PolyJIT: Polyhedral Optimization Just in Time
PolyJIT: Polyhedral Optimization Just in Time
复制标题
PolyJIT:及时多面优化
DOI:
10.1007/s10766-018-0597-3
复制
发表时间:
2019
影响因子:
1.5
通讯作者:
Christian Lengauer
中科院分区:
文献类型:
--
作者:
Andreas Simburger;Sven Apel;Armin Größlinger;Christian Lengauer
While polyhedral optimization appeared in mainstream compilers during the past decade, its profitability in scenarios outside its classic domain of linear-algebra programs has remained in question. Recent implementations, such as the LLVM pluginPolly, produce promising speedups, but the restriction to affine loop programs with control flow known at compile time continues to be a limiting factor.PolyJITcombines polyhedral optimization with multi-versioning at run time, at which one has access to knowledge enabling polyhedral optimization, which is not available at compile time. By means of a fully-fledged implementation of a light-weight just-in-time compiler and a series of experiments on a selection of real-world and benchmark programs, we demonstrate that the consideration of run-time knowledge helps in tackling compile-time violations of affinity and, consequently, offers new opportunities of optimization at run time.
登录
查看更多内容
DOI:
--
发表时间:
2010
期刊:
--
影响因子:
--
作者:
Armin Größlinger
通讯作者:
Armin Größlinger
DOI:
--
发表时间:
2016
期刊:
影响因子:
--
作者:
A. Ljilja;N. Radović;J. Tekavec
通讯作者:
J. Tekavec
DOI:
--
发表时间:
2011
期刊:
Encyclopedia of Parallel Computing
影响因子:
--
作者:
U. Banerjee
通讯作者:
U. Banerjee
影响因子:
2.1
作者:
Stone JE;Gohara D;Shi G
通讯作者:
Shi G
DOI:
10.1145/2751205.2751248
发表时间:
2015
期刊:
Proceedings of the 29th ACM on International Conference on Supercomputing
影响因子:
--
作者:
T. Grosser;J. Ramanujam;L. Pouchet;P. Sadayappan;Sebastian Pop
通讯作者:
Sebastian Pop