CC* Compute: Central Computing with Advanced Implementation at San Diego State University

这个项目建立了一个计算系统，帮助圣地亚哥州立大学的研究人员通过不断发展的计算机处理硬件来加速他们的工作。教师和学生将开发代码，其中大部分目前在传统处理单元上运行，以利用图形处理单元和现场可编程门阵列的增强计算能力，这有效地允许计算机芯片的电路为特定的计算任务进行优化。该系统的应用程序包括模拟地下二氧化碳封存，开发新的计算机程序以识别生物多样性环境中的致病生物和其他生物，以及研究核结构、脑成像、病毒运动和发动机设计。其中一个pi指导新用户的培训，基础设施被纳入本科生和研究生可用的几门课程中。外部用户可以通过太平洋研究平台访问该资源。一个新的高性能计算集群为圣地亚哥州立大学和整个地区的研究人员提供了先进的处理器硬件。该集群经过优化，支持将内部开发的现有软件转移到促进分布式计算和/或电子设计自动化的处理器上。在加速项目和现代化计算方法培训的同时，这项工作还通过量化先进硬件可能增强的研究，为大学的长期网络基础设施采购计划提供信息。集群容量的20%通过太平洋研究平台保留给校外使用，5%用于培训和课程，以促进劳动力发展。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。

This project establishes a computing system that assists researchers at San Diego State University to accelerate their work through ongoing developments in computer processing hardware. Faculty and students will develop code, most of it currently running on traditional processing units, to take advantage of the enhanced computing power of graphical processing units and field programmable gate arrays, which effectively allow the circuitry of the computer chip to be optimized for specific computing tasks. Applications hosted on this system include simulations of subterranean carbon dioxide sequestration, the development of new computer programs to identify disease-causing and other organisms in biologically diverse environments, and studies of nuclear structure, brain imaging, the motion of viruses, and engine design. One of the PIs directs the training of new users, and the infrastructure is incorporated into several courses available to undergraduates and graduate students. External users can access the resource through the Pacific Research Platform.A new, high-performance computing cluster offers advanced processor hardware to researchers at San Diego State University and throughout the region. The cluster is optimized to support transfer of existing software developed in-house to processors that promote distributed computing and/or electronic design automation. While accelerating projects and modernizing training in computational methods, this work also informs the University’s long-range cyberinfrastructure acquisition plans by quantifying the enhancement of research possible with advanced hardware. 20% of the cluster capacity is reserved for extramural use through the Pacific Research Platform, and 5% for training and coursework to advance workforce development.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.