II-EN: Collaborative Research: Large-Scale FPGA-Centric Cluster with Direct and Programmable Communication

与理论和实验一起，计算机模拟现在构成了科学探究的第三大支柱，使研究人员能够建立和测试复杂现象的模型，这些模型要么无法在实验室中复制，要么成本高昂。应用范围从实际的，如设计更有效的飞机和有效的药物，以了解疾病的分子基础，如阿尔茨海默氏症的基础研究？S.然而，计算能力目前只是所需的一小部分：详细的生物模拟仅限于少量的大分子;模拟细胞需要数百万的额外因素，而模拟更大的结构则远远不止这些。这项工作的总体目标是使科学计算用户社区能够通过从现成组件构建的可扩展，具有成本效益，高性能，通用系统进行变革性研究。具体目标是建立一个计算集群和相关基础设施，以促进推进此类计算机系统的研究。要探索的统一技术机制是在以加速器为中心的集群中通过直接和可编程互连集成通信和计算。限制性能的三个基本问题是计算效率、功率密度和通信延迟。所有这些问题都通过增加异质性来解决，但最后一个问题特别是通过将通信集成到加速器中来解决。这种集成支持计算组件之间的直接和可编程通信。直接链接可以绕过CPU、网络接口甚至设备内存。可编程通信使数据传输即使在大量负载下也能高效进行。建议的基础设施是一个大规模的FPGA为中心的集群直接和可编程通信（DPC）。这个服务器类别被称为Novo-G#，其中#是DPC的一个位置保持器，因为这个奖项的目标是增强和利用Novo-G，佛罗里达大学的可重新配置的超级计算机。基础设施将包括物理硬件，但也包括软件和配置，以提高一般可用性和支持的研究项目。与Novo-G一样，该基础设施的另一个方面是协作者社区，他们将贡献工具，应用程序，评估和反馈。目前，已经确定了一些内部和外部合作者，但还有更多潜在的研究项目？在应用程序、体系结构和系统的不同领域，将由拟议的基础设施启用。启用研究的更广泛影响是提高科学计算的能力。拟议的基础设施的技术更广泛的影响是为计算机科学和工程的各种领域的变革性研究提供系统测试平台，包括可编程网络组件，特别是加速器的处理器/网络接口，基于FPGA的系统，可重构计算中的应用，具有直接和可编程通信的集群架构，以及支持此类集群的库和工具。使用基础设施的研究人员社区将包括PI及其合作者，但也包括致力于为基础设施做出贡献的更广泛社区的成员。该基础设施将提供一个平台，以开发新的教育和外联组成部分。

Together with theory and experimentation, computer simulation now constitutes the third pillar of scientific inquiry, enabling researchers to build and test models of complex phenomena that either cannot be, or would be prohibitively expensive to be, replicated in the laboratory. Applications range from the practical, such as designing more efficient aircraft and effective drugs, to basic research in understanding the molecular basis of diseases such as Alzheimer?s. Yet computing capability is currently only a small fraction of what is needed: detailed biological simulations are limited to small numbers of macro-molecules; additional factors of millions are needed to simulate cells and far more than that for larger structures. The overall goal of this work is to give the Scientific Computing user community the capability to conduct transformative research via scalable, cost-effective, high-performance, general-purpose systems built from off-the-shelf components. The particular objective is to build a compute cluster and related infrastructure that facilitates research that advances such computer systems. The unifying technical mechanism to be explored is the integration of communication and computation in accelerator-centric clusters with direct and programmable interconnects.Three fundamental issues limiting performance are computational efficiency, power density, and communication latency. All of these issues are being addressed through increased heterogeneity, but the last in particular by integrating communication into the accelerator. This integration enables direct and programmable communication among compute components. Direct links enable the bypassing of CPU, network interface, and even device memory. Programmable communication enables data transfers to proceed with high efficiency even under substantial loads. The proposed infrastructure is a large-scale FPGA-centric cluster with direct and programmable communication (DPC). This server class is referred to as Novo-G#, where # is a place holder for DPC, because this award will target enhancing and leveraging Novo-G, the reconfigurable supercomputer at the University of Florida. The infrastructure will consist of the physical hardware, but also software and configurations to be developed to enhance both general usability and the enabled research projects. Another aspect of this infrastructure, as with the Novo-G, is the community of collaborators who will contribute tools, applications, evaluation, and feedback. Currently, a number of internal and external collaborators have been identified but there are more potential research projects?in diverse areas of applications, architecture, and systems that will be enabled by the proposed infrastructure.The broader impact of the enabled research is to advance the capability of scientific computing. The technical broader impact of the proposed infrastructure is to provide a system testbed for transformative research in a variety of areas in Computer Science and Engineering including programmable network components, processor/network interfaces especially for accelerators, FPGA-based systems, applications in Reconfigurable Computing, architecture of clusters with direct and programmable communication, and libraries and tools to support such clusters. The community of researchers using the infrastructure will consist of the PIs and their collaborators, but also the members of the broader community who commit to contributing to the infrastructure. The infrastructure will provide a platform to develop novel components for education and outreach.