Skip to Main content Skip to Navigation
Conference papers

Dynamic Configuration of CUDA Runtime Variables for CDP-based Divide-and-Conquer Algorithms

Abstract : CUDA Dynamic Parallelism (CDP) is an extension of the GPGPU programming model proposed to better address irregular applications and recursive patterns of computation. However, processing memory demanding problems by using CDP is not straightforward, because of its particular memory organization. This work presents an algorithm to deal with such an issue. It dynamically calculates and configures the CDP runtime variables and the GPU heap on the basis of an analysis of the partial backtracking tree. The proposed algorithm was implemented for solving permutation combinatorial problems and experimented on two test-cases: N-Queens and the Asymmetric Travelling Salesman Problem. The proposed algorithm allows different CDP-based backtracking from the literature to solve memory demanding problems, adaptively with respect to the number of recursive kernel generations and the presence of dynamic allocations on GPU.
Complete list of metadata

Cited literature [17 references]  Display  Hide  Download
Contributor : Tiago Carneiro Pessoa <>
Submitted on : Monday, November 12, 2018 - 3:16:34 PM
Last modification on : Friday, December 11, 2020 - 6:44:07 PM
Long-term archiving on: : Wednesday, February 13, 2019 - 2:48:32 PM


Files produced by the author(s)


  • HAL Id : hal-01919532, version 1



Tiago Carneiro, Jan Gmys, Nouredine Melab, Francisco Heron de Carvalho Junior, Pedro Pedrosa Rebouças Filho, et al.. Dynamic Configuration of CUDA Runtime Variables for CDP-based Divide-and-Conquer Algorithms. VECPAR 2018 - 13th International Meeting on High Performance Computing for Computational Science, Sep 2018, São Pedro, Brazil. ⟨hal-01919532⟩



Record views


Files downloads