Bücher von Hao Yu

Exa-scale computing needs to re-examine the existing hardware platform that can support intensive data-oriented computing. Since the main bottleneck is from memory, we aim to develop an energy-efficient in-memory computing platform in this book. First, the models of spin-transfer torque magnetic tunnel junction and racetrack memory are presented. Next, we show that the spintronics could be a candidate for future data-oriented computing for storage, logic, and interconnect. As a result, by utilizing spintronics, in-memory-based computing has been applied for data encryption and machine learning. The implementations of in-memory AES, Simon cipher, as well as interconnect are explained in details. In addition, in-memory-based machine learning and face recognition are also illustrated in this book.

In my book, I give the analogy of the main results in one of Kevin Costellös paper for open-closed topological conformal field theory. In other words, I show that there is a Batalin-Vilkovisky algebraic structure on the open-closed moduli space (moduli space of Riemann surface with boundary and marked points) , which is defined by Harrelson, Voronov and Zuniga, and the most important, there is a solution up to homotopy to the quantum master equation of that BV algebra if the initial condition is given, under the assumption that a new geometric chain theory gives rise to ordinary homology. This solution is expected to encode the fundamental chain of compactified open-closed moduli space, which is studied thoroughly by C.-C.Liu, as exactly in the closed case. We hope this result can give new insights into the mysterious two dimensional open-closed field theory.

With focused coverage of key topics ranging from device fabrication to hybrid NVM memory system design-space optimization, this systematic treatment of emerging nano-scale NVM devices adopts a circuits/systems perspective that includes memristic dynamics.

This book covers statistical modeling and analysis of VLSI systems with a focus on interconnects, on-chip power grids and clock networks and analog/mixed-signal circuits. It offers an analysis of each algorithm with applications in real circuit design.

3D integration is an emerging technology for the design of many-core microprocessors and memory integration.