SSCS Technical Webinars

Abstract: Compute-in-memory (CIM) and processing-near-memory (PNM) have emerged as promising approaches to overcome the limitations of architectures that separate processing from memory. While this bottleneck is often attributed to von Neumann’s design, such critiques overlook its historical significance: the separation of logic and memory enabled the decoupling of software from hardware, laying the foundation for general-purpose […]

Abstract: This presentation will elaborate on some of the technical content of the paper of the same title published in the OJSSCS. The paper employs several methods that may be unfamiliar to readers. They are: How to separate PM from AM in a noise spectrum How to formulate approximate transfer functions for circuits subject to periodic […]

Abstract: Computing-in-memory (CiM), in conjunction with ultra-low precision (ULP) inputs and weights, promises a pathway towards the deployment of DNN workloads on resource-constrained edge platforms. For instance, CiM-enabled binary neural network (BNN) accelerators (with inputs and weights quantized to two states: {-1,1}) have shown potential by significantly reducing storage and energy cost while maintaining acceptable […]

Abstract: Three-dimensional integrated circuits (3D ICs) are shaping the future of AI hardware by stacking multiple chips vertically to achieve higher bandwidth, lower latency, and better energy efficiency. But this vertical integration also introduces new design challenges, including heat dissipation, power delivery, cross-layer timing, clock distribution, routing congestion, and multi-physics reliability, making manual design impractical. […]

Abstract: With emerging trends such as machine learning, the internet of everything, brain–machine interfaces, autonomous driving, 6G communications, and quantum computing, circuit designers are increasingly challenged to achieve drastic improvements in accuracy, speed, and power efficiency. Yet, as CMOS circuit designs have matured over the past five decades, we often find ourselves constrained by well-established […]