EAGER: Cybermanufacturing: Software/Hardware Combined Acceleration for 3D Printing in Mass Customization

制造业和生产对提高人类生活质量和可持续性做出了巨大贡献。当前的市场趋势，如消费者对品种、产品生命周期短、产品质量高和成本低的需求，导致需要高效、反应灵敏、稳健和可持续的制造和生产模式。3D打印技术具有可负担性和可定制性的优点，但如何缩短每件产品的交货时间是3D打印技术在现实生活中大规模定制化应用的关键挑战。3D打印一个产品单元的交货时间来源于两个方面，即预制计算和制造过程。预制计算日益重要，成为3D打印大规模定制制造流程中的瓶颈。这个探索性研究（EAGER）项目旨在通过新的计算方法解决这一问题，该方法有望将预制计算时间缩短两个数量级。该项目旨在开发大规模定制3D打印的变革性计算范式。该项目将追求两个新颖和互补的目标：1)为可扩展和时间高效的预制计算框架设计一套有质量保证的几何算法；2)开发一个低复杂度和高效的计算系统，以促进和加速这些方法和算法在目标1中的使用。这种新的计算机系统专注于特定领域的计算平台，作为下一个颠覆性的技术，以提高功率-性能-运行时效率。具体来说，该团队将开发基于加速器的架构，用于计算几何算法的原语。这种新的硬件架构将利用并行性和定制性，以更少的延迟、更低的复杂性和更高的计算能力提高3D打印新计算范式的效率。

Manufacturing and production have been big contributors to improved quality and sustainability of human life. Current market trends, such as consumer demand for variety, short product life cycles, high product quality and low cost, have resulted in the need for efficient, responsive, robust and sustainable manufacturing and production paradigm. 3D printing technologies hold the merit of affordability and customizability, while the key challenge in applying 3D printing for mass customization in real life is how to reduce the lead time per unit. The lead time of 3D printing a product unit comes from two sources, i.e., the pre-fabrication computation and manufacturing process. The pre-fabrication computation is increasingly significant and becomes the bottleneck in the manufacturing flow of mass customization in 3D Printing. This EArly-concept Grant for Exploratory Research (EAGER) project looks to address this problem through new computational methods with potential for two orders of magnitude reduction in time for pre-facbrication computation.This project aims to develop a transformative computational paradigm of 3D printing in mass customization. The project will pursue two novel and complementary objectives: 1) design a suite of quality-guaranteed geometric algorithms for the scalable and time-efficient pre-fabrication computation framework.; and 2) develop a low-complexity and efficient computing system to facilitate and accelerate the use of these methods and algorithms in Objective1. This new computer system focuses on domain-specific computing platforms as the next disruptive technology for power-performance-runtime efficiency improvement. Specifically, the team will develop accelerator-based architectures for computing primitives of geometric algorithms. This new hardware architecture will exploit the parallelism and customization to improve the efficiency of the new computational paradigm in 3D printing with less delay, lower complexity and higher computing power.