Memory bandwidth is strongly correlated to the complexity of the memory access pattern of a running application. To improve memory performance of applications with irregular and/or unpredictable memory patterns, we need tools to analyze these patterns during application development. In this work, we present a software tool for the analysis and visualization of memory access patterns. We perform memory tracing and profiling, we do data processing and filtering, and we use visualization algorithms to produce three dimensional graphs that describe the patterns both in space and in time. Finally, we evaluate our toolflow on a variety of applications.
翻译:内存带宽与运行中的应用程序的内存存存存模式的复杂性密切相关。 为了改进非常规和(或)不可预测的内存模式应用程序的内存性能, 我们需要在应用开发过程中分析这些模式的工具。 在这项工作中, 我们为内存存存存存存存存存存模式的分析和可视化提供了一个软件工具。 我们进行内存追踪和剖析, 我们进行数据处理和过滤, 我们使用可视化算法来生成三个维图, 描述空间和时间的图案。 最后, 我们评估各种应用程序上的工具流 。