Enabling FPGAs in new HPC heterogeneous systems through dataflow abstractions and enhanced flexibility

科学计算广泛地使用了hpc系统中大量的硬件资源。该领域不断增长的需求要求在可行的时间内寻找新的策略来处理越来越多的数据。其中一个策略是使用fpga，因为它们的可重构性使它们能够克服传统HPC硬件所面临的一些限制。然而，编程它们需要HPC软件开发人员不具备的特定知识，而且它们也非常死板，这阻碍了它们在HPC系统中的集成。我们的假设是，考虑到高性能计算工作负载的fpga的改进工具将导致该技术更好地适应超级计算。为了回答这个研究问题，我们同时关注性能和灵活性的问题。与传统编程语言相比，FPGA的结构更适合数据流方法。因此，我们正在探索向程序员公开的数据流层所提供的性能改进。同时，我们正在研究先进的重新配置技术如何帮助FPGA上的工作负载的动态管理，并允许克服其固有的刚性。

Scientific computing makes extensive use of the very large collections of hardware resources found inHPC systems. The ever growing demand of this domain requires the search of new strategies to deal withincreasing amounts of data in feasible time to solution. One of these strategies is the use of FPGAs, since theirreconfigurability allows them to overcome some of the limitations faced by the traditional HPC hardware. However, programming themrequires specific knowledge foreign to HPC software developers and they are also very rigid, which hinders their integration in HPCsystems.Our hypothesis is that improved tooling for FPGAs with HPC workloads in mind will result in the technology better suiting supercomputing.To answer this research question we focus both on the issues of performance and flexibility. The architecture of the FPGA maps better to adataflow approach than the traditional programming languages. Hence, we are exploring the performance improvements provided by a dataflow layerexposed to the programmer. At the same time, we are looking into how advanced reconfiguration techniques help dynamic management of the workloads on FPGA and allow to overcome their native rigidity.