preprint · 2016
Parallel floating-point expansions for extended-precision GPU computations
Caroline Collange, Mioara Joldeş, Jean‐Michel Muller, Valentina Popescu
Cited by 2Abstract and details only
Abstract
GPUs are an important hardware development platform for problems where massive parallel computations are needed. Many of these problems require a higher precision than the standard double floating-point (FP) available. One common way of extending the precision is the multiple-component approach, in which real numbers are represented as the unevaluated sum of several standard machine precision FP numbers. This representation is called a FP expansion and it offers the simplicity of using directly available and highly optimized FP operations. In this article we present new data-parallel algorithms for adding and multiplying FP expansions specially designed for extended precision computations on GPUs. These are generalized algorithms that can manipulate FP expansions of different sizes (from double-double up to a few tens of doubles) and ensure a certain worst case error bound on the results.
Cite this paper
Collange, C., Joldeş, M., Muller, J., & Popescu, V. (2016). Parallel floating-point expansions for extended-precision GPU computations. https://doi.org/10.1109/asap.2016.7760783
Collange, Caroline, et al. “Parallel floating-point expansions for extended-precision GPU computations.” 2016, pp. 139–46, https://doi.org/10.1109/asap.2016.7760783.
Collange, Caroline, Mioara Joldeş, Jean‐Michel Muller, and Valentina Popescu. 2016. “Parallel floating-point expansions for extended-precision GPU computations.” https://doi.org/10.1109/asap.2016.7760783.
Collange, C. et al. (2016) ‘Parallel floating-point expansions for extended-precision GPU computations’. Available at: https://doi.org/10.1109/asap.2016.7760783.
@misc{collange2016parallel,
title = {{Parallel floating-point expansions for extended-precision GPU computations}},
author = {Collange, Caroline and Joldeş, Mioara and Muller, Jean‐Michel and Popescu, Valentina},
pages = {139--146},
year = {2016},
doi = {10.1109/asap.2016.7760783}
}Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.