Title :
Use of CUDA for the Continuous Space Language Model
Author :
Thompson, Elizabeth A. ; Anderson, T.
Author_Institution :
Dept. of Eng., Purdue Univ. Fort Wayne, Fort Wayne, IN, USA
Abstract :
The training phase of the Continuous Space Language Model (CSLM) was implemented in the NVIDIA hardware/software architecture Compute Unified Device Architecture (CUDA). Implementation was accomplished using a combination of CUBLAS library routines and CUDA kernel calls on three different CUDA enabled devices of varying compute capability and a time savings over the traditional CPU approach demonstrated.
Keywords :
hardware-software codesign; language translation; parallel architectures; software architecture; statistical analysis; CPU approach; CSLM; CUBLAS library routines; CUDA; CUDA kernel calls; NVIDIA hardware-software architecture; compute unified device architecture; continuous space language model; statistical machine translation; training phase; Algorithm design and analysis; Computer architecture; Graphics processing units; Instruction sets; Kernel; Libraries; Training; CSLM; CUBLAS; CUDA; GPU; statistical signal processing;
Conference_Titel :
High Performance Extreme Computing (HPEC), 2012 IEEE Conference on
Conference_Location :
Waltham, MA
Print_ISBN :
978-1-4673-1577-7
DOI :
10.1109/HPEC.2012.6408661
