论文标题

迈向分布式异质系统的性能便携式编程

Towards Performance Portable Programming for Distributed Heterogeneous Systems

论文作者

Thomadakis, Polykarpos, Chrisochoides, Nikos

论文摘要

硬件异质性在这里保持高性能计算。大型系统目前每个计算节点都配备了多个GPU加速器,并有望在将来合并更专业的硬件。计算生态系统中的这种转变为提高性能提供了许多机会。但是,这也增加了此类架构的编程复杂性。这项工作引入了一个运行时框架,该框架可以为异构系统轻松编程,同时有效地利用硬件资源。该框架集成在分布式和可扩展的运行时系统中,以促进跨异构节点的性能便携性。除了设计外,本文还描述了执行的实现和优化,在共享内存基准和分布式设备通信中最多可提高300%。初步结果表明,我们的软件在隐藏硬件的特质时会在分布式的Jacobi代理应用程序中获得低开销,并在分布式的Jacobi代理应用程序中取得了40%的改善。

Hardware heterogeneity is here to stay for high-performance computing. Large-scale systems are currently equipped with multiple GPU accelerators per compute node and are expected to incorporate more specialized hardware in the future. This shift in the computing ecosystem offers many opportunities for performance improvement; however, it also increases the complexity of programming for such architectures. This work introduces a runtime framework that enables effortless programming for heterogeneous systems while efficiently utilizing hardware resources. The framework is integrated within a distributed and scalable runtime system to facilitate performance portability across heterogeneous nodes. Along with the design, this paper describes the implementation and optimizations performed, achieving up to 300% improvement in a shared memory benchmark and up to 10 times in distributed device communication. Preliminary results indicate that our software incurs low overhead and achieves 40% improvement in a distributed Jacobi proxy application while hiding the idiosyncrasies of the hardware.

扫码加入交流群

加入微信交流群

微信交流群二维码

扫码加入学术交流群,获取更多资源