Memory-Efficient Hardware Performance Counters with Approximate-Counting Algorithms

Hardware performance counters are special registers on processors that track the hardware activities. While the performance counter data are useful for many applications, there are challenges in efficiently collecting many event statistics simultaneously, due to the limited number of performance cou...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2021 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS) s. 226 - 228
Hlavní autoři: Xu, Jingyi, Kim, Sehoon, Nikolic, Borivoje, Shao, Yakun Sophia
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.03.2021
Témata:
Approximate Counting Algorithms
Approximation algorithms
Hardware
Hardware Performance Counter
Heuristic algorithms
Memory management
Probability
Program processors
Sketching Algorithms
Software
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Hardware performance counters are special registers on processors that track the hardware activities. While the performance counter data are useful for many applications, there are challenges in efficiently collecting many event statistics simultaneously, due to the limited number of performance counters on chip. We propose an efficient hardware performance counter design that uses approximate-counting algorithms to improve the number of events tracked on-chip without incurring significant memory overhead. These counters are more memory efficient because they increment counts according to a dynamic probability and approximate the exact counts. Compared with multiplexed hardware performance counters, our approximate hardware counters have a statistically provable memory-accuracy trade-off and are entirely managed in hardware.
AbstractList Hardware performance counters are special registers on processors that track the hardware activities. While the performance counter data are useful for many applications, there are challenges in efficiently collecting many event statistics simultaneously, due to the limited number of performance counters on chip. We propose an efficient hardware performance counter design that uses approximate-counting algorithms to improve the number of events tracked on-chip without incurring significant memory overhead. These counters are more memory efficient because they increment counts according to a dynamic probability and approximate the exact counts. Compared with multiplexed hardware performance counters, our approximate hardware counters have a statistically provable memory-accuracy trade-off and are entirely managed in hardware.
Author Nikolic, Borivoje
Shao, Yakun Sophia
Xu, Jingyi
Kim, Sehoon
Author_xml – sequence: 1
  givenname: Jingyi
  surname: Xu
  fullname: Xu, Jingyi
  organization: University of California,Berkeley
– sequence: 2
  givenname: Sehoon
  surname: Kim
  fullname: Kim, Sehoon
  organization: University of California,Berkeley
– sequence: 3
  givenname: Borivoje
  surname: Nikolic
  fullname: Nikolic, Borivoje
  organization: University of California,Berkeley
– sequence: 4
  givenname: Yakun Sophia
  surname: Shao
  fullname: Shao, Yakun Sophia
  organization: University of California,Berkeley
BookMark eNotj11LwzAYRiPohZv-AkHyB1rz5qNtLsuYbjBxUL0eafNmBtakpJW5f29Rr87FgcPzLMh1iAEJeQSWAzD9tG32ddMoEJXKOeOQM8YkXJEFlLyCqpBC35LmFfuYLtnaOd95DBPdmGTPJiHdY3Ix9SZ0SFfxK0yYRnr20yethyHFb9-bCbNf48OR1qdjTLPtxzty48xpxPt_LsnH8_p9tcl2by_bVb3LPGdiyqwzpVQWSlUZ7ZhggNx0omVcCF1A0SngpWWtaQ0q5MgFtlw6sKDaSksrluThr-sR8TCkeVC6HLRk87tS_AB_dE8G
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ISPASS51385.2021.00041
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 1728186439
9781728186436
EndPage 228
ExternalDocumentID 9408187
Genre orig-research
GrantInformation_xml – fundername: NSF
  grantid: 1955450
  funderid: 10.13039/100000001
GroupedDBID 6IE
6IL
CBEJK
RIE
RIL
ID FETCH-LOGICAL-i203t-dfa745d1758a9f0301e2ac3b02339616c5127d0babae5e2e23eb24f1d15b894d3
IEDL.DBID RIE
ISICitedReferencesCount 2
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000672618800030&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Thu Jan 18 11:13:08 EST 2024
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i203t-dfa745d1758a9f0301e2ac3b02339616c5127d0babae5e2e23eb24f1d15b894d3
PageCount 3
ParticipantIDs ieee_primary_9408187
PublicationCentury 2000
PublicationDate 2021-March
PublicationDateYYYYMMDD 2021-03-01
PublicationDate_xml – month: 03
  year: 2021
  text: 2021-March
PublicationDecade 2020
PublicationTitle 2021 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)
PublicationTitleAbbrev ISPASS
PublicationYear 2021
Publisher IEEE
Publisher_xml – name: IEEE
Score 1.7648994
Snippet Hardware performance counters are special registers on processors that track the hardware activities. While the performance counter data are useful for many...
SourceID ieee
SourceType Publisher
StartPage 226
SubjectTerms Approximate Counting Algorithms
Approximation algorithms
Hardware
Hardware Performance Counter
Heuristic algorithms
Memory management
Probability
Program processors
Sketching Algorithms
Software
Title Memory-Efficient Hardware Performance Counters with Approximate-Counting Algorithms
URI https://ieeexplore.ieee.org/document/9408187
WOSCitedRecordID wos000672618800030&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NSwMxEA1t8eBJpRW_2YNHY3fz0WyOpbTowVJYhd5KsplIQVvZfqj_3snu0iJ48bZkdxOYHN5M8t4bQm6FCVQEcBShNsYCxQpqARM5MCp1mICw3FbNJtR4nE6netIgdzstDACU5DO4D4_lXb5b5ptwVNbVIhiwqSZpKqUqrVYt-k1i3X3MJv0skwlPJdZ9LCmNOJNfXVNK0Bgd_W-5Y9LZq--iyQ5XTkgDFm2SPQVK7DcdlpYP-F8U7tw_TYHf7rn_UZCYB7_MKJyvRv1gGP41x6QU6KBuChH1316XBb59X3XIy2j4PHigdUMEOmcxX1PnjRLSIeKnRvtQzAAzObeIu1z3kl6O6K1cbI01IIEB41g3C59g0G2qheOnpLVYLuCMRDgAPS2t98yIPBfaS-689M7gNKlU56QdAjL7qDwvZnUsLv4eviSHIeIVN-uKtNbFBq7JQb5dz1fFTblRP9Z_mNA
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Na8JAEF2sLbSntmjpd3PosanJfpjsUURRqiLEgjfZzc4WodUStR__vrNJUAq99BY2yS7MHt7M7ntvCLnnylERwPgItQEWKJr7GjCRAxXFBhMQmuqi2UQ0GsXTqRxXyMNWCwMAOfkMHt1jfpdvlunGHZU1JHcGbNEe2Rec07BQa5Wy3zCQjX4ybiWJCFkssPKjYW7FGf7qm5LDRvf4fwuekPpOf-eNt8hySiqwqJFk6Eix334nN33A_zx36_6pMvx2x_73nMjcOWZ67oTVaznL8K85pqXgt8u2EF7r9WWZ4du3VZ08dzuTds8vWyL4cxqwtW-sirgwiPmxktaVM0BVyjQiL5PNsJkifkcm0EorEECBMqycuQ0x7DqW3LAzUl0sF3BOPByAphTaWqp4mnJpBTNWWKNwmlhEF6TmAjJ7L1wvZmUsLv8eviOHvclwMBv0R09X5MhFv2BqXZPqOtvADTlIP9bzVXabb9oP9o6cFw
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2021+IEEE+International+Symposium+on+Performance+Analysis+of+Systems+and+Software+%28ISPASS%29&rft.atitle=Memory-Efficient+Hardware+Performance+Counters+with+Approximate-Counting+Algorithms&rft.au=Xu%2C+Jingyi&rft.au=Kim%2C+Sehoon&rft.au=Nikolic%2C+Borivoje&rft.au=Shao%2C+Yakun+Sophia&rft.date=2021-03-01&rft.pub=IEEE&rft.spage=226&rft.epage=228&rft_id=info:doi/10.1109%2FISPASS51385.2021.00041&rft.externalDocID=9408187