Deploying Generative AI At Scale With Flexibility And Speed


As the types of content that generative AI (GenAI) can process expands to advanced video, images, audio, and text, the race to innovate is creating new hurdles for developers. Discover how to overcome the challenges surrounding scalability and speed of GenAI development to offer cutting-edge experiences. Read more here and learn: How to run and scale GenAI workloads efficiently. Tech... » read more

Verifying SRAM Yield Inclusive Of Rare And Random Defects


Large disparities were observed between wafer level SRAM Access Disturb related bit-fails as measured on silicon wafers and the number of such bit-fails as predicted by intrinsic device variability alone. Root cause investigations pointed to a rare but random defect lowering threshold voltage of the NFET devices of the SRAM bit-cell. This work presents a novel method to enable the inclusion of ... » read more

Research Bits: Dec. 11


Photonic AI processor Researchers from Massachusetts Institute of Technology (MIT), Enosemi, and Periplous developed a fully integrated photonic processor that can perform all the key computations of a deep neural network optically on the chip. The chip is fabricated using commercial foundry processes and uses three layers of devices that perform linear and nonlinear operations. A particula... » read more

Automotive Design: How AI Is Transforming The Art Of Simulation


The automotive sector is about to experience a major wave of innovation as artificial intelligence (AI) is applied to design simulation, according to experts. The technology makes it possible to reduce the time needed to run the analyses for crash-test simulations — one of the most data-heavy exercises in automotive design — from several days to minutes. Read more here to learn about a p... » read more

Research Bits: Dec. 3


Self-assembly of mixed-metal oxide arrays Researchers from North Carolina State University and Iowa State University demonstrated a technique for self-assembling electronic devices. The proof-of-concept work was used to create diodes and transistors with high yield and could be used for more complex electronic devices. “Our self-assembling approach is significantly faster and less expensi... » read more

Aging, Complexity, And AI In Analog Design


Experts at the Table: Semiconductor Engineering sat down to discuss abstraction in analog vs. digital, how analog circuits age, the growing role of AI, and why there is so much margin in analog designs, with Mo Faisal, president and CEO of Movellus; Hany Elhak, executive director of product management at Synopsys; Cedric Pujol, product manager at Keysight; and Pradeep Thiagarajan, principal pro... » read more

GenAI + Semiconductors + Humanity


Silicon Catalyst held its 2024 Semiconductor Industry Forum in Mountain View, CA, at the Computer History Museum on November 13th. Richard Curtin, managing partner for Si Catalyst, opened the event by thanking David House, vice chair of the Board at the Computer History Museum and creator of the 4004 processor, and the CHM staff for hosting the event. Richard talked about the start of se... » read more

Research Bits: Nov. 25


3D-printed ESD protection Researchers from Lawrence Livermore National Laboratory developed a printable elastomeric silicone foam for electronics packaging that provides both mechanical and electrostatic discharge (ESD) protection. The team used a 3D printing technique called direct ink writing (DIW), an extrusion process in which a paste with controlled rheological properties such as elast... » read more

Research Bits: Nov. 19


Starchy nanocomposite films Researchers from Queen Mary University of London created biodegradable, flexible, and electrically conductive nanocomposite films made using potato starch instead of petroleum-based materials. The starch-based films decompose within a month when buried in soil. In addition to starch, the nanocomposite films contain the conductive 2D material MXene. Adjusting the ... » read more

Small Language Models: A Solution To Language Model Deployment At The Edge?


While Large Language Models (LLMs) like GPT-3 and GPT-4 have quickly become synonymous with AI, LLM mass deployments in both training and inference applications have, to date, been predominately cloud-based. This is primarily due to the sheer size of the models; the resulting processing and memory requirements often overwhelm the capabilities of edge-based systems. While the efficiency of Exped... » read more

← Older posts Newer posts →