|
| This Article | ||
| ||
| Share | ||
| Bibliographic References | ||
| Add to: | ||
 Digg  Furl  Spurl  Blink  Simpy  Google  Del.icio.us  Y!MyWeb | ||
| Search | ||
| ||
2009 IEEE International Conference on Data Mining Workshops
HOCT: A Highly Scalable Algorithm for Training Linear CRF on Modern Hardware
Miami, Florida, USA
December 06-December 06
ISBN: 978-0-7695-3902-7
| ASCII Text | x | ||
| Tianyuan Chen, Lei Chang, Jianqing Ma, Wei Zhang, Feng Gao, "HOCT: A Highly Scalable Algorithm for Training Linear CRF on Modern Hardware," 2012 IEEE 12th International Conference on Data Mining Workshops, pp. 276-281, 2009 IEEE International Conference on Data Mining Workshops, 2009. | |||
| BibTex | x | ||
| @article{ 10.1109/ICDMW.2009.69, author = {Tianyuan Chen and Lei Chang and Jianqing Ma and Wei Zhang and Feng Gao}, title = {HOCT: A Highly Scalable Algorithm for Training Linear CRF on Modern Hardware}, journal ={2012 IEEE 12th International Conference on Data Mining Workshops}, volume = {0}, year = {2009}, isbn = {978-0-7695-3902-7}, pages = {276-281}, doi = {http://doi.ieeecomputersociety.org/10.1109/ICDMW.2009.69}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, } | |||
| RefWorks Procite/RefMan/Endnote | x | ||
| TY - CONF JO - 2012 IEEE 12th International Conference on Data Mining Workshops TI - HOCT: A Highly Scalable Algorithm for Training Linear CRF on Modern Hardware SN - 978-0-7695-3902-7 SP276 EP281 A1 - Tianyuan Chen, A1 - Lei Chang, A1 - Jianqing Ma, A1 - Wei Zhang, A1 - Feng Gao, PY - 2009 VL - 0 JA - 2012 IEEE 12th International Conference on Data Mining Workshops ER - | |||
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ICDMW.2009.69
This paper proposes an efficient algorithm, HOCT, for CRF training on modern computer architectures. First, software prefetching techniques are utilized to hide cache miss latency. Second, we exploit SIMD to process data in parallel. Third, when dealing with large data sets, we let HOCT instead of operating system to manage swapping operations. Our experiments on various real data sets show that HOCT yields a fourfold speedup when the data can fit in memory, and over a 30-fold speedup when the memory requirement exceeds the physical memory.
Citation:
Tianyuan Chen, Lei Chang, Jianqing Ma, Wei Zhang, Feng Gao, "HOCT: A Highly Scalable Algorithm for Training Linear CRF on Modern Hardware," icdmw, pp.276-281, 2009 IEEE International Conference on Data Mining Workshops, 2009
Usage of this product signifies your acceptance of the Terms of Use.