John A. Stratton, Sam S. Stone, Wen-mei W. Hwu. MCUDA: An Efficient Implementation of CUDA Kernels for Multi-core CPUs. In José Nelson Amaral, editor, Languages and Compilers for Parallel Computing, 21th International Workshop, LCPC 2008, Edmonton, Canada, July 31 - August 2, 2008, Revised Selected Papers. Volume 5335 of Lecture Notes in Computer Science, pages 16-30, Springer, 2008. [doi]
@inproceedings{StrattonSH08,
title = {MCUDA: An Efficient Implementation of CUDA Kernels for Multi-core CPUs},
author = {John A. Stratton and Sam S. Stone and Wen-mei W. Hwu},
year = {2008},
doi = {10.1007/978-3-540-89740-8_2},
url = {http://dx.doi.org/10.1007/978-3-540-89740-8_2},
researchr = {https://researchr.org/publication/StrattonSH08},
cites = {0},
citedby = {0},
pages = {16-30},
booktitle = {Languages and Compilers for Parallel Computing, 21th International Workshop, LCPC 2008, Edmonton, Canada, July 31 - August 2, 2008, Revised Selected Papers},
editor = {José Nelson Amaral},
volume = {5335},
series = {Lecture Notes in Computer Science},
publisher = {Springer},
isbn = {978-3-540-89739-2},
}