Artificial Intelligence is becoming ubiquitous in products and services that we use daily. Although the domain of AI has seen substantial improvements over recent years, its effectiveness is limited by the capabilities of current computing technology. Recently, there have been several architectural innovations for AI using emerging nanotechnology. These architectures implement mathematical computations of AI with circuits that utilize physical behavior of nanodevices purpose-built for such computations. This approach leads to a much greater efficiency vs.
Three-dimensional integrated circuits (3D-ICs) provide a feasible path for scaling CMOS technology in the foreseeable future. IMEC and IRDS roadmaps project that 3D integration is a key avenue for the IC industry beyond 2024. They project that some form of 3D-IC technology based on nanosheets/nanowires is likely to become mainstream soon.
Hardware implementations of artificial neural networks (ANNs) have become feasible due to the advent of persistent 2-terminal devices such as memristor, phase change memory, MTJs, etc. Hybrid memristor crossbar/CMOS systems have been studied extensively and demonstrated experimentally. In these circuits, memristors located at each cross point in a crossbar are, however, stacked on top of CMOS circuits using back end of line processing (BOEL), limiting scaling.
Non-volatile 3D FPGA research to date utilizes layer-by-layer stacking of 2D CMOS / RRAM circuits. On the other hand, vertically-composed 3D FPGA that integrates CMOS and RRAM circuits has eluded us, owing to the difficult requirement of highly customized regional doping and material insertion in 3D to build and route complementary p- and n-type transistors as well as resistive switches. In the layer-by-layer nonvolatile 3D FPGA, the connectivity between the monolithically stacked RRAMs and underlying CMOS circuits is likely to be limited and lead to large parasitic RCs.
Monolithic 3D IC (M3D) shows degradation in performance compared to 2D IC due to the restricted thermal budget during fabrication of sequential device layers. A transistor-level (TR-L) partitioning design is used in M3D to mitigate this degradation. Silicon validated 14nm FinFET data and models are used in a device-to-system evaluation to compare the TR-L partitioned M3D’s (TR-L M3D) performance against the conventional gate-level (G-L) partitioned M3D’s performance as well as standard 2D IC.
Gene Expression Networks (GENs) attempt to model how genetic information stored in the DNA (Genotype) results in the synthesis of proteins, and consequently, the physical traits of an organism (Phenotype). Deciphering GENs plays an important role in a wide range of applications from genetic studies of the origins of life to personalized healthcare. Probabilistic graphical models such as Bayesian Networks (BNs) are used to perform learning and inference of GENs from genetic data.
Probabilistic graphical models like Bayesian Networks (BNs) are powerful cognitive-computing formalisms, with many similarities to human cognition. These models have a multitude of real-world applications. New emerging-technology based circuit paradigms leveraging physical equivalence e.g., operating directly on probabilities vs. introducing layers of abstraction, have shown promise in raising the performance and overall efficiency of BNs, enabling networks with millions of random variables.
Parallel and monolithic 3D integration directions realize 3D integrated circuits (ICs) by utilizing layer-by-layer implementations, with each functional layer being composed in 2D. In contrast, vertically-composed 3D CMOS has eluded us likely due to the seemingly insurmountable requirement of highly customized complex routing and regional 3D doping to form and connect CMOS pull-up and pull-down networks in 3D. In the current layer-by-layer directions, routing can be worse than 2D CMOS because of the limited pin access.
Thermal management is one of the critical challenges in 3D integrated circuits. Incorporating thermal optimizations during the circuit design stages requires a convenient automatic method of doing thermal characterization for feedback purposes. In this paper, we present a methodology, which supports thermal characterization by automatically extracting the steady-state thermal modeling resistance network from a post-placement physical design. The method follows a two-level hierarchical approach.