Cargando…
Number Formats, Error Mitigation, and Scope for 16‐Bit Arithmetics in Weather and Climate Modeling Analyzed With a Shallow Water Model
The need for high‐precision calculations with 64‐bit or 32‐bit floating‐point arithmetic for weather and climate models is questioned. Lower‐precision numbers can accelerate simulations and are increasingly supported by modern computing hardware. This paper investigates the potential of 16‐bit arith...
Autores principales: | Klöwer, M., Düben, P. D., Palmer, T. N. |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
John Wiley and Sons Inc.
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7685161/ https://www.ncbi.nlm.nih.gov/pubmed/33282116 http://dx.doi.org/10.1029/2020MS002246 |
Ejemplares similares
-
Fluid Simulations Accelerated With 16 Bits: Approaching 4x Speedup on A64FX by Squeezing ShallowWaters.jl Into Float16
por: Klöwer, Milan, et al.
Publicado: (2022) -
Qubit readout error mitigation with bit-flip averaging
por: Smith, Alistair W. R., et al.
Publicado: (2021) -
Assessing the scales in numerical weather and climate predictions: will exascale be the rescue?
por: Neumann, Philipp, et al.
Publicado: (2019) -
Mind the Gap: Bit-vector Interpolation recast over Linear Integer Arithmetic
por: Okudono, Takamasa, et al.
Publicado: (2020) -
Error coding for arithmetic processors
por: Rao, Thammavarapu R N
Publicado: (1974)