Idioma:

Sorting Large Multifield Records on a GPU

Bandyopadhyay, S. ; Sahni, S.

2011 IEEE 17th International Conference on Parallel and Distributed Systems, 2011, p.149-156

Texto completo disponível

Citações Citado por

Título:
Sorting Large Multifield Records on a GPU
Autor: Bandyopadhyay, S. ; Sahni, S.
Assuntos: Arrays ; Graphics processing unit ; Graphics Processing Units ; Histograms ; Instruction sets ; Layout ; radix sort ; sample sort ; Sorting ; sorting multifield records ; Tiles
É parte de: 2011 IEEE 17th International Conference on Parallel and Distributed Systems, 2011, p.149-156
Descrição: We extend the fastest comparison based (sample sort) and non-comparison based (radix sort) number sorting algorithms on a GPU to sort large multifield records. Two extensions - direct (the entire record is moved whenever its key is to be moved) and indirect ((key, index) pairs are sorted using the direct extension and then records are ordered according to the obtained index permutation) are discussed. Our results show that for the By Field layout, the direct extension of the radix sort algorithm GRS[1] is the fastest for 32-bit keys when records have at least 12 fields, otherwise, the direct extension of the radix sort algorithm SRTS[14] is the fastest. For the Hybrid layout, the indirect extension of SRTS is the fastest for records with 2 or more keys.
Editor: IEEE
Idioma: Inglês

Links

Voltar para lista de resultados

Anterior Resultado 18 Avançar Ir para próxima página