TY - GEN
T1 - Search space generation and pruning system for autotuners
AU - Luszczek, Piotr
AU - Gates, Mark
AU - Kurzak, Jakub
AU - Danalis, Anthony
AU - Dongarra, Jack
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2016/7/18
Y1 - 2016/7/18
N2 - This work tackles two simultaneous challenges faced by autotuners: the ease ofdescribing a complex, multidimensional search space, and the speed ofevaluating that space, while applying a multitude of pruning constraints. Thisarticle presents a declarative notation for describing a search space and atranslation system for conversion to a standard C code for fast andmultithreaded, as necessary, evaluation. The notation is Python-based and thussimple in syntax and easy to assimilate by the user interested in tuningrather than learning a new programming language. A large number of dimensionsand a large number of pruning constraints may be expressed with littleeffort. The system is discussed in the context of autotuning the canonicalmatrix multiplication kernel for NVIDIA GPUs, where the search space has 15dimensions and involves application of 10 complex pruning constrains. Thespeed of evaluation is compared against generators created using imperativeprogramming style in various scripting and compiled languages.
AB - This work tackles two simultaneous challenges faced by autotuners: the ease ofdescribing a complex, multidimensional search space, and the speed ofevaluating that space, while applying a multitude of pruning constraints. Thisarticle presents a declarative notation for describing a search space and atranslation system for conversion to a standard C code for fast andmultithreaded, as necessary, evaluation. The notation is Python-based and thussimple in syntax and easy to assimilate by the user interested in tuningrather than learning a new programming language. A large number of dimensionsand a large number of pruning constraints may be expressed with littleeffort. The system is discussed in the context of autotuning the canonicalmatrix multiplication kernel for NVIDIA GPUs, where the search space has 15dimensions and involves application of 10 complex pruning constrains. Thespeed of evaluation is compared against generators created using imperativeprogramming style in various scripting and compiled languages.
KW - Multidimensional search space enumeration
KW - Performance autotuning
UR - http://www.scopus.com/inward/record.url?scp=84991696529&partnerID=8YFLogxK
U2 - 10.1109/IPDPSW.2016.197
DO - 10.1109/IPDPSW.2016.197
M3 - Conference contribution
AN - SCOPUS:84991696529
T3 - Proceedings - 2016 IEEE 30th International Parallel and Distributed Processing Symposium, IPDPS 2016
SP - 1545
EP - 1554
BT - Proceedings - 2016 IEEE 30th International Parallel and Distributed Processing Symposium, IPDPS 2016
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 30th IEEE International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2016
Y2 - 23 May 2016 through 27 May 2016
ER -