IEEE Transactions on Parallel and Distributed Systems · 2018 · 12 citations · 26 references
ComputingComputer ScienceHigh-performance ComputingOptimizationParallel AlgorithmsParallel ComputingAlgorithm AnalysisData ParallelismGraphics Processing Unit ArchitectureGraphics Processing Unit ComputingGraphics Processing UnitsParallel Computing SystemsData Parallel ExecutionEfficiencyGpu ArchitectureGpu Parallel AlgorithmsParallel EfficiencyScientific Computing On GpusThread Block SchedulingThread Parallelism
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.
26
Martin Gardner · Scientific American · 1970 · 1.6K citations
Scalable parallel programming with CUDA
John Nickolls, Ian Buck, Michael Garland et al. · 2008 · 1.6K citations