首页|Analysis and Reproducibility of “Productivity, Portability, Performance: Data-Centric Python”
Analysis and Reproducibility of “Productivity, Portability, Performance: Data-Centric Python”
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
IEEE
This report analyses the reproducibility of the results obtained in the NPBench (Ziogas et al. 2021) paper. We begin by providing the reader with some background information and a demonstration on the simplicity of DaCe. We then reproduce a subset of the results presented in the original paper, specifically: the comparison of DaCe on CPU and GPU over NumPy and its parallel efficiency in a distributed environment. For most benchmarks we show that we can obtain similar results on our machine. Despite that, for some benchmarks we cannot conclude the same without reasonable doubt. The experimental runs were performed during the SC22 Student Cluster Competition in Dallas, TX.
CodesPythonBenchmark testingGraphics processing unitsOptimizationReproducibility of resultsProductivity
Christopher Lompa、Piotr Luczynski
展开 >
Department of Mathematics, ETH Zurich Switzerland, Zürich, Switzerland
Department of Computer Science, ETH Zurich Switzerland, Zürich, Switzerland
NETL
NSTL
IEEE
