國立虎尾科技大學 |

Parallelization and Scalability Analysis of the 3D Spatially Variant Lattice Algorithm.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Parallelization and Scalability Analysis of the 3D Spatially Variant Lattice Algorithm./
作者:	Lopez, Henry R. Moncada.
面頁冊數:	1 online resource (120 pages)
附註:	Source: Dissertation Abstracts International, Volume: 79-10(E), Section: B.
Contained By:	Dissertation Abstracts International79-10B(E).
標題:	Computer science. -
電子資源:	click for full text (PQDT)
ISBN:	9780438031791

Parallelization and Scalability Analysis of the 3D Spatially Variant Lattice Algorithm.
Lopez, Henry R. Moncada.

Parallelization and Scalability Analysis of the 3D Spatially Variant Lattice Algorithm. - 1 online resource (120 pages)

Source: Dissertation Abstracts International, Volume: 79-10(E), Section: B.

Thesis (Ph.D.)--The University of Texas at El Paso, 2018.

Includes bibliographical references

The purpose of this research is to design a faster implementation of an algorithm to generate 3D spatially variant lattices (SVL) and improve its performance when it is running on a parallel computer system.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9780438031791Subjects--Topical Terms:

573171
Computer science.
Index Terms--Genre/Form:

554714
Electronic books.

Parallelization and Scalability Analysis of the 3D Spatially Variant Lattice Algorithm.
LDR:03734ntm a2200397Ki 4500 001 916714
005 20180927111922.5
006 m o u
007 cr mn||||a|a||
008 190606s2018 xx obm 000 0 eng d
020 $a 9780438031791
035 $a (MiAaPQ)AAI10824303
035 $a (MiAaPQ)utep:12716
035 $a AAI10824303
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Lopez, Henry R. Moncada. $3 1190530
245 1 0 $a Parallelization and Scalability Analysis of the 3D Spatially Variant Lattice Algorithm.
264 0 $c 2018
300 $a 1 online resource (120 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertation Abstracts International, Volume: 79-10(E), Section: B.
500 $a Advisers: Shirley V. Moore; Raymond C. Rumpf.
502 $a Thesis (Ph.D.)--The University of Texas at El Paso, 2018.
504 $a Includes bibliographical references
520 $a The purpose of this research is to design a faster implementation of an algorithm to generate 3D spatially variant lattices (SVL) and improve its performance when it is running on a parallel computer system.
520 $a The algorithm is used to synthesize a SVL for a periodic structure. The algorithm has the ability to spatially vary the unit cell, the orientation of the unit cells, lattice spacing, fill fraction, material composition, and lattice symmetry. The algorithm produces a lattice that is smooth, continuous and free of defects. The lattice spacing remains strikingly uniform even when the lattice is spatially varied. This is important for maintaining consistent properties throughout the lattice. Periodic structures like photonic crystals or metamaterial devices can be enhanced using the spatially variant algorithm, thus unlocking new physical mechanisms.
520 $a Our current effort is to write a portable computer program for parallel architectures. To develop and write the code, we pick a general purpose programming language that supports structured programming. For the parallel code, we use the FFTW (Fastest Fourier Transform in the West) for handling the Fourier transform of the unit cell device and PETSc (Portable, Extensible Toolkit for Scientific Computation) for handling the numerical linear algebra operations. Using Message Passing Interface (MPI) for distributed memory helps us to improve the performance of the code that generates 3D SVL when it is executed on a parallel system.
520 $a We study the efficiency and scalability of the SVL code on the two architectures on Stampede2 (KNL and SKX). A scalable code can handle proportionally very small to large tasks of computational operations. To scale the SVL code, we use isoefficiency analysis to proportionally increase the problem size and resources to study the scalability of the SVL code. This type of analysis is important to understand the performance of the SVL code when it is executed on a supercomputer and find the best way to maximize its performance.
520 $a Our future work consists of improving the efficiency and scalability by reducing the overload performance of communication overhead. Moving data limited the performance achievement of the SVL code. Improving the scalability as the problem size and the number of processors grow is an essential factor in getting a better performance of the SVL code.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
650 4 $a Electrical engineering. $3 596380
650 4 $a Electromagnetics. $3 1178899
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
690 $a 0544
690 $a 0607
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a The University of Texas at El Paso. $b Computational Science. $3 845724
773 0 $t Dissertation Abstracts International $g 79-10B(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10824303 $z click for full text (PQDT)