Title
Parallel Reproducible Summation
Abstract
Reproducibility, i.e. getting bitwise identical floating point results from multiple runs of the same program, is a property that many users depend on either for debugging or correctness checking in many codes [10]. However, the combination of dynamic scheduling of parallel computing resources, and floating point nonassociativity, makes attaining reproducibility a challenge even for simple reducti...
Year
DOI
Venue
2015
10.1109/TC.2014.2345391
IEEE Transactions on Computers
Keywords
Field
DocType
Vectors,Program processors,Accuracy,Standards,Algorithm design and analysis,Numerical analysis,Computational modeling
Pairwise summation,Computer science,Round-off error,Massively parallel,Floating point,Double-precision floating-point format,Parallel computing,Kahan summation algorithm,Algorithm,Rounding,Minifloat
Journal
Volume
Issue
ISSN
64
7
0018-9340
Citations 
PageRank 
References 
12
0.78
0
Authors
2
Name
Order
Citations
PageRank
James Demmel14817551.47
Hong Diep Nguyen21388.93