L2 Cache Modeling for Scientific Applications on Chip Multi-Processors

It is critical to provide high performance for scientific applications running on chip multi-processors (CMP). A CMP architecture often comprises a shared 12 cache and lower-level storages. The shared 12 cache can reduce the number of cache misses if the data are accessed in common by several thread...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of the International Conference on Parallel Processing p. 51
Main Authors: Fengguang Song, Moore, S., Dongarra, J.
Format: Conference Proceeding
Language:English
Published: IEEE 01.09.2007
Subjects:
Analytical models
Application software
architecture
cache
Capacity planning
chip multi-processor
Computer architecture
Computer science
Degradation
multi-threaded programming
Parallel processing
performance modeling
Predictive models
Sparse matrices
Yarn
ISSN:0190-3918
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract It is critical to provide high performance for scientific applications running on chip multi-processors (CMP). A CMP architecture often comprises a shared 12 cache and lower-level storages. The shared 12 cache can reduce the number of cache misses if the data are accessed in common by several threads, but it can also lead to performance degradation due to resource contention. Sometimes running threads on all cores can cause severe contention and increase the number of cache misses greatly. To investigate how the performance of a thread varies when running it concurrently with other threads on the remaining cores, we develop an analytical model to predict the number of misses on the shared L2 cache. In particular, we apply the model to thread-parallel numerical pro grams. We assume that all the threads compute homogeneous tasks and share a fully associative L2 cache. We use circular sequence profiling and stack processing techniques to analyze the L2 cache trace to predict the number of compulsory cache misses, capacity cache misses on shared data, and capacity cache misses on private data, respectively. Our method is able to predict the L2 cache performance for threads that have a global shared address space. For scientific applications, threads often have overlapping memory footprints. We use a cycle accurate simulator to validate the model with three scientific programs: dense matrix multiplication, blocked dense matrix multiplication, and sparse matrix-vector product. The average relative errors for the three experiments are 8.01%, 1.85%, and 2.41%, respectively.
AbstractList It is critical to provide high performance for scientific applications running on chip multi-processors (CMP). A CMP architecture often comprises a shared 12 cache and lower-level storages. The shared 12 cache can reduce the number of cache misses if the data are accessed in common by several threads, but it can also lead to performance degradation due to resource contention. Sometimes running threads on all cores can cause severe contention and increase the number of cache misses greatly. To investigate how the performance of a thread varies when running it concurrently with other threads on the remaining cores, we develop an analytical model to predict the number of misses on the shared L2 cache. In particular, we apply the model to thread-parallel numerical pro grams. We assume that all the threads compute homogeneous tasks and share a fully associative L2 cache. We use circular sequence profiling and stack processing techniques to analyze the L2 cache trace to predict the number of compulsory cache misses, capacity cache misses on shared data, and capacity cache misses on private data, respectively. Our method is able to predict the L2 cache performance for threads that have a global shared address space. For scientific applications, threads often have overlapping memory footprints. We use a cycle accurate simulator to validate the model with three scientific programs: dense matrix multiplication, blocked dense matrix multiplication, and sparse matrix-vector product. The average relative errors for the three experiments are 8.01%, 1.85%, and 2.41%, respectively.
Author Dongarra, J.
Moore, S.
Fengguang Song
Author_xml – sequence: 1
  surname: Fengguang Song
  fullname: Fengguang Song
  organization: Dept. of Comput. Sci., Univ. of Tennessee, Knoxville, TN
– sequence: 2
  givenname: S.
  surname: Moore
  fullname: Moore, S.
  organization: Dept. of Comput. Sci., Univ. of Tennessee, Knoxville, TN
– sequence: 3
  givenname: J.
  surname: Dongarra
  fullname: Dongarra, J.
  organization: Dept. of Comput. Sci., Univ. of Tennessee, Knoxville, TN
BookMark eNotzE1LwzAcgPEIE1ynN29e8gVa_0mapDmO4nTQYcEdvI00Ly5Sk9LUg99ewZ0efpenQKuYokPonkBFCKjHfdv3FQWQFadXqAApFKeKsfcVWgNRUDJFmhtU5PwJQIHxeo12HcWtNmeHD8m6McQP7NOM30xwcQk-GLydpjEYvYQUM04Rt-cw4cP3uISyn5NxOac536Jrr8fs7i7doOPu6di-lN3r877ddmVQsJSUeSGlINI3RA9SGWsGAcq4wVhviNZCcOUtlQOzhA6kthI0-7NwXvOasQ16-N8G59xpmsOXnn9ONatZwxv2C27GS7I
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ICPP.2007.52
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
Discipline Architecture
Computer Science
EISBN 076952933X
9780769529332
EndPage 51
ExternalDocumentID 4343858
Genre orig-research
GroupedDBID -~X
23M
29P
6IE
6IF
6IH
6IK
6IL
6IN
AAJGR
AAWTH
ABDPE
ADZIZ
AFFNX
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IPLJI
M43
OCL
RIE
RIL
RNS
XOL
ID FETCH-LOGICAL-i90t-23f677617f81ab79cdcb609cebcdfc1aa6659fd27b3d12b14d70a3d276efa5433
IEDL.DBID RIE
ISSN 0190-3918
IngestDate Wed Aug 27 02:09:16 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i90t-23f677617f81ab79cdcb609cebcdfc1aa6659fd27b3d12b14d70a3d276efa5433
PageCount 1
ParticipantIDs ieee_primary_4343858
PublicationCentury 2000
PublicationDate 2007-Sept.
PublicationDateYYYYMMDD 2007-09-01
PublicationDate_xml – month: 09
  year: 2007
  text: 2007-Sept.
PublicationDecade 2000
PublicationTitle Proceedings of the International Conference on Parallel Processing
PublicationTitleAbbrev ICPP
PublicationYear 2007
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0020354
ssib015831335
Score 1.7612944
Snippet It is critical to provide high performance for scientific applications running on chip multi-processors (CMP). A CMP architecture often comprises a shared 12...
SourceID ieee
SourceType Publisher
StartPage 51
SubjectTerms Analytical models
Application software
architecture
cache
Capacity planning
chip multi-processor
Computer architecture
Computer science
Degradation
multi-threaded programming
Parallel processing
performance modeling
Predictive models
Sparse matrices
Yarn
Title L2 Cache Modeling for Scientific Applications on Chip Multi-Processors
URI https://ieeexplore.ieee.org/document/4343858
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV05T8MwFH4qFQNiKLRF3PLASGgcx9dYRVQgoSpDh26Vr4guSdWD34-dpMfAwuZjsZ5tPT-_930fwAtx2GrvhiJrjQ9QuFWR4safZWm889MmVrwRm-DTqZjPZd6B1wMWxjlXF5-5t9Csc_m2MrvwVTYKKEhBxRmccc4arNb-7GAqiA-3jjx7MaHpHipNJBaHonc5-szyvCEvDHCjE1GV2qdMev9bzRUMj-A8lB_czjV0XNmHy_FJQqAPvb1YA2rv7gAmXwnKAnszCvJnAYSO_Hu1ma_rhdD4JJeNqhJl38sVqgG6UQsnqNabIcwm77PsI2pFFKKljLdRQgrmjYV5IbDSXBprNIulcdrYwmClGKOysAnXxOJE49TyWBHfZ65QNCXkBrplVbpbQCwmwhluRQhaitQ_LSQtUuNoIgM1enIHg2CkxaqhyVi09rn_e_gBLppv0lCu9Qjd7XrnnuDc_GyXm_Vzvbe_0_ui9g
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV05T8MwFH4qBQnEUGiLuPHASGgSx7E9VhFVK0qVoUO3yldEl6Tqwe_HTtJjYGHzsVg-9N7ze9_3AbxiE2hpzZCntbIBCtXCE1TZu8yVNX5S-YJWYhN0MmGzGU8b8LbHwhhjyuIz8-6aZS5fF2rrvsp6DgXJCDuBUxJFoV-htXa3JyAM24DrwLTnYxLtwNKYB2xf9s57oyRNK_pCBzg6klUprcqg9b_1XEH3AM9D6d7wXEPD5G247B-lBNrQ2sk1oPr1dmAwDlHi-JuRE0BzMHRkPdZqvqwYQv2jbDYqcpR8L5aohOh6NaCgWK27MB18TJOhV8soeAvub7wQZzGl1lHJWCAk5UorGftcGal0pgIh4pjwTIdUYh2EMog09QW2_dhkgkQY30AzL3JzCyj2MTOKaubCliyyzgUnWaQMCbkjRw_voOM2ab6siDLm9f7c_z38AufD6dd4Ph5NPh_govo0dcVbj9DcrLbmCc7Uz2axXj2X5_wLf6amPQ
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%3Ajournal&rft.genre=proceeding&rft.title=Proceedings+of+the+International+Conference+on+Parallel+Processing&rft.atitle=L2+Cache+Modeling+for+Scientific+Applications+on+Chip+Multi-Processors&rft.au=Fengguang+Song&rft.au=Moore%2C+S.&rft.au=Dongarra%2C+J.&rft.date=2007-09-01&rft.pub=IEEE&rft.issn=0190-3918&rft.spage=51&rft.epage=51&rft_id=info:doi/10.1109%2FICPP.2007.52&rft.externalDocID=4343858
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0190-3918&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0190-3918&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0190-3918&client=summon