Competitiveness of a Non-Linear Block-Space GPU Thread Map for Simplex Domains

Cristóbal A. Navarro, Matthieu Vernier, Benjamín Bustos, Nancy Hitschfeld

IEEE Transactions on Parallel and Distributed Systems · 2018 · 12 citations · 26 references

Concepts

Abstract

This work presents and studies the efficiency problem of mapping GPU threads onto simplex domains. A non-linear map <inline-formula><tex-math notation="LaTeX">$\lambda (\omega)$</tex-math></inline-formula> is formulated based on a block-space enumeration principle that reduces the number of thread-blocks by a factor of approximately <inline-formula><tex-math notation="LaTeX">$2\times$</tex-math></inline-formula> and <inline-formula> <tex-math notation="LaTeX">$6\times$</tex-math></inline-formula> for 2-simplex and 3-simplex domains, respectively, when compared to the standard approach. Performance results show that <inline-formula><tex-math notation="LaTeX">$\lambda (\omega)$</tex-math> </inline-formula> is competitive and even the fastest map when ran in recent GPU architectures such as the Tesla V100, where it reaches up to <inline-formula><tex-math notation="LaTeX">$1.5\times$</tex-math></inline-formula> of speedup in 2-simplex tests. In 3-simplex tests, it reaches up to <inline-formula><tex-math notation="LaTeX">$2.3\times$</tex-math></inline-formula> of speedup for small workloads and up to <inline-formula><tex-math notation="LaTeX">$1.25\times$</tex-math></inline-formula> for larger ones. The results obtained make <inline-formula><tex-math notation="LaTeX">$\lambda (\omega)$</tex-math></inline-formula> a useful GPU optimization technique with applications on parallel problems that define all-pairs, all-triplets or nearest neighbors interactions in a 2-simplex or 3-simplex domain.

References

26