Characterizing Power and Performance of GPU Memory Access
Characterizing Power and Performance of GPU Memory Access
复制标题
表征 GPU 内存访问的功率和性能
DOI：
--
复制
发表时间：
2016
期刊：
影响因子：
--
通讯作者：
Rong Ge
中科院分区：
文献类型：
--
作者：
Tyler N. Allen;Rong Ge
功率是HPC未来和在功率预算下实现百亿亿次计算的主要限制因素。GPU现已成为HPC中的主流并行计算设备，优化GPU上的功耗对于实现未来目标至关重要。GPU内存很少被研究，特别是功耗。然而，内存访问消耗大量的功率，并且对于理解和优化GPU功率使用至关重要。在这项工作中，我们研究了各种GPU内存访问的功率和性能特性。我们采取实证的方法和实验研究和评估GPU的功率和性能如何随数据访问模式和软件参数（包括GPU线程块大小）而变化。此外，我们还考虑了GPU处理单元和全局内存上的先进节能技术动态电压和频率缩放（DVFS）。我们分析了功率和性能，并为大量使用特定内存操作的应用程序的最佳参数提供了一些建议。
Power is a major limiting factor for the future of HPC and the realization of exascale computing under a power budget. GPUs have now become a mainstream parallel computation device in HPC, and optimizing power usage on GPUs is critical to achieving future goals. GPU memory is seldom studied, especially for power usage. Nevertheless, memory accesses draw significant power and are critical to understanding and optimizing GPU power usage. In this work we investigate the power and performance characteristics of various GPU memory accesses. We take an empirical approach and experimentally examine and evaluate how GPU power and performance vary with data access patterns and software parameters including GPU thread block size. In addition, we take into account the advanced power saving technology dynamic voltage and frequency scaling (DVFS) on GPU processing units and global memory. We analyze power and performance and provide some suggestions for the optimal parameters for applications that heavily use specific memory operations.