3D integration plays a crucial role in the semiconductor industry, as it significantly boosts chip density while reducing the length of interconnections. In particular, monolithic 3D (M3D) technology, which involves the sequential fabrication of top devices over the bottom devices, allows for high integration density compared to Through Silicon Via (TSV) technology. We develop 3D-integrated logic and memory devices based on a Back-End-of-Line (BEOL) compatible process. These include complementary FET (CFET), 3D DRAM, and 3D NAND. Furthermore, we deploy 3D-integrated devices to various applications such as neuromorphic and quantum computing.
Neuromorphic hardware represents artificial intelligence (AI) hardware designed to perform AI tasks with ultra-low power by mimicking the human brain that consumes only 20 W. To create neuromorphic hardware, it is essential to employ artificial neurons and synapses that mimic the functionalities of biological neural networks. We develop various neuron and synaptic devices, as well as perform system-level studies including deep neural network, spiking neural network, oscillatory neural network, and Hopfield neural network. Furthermore, we develop diverse neuromorphic sensors that have both neuromorphic and sensory functions, enabling in-sensor computing for ultra-low power Internet of Things (IoT) sensors.
Machine learning is changing the world in various aspects of human life, including autonomous car, healthcare service, entertainment, and more. The remarkable capabilities of optimization and decision-making inherent in machine learning have the potential to reshape the landscape of semiconductor technologies. This includes reducing computation times in Technology Computer-Aided Design (TCAD) simulations, optimizing processes, and refining device designs. We explore opportunities where machine learning and AI technologies can serve as catalysts for growth within the semiconductor industry.