SBIR Phase I: High Performance Low Power Dense Server for Cloud

这个小企业创新研究（SBIR）第一阶段项目的更广泛的影响/商业潜力是加速处理大数据的最常见计算，并对流入企业数据中心的数据流执行实时分析。对于相同的总成本，拟议项目所采用的先进技术预计将使性能提高12倍。作为改进的一部分，它有望将每条指令的能量减少25倍或更多。这使得企业可以应用更高级的分析技术，并对不断变化的业务条件做出更快的反应。这个小企业创新研究（SBIR）第一阶段项目解决了在固定预算下处理更多数据的日益增长的需求。目标是为一组日益重要的应用程序提供加速器技术，这些应用程序目前还没有得到通用CPU技术的充分支持。该项目的最终目标是提供一种基于新型加速器微架构的硅芯片填充的PCIe加速卡。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 Small Business Innovation Research (SBIR) Phase I project is to accelerate the most common computations in processing Big Data and performing real-time analyses on data streaming-in to enterprise data centers. For the same total cost, the technology advanced by the proposed project is expected to increase performance by a factor of 12. As part of this improvement, it is expected to reduce the energy per instruction by a factor of 25 times or greater. This frees businesses to apply more advanced analytics techniques and react more quickly to changing business conditions.This Small Business Innovation Research (SBIR) Phase I project addresses the ever-growing need to process more data, but on a fixed budget. The objective is to provide accelerator technology for an increasingly critical set of applications that are currently underserved by generic CPU technology. The project aims eventually to deliver a PCIe accelerator card populated by silicon chips based on a new type of accelerator micro-architecture.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.