Disasters like earthquakes, floods, and hurricanes have proven to be dangerous as they account for the loss of lives and extreme damage to infrastructure which in turn affects the economy. In the early hours after the disasters, time is of the essence, and performing rescue operations is the utmost priority of the government officials. For rapid disaster assessment, rapid rescue operations need to be carried out which include finding the stranded people, distributing aid to them, and moving them to safe locations. To carry out rapid disaster assessment, big disaster data acquired from different sensors like imaging sensors and Light Detection and Ranging (LiDAR) sensors need to be processed and this is where the knowledge of High-Performance Computing for data-intensive Geo-computations can be applied. This chapter helps the researchers and practitioners to gain an insight into various ways to acquire big disaster data, understanding the need for High-Performance Computing, hardware, and the programming model, and using embedded HPC devices such as NVIDIA Jetson Nano to build an end-to-end application for detecting damaged buildings due to earthquake. This chapter proposes an Embedded High-Performance Computing driven rapid disaster-affected buildings detection framework for real-time inferencing using pre-earthquake and post-earthquake LiDAR dataset. We envisage that by the end of the chapter, learners will be able to apply the knowledge for processing big disaster data using High-Performance Computing which can be applied in the remote sensing domain for various humanitarian and rescue operations in rapid disaster monitoring, surveying, and defense applications such as automatic target recognition and border surveillance.