NumaPerf: predictive NUMA profiling
NumaPerf: predictive NUMA profiling
复制标题
NumaPerf:预测 NUMA 分析
DOI:
10.1145/3447818.3460361
复制
发表时间:
2021
期刊:
影响因子:
--
通讯作者:
Liu, Tongping
中科院分区:
文献类型:
--
作者:
Zhao, Xin;Zhou, Jin;Guan, Hui;Wang, Wei;Liu, Xu;Liu, Tongping
It is extremely challenging to achieve optimal performance of parallel applications on a NUMA architecture, which necessitates the assistance of profiling tools. However, existing NUMA-profiling tools share some similar shortcomings, such as portability, effectiveness, and helpfulness issues. This paper proposes a novel profiling tool–NumaPerf–that overcomes these issues. NumaPerf aims to identify potential performance issues for any NUMA architecture, instead of only on the current hardware. To achieve this, NumaPerf focuses on memory sharing patterns between threads, instead of real remote accesses. NumaPerf further detects potential thread migrations and load imbalance issues that could significantly affect the performance but are omitted by existing profilers. NumaPerf also identifies cache coherence issues separately that may require different fix strategies. Based on our extensive evaluation, NumaPerf can identify more performance issues than any existing tool, while fixing them leads to significant performance speedup.
登录
查看更多内容
DOI:
--
发表时间:
2018
期刊:
ACM SIGPLAN Symposium on Principles & Practice of Parallel Programming
影响因子:
--
作者:
Milind Chabbi;Shasha Wen;Xu Liu
通讯作者:
Xu Liu
DOI:
--
发表时间:
2019
期刊:
Information Security Conference
影响因子:
--
作者:
Christian Helm;K. Taura
通讯作者:
K. Taura
DOI:
10.1007/978-3-030-10549-5_13
发表时间:
2018
期刊:
Proceedings of the 2018 International Conference on Supercomputing
影响因子:
--
作者:
S. Valat;O. Bouizi
通讯作者:
O. Bouizi
DOI:
10.1145/3225058.3225094
发表时间:
2018
期刊:
Proceedings of the 47th International Conference on Parallel Processing
影响因子:
--
作者:
François Trahay;Manuel Selva;L. Morel;K. Marquet
通讯作者:
K. Marquet
DOI:
10.1145/2500468.2500477
发表时间:
2013
期刊:
Commun. ACM
影响因子:
--
作者:
Christoph Lameter
通讯作者:
Christoph Lameter