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 2302.11467cs.DCcs.LGcs.PF
收藏

基于图神经网络的功率约束自整定

Power Constrained Autotuning using Graph Neural Networks

Iowa State University(爱荷华州立大学);University of Oregon(俄勒冈大学)

Akash Dutta, Jee Choi, Ali Jannesari

摘要:

多核和众核处理器的最新进展已经导致科学计算应用的性能的显著改善。然而,大量复杂内核的加入也增加了整体功耗,功耗已经成为现代处理器中的一阶设计约束。虽然我们可以通过简单地应用基于软件的功耗约束来限制功耗,但盲目地应用它们将导致严重的性能下降。为了解决在现代多核处理器上提高科学应用的性能、功耗和能源效率的挑战,我们提出了一种新的基于图神经网络的自动调整方法,该方法(i)在预定义的功耗约束下优化运行时性能,(ii)通过最小化能量延迟乘积同时优化运行时性能和能源效率。这种方法背后的关键思想在于将并行代码区域建模为流感知代码图,以捕获语义和结构化代码特征。我们证明了我们的方法的有效性进行了广泛的评估$30$基准和代理/迷你应用程序与$68$ OpenMP代码区域。我们的方法确定了在不同的功率约束,产生几何平均性能提高超过$25\%$和$13\%$在32核Skylake和$16$核Haswell处理器上的默认OpenMP配置。此外,当我们针对能量延迟乘积进行优化时,对于相同的Skylake和Haswell处理器,我们的自动调谐器所选择的OpenMP配置分别在Thermal Design Power下与默认的OpenMP配置相比,表现出$21\%$和$11\%$的性能提高以及$29\%$和$18\%$的能量降低。

英文摘要:

Recent advances in multi and many-core processors have led to significant improvements in the performance of scientific computing applications. However, the addition of a large number of complex cores have also increased the overall power consumption, and power has become a first-order design constraint in modern processors. While we can limit power consumption by simply applying software-based power constraints, applying them blindly will lead to non-trivial performance degradation. To address the challenge of improving the performance, power, and energy efficiency of scientific applications on modern multi-core processors, we propose a novel Graph Neural Network based auto-tuning approach that (i) optimizes runtime performance at pre-defined power constraints, and (ii) simultaneously optimizes for runtime performance and energy efficiency by minimizing the energy-delay product. The key idea behind this approach lies in modeling parallel code regions as flow-aware code graphs to capture both semantic and structural code features. We demonstrate the efficacy of our approach by conducting an extensive evaluation on $30$ benchmarks and proxy-/mini-applications with $68$ OpenMP code regions. Our approach identifies OpenMP configurations at different power constraints that yield a geometric mean performance improvement of more than $25\%$ and $13\%$ over the default OpenMP configuration on a 32-core Skylake and a $16$-core Haswell processor respectively. In addition, when we optimize for the energy-delay product, the OpenMP configurations selected by our auto-tuner demonstrate both performance improvement of $21\%$ and $11\%$ and energy reduction of $29\%$ and $18\%$ over the default OpenMP configuration at Thermal Design Power for the same Skylake and Haswell processors, respectively.

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。

↑