arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2012.11473cs.ARcs.PF
收藏

PALMED:超标量体系结构的吞吐量表征--扩展版

PALMED: Throughput Characterization for Superscalar Architectures -- Extended Version

Nicolas Derumigny, Fabian Gruber, Théophile Bastian, Guillaume Iooss, Christophe Guillon, Louis-Noël Pouchet, Fabrice Rastello

摘要:

在超标量体系结构中,调度器动态地将微操作($μ$ OP)分配给执行端口。体系结构的端口映射描述了指令如何分解为$μ$ OP,并为每个$μ$ OP列出它可以映射到的端口集。编译器和性能调试工具使用它来表征作为循环的核心组件重复执行的指令序列的性能吞吐量。本文介绍了一种双重等价表示:一个架构的资源映射是一个抽象模型,在这个模型中,要执行一条指令,必须使用一组抽象资源,这些抽象资源本身代表执行端口的组合。对于给定的体系结构,找到端口映射是一个重要但困难的问题。构建资源映射是一个更容易处理的问题,并提供了一个更简单和等效的模型。本文介绍了Palmed,一个工具,自动建立一个资源映射的流水线,超标量,乱序CPU架构。Palmed不需要硬件性能计数器,仅依赖于运行时测量。我们通过从SPEC CPU 2017基准的编译二进制文件中提取一组代表性的基本块来评估我们的吞吐量建模的双重表示的相关性。我们将现有机器模型预测的吞吐量与Palmed预测的吞吐量进行了比较,发现其准确度与最先进的工具相当,在英特尔Skylake微架构上实现了低于10%的均方出错率。

英文摘要:

In a super-scalar architecture, the scheduler dynamically assigns micro-operations ($μ$OPs) to execution ports. The port mapping of an architecture describes how an instruction decomposes into $μ$OPs and lists for each $μ$OP the set of ports it can be mapped to. It is used by compilers and performance debugging tools to characterize the performance throughput of a sequence of instructions repeatedly executed as the core component of a loop. This paper introduces a dual equivalent representation: The resource mapping of an architecture is an abstract model where, to be executed, an instruction must use a set of abstract resources, themselves representing combinations of execution ports. For a given architecture, finding a port mapping is an important but difficult problem. Building a resource mapping is a more tractable problem and provides a simpler and equivalent model. This paper describes Palmed, a tool that automatically builds a resource mapping for pipelined, super-scalar, out-of-order CPU architectures. Palmed does not require hardware performance counters, and relies solely on runtime measurements. We evaluate the pertinence of our dual representation for throughput modeling by extracting a representative set of basic-blocks from the compiled binaries of the SPEC CPU 2017 benchmarks. We compared the throughput predicted by existing machine models to that produced by Palmed, and found comparable accuracy to state-of-the art tools, achieving sub-10 % mean square error rate on this workload on Intel's Skylake microarchitecture.

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。

↑