PFI-RP: Partnership to develop next-generation memory chips for intelligent computing systems.

创新伙伴关系-研究伙伴关系（PFI-RP）项目的更广泛影响/商业潜力在于为节能和高性能计算系统提供新的硬件平台。大数据的兴起使云计算和边缘设备上的人工智能（AI）出现，并从根本上改变了计算、网络和数据存储行业。然而，现有的硬件无法支撑以数据为中心的计算的快速增长。特别是，快速和节能的人工智能需要更好的嵌入式内存技术（即计算机芯片内的数据存储设备），这些技术可以同时快速读写，同时提供低成本的高容量和低功耗。该项目将通过开发一种新型片上磁存储设备来解决这一挑战，重点关注其在数据存储、人工智能、通信和网络市场的商业化。拟议的项目将开发一种新型的磁随机存取存储器（MRAM），称为电压控制自旋轨道（VCSO）存储器。MRAM因其低功耗和高耐用性而成为新兴人工智能系统的主要竞争者，经过十多年的研究和开发，正在进入半导体行业的批量生产。然而，它目前的版本受到密度和速度的限制，这限制了它的最终目标市场。该项目将基于新的物理原理和材料开发器件和存储阵列，这将使器件克服现有MRAM的物理限制，实现更高的速度和更好的可扩展性，以更小的位尺寸。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

The broader impact/commercial potential of this Partnerships for Innovation - Research Partnerships (PFI-RP) project is in providing a new hardware platform for energy-efficient and high-performance computing systems. The rise of big data has enabled the emergence of artificial intelligence (AI) in the cloud and on edge devices, and is fundamentally transforming the computing, networking and data storage industries. However, existing hardware cannot sustain the rapid growth of data-centric computing. In particular, fast and energy-efficient AI requires better embedded memory technologies (i.e. data storage devices inside computer chips) that are simultaneously fast to read and write, while delivering high capacities with low cost, along with low power consumption. This project will address this challenge by developing a novel type of on-chip magnetic memory device, focusing on its commercialization in the data storage, AI, communications and networking markets. The proposed project will develop a new type of magnetic random access memory (MRAM), referred to as voltage-controlled spin-orbit (VCSO) memory. MRAM is the leading contender for emerging AI systems due to its low power consumption and high endurance, and is entering volume manufacturing across the semiconductor industry after more than a decade of research and development. However, its current version suffers from density and speed limitations that limit its ultimate addressable market. This project will develop devices and memory arrays based on new physical principles and materials, which will allow the devices to overcome the physical limitations of existing MRAM, and achieve higher speeds with better scalability to smaller bit dimensions.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.