Premium
A customized precision format based on mantissa segmentation for accelerating sparse linear algebra
Author(s) -
Grützmacher Thomas,
Cojean Terry,
Flegar Goran,
Göbel Fritz,
Anzt Hartwig
Publication year - 2020
Publication title -
concurrency and computation: practice and experience
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.309
H-Index - 67
eISSN - 1532-0634
pISSN - 1532-0626
DOI - 10.1002/cpe.5418
Subject(s) - computer science , single precision floating point format , floating point , memory footprint , double precision floating point format , parallel computing , decoupling (probability) , computer hardware , algorithm , computer engineering , programming language , control engineering , engineering
Summary In this work, we pursue the idea of radically decoupling the floating point format used for arithmetic operations from the format used to store the data in memory. We complement this idea with a customized precision memory format derived by splitting the mantissa (significand) of standard IEEE formats into segments, such that values can be accessed faster if lower accuracy is acceptable. Combined with precision‐aware algorithms that dynamically adapt the data access accuracy to the numerical requirements, the customized precision memory format can render attractive runtime savings without impacting the memory footprint of the data or the accuracy of the final result. In an experimental analysis using the adaptive precision Jacobi method on diagonalizable test problems, we assess the benefits of the mantissa‐segmenting customized precision format on recent multi‐ and manycore architectures.