DMCA
On-the-Fly Elimination of Dynamic Irregularities for GPU Computing
| Citations: | 42 - 9 self |
BibTeX
@MISC{Zhang_on-the-flyelimination,
author = {Eddy Z. Zhang and Yunlian Jiang and Ziyu Guo and Kai Tian and Xipeng Shen},
title = {On-the-Fly Elimination of Dynamic Irregularities for GPU Computing},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
The power-efficient massively parallel Graphics Processing Units (GPUs) have become increasingly influential for scientific computing over the past few years. However, their efficiency is sensitive to dynamic irregular memory references and control flows in an application. Experiments have shown great performance gains when these irregularities are removed. But it remains an open question how to achieve those gains through software approaches on real GPUs. In this paper, we present a systematic exploration to tackle dynamic irregularities in both control flows and memory references. We report findings on their inherent properties, including interactions among different types of irregularities, their relations with program data and threads, the computational complexities in removing them, and heuristics-based algorithms for their removal through data reordering, job swapping, and hybrid transformations. Based on these findings, we develop a framework, named G-Streamline, as a unified software solution to dynamic irregularities in GPU computing. G-Streamline has several distinctive properties. It is a pure software solution and works on the fly, requiring no hardware extensions or offline profiling. It treats both types of irregularities at the same time in a holistic fashion, maximizing the whole-program performance by resolving conflicts among optimizations. Its optimization overhead is largely transparent to GPU kernel executions, jeopardizing no basic efficiency of the GPU application. Finally, it is robust to the presence of various complexities in GPU applications. Our experiments results demonstrate that G-Streamline is effective in reducing both types of dynamic irregularities and is capable of producing significant performance improvements for a variety of applications.
Keyphrases
dynamic irregularity on-the-fly elimination gpu computing gpu application hybrid transformation various complexity job swapping scientific computing open question offline profiling unified software solution parallel graphic memory reference several distinctive property systematic exploration past year great performance gain data reordering whole-program performance inherent property real gpus hardware extension experiment result heuristics-based algorithm gpu kernel execution program data holistic fashion software approach computational complexity irregular memory reference different type optimization overhead basic efficiency pure software solution significant performance improvement
