arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.28645cs.AR
收藏

紧密耦合处理器数组(TCPAs)中的循环控制管理

Loop Control Management in Tightly Coupled Processor Arrays (TCPAs)

Friedrich-Alexander-Universität Erlangen-Nürnberg(埃尔朗根-纽伦堡弗里德里希·亚历山大大学)

Dominik Walter, Frank Hannig, Jürgen Teich

AI总结:

本文提出通过多维循环内核的多面体表示减少循环控制信号,实现15至45倍的控制信号缩减,采用轻量级全局控制器架构,实现零开销的循环控制。

摘要:

多维循环内核常因控制开销主导并行循环加速器的执行时间。紧密耦合处理器数组(TCPAs)将循环控制卸载到全局控制器(GC),但现有方法仍需数百个控制信号。我们提出一种方法,从迭代空间的多面体表示中推导并激进减少这些控制条件,从而在多个基准测试中实现15至45倍的控制信号缩减。我们引入了一种轻量级GC架构,利用有界评估单元将条件评估为多面体的并集,所需硬件仅相当于单个处理元件。控制信号在整个数组中分布,仅需少量延迟元件,从而实现零开销的循环控制。我们在PolyBench内核上的评估显示,整个控制流所需的总数组资源不到10%。

英文摘要:

Multidimensional loop kernels often suffer from control overhead that can dominate execution time on parallel loop accelerators. Tightly Coupled Processor Arrays (TCPAs) offload loop control to a global controller (GC), but existing approaches still require hundreds of control signals. We propose a method to derive and aggressively reduce these control conditions from a polyhedral representation of the iteration space, achieving reductions of 15x to 45x in control signals across several benchmarks. We introduce a lightweight GC architecture that evaluates conditions as unions of polyhedra using bounded evaluation units, requiring hardware comparable to a single processing element. Control signals are distributed throughout the array with a minimal number of delay elements resulting in zero-overhead loop control. Our evaluation on PolyBench kernels shows that the entire control flow requires < 10 % of the total array resources.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑