Acceleration of PageRank with Customized Precision Based on Mantissa Segmentation
Impact
Scholar |
Other documents of the author: Grützmacher, Thomas; Cojean, Terry; Flegar, Goran; Anzt, Hartwig; Quintana-Orti, Enrique S.
Metadata
Show full item recordcomunitat-uji-handle:10234/9
comunitat-uji-handle2:10234/7036
comunitat-uji-handle3:10234/8620
comunitat-uji-handle4:
INVESTIGACIONThis resource is restricted
https://doi.org/10.1145/3380934 |
Metadata
Title
Acceleration of PageRank with Customized Precision Based on Mantissa SegmentationAuthor (s)
Date
2020-03Publisher
Association for Computing Machinery (ACM)ISSN
2329-4949; 2329-4957Bibliographic citation
Thomas Grützmacher, Terry Cojean, Goran Flegar, Hartwig Anzt, and Enrique S. Quintana-Ortí. 2020. Acceleration of PageRank with Customized Precision Based on Mantissa Segmentation. ACM Trans. Parallel Comput. 7, 1, Article 4 (March 2020), 19 pages. https://doi.org/10.1145/3380934Type
info:eu-repo/semantics/articlePublisher version
https://dl.acm.org/doi/fullHtml/10.1145/3380934Version
info:eu-repo/semantics/publishedVersionSubject
Abstract
We describe the application of a communication-reduction technique for the PageRank algorithm that dynamically adapts the precision of the data access to the numerical requirements of the algorithm as the iteration ... [+]
We describe the application of a communication-reduction technique for the PageRank algorithm that dynamically adapts the precision of the data access to the numerical requirements of the algorithm as the iteration converges. Our variable-precision strategy, using a customized precision format based on mantissa segmentation (CPMS), abandons the IEEE 754 single- and double-precision number representation formats employed in the standard implementation of PageRank, and instead handles the data in memory using a customized floating-point format. The customized format enables fast data access in different accuracy, prevents overflow/ underflow by preserving the ieee 754 double-precision exponent, and efficiently avoids data duplication, since all bits of the original ieee 754 double-precision mantissa are preserved in memory, but re-organized for efficient reduced precision access. With this approach, the truncated values (omitting significand bits), as well as the original ieee double-precision values, can be retrieved without duplicating the data in different formats.
Our numerical experiments on an NVIDIA V100 GPU (Volta architecture) and a server equipped with two Intel Xeon Platinum 8168 CPUs (48 cores in total) expose that, compared with a standard ieee double-precision implementation, the CPMS-based PageRank completes about 10% faster if high-accuracy output is needed, and about 30% faster if reduced output accuracy is acceptable. [-]
Is part of
ACM Transactions on Parallel Computing, 2020, vol. 7, no 1Rights
Copyright © Association for Computing Machinery
http://rightsstatements.org/vocab/InC/1.0/
info:eu-repo/semantics/restrictedAccess
http://rightsstatements.org/vocab/InC/1.0/
info:eu-repo/semantics/restrictedAccess
This item appears in the folowing collection(s)
- ICC_Articles [424]