In this paper we present a heavily exploration oriented implementation of genetic algorithms to be executed on graphic processor units (GPUs) that is optimized with our novel mechanism for scheduling GPU-side synchronized jobs that takes inspiration from the concept of persistent threads. Persistent Threads allow an efficient distribution of work loads throughout the GPU so to fully exploit the CUDA (NVIDIA's proprietary Compute Unified Device Architecture) architecture. Our approach (named Scheduled Light Kernel, SLK) uses a specifically designed data structure for issuing sequences of commands from the CPU to the GPU able to minimize CPUGPU communications, exploit streams of concurrent execution of different device side functions within different Streaming Multiprocessors and minimize kernels launch overhead. Results obtained on two completely different experimental settings show that our approach is able to dramatically increase the performance of the tested genetic algorithms compared to the baseline implementation that (while still running on a GPU) does not exploit our proposed approach. Our proposed SLK approach does not require substantial code rewriting and is also compared to newly introduced features in the last CUDA development toolkit, such as nested kernel invocations for dynamic parallelism.

Efficient Implementation of Genetic Algorithms on GP-GPU with Scheduled Persistent CUDA Threads / Capodieci, Nicola; Burgio, Paolo. - (2015), pp. 6-12. ((Intervento presentato al convegno Seventh International Symposium on Parallel Architectures, Algorithms and Programming (PAAP), 2015 tenutosi a Nanjing (China) nel 12-14 Dicembre 2015 [10.1109/PAAP.2015.13].

Efficient Implementation of Genetic Algorithms on GP-GPU with Scheduled Persistent CUDA Threads

CAPODIECI, NICOLA;BURGIO, PAOLO
2015

Abstract

In this paper we present a heavily exploration oriented implementation of genetic algorithms to be executed on graphic processor units (GPUs) that is optimized with our novel mechanism for scheduling GPU-side synchronized jobs that takes inspiration from the concept of persistent threads. Persistent Threads allow an efficient distribution of work loads throughout the GPU so to fully exploit the CUDA (NVIDIA's proprietary Compute Unified Device Architecture) architecture. Our approach (named Scheduled Light Kernel, SLK) uses a specifically designed data structure for issuing sequences of commands from the CPU to the GPU able to minimize CPUGPU communications, exploit streams of concurrent execution of different device side functions within different Streaming Multiprocessors and minimize kernels launch overhead. Results obtained on two completely different experimental settings show that our approach is able to dramatically increase the performance of the tested genetic algorithms compared to the baseline implementation that (while still running on a GPU) does not exploit our proposed approach. Our proposed SLK approach does not require substantial code rewriting and is also compared to newly introduced features in the last CUDA development toolkit, such as nested kernel invocations for dynamic parallelism.
2015
Seventh International Symposium on Parallel Architectures, Algorithms and Programming (PAAP), 2015
Nanjing (China)
12-14 Dicembre 2015
6
12
Capodieci, Nicola; Burgio, Paolo
Efficient Implementation of Genetic Algorithms on GP-GPU with Scheduled Persistent CUDA Threads / Capodieci, Nicola; Burgio, Paolo. - (2015), pp. 6-12. ((Intervento presentato al convegno Seventh International Symposium on Parallel Architectures, Algorithms and Programming (PAAP), 2015 tenutosi a Nanjing (China) nel 12-14 Dicembre 2015 [10.1109/PAAP.2015.13].
File in questo prodotto:
File Dimensione Formato  
File.pdf

non disponibili

Descrizione: Articolo da IEEExplore
Tipologia: Versione dell'editore (versione pubblicata)
Dimensione 243.49 kB
Formato Adobe PDF
243.49 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

Licenza Creative Commons
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11380/1129949
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 10
  • ???jsp.display-item.citation.isi??? 10
social impact