@inproceedings{d3f39358da3f4d1697e9ae99513b5835,
title = "Design of application specific throughput processor for matrix operations",
abstract = "In modern computation routines, matrix operations are broadly used in many scientific realms, ranging from high performance supercomputers to resource constrained embedded devices. Previous studies have revealed that the computation efficiency of matrix operations is significantly determined by the data accesses behavior of the computation platform. This paper introduces an integrated multicore system, including software stacks and hardware modules that can accelerate matrix operations and reduce data access overhead. With the proposed hardware module, the performance of our multicore embedded platform can improve up to 24.09%. Besides the hardware design, we also develop a framework that can facilitate the prototyping of embedded system designs, including functional verification of hardware modules as well as co-simulation with high level OpenCL language.",
keywords = "Design framework, FPGA, Matrix operations, OpenCL, Throughput processor",
author = "Wu, {Ping Ju} and Lin, {Chien Yu} and Bo-Cheng Lai",
year = "2015",
month = dec,
day = "9",
doi = "10.1109/NBiS.2015.50",
language = "English",
series = "Proceedings - 2015 18th International Conference on Network-Based Information Systems, NBiS 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "324--331",
editor = "Leonard Barolli and Makoto Takizawa and Fatos Xhafa and Hui-Huang Hsu and Tomoya Enokido",
booktitle = "Proceedings - 2015 18th International Conference on Network-Based Information Systems, NBiS 2015",
address = "United States",
note = "null ; Conference date: 02-09-2015 Through 04-09-2015",
}