Production-quality parallel applications are often a mixture of diverse operations, such as computation- and communication-intensive, regular and irregular, tightly coupled and loosely linked operations. In conventional construction of parallel applications, each process performs all the operations, which might result inefficient and seriously limit scalability, especially at large scale. We propose a decoupling strategy to improve the scalability of applications running on large-scale systems.
Our strategy separates application operations onto groups of processes and enables a dataflow processing paradigm among the groups. This mechanism is effective in reducing the impact of load imbalance and increases the parallel efficiency by pipelining multiple operations. We provide a proof-of-concept implementation using MPI, the de-facto programming system on current supercomputers. We demonstrate the effectiveness of this strategy by decoupling the reduce, particle communication, halo exchange and I/O operations in a set of scientific and data-analytics applications. A performance evaluation on 8,192 processes of a Cray XC40 supercomputer shows that the proposed approach can achieve up to 4x performance improvement.
Harvesting energy consumption on European HPC systems: Sharing Experience from the CEEC project
Friedrich-Alexander-University(弗里德里希·阿列克桑德大学);University of Stuttgart(斯图加特大学);Aristotle University of Thessaloniki(塞萨洛尼基亚里士多德大学);Uppsala University(乌普萨拉大学)
RISC-V for HPC: Where we are and where we need to go
在英国ExCALIBUR H&ES exascale计划的资助下,自2022年初以来,我们为HPC提供了一个RISC-V测试平台,为科学软件开发人员提供免费访问权限,让他们在工作负载中尝试RISC-V。基于我们为HPC社区提供RISC-V访问的经验,以及我们与RISC-V社区的广泛参与,在此扩展摘要中,我们总结了RISC-V for HPC的当前状态,并考虑了应解决的高优先级领域,以帮助推动采用。
SAGE: Percipient Storage for Exascale Data Centric Computing
我们的目标是实现一个大数据/极端计算(BDEC)能力的系统基础设施,因为我们走向时代的Exascale计算-称为SAGE(Percipient StorAGe for Exascale Data Centric Computing)。SAGE系统将能够在Exascale范围内存储和处理大量数据,并为Exascale级应用程序提供使用这种存储基础设施的能力。SAGE解决了在下一代以数据为中心的计算时代,大数据分析和HPC之间越来越多的重叠,由于大量数据源的激增,例如大型分散的科学仪器和传感器,其数据需要处理,分析和集成到模拟中,以获得科学和创新的见解。事实上,Exascale I/O作为模拟代码尚未充分处理的问题,已由SAGE平台适当解决。本文的目的是讨论的软件架构的SAGE系统,并期待在早期的结果,我们已经获得了一些关键的方法,系统的不断发展。
Optimization of hybrid parallel application execution in heterogeneous high performance computing systems considering execution time and power consumption