Eintrag weiter verarbeiten
Performance of large low-associativity caches
Gespeichert in:
| Zeitschriftentitel: | ACM SIGMETRICS Performance Evaluation Review |
|---|---|
| Personen und Körperschaften: | , , , |
| In: | ACM SIGMETRICS Performance Evaluation Review, 37, 2010, 4, S. 11-18 |
| Format: | E-Article |
| Sprache: | Englisch |
| veröffentlicht: |
Association for Computing Machinery (ACM)
|
| Schlagwörter: |
| author_facet |
Dube, Parijat Zhang, Li Daly, David Bivens, Alan Dube, Parijat Zhang, Li Daly, David Bivens, Alan |
|---|---|
| author |
Dube, Parijat Zhang, Li Daly, David Bivens, Alan |
| spellingShingle |
Dube, Parijat Zhang, Li Daly, David Bivens, Alan ACM SIGMETRICS Performance Evaluation Review Performance of large low-associativity caches Computer Networks and Communications Hardware and Architecture Software |
| author_sort |
dube, parijat |
| spelling |
Dube, Parijat Zhang, Li Daly, David Bivens, Alan 0163-5999 Association for Computing Machinery (ACM) Computer Networks and Communications Hardware and Architecture Software http://dx.doi.org/10.1145/1773394.1773397 <jats:p>While it is known that lowering the associativity of caches degrades cache performance, little is understood about the degree of this effect or how to lessen the effect, especially in very large caches. Most existing works on cache performance are simulation or emulation based and there is a lack of analytical\ models characterizing performance in terms of different configuration parameters such as line size, cache size, associativity and workload specific parameters. We develop analytical models to study performance of large cache architectures by capturing the dependence of miss ratio on associativity and other configuration parameters. While high associativity may decrease cache misses, for very large caches the corresponding increase in hardware cost and power may be significant. We use our models as well as simulation to study different proposals for reducing misses in low associativity caches, specifically, address space randomization and victim caches. Our analysis provides specific detail on the impact of these proposals, and a clearer understanding of why they do or do not work.</jats:p> Performance of large low-associativity caches ACM SIGMETRICS Performance Evaluation Review |
| doi_str_mv |
10.1145/1773394.1773397 |
| facet_avail |
Online |
| finc_class_facet |
Informatik Technik |
| format |
ElectronicArticle |
| fullrecord |
blob:ai-49-aHR0cDovL2R4LmRvaS5vcmcvMTAuMTE0NS8xNzczMzk0LjE3NzMzOTc |
| id |
ai-49-aHR0cDovL2R4LmRvaS5vcmcvMTAuMTE0NS8xNzczMzk0LjE3NzMzOTc |
| institution |
DE-Zi4 DE-15 DE-105 DE-14 DE-Ch1 |
| imprint |
Association for Computing Machinery (ACM), 2010 |
| imprint_str_mv |
Association for Computing Machinery (ACM), 2010 |
| issn |
0163-5999 |
| issn_str_mv |
0163-5999 |
| language |
English |
| mega_collection |
Association for Computing Machinery (ACM) (CrossRef) |
| match_str |
dube2010performanceoflargelowassociativitycaches |
| publishDateSort |
2010 |
| publisher |
Association for Computing Machinery (ACM) |
| recordtype |
ai |
| record_format |
ai |
| series |
ACM SIGMETRICS Performance Evaluation Review |
| source_id |
49 |
| title |
Performance of large low-associativity caches |
| title_unstemmed |
Performance of large low-associativity caches |
| title_full |
Performance of large low-associativity caches |
| title_fullStr |
Performance of large low-associativity caches |
| title_full_unstemmed |
Performance of large low-associativity caches |
| title_short |
Performance of large low-associativity caches |
| title_sort |
performance of large low-associativity caches |
| topic |
Computer Networks and Communications Hardware and Architecture Software |
| url |
http://dx.doi.org/10.1145/1773394.1773397 |
| publishDate |
2010 |
| physical |
11-18 |
| description |
<jats:p>While it is known that lowering the associativity of caches degrades cache performance, little is understood about the degree of this effect or how to lessen the effect, especially in very large caches. Most existing works on cache performance are simulation or emulation based and there is a lack of analytical\ models characterizing performance in terms of different configuration parameters such as line size, cache size, associativity and workload specific parameters. We develop analytical models to study performance of large cache architectures by capturing the dependence of miss ratio on associativity and other configuration parameters. While high associativity may decrease cache misses, for very large caches the corresponding increase in hardware cost and power may be significant. We use our models as well as simulation to study different proposals for reducing misses in low associativity caches, specifically, address space randomization and victim caches. Our analysis provides specific detail on the impact of these proposals, and a clearer understanding of why they do or do not work.</jats:p> |
| container_issue |
4 |
| container_start_page |
11 |
| container_title |
ACM SIGMETRICS Performance Evaluation Review |
| container_volume |
37 |
| format_de105 |
Article, E-Article |
| format_de14 |
Article, E-Article |
| format_de15 |
Article, E-Article |
| format_de520 |
Article, E-Article |
| format_de540 |
Article, E-Article |
| format_dech1 |
Article, E-Article |
| format_ded117 |
Article, E-Article |
| format_degla1 |
E-Article |
| format_del152 |
Buch |
| format_del189 |
Article, E-Article |
| format_dezi4 |
Article |
| format_dezwi2 |
Article, E-Article |
| format_finc |
Article, E-Article |
| format_nrw |
Article, E-Article |
| _version_ |
1792329510661652480 |
| geogr_code |
not assigned |
| last_indexed |
2024-03-01T13:10:19.25Z |
| geogr_code_person |
not assigned |
| openURL |
url_ver=Z39.88-2004&ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fvufind.svn.sourceforge.net%3Agenerator&rft.title=Performance+of+large+low-associativity+caches&rft.date=2010-03-27&genre=article&issn=0163-5999&volume=37&issue=4&spage=11&epage=18&pages=11-18&jtitle=ACM+SIGMETRICS+Performance+Evaluation+Review&atitle=Performance+of+large+low-associativity+caches&aulast=Bivens&aufirst=Alan&rft_id=info%3Adoi%2F10.1145%2F1773394.1773397&rft.language%5B0%5D=eng |
| SOLR | |
| _version_ | 1792329510661652480 |
| author | Dube, Parijat, Zhang, Li, Daly, David, Bivens, Alan |
| author_facet | Dube, Parijat, Zhang, Li, Daly, David, Bivens, Alan, Dube, Parijat, Zhang, Li, Daly, David, Bivens, Alan |
| author_sort | dube, parijat |
| container_issue | 4 |
| container_start_page | 11 |
| container_title | ACM SIGMETRICS Performance Evaluation Review |
| container_volume | 37 |
| description | <jats:p>While it is known that lowering the associativity of caches degrades cache performance, little is understood about the degree of this effect or how to lessen the effect, especially in very large caches. Most existing works on cache performance are simulation or emulation based and there is a lack of analytical\ models characterizing performance in terms of different configuration parameters such as line size, cache size, associativity and workload specific parameters. We develop analytical models to study performance of large cache architectures by capturing the dependence of miss ratio on associativity and other configuration parameters. While high associativity may decrease cache misses, for very large caches the corresponding increase in hardware cost and power may be significant. We use our models as well as simulation to study different proposals for reducing misses in low associativity caches, specifically, address space randomization and victim caches. Our analysis provides specific detail on the impact of these proposals, and a clearer understanding of why they do or do not work.</jats:p> |
| doi_str_mv | 10.1145/1773394.1773397 |
| facet_avail | Online |
| finc_class_facet | Informatik, Technik |
| format | ElectronicArticle |
| format_de105 | Article, E-Article |
| format_de14 | Article, E-Article |
| format_de15 | Article, E-Article |
| format_de520 | Article, E-Article |
| format_de540 | Article, E-Article |
| format_dech1 | Article, E-Article |
| format_ded117 | Article, E-Article |
| format_degla1 | E-Article |
| format_del152 | Buch |
| format_del189 | Article, E-Article |
| format_dezi4 | Article |
| format_dezwi2 | Article, E-Article |
| format_finc | Article, E-Article |
| format_nrw | Article, E-Article |
| geogr_code | not assigned |
| geogr_code_person | not assigned |
| id | ai-49-aHR0cDovL2R4LmRvaS5vcmcvMTAuMTE0NS8xNzczMzk0LjE3NzMzOTc |
| imprint | Association for Computing Machinery (ACM), 2010 |
| imprint_str_mv | Association for Computing Machinery (ACM), 2010 |
| institution | DE-Zi4, DE-15, DE-105, DE-14, DE-Ch1 |
| issn | 0163-5999 |
| issn_str_mv | 0163-5999 |
| language | English |
| last_indexed | 2024-03-01T13:10:19.25Z |
| match_str | dube2010performanceoflargelowassociativitycaches |
| mega_collection | Association for Computing Machinery (ACM) (CrossRef) |
| physical | 11-18 |
| publishDate | 2010 |
| publishDateSort | 2010 |
| publisher | Association for Computing Machinery (ACM) |
| record_format | ai |
| recordtype | ai |
| series | ACM SIGMETRICS Performance Evaluation Review |
| source_id | 49 |
| spelling | Dube, Parijat Zhang, Li Daly, David Bivens, Alan 0163-5999 Association for Computing Machinery (ACM) Computer Networks and Communications Hardware and Architecture Software http://dx.doi.org/10.1145/1773394.1773397 <jats:p>While it is known that lowering the associativity of caches degrades cache performance, little is understood about the degree of this effect or how to lessen the effect, especially in very large caches. Most existing works on cache performance are simulation or emulation based and there is a lack of analytical\ models characterizing performance in terms of different configuration parameters such as line size, cache size, associativity and workload specific parameters. We develop analytical models to study performance of large cache architectures by capturing the dependence of miss ratio on associativity and other configuration parameters. While high associativity may decrease cache misses, for very large caches the corresponding increase in hardware cost and power may be significant. We use our models as well as simulation to study different proposals for reducing misses in low associativity caches, specifically, address space randomization and victim caches. Our analysis provides specific detail on the impact of these proposals, and a clearer understanding of why they do or do not work.</jats:p> Performance of large low-associativity caches ACM SIGMETRICS Performance Evaluation Review |
| spellingShingle | Dube, Parijat, Zhang, Li, Daly, David, Bivens, Alan, ACM SIGMETRICS Performance Evaluation Review, Performance of large low-associativity caches, Computer Networks and Communications, Hardware and Architecture, Software |
| title | Performance of large low-associativity caches |
| title_full | Performance of large low-associativity caches |
| title_fullStr | Performance of large low-associativity caches |
| title_full_unstemmed | Performance of large low-associativity caches |
| title_short | Performance of large low-associativity caches |
| title_sort | performance of large low-associativity caches |
| title_unstemmed | Performance of large low-associativity caches |
| topic | Computer Networks and Communications, Hardware and Architecture, Software |
| url | http://dx.doi.org/10.1145/1773394.1773397 |