@article {10.3844/jcssp.2018.699.704,
article_type = {journal},
title = {Evaluating the Efficiency of CPUs, GPUs and FPGAs on a Near-Duplicate Document Detection Via OpenCL},
author = {Canhasi, Ercan},
volume = {14},
number = {5},
year = {2018},
month = {Apr},
pages = {699-704},
doi = {10.3844/jcssp.2018.699.704},
url = {https://thescipub.com/abstract/jcssp.2018.699.704},
abstract = {Discovering identical or near-identical items is urgently important in many applications such as Web crawling since it drastically reduces the text processing costs. Simhash is a widely used technique, able to attribute a bit-string identity to a text, such that similar texts have similar identities. In this study, a real-time solution for a simhash calculation in OpenCL is presented. We also show how it can be utilized by multi-CPUs, GPUs and FPGAs. As a result we indicate that the bottom line computation realized on the FPGA through OpenCL provides significant power advantages.},
journal = {Journal of Computer Science},
publisher = {Science Publications}
}