memCUDA: Map Device Memory to Host Memory on GPGPU Platform

Abstract : The Compute Unified Device Architecture (CUDA) programming environment from NVIDIA is a milestone towards making programming many-core GPUs more flexible to programmers. However, there are still many challenges for programmers when using CUDA. One is how to deal with GPU device memory, and data transfer between host memory and GPU device memory explicitly. In this study, source-to-source compiling and runtime library technologies are used to implement an experimental programming system based on CUDA, called memCUDA, which can automatically map GPU device memory to host memory. With some pragma directive language, programmer can directly use host memory in CUDA kernel functions, during which the tedious and error-prone data transfer and device memory management are shielded from programmer. The performance is also improved with some near-optimal technologies. Experiment results show that memCUDA programs can get similar effect with well-optimized CUDA programs with more compact source code.
Type de document :
Communication dans un congrès
Chen Ding; Zhiyuan Shao; Ran Zheng. IFIP International Conference on Network and Parallel Computing (NPC), Sep 2010, Zhengzhou, China. Springer, Lecture Notes in Computer Science, LNCS-6289, pp.299-313, 2010, Network and Parallel Computing. 〈10.1007/978-3-642-15672-4_26〉
Liste complète des métadonnées

Littérature citée [13 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01058920
Contributeur : Hal Ifip <>
Soumis le : jeudi 28 août 2014 - 15:56:36
Dernière modification le : lundi 13 août 2018 - 13:34:02
Document(s) archivé(s) le : samedi 29 novembre 2014 - 10:45:56

Fichier

memCUDA_npc_final.pdf
Fichiers produits par l'(les) auteur(s)

Licence


Distributed under a Creative Commons Paternité 4.0 International License

Identifiants

Citation

Hai Jin, Bo Li, Qin Zhang, Wenbing Ao. memCUDA: Map Device Memory to Host Memory on GPGPU Platform. Chen Ding; Zhiyuan Shao; Ran Zheng. IFIP International Conference on Network and Parallel Computing (NPC), Sep 2010, Zhengzhou, China. Springer, Lecture Notes in Computer Science, LNCS-6289, pp.299-313, 2010, Network and Parallel Computing. 〈10.1007/978-3-642-15672-4_26〉. 〈hal-01058920〉

Partager

Métriques

Consultations de la notice

177

Téléchargements de fichiers

365