Investigating the effect of varying block size on power and energy consumption of GPU kernels
Power consumption is likely to remain a significant concern for exascale performance in the foreseeable future. In addition, graphics processing units (GPUs) have become an accepted architectural feature for exascale computing due to their scalable performance and power efficiency. In a recent study...
Gespeichert in:
| Veröffentlicht in: | The Journal of supercomputing 2022-09, Vol.78 (13), p.14919-14939 |
|---|---|
| Hauptverfasser: | , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 14939 |
|---|---|
| container_issue | 13 |
| container_start_page | 14919 |
| container_title | The Journal of supercomputing |
| container_volume | 78 |
| creator | Ikram, Muhammad Jawad Saleh, Mostafa Elsayed Al-Hashimi, Muhammad Abdulhamid Abulnaja, Osama Ahmed |
| description | Power consumption is likely to remain a significant concern for
exascale
performance in the foreseeable future. In addition,
graphics processing units (GPUs)
have become an accepted architectural feature for exascale computing due to their scalable performance and power efficiency. In a recent study, we found that we can achieve a reasonable amount of
power
and
energy
savings based on the selection of algorithms. In this research, we suggest that we can save more power and energy by varying the
block size
in the
kernel configuration
. We show that we may attain more savings by selecting the optimum
block size
while executing the workload. We investigated two kernels on NVIDIA Tesla K40 GPU, a Bitonic Mergesort and Vector Addition kernels, to study the effect of varying block sizes on GPU
power
and
energy
consumption. The study should offer insights for upcoming exascale systems in terms of
power
and
energy
efficiency. |
| doi_str_mv | 10.1007/s11227-022-04473-9 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2699983067</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2699983067</sourcerecordid><originalsourceid>FETCH-LOGICAL-c363t-8aff48a8711de75696dadf489180fea1ea9336241d7a292b00838b89d9ec86b3</originalsourceid><addsrcrecordid>eNp9UMtOwzAQtBBIlMIPcLLEOeBXY_uIKiiVKsGhHJHlJJuQPuxgp0Xl63EJEjdOu5qdmdUMQteU3FJC5F2klDGZEcYyIoTkmT5BIzpJCxFKnKIR0YxkaiLYObqIcUUIEVzyEXqbuz3Evm1s37oG9--Aoa6h7LGv8d6GwxEtNr5c49h-AfYOd_4TArauwuAgNAdcehd3265v0zGpZi-veA3BwSZeorPabiJc_c4xWj4-LKdP2eJ5Np_eL7KS57zPlK1roaySlFYgJ7nOK1slRFNFarAUrOY8Z4JW0jLNCkIUV4XSlYZS5QUfo5vBtgv-Y5fimJXfBZc-GpZrrRUnuUwsNrDK4GMMUJsutNsU0VBiji2aoUWTWjQ_LRqdRHwQxUR2DYQ_639U33_hdV8</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2699983067</pqid></control><display><type>article</type><title>Investigating the effect of varying block size on power and energy consumption of GPU kernels</title><source>SpringerLink Journals - AutoHoldings</source><creator>Ikram, Muhammad Jawad ; Saleh, Mostafa Elsayed ; Al-Hashimi, Muhammad Abdulhamid ; Abulnaja, Osama Ahmed</creator><creatorcontrib>Ikram, Muhammad Jawad ; Saleh, Mostafa Elsayed ; Al-Hashimi, Muhammad Abdulhamid ; Abulnaja, Osama Ahmed</creatorcontrib><description>Power consumption is likely to remain a significant concern for
exascale
performance in the foreseeable future. In addition,
graphics processing units (GPUs)
have become an accepted architectural feature for exascale computing due to their scalable performance and power efficiency. In a recent study, we found that we can achieve a reasonable amount of
power
and
energy
savings based on the selection of algorithms. In this research, we suggest that we can save more power and energy by varying the
block size
in the
kernel configuration
. We show that we may attain more savings by selecting the optimum
block size
while executing the workload. We investigated two kernels on NVIDIA Tesla K40 GPU, a Bitonic Mergesort and Vector Addition kernels, to study the effect of varying block sizes on GPU
power
and
energy
consumption. The study should offer insights for upcoming exascale systems in terms of
power
and
energy
efficiency.</description><identifier>ISSN: 0920-8542</identifier><identifier>EISSN: 1573-0484</identifier><identifier>DOI: 10.1007/s11227-022-04473-9</identifier><language>eng</language><publisher>New York: Springer US</publisher><subject>Algorithms ; Compilers ; Computer Science ; Energy consumption ; Graphics processing units ; Interpreters ; Kernels ; Power consumption ; Power efficiency ; Processor Architectures ; Programming Languages</subject><ispartof>The Journal of supercomputing, 2022-09, Vol.78 (13), p.14919-14939</ispartof><rights>The Author(s) 2022</rights><rights>The Author(s) 2022. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c363t-8aff48a8711de75696dadf489180fea1ea9336241d7a292b00838b89d9ec86b3</citedby><cites>FETCH-LOGICAL-c363t-8aff48a8711de75696dadf489180fea1ea9336241d7a292b00838b89d9ec86b3</cites><orcidid>0000-0001-9340-9777</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s11227-022-04473-9$$EPDF$$P50$$Gspringer$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s11227-022-04473-9$$EHTML$$P50$$Gspringer$$Hfree_for_read</linktohtml><link.rule.ids>314,776,780,27901,27902,41464,42533,51294</link.rule.ids></links><search><creatorcontrib>Ikram, Muhammad Jawad</creatorcontrib><creatorcontrib>Saleh, Mostafa Elsayed</creatorcontrib><creatorcontrib>Al-Hashimi, Muhammad Abdulhamid</creatorcontrib><creatorcontrib>Abulnaja, Osama Ahmed</creatorcontrib><title>Investigating the effect of varying block size on power and energy consumption of GPU kernels</title><title>The Journal of supercomputing</title><addtitle>J Supercomput</addtitle><description>Power consumption is likely to remain a significant concern for
exascale
performance in the foreseeable future. In addition,
graphics processing units (GPUs)
have become an accepted architectural feature for exascale computing due to their scalable performance and power efficiency. In a recent study, we found that we can achieve a reasonable amount of
power
and
energy
savings based on the selection of algorithms. In this research, we suggest that we can save more power and energy by varying the
block size
in the
kernel configuration
. We show that we may attain more savings by selecting the optimum
block size
while executing the workload. We investigated two kernels on NVIDIA Tesla K40 GPU, a Bitonic Mergesort and Vector Addition kernels, to study the effect of varying block sizes on GPU
power
and
energy
consumption. The study should offer insights for upcoming exascale systems in terms of
power
and
energy
efficiency.</description><subject>Algorithms</subject><subject>Compilers</subject><subject>Computer Science</subject><subject>Energy consumption</subject><subject>Graphics processing units</subject><subject>Interpreters</subject><subject>Kernels</subject><subject>Power consumption</subject><subject>Power efficiency</subject><subject>Processor Architectures</subject><subject>Programming Languages</subject><issn>0920-8542</issn><issn>1573-0484</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>C6C</sourceid><recordid>eNp9UMtOwzAQtBBIlMIPcLLEOeBXY_uIKiiVKsGhHJHlJJuQPuxgp0Xl63EJEjdOu5qdmdUMQteU3FJC5F2klDGZEcYyIoTkmT5BIzpJCxFKnKIR0YxkaiLYObqIcUUIEVzyEXqbuz3Evm1s37oG9--Aoa6h7LGv8d6GwxEtNr5c49h-AfYOd_4TArauwuAgNAdcehd3265v0zGpZi-veA3BwSZeorPabiJc_c4xWj4-LKdP2eJ5Np_eL7KS57zPlK1roaySlFYgJ7nOK1slRFNFarAUrOY8Z4JW0jLNCkIUV4XSlYZS5QUfo5vBtgv-Y5fimJXfBZc-GpZrrRUnuUwsNrDK4GMMUJsutNsU0VBiji2aoUWTWjQ_LRqdRHwQxUR2DYQ_639U33_hdV8</recordid><startdate>20220901</startdate><enddate>20220901</enddate><creator>Ikram, Muhammad Jawad</creator><creator>Saleh, Mostafa Elsayed</creator><creator>Al-Hashimi, Muhammad Abdulhamid</creator><creator>Abulnaja, Osama Ahmed</creator><general>Springer US</general><general>Springer Nature B.V</general><scope>C6C</scope><scope>AAYXX</scope><scope>CITATION</scope><orcidid>https://orcid.org/0000-0001-9340-9777</orcidid></search><sort><creationdate>20220901</creationdate><title>Investigating the effect of varying block size on power and energy consumption of GPU kernels</title><author>Ikram, Muhammad Jawad ; Saleh, Mostafa Elsayed ; Al-Hashimi, Muhammad Abdulhamid ; Abulnaja, Osama Ahmed</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c363t-8aff48a8711de75696dadf489180fea1ea9336241d7a292b00838b89d9ec86b3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Algorithms</topic><topic>Compilers</topic><topic>Computer Science</topic><topic>Energy consumption</topic><topic>Graphics processing units</topic><topic>Interpreters</topic><topic>Kernels</topic><topic>Power consumption</topic><topic>Power efficiency</topic><topic>Processor Architectures</topic><topic>Programming Languages</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Ikram, Muhammad Jawad</creatorcontrib><creatorcontrib>Saleh, Mostafa Elsayed</creatorcontrib><creatorcontrib>Al-Hashimi, Muhammad Abdulhamid</creatorcontrib><creatorcontrib>Abulnaja, Osama Ahmed</creatorcontrib><collection>Springer Nature OA Free Journals</collection><collection>CrossRef</collection><jtitle>The Journal of supercomputing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Ikram, Muhammad Jawad</au><au>Saleh, Mostafa Elsayed</au><au>Al-Hashimi, Muhammad Abdulhamid</au><au>Abulnaja, Osama Ahmed</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Investigating the effect of varying block size on power and energy consumption of GPU kernels</atitle><jtitle>The Journal of supercomputing</jtitle><stitle>J Supercomput</stitle><date>2022-09-01</date><risdate>2022</risdate><volume>78</volume><issue>13</issue><spage>14919</spage><epage>14939</epage><pages>14919-14939</pages><issn>0920-8542</issn><eissn>1573-0484</eissn><abstract>Power consumption is likely to remain a significant concern for
exascale
performance in the foreseeable future. In addition,
graphics processing units (GPUs)
have become an accepted architectural feature for exascale computing due to their scalable performance and power efficiency. In a recent study, we found that we can achieve a reasonable amount of
power
and
energy
savings based on the selection of algorithms. In this research, we suggest that we can save more power and energy by varying the
block size
in the
kernel configuration
. We show that we may attain more savings by selecting the optimum
block size
while executing the workload. We investigated two kernels on NVIDIA Tesla K40 GPU, a Bitonic Mergesort and Vector Addition kernels, to study the effect of varying block sizes on GPU
power
and
energy
consumption. The study should offer insights for upcoming exascale systems in terms of
power
and
energy
efficiency.</abstract><cop>New York</cop><pub>Springer US</pub><doi>10.1007/s11227-022-04473-9</doi><tpages>21</tpages><orcidid>https://orcid.org/0000-0001-9340-9777</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0920-8542 |
| ispartof | The Journal of supercomputing, 2022-09, Vol.78 (13), p.14919-14939 |
| issn | 0920-8542 1573-0484 |
| language | eng |
| recordid | cdi_proquest_journals_2699983067 |
| source | SpringerLink Journals - AutoHoldings |
| subjects | Algorithms Compilers Computer Science Energy consumption Graphics processing units Interpreters Kernels Power consumption Power efficiency Processor Architectures Programming Languages |
| title | Investigating the effect of varying block size on power and energy consumption of GPU kernels |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-29T17%3A38%3A02IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Investigating%20the%20effect%20of%20varying%20block%20size%20on%20power%20and%20energy%20consumption%20of%20GPU%20kernels&rft.jtitle=The%20Journal%20of%20supercomputing&rft.au=Ikram,%20Muhammad%20Jawad&rft.date=2022-09-01&rft.volume=78&rft.issue=13&rft.spage=14919&rft.epage=14939&rft.pages=14919-14939&rft.issn=0920-8542&rft.eissn=1573-0484&rft_id=info:doi/10.1007/s11227-022-04473-9&rft_dat=%3Cproquest_cross%3E2699983067%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2699983067&rft_id=info:pmid/&rfr_iscdi=true |