planar chips developed at 3nm, it will be more difficult to build both thin and thick oxide devices, which will have an impact on everything from power to... » read more

Power And Performance Optimization At 7/5/3nm


Semiconductor Engineering sat down to discuss power optimization with Oliver King, CTO at Moortec; João Geada, chief technologist at Ansys; Dino Toffolon, senior vice president of engineering at Synopsys; Bryan Bowyer, director of engineering at Mentor, a Siemens Business; Kiran Burli, senior director of marketing for Arm's Physical Design Group; Kam Kittrell, senior product management group d... » read more

Chiplet Reliability Challenges Ahead


Assembling chips using LEGO-like hard IP is finally beginning to take root, more than two decades after it was first proposed, holding the promise of faster time to market with predictable results and higher yield. But as these systems of chips begin showing up in mission-critical and safety-critical applications, ensuring reliability is proving to be stubbornly difficult. The main driver fo... » read more

Secure Networking Basics: MACsec, IPsec, And SSL/TLS/DTLS


The MACsec, IPsec and SSL/TLS/DTLS protocols are the primary means of securing data in motion (communicated between connected devices). These protocols can be anchored in hardware or implemented in software as part of an end-to-end security architecture. This white paper provides fundamental information on each of these protocols including their interrelationships and use cases. ... » read more

Blog Review: Aug. 12


Arm's Greg Yeric takes a look at what semiconductor manufacturing might look like in 2030 as the price of equipment rises and possibilities for when the next upgrade to EUV, high numerical aperture, eventually runs out of steam. Synopsys' Taylor Armerding explains the difference between bugs and security flaws and why it's so important to pay attention to potential problems in a design's spe... » read more

Week In Review: Design, Low Power


M&A Goodix acquired Dream Chip Technologies. Shenzhen-based Goodix is known for fingerprint and other biometric sensors and authentication solutions, as well as Arm and RISC-V based MCUs. It is reportedly among the ten largest Chinese chipmakers, according to EqualOcean. Terms of the deal were not disclosed. Based in Garbsen, Germany, Dream Chip Technologies originally was founded in ... » read more

Combating Counterfeit Chips


The harsh reality is that today, the authenticity of chips is often impossible to guarantee. The counterfeit chip market is sizeable and growing with a worldwide value estimated at $75B in 2019. Those counterfeits are believed to have been integrated into more than $169B of electronic devices. Recent confirmed incidents of counterfeit parts found in electronic systems include defibrillators, ai... » read more

Big Changes In AI Design


Semiconductor Engineering sat down to discuss AI and its move to the edge with Steven Woo, vice president of enterprise solutions technology and distinguished inventor at Rambus; Kris Ardis, executive director at Maxim Integrated; Steve Roddy, vice president of Arm's Products Learning Group; and Vinay Mehta, inference technical marketing manager at Flex Logix. What follows are excerpts of that ... » read more

Blog Review: Aug. 5


Rambus' Scott Best explains some more sophisticated chip attacks, such as side-channel attacks, clocking attacks, fault injection, and infrared emission analysis, and countermeasures that can be adopted against them. Arm's Mark O'Connor considers ways that deployed neural networks could adapt to examples it sees in real-world use and generate more accurate predictions. Mentor's Chris Spea... » read more

← Older posts Newer posts →