STTR Phase II: Splintered Topologically Close-Packed (TCP) Offload Engine for Grid Computing and Bandwith-Delay Product (BWDP)

该小型企业技术转移(STTR)第二阶段研究项目解决了具有极端带宽延迟产品的网络的挑战。需要向国家研究实验室和航空航天公司使用的这种网络上的大宗数据传输提供必要的终端资源，以确保以具有成本效益的方式实现高性能。该项目的成果试图提供与Gridftp当前和未来版本的兼容性。该项目通过使用一种新型的卸载引擎来解决这些挑战。在第一阶段项目中，完成了对低成本、高性能现场可编程门阵列(FPGA)子系统的卸载引擎架构、固件和知识产权(IP)的推导和模拟的可行性。这项研究的成功结果将极大地推动网格计算中使用的卸载引擎的技术水平。即时的应用包括满足e-Science社区对可扩展的10-100 Gbps卸载引擎的需求，同时支持GridFTP的当前和未来版本。其他应用包括使用我们的超高速卸载引擎进行网格和集群计算，利用我们的开源固件。该项目产生的现场可编程门阵列代码有可能被用作知识产权，然后可以销售给卸载发动机制造商。这些IP核将为现有发动机公司节省成本效益，并将加快产品推向市场。

This Small Business Technology Transfer (STTR) Phase II research project addresses the challenges of networks with extreme bandwidth delay products. Bulk data transfer over such networks used by national research laboratories and aerospace companies need to be provided with the endpoint resources required to ensure high performance in a cost effective manner. The outcomes of this project attempts to provide compatibility with present and future versions of GridFTP. The project addresses these challenges through the use of a novel offload engine. During the Phase I project, the feasibility of deriving and simulating the offload engine architecture, firmware, and creation of intellectual property (IP) for low-cost, high-performance field programmable gate array (FPGA) subsystems was completed. Successful results from this research will significantly advance the state of the art for off-load engines used in grid computing. Immediate applications include accommodating the e-Science community's need for scalable 10-100 Gbps off-load engines, while supporting present and future versions of GridFTP. Other applications include the use of our ultra high-speed offload engines for grid and cluster computing, utilizing our open source firmware. The FPGA code resulting from this project has the potential to be used as intellectual property that could then be marketed to off-load engine manufacturers. These IP cores would accrue cost-effective savings for existing engine firms and would accelerate products to the market.