Keywords (tags) and Publication List
Shen, Xipeng; Liu, Yixun; Zhang, Eddy Z; Bhamidipati, Poornima An Infrastructure for Tackling Input-Sensitivity of GPU Program Optimizations Journal Article Int. J. Parallel Program., 41 (6), pp. 855–869, 2013, ISSN: 0885-7458. Abstract | Links | BibTeX | Tags: Cross-input adaptation, CUDA, Empirical search, G-ADAPT, GPU, Program optimizations
2013
title = {An Infrastructure for Tackling Input-Sensitivity of GPU Program Optimizations},
author = {Xipeng Shen and Yixun Liu and Eddy Z Zhang and Poornima Bhamidipati},
url = {https://doi.org/10.1007/s10766-012-0236-3},
doi = {10.1007/s10766-012-0236-3},
issn = {0885-7458},
year = {2013},
date = {2013-01-01},
journal = {Int. J. Parallel Program.},
volume = {41},
number = {6},
pages = {855–869},
publisher = {Kluwer Academic Publishers},
address = {USA},
abstract = {Graphic processing units (GPU) have become increasingly adopted for the enhancement of computing throughput. However, the development of a high-quality GPU application is challenging, due to the large optimization space and complex unpredictable effects of optimizations on GPU program performance. Many recent efforts have been employing empirical search-based auto-tuners to tackle the problem, but few of them have concentrated on the influence of program inputs on the optimizations. In this paper, based on a set of CUDA and OpenCL kernels, we report some evidences on the importance for auto-tuners to adapt to program input changes, and present a framework, G-ADAPT+, to address the influence by constructing cross-input predictive models for automatically predicting the (near-)optimal configurations for an arbitrary input to a GPU program. G-ADAPT+ is based on source-to-source compilers, specifically, Cetus and ROSE. It supports the optimizations of both CUDA and OpenCL programs.},
keywords = {Cross-input adaptation, CUDA, Empirical search, G-ADAPT, GPU, Program optimizations},
pubstate = {published},
tppubtype = {article}
}