Improving parallel Self-organizing Map using heterogeneous uniform memory access / Muhammad Firdaus Mustapha

Self-organizing Map (SOM) is a very popular algorithm that has been used as clustering algorithm and data exploration. SOM consists of complex calculations where the calculation of complexity depending on the circumstances. Many researchers have managed to improve online SOM processing speed using H...

Full description

Bibliographic Details
Main Author:	Mustapha, Muhammad Firdaus
Format:	Book Section
Language:	English
Published:	Institute of Graduate Studies, UiTM 2018
Subjects:	Instruments and machines
Online Access:	http://ir.uitm.edu.my/id/eprint/22098/ http://ir.uitm.edu.my/id/eprint/22098/1/ABS_MUHAMMAD%20FIRDAUS%20MUSTAPHA%20TDRA%20VOL%2014%20IGS%2018.pdf

id	uitm-22098
recordtype	eprints
spelling	uitm-220982018-11-13T08:23:26Z http://ir.uitm.edu.my/id/eprint/22098/ Improving parallel Self-organizing Map using heterogeneous uniform memory access / Muhammad Firdaus Mustapha Mustapha, Muhammad Firdaus Instruments and machines Self-organizing Map (SOM) is a very popular algorithm that has been used as clustering algorithm and data exploration. SOM consists of complex calculations where the calculation of complexity depending on the circumstances. Many researchers have managed to improve online SOM processing speed using Heterogeneous Computing (HC). HC is a combination of Central Processing Unit (CPU) and Graphic Processing Unit (GPU) that work closely together. Standard HC can be represented by CPU and GPU accessing separate memory blocks. In spite of excellent performance using standard HC, there is a situation that causes computer hardware underutilized when executing online SOM variant. In details, the situation occurs when number of cores is larger than the number of neurons on map. Moreover, the complexities of SOM steps also increase the usage of high memory capacity which leads to high rate memory transfer. This situation is caused by the standard HC implements "deep copies" in storing processing objects which lead to communication latency. Recently, combination CPU and GPU that integrated together on a single chip are rapidly attractive the design paradigm for recent platform because of their remarkable parallel processing abilities. This kind of microprocessor is based on Heterogeneous Unified Memory Access (HUMA) model. This model allows both CPU and GPU to access and store into the same memory location which avoids redundant copies of objects by "deep copies" method. Therefore, the main goal of this research is to reduce computation time of SOM training through implementing on HUMA platform and improve GPU cores utilization… Institute of Graduate Studies, UiTM 2018 Book Section PeerReviewed text en http://ir.uitm.edu.my/id/eprint/22098/1/ABS_MUHAMMAD%20FIRDAUS%20MUSTAPHA%20TDRA%20VOL%2014%20IGS%2018.pdf Mustapha, Muhammad Firdaus (2018) Improving parallel Self-organizing Map using heterogeneous uniform memory access / Muhammad Firdaus Mustapha. In: The Doctoral Research Abstracts. IGS Biannual Publication, 14 . Institute of Graduate Studies, UiTM, Shah Alam.
repository_type	Digital Repository
institution_category	Local University
institution	Universiti Teknologi MARA
building	UiTM Institutional Repository
collection	Online Access
language	English
topic	Instruments and machines
spellingShingle	Instruments and machines Mustapha, Muhammad Firdaus Improving parallel Self-organizing Map using heterogeneous uniform memory access / Muhammad Firdaus Mustapha
description	Self-organizing Map (SOM) is a very popular algorithm that has been used as clustering algorithm and data exploration. SOM consists of complex calculations where the calculation of complexity depending on the circumstances. Many researchers have managed to improve online SOM processing speed using Heterogeneous Computing (HC). HC is a combination of Central Processing Unit (CPU) and Graphic Processing Unit (GPU) that work closely together. Standard HC can be represented by CPU and GPU accessing separate memory blocks. In spite of excellent performance using standard HC, there is a situation that causes computer hardware underutilized when executing online SOM variant. In details, the situation occurs when number of cores is larger than the number of neurons on map. Moreover, the complexities of SOM steps also increase the usage of high memory capacity which leads to high rate memory transfer. This situation is caused by the standard HC implements "deep copies" in storing processing objects which lead to communication latency. Recently, combination CPU and GPU that integrated together on a single chip are rapidly attractive the design paradigm for recent platform because of their remarkable parallel processing abilities. This kind of microprocessor is based on Heterogeneous Unified Memory Access (HUMA) model. This model allows both CPU and GPU to access and store into the same memory location which avoids redundant copies of objects by "deep copies" method. Therefore, the main goal of this research is to reduce computation time of SOM training through implementing on HUMA platform and improve GPU cores utilization…
format	Book Section
author	Mustapha, Muhammad Firdaus
author_facet	Mustapha, Muhammad Firdaus
author_sort	Mustapha, Muhammad Firdaus
title	Improving parallel Self-organizing Map using heterogeneous uniform memory access / Muhammad Firdaus Mustapha
title_short	Improving parallel Self-organizing Map using heterogeneous uniform memory access / Muhammad Firdaus Mustapha
title_full	Improving parallel Self-organizing Map using heterogeneous uniform memory access / Muhammad Firdaus Mustapha
title_fullStr	Improving parallel Self-organizing Map using heterogeneous uniform memory access / Muhammad Firdaus Mustapha
title_full_unstemmed	Improving parallel Self-organizing Map using heterogeneous uniform memory access / Muhammad Firdaus Mustapha
title_sort	improving parallel self-organizing map using heterogeneous uniform memory access / muhammad firdaus mustapha
publisher	Institute of Graduate Studies, UiTM
publishDate	2018
url	http://ir.uitm.edu.my/id/eprint/22098/ http://ir.uitm.edu.my/id/eprint/22098/1/ABS_MUHAMMAD%20FIRDAUS%20MUSTAPHA%20TDRA%20VOL%2014%20IGS%2018.pdf
first_indexed	2023-09-18T23:07:55Z
last_indexed	2023-09-18T23:07:55Z
_version_	1777418607727214592

Improving parallel Self-organizing Map using heterogeneous uniform memory access / Muhammad Firdaus Mustapha

Similar Items