Loading…

On the High-Performance Computing of Layered Green's Function Based on the Graphics Processing Unit

The efficient evaluation of Sommerfeld integrals (SIs) in planar layered media has been a long-term bottleneck in the accurate electromagnetic analysis of modern radio frequency (RF) circuits, chips, and devices. This work investigates the high-performance computing of SIs using modern graphics proc...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on antennas and propagation 2024-06, Vol.72 (6), p.5159-5170
Main Authors: Wu, Bi-Yi, Yan, Chao-Ze, Yuan, Xin, Zhang, Qianyun, He, Wei-Jia, Sheng, Xin-Qing
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites cdi_FETCH-LOGICAL-c175t-8baabef70ca12b1ef55c1206b0f35637bf753dff1ee2e30d125ff1f64acf71c03
container_end_page 5170
container_issue 6
container_start_page 5159
container_title IEEE transactions on antennas and propagation
container_volume 72
creator Wu, Bi-Yi
Yan, Chao-Ze
Yuan, Xin
Zhang, Qianyun
He, Wei-Jia
Sheng, Xin-Qing
description The efficient evaluation of Sommerfeld integrals (SIs) in planar layered media has been a long-term bottleneck in the accurate electromagnetic analysis of modern radio frequency (RF) circuits, chips, and devices. This work investigates the high-performance computing of SIs using modern graphics processing units (GPUs) to alleviate this difficulty. Based on the numerical integration procedure with controllable accuracy for SIs, the GPU parallel schemes for SI heads and SI tails are first presented. By eliminating the redundant calculations in SI of multiple frequencies, highly efficient parallel computing enhanced by tensor cores of GPU is developed, and it evaluates the multiple frequency SIs simultaneously. In addition, the mixed-precision computing that further accelerates computing is also studied and tested. Extensively numerical experiments are carried out on two commercial gaming GPUs and verify the performance of the proposed parallel scheme. It achieves a dozen to hundreds speedup compared to that using two high-end CPUs with full OpenMP parallelization.
doi_str_mv 10.1109/TAP.2024.3387835
format article
fullrecord <record><control><sourceid>proquest_ieee_</sourceid><recordid>TN_cdi_proquest_journals_3065466670</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10504761</ieee_id><sourcerecordid>3065466670</sourcerecordid><originalsourceid>FETCH-LOGICAL-c175t-8baabef70ca12b1ef55c1206b0f35637bf753dff1ee2e30d125ff1f64acf71c03</originalsourceid><addsrcrecordid>eNpNkL1rAjEYxkNpodZ279Ah0KHT2XxcknO0UrUg6KDQLeTiGz2pyTW5G_zve3IOnV6el-cDfgg9UzKilIzfN5P1iBGWjzgvVMHFDRpQIYqMMUZv0YAQWmRjJr_v0UNKx07mRZ4PkF153BwAL6r9IVtDdCGejLeAp-FUt03l9zg4vDRniLDD8wjg3xKetd42VfD4w6TuHfqOeTT1obIJr2OwkNIlvPVV84junPlJ8HS9Q7SdfW6mi2y5mn9NJ8vMUiWarCiNKcEpYg1lJQUnhKWMyJI4LiRXpVOC75yjAAw42VEmOuFkbqxT1BI-RK99bx3Dbwup0cfQRt9Nak6kyKWU6uIivcvGkFIEp-tYnUw8a0r0BaXuUOoLSn1F2UVe-kgFAP_sguRKUv4H5ttwKQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3065466670</pqid></control><display><type>article</type><title>On the High-Performance Computing of Layered Green's Function Based on the Graphics Processing Unit</title><source>IEEE Xplore (Online service)</source><creator>Wu, Bi-Yi ; Yan, Chao-Ze ; Yuan, Xin ; Zhang, Qianyun ; He, Wei-Jia ; Sheng, Xin-Qing</creator><creatorcontrib>Wu, Bi-Yi ; Yan, Chao-Ze ; Yuan, Xin ; Zhang, Qianyun ; He, Wei-Jia ; Sheng, Xin-Qing</creatorcontrib><description>The efficient evaluation of Sommerfeld integrals (SIs) in planar layered media has been a long-term bottleneck in the accurate electromagnetic analysis of modern radio frequency (RF) circuits, chips, and devices. This work investigates the high-performance computing of SIs using modern graphics processing units (GPUs) to alleviate this difficulty. Based on the numerical integration procedure with controllable accuracy for SIs, the GPU parallel schemes for SI heads and SI tails are first presented. By eliminating the redundant calculations in SI of multiple frequencies, highly efficient parallel computing enhanced by tensor cores of GPU is developed, and it evaluates the multiple frequency SIs simultaneously. In addition, the mixed-precision computing that further accelerates computing is also studied and tested. Extensively numerical experiments are carried out on two commercial gaming GPUs and verify the performance of the proposed parallel scheme. It achieves a dozen to hundreds speedup compared to that using two high-end CPUs with full OpenMP parallelization.</description><identifier>ISSN: 0018-926X</identifier><identifier>EISSN: 1558-2221</identifier><identifier>DOI: 10.1109/TAP.2024.3387835</identifier><identifier>CODEN: IETPAK</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Controllability ; Graphics processing unit (GPU) ; Graphics processing units ; Green's function methods ; Green's functions ; Green’s function ; Head ; High performance computing ; Instruction sets ; integral equation ; mixed-precision ; Numerical integration ; Parallel processing ; Silicon ; Sommerfeld integrals (SIs) ; Tail ; tensor cores ; Tensors</subject><ispartof>IEEE transactions on antennas and propagation, 2024-06, Vol.72 (6), p.5159-5170</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c175t-8baabef70ca12b1ef55c1206b0f35637bf753dff1ee2e30d125ff1f64acf71c03</cites><orcidid>0000-0001-7790-3839 ; 0000-0002-4614-6545 ; 0009-0001-9559-4109 ; 0000-0002-8136-3705 ; 0000-0002-2147-4059</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10504761$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,27924,27925,54796</link.rule.ids></links><search><creatorcontrib>Wu, Bi-Yi</creatorcontrib><creatorcontrib>Yan, Chao-Ze</creatorcontrib><creatorcontrib>Yuan, Xin</creatorcontrib><creatorcontrib>Zhang, Qianyun</creatorcontrib><creatorcontrib>He, Wei-Jia</creatorcontrib><creatorcontrib>Sheng, Xin-Qing</creatorcontrib><title>On the High-Performance Computing of Layered Green's Function Based on the Graphics Processing Unit</title><title>IEEE transactions on antennas and propagation</title><addtitle>TAP</addtitle><description>The efficient evaluation of Sommerfeld integrals (SIs) in planar layered media has been a long-term bottleneck in the accurate electromagnetic analysis of modern radio frequency (RF) circuits, chips, and devices. This work investigates the high-performance computing of SIs using modern graphics processing units (GPUs) to alleviate this difficulty. Based on the numerical integration procedure with controllable accuracy for SIs, the GPU parallel schemes for SI heads and SI tails are first presented. By eliminating the redundant calculations in SI of multiple frequencies, highly efficient parallel computing enhanced by tensor cores of GPU is developed, and it evaluates the multiple frequency SIs simultaneously. In addition, the mixed-precision computing that further accelerates computing is also studied and tested. Extensively numerical experiments are carried out on two commercial gaming GPUs and verify the performance of the proposed parallel scheme. It achieves a dozen to hundreds speedup compared to that using two high-end CPUs with full OpenMP parallelization.</description><subject>Controllability</subject><subject>Graphics processing unit (GPU)</subject><subject>Graphics processing units</subject><subject>Green's function methods</subject><subject>Green's functions</subject><subject>Green’s function</subject><subject>Head</subject><subject>High performance computing</subject><subject>Instruction sets</subject><subject>integral equation</subject><subject>mixed-precision</subject><subject>Numerical integration</subject><subject>Parallel processing</subject><subject>Silicon</subject><subject>Sommerfeld integrals (SIs)</subject><subject>Tail</subject><subject>tensor cores</subject><subject>Tensors</subject><issn>0018-926X</issn><issn>1558-2221</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNpNkL1rAjEYxkNpodZ279Ah0KHT2XxcknO0UrUg6KDQLeTiGz2pyTW5G_zve3IOnV6el-cDfgg9UzKilIzfN5P1iBGWjzgvVMHFDRpQIYqMMUZv0YAQWmRjJr_v0UNKx07mRZ4PkF153BwAL6r9IVtDdCGejLeAp-FUt03l9zg4vDRniLDD8wjg3xKetd42VfD4w6TuHfqOeTT1obIJr2OwkNIlvPVV84junPlJ8HS9Q7SdfW6mi2y5mn9NJ8vMUiWarCiNKcEpYg1lJQUnhKWMyJI4LiRXpVOC75yjAAw42VEmOuFkbqxT1BI-RK99bx3Dbwup0cfQRt9Nak6kyKWU6uIivcvGkFIEp-tYnUw8a0r0BaXuUOoLSn1F2UVe-kgFAP_sguRKUv4H5ttwKQ</recordid><startdate>20240601</startdate><enddate>20240601</enddate><creator>Wu, Bi-Yi</creator><creator>Yan, Chao-Ze</creator><creator>Yuan, Xin</creator><creator>Zhang, Qianyun</creator><creator>He, Wei-Jia</creator><creator>Sheng, Xin-Qing</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SP</scope><scope>8FD</scope><scope>L7M</scope><orcidid>https://orcid.org/0000-0001-7790-3839</orcidid><orcidid>https://orcid.org/0000-0002-4614-6545</orcidid><orcidid>https://orcid.org/0009-0001-9559-4109</orcidid><orcidid>https://orcid.org/0000-0002-8136-3705</orcidid><orcidid>https://orcid.org/0000-0002-2147-4059</orcidid></search><sort><creationdate>20240601</creationdate><title>On the High-Performance Computing of Layered Green's Function Based on the Graphics Processing Unit</title><author>Wu, Bi-Yi ; Yan, Chao-Ze ; Yuan, Xin ; Zhang, Qianyun ; He, Wei-Jia ; Sheng, Xin-Qing</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c175t-8baabef70ca12b1ef55c1206b0f35637bf753dff1ee2e30d125ff1f64acf71c03</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Controllability</topic><topic>Graphics processing unit (GPU)</topic><topic>Graphics processing units</topic><topic>Green's function methods</topic><topic>Green's functions</topic><topic>Green’s function</topic><topic>Head</topic><topic>High performance computing</topic><topic>Instruction sets</topic><topic>integral equation</topic><topic>mixed-precision</topic><topic>Numerical integration</topic><topic>Parallel processing</topic><topic>Silicon</topic><topic>Sommerfeld integrals (SIs)</topic><topic>Tail</topic><topic>tensor cores</topic><topic>Tensors</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Wu, Bi-Yi</creatorcontrib><creatorcontrib>Yan, Chao-Ze</creatorcontrib><creatorcontrib>Yuan, Xin</creatorcontrib><creatorcontrib>Zhang, Qianyun</creatorcontrib><creatorcontrib>He, Wei-Jia</creatorcontrib><creatorcontrib>Sheng, Xin-Qing</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005–Present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998–Present</collection><collection>IEEE Electronic Library Online</collection><collection>CrossRef</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Technology Research Database</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>IEEE transactions on antennas and propagation</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Wu, Bi-Yi</au><au>Yan, Chao-Ze</au><au>Yuan, Xin</au><au>Zhang, Qianyun</au><au>He, Wei-Jia</au><au>Sheng, Xin-Qing</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>On the High-Performance Computing of Layered Green's Function Based on the Graphics Processing Unit</atitle><jtitle>IEEE transactions on antennas and propagation</jtitle><stitle>TAP</stitle><date>2024-06-01</date><risdate>2024</risdate><volume>72</volume><issue>6</issue><spage>5159</spage><epage>5170</epage><pages>5159-5170</pages><issn>0018-926X</issn><eissn>1558-2221</eissn><coden>IETPAK</coden><abstract>The efficient evaluation of Sommerfeld integrals (SIs) in planar layered media has been a long-term bottleneck in the accurate electromagnetic analysis of modern radio frequency (RF) circuits, chips, and devices. This work investigates the high-performance computing of SIs using modern graphics processing units (GPUs) to alleviate this difficulty. Based on the numerical integration procedure with controllable accuracy for SIs, the GPU parallel schemes for SI heads and SI tails are first presented. By eliminating the redundant calculations in SI of multiple frequencies, highly efficient parallel computing enhanced by tensor cores of GPU is developed, and it evaluates the multiple frequency SIs simultaneously. In addition, the mixed-precision computing that further accelerates computing is also studied and tested. Extensively numerical experiments are carried out on two commercial gaming GPUs and verify the performance of the proposed parallel scheme. It achieves a dozen to hundreds speedup compared to that using two high-end CPUs with full OpenMP parallelization.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/TAP.2024.3387835</doi><tpages>12</tpages><orcidid>https://orcid.org/0000-0001-7790-3839</orcidid><orcidid>https://orcid.org/0000-0002-4614-6545</orcidid><orcidid>https://orcid.org/0009-0001-9559-4109</orcidid><orcidid>https://orcid.org/0000-0002-8136-3705</orcidid><orcidid>https://orcid.org/0000-0002-2147-4059</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 0018-926X
ispartof IEEE transactions on antennas and propagation, 2024-06, Vol.72 (6), p.5159-5170
issn 0018-926X
1558-2221
language eng
recordid cdi_proquest_journals_3065466670
source IEEE Xplore (Online service)
subjects Controllability
Graphics processing unit (GPU)
Graphics processing units
Green's function methods
Green's functions
Green’s function
Head
High performance computing
Instruction sets
integral equation
mixed-precision
Numerical integration
Parallel processing
Silicon
Sommerfeld integrals (SIs)
Tail
tensor cores
Tensors
title On the High-Performance Computing of Layered Green's Function Based on the Graphics Processing Unit
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T17%3A07%3A25IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_ieee_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=On%20the%20High-Performance%20Computing%20of%20Layered%20Green's%20Function%20Based%20on%20the%20Graphics%20Processing%20Unit&rft.jtitle=IEEE%20transactions%20on%20antennas%20and%20propagation&rft.au=Wu,%20Bi-Yi&rft.date=2024-06-01&rft.volume=72&rft.issue=6&rft.spage=5159&rft.epage=5170&rft.pages=5159-5170&rft.issn=0018-926X&rft.eissn=1558-2221&rft.coden=IETPAK&rft_id=info:doi/10.1109/TAP.2024.3387835&rft_dat=%3Cproquest_ieee_%3E3065466670%3C/proquest_ieee_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c175t-8baabef70ca12b1ef55c1206b0f35637bf753dff1ee2e30d125ff1f64acf71c03%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=3065466670&rft_id=info:pmid/&rft_ieee_id=10504761&rfr_iscdi=true