Skip to Main content Skip to Navigation
Conference papers

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.
Document type :
Conference papers
Complete list of metadata

Cited literature [13 references]  Display  Hide  Download

https://hal.inria.fr/hal-01058920
Contributor : Hal Ifip <>
Submitted on : Thursday, August 28, 2014 - 3:56:36 PM
Last modification on : Monday, August 13, 2018 - 1:34:02 PM
Long-term archiving on: : Saturday, November 29, 2014 - 10:45:56 AM

File

memCUDA_npc_final.pdf
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

Hai Jin, Bo Li, Qin Zhang, Wenbing Ao. memCUDA: Map Device Memory to Host Memory on GPGPU Platform. IFIP International Conference on Network and Parallel Computing (NPC), Sep 2010, Zhengzhou, China. pp.299-313, ⟨10.1007/978-3-642-15672-4_26⟩. ⟨hal-01058920⟩

Share

Metrics

Record views

288

Files downloads

658