TY - GEN
T1 - FQL
T2 - 6th Annual Workshop on HPC User Support Tools, HUST 2019, International Workshop on Software Engineering for HPC-Enabled Research, SE-HER 2019, and 3rd Workshop on Interactive High-Performance Computing, WIHPC 2019, held in conjunction with the International Conference for High Performance Computing, Networking, Storage, and Analysis, SC 2019
AU - Zheng, Weijian
AU - Wang, Dali
AU - Song, Fengguang
N1 - Publisher Copyright:
© 2020, This is a U.S. government work and not under copyright protection in the U.S.; foreign copyright protection may apply.
PY - 2020
Y1 - 2020
N2 - The amount of large-scale scientific computing software is dramatically increasing. In this work, we designed a new query language, named Feature Query Language (FQL), to collect and extract HPC-related software features or metadata from a quick static code analysis. We also designed and implemented an FQL-based toolkit to automatically detect and present software features using an extensible query repository. A number of large-scale, high performance computing (HPC) scientific applications have been studied in the paper with the FQL toolkit to demonstrate the HPC-related feature extraction and information/metadata collection. Different from the existing static software analysis and refactoring tools which focus on software debug, development and code transformation, the FQL toolkit is simpler, significantly lightweight and strives to collect various and diverse software metadata with ease and rapidly.
AB - The amount of large-scale scientific computing software is dramatically increasing. In this work, we designed a new query language, named Feature Query Language (FQL), to collect and extract HPC-related software features or metadata from a quick static code analysis. We also designed and implemented an FQL-based toolkit to automatically detect and present software features using an extensible query repository. A number of large-scale, high performance computing (HPC) scientific applications have been studied in the paper with the FQL toolkit to demonstrate the HPC-related feature extraction and information/metadata collection. Different from the existing static software analysis and refactoring tools which focus on software debug, development and code transformation, the FQL toolkit is simpler, significantly lightweight and strives to collect various and diverse software metadata with ease and rapidly.
KW - Feature Query Language
KW - High-performance computing
KW - Static code analysis
UR - https://www.scopus.com/pages/publications/85082987498
U2 - 10.1007/978-3-030-44728-1_8
DO - 10.1007/978-3-030-44728-1_8
M3 - Conference contribution
AN - SCOPUS:85082987498
SN - 9783030447274
T3 - Communications in Computer and Information Science
SP - 129
EP - 142
BT - Tools and Techniques for High Performance Computing - Selected Workshops, HUST, SE-HER and WIHPC, held in Conjunction with SC 2019, Revised Selected Papers
A2 - Juckeland, Guido
A2 - Chandrasekaran, Sunita
PB - Springer
Y2 - 17 November 2019 through 18 November 2019
ER -