{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T07:06:07Z","timestamp":1774595167011,"version":"3.50.1"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2001,6,1]],"date-time":"2001-06-01T00:00:00Z","timestamp":991353600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2001,6,1]],"date-time":"2001-06-01T00:00:00Z","timestamp":991353600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["International Journal of Parallel Programming"],"published-print":{"date-parts":[[2001,6]]},"DOI":"10.1023\/a:1011119519789","type":"journal-article","created":{"date-parts":[[2002,12,23]],"date-time":"2002-12-23T08:43:03Z","timestamp":1040632983000},"page":"217-247","source":"Crossref","is-referenced-by-count":109,"title":["Improving Memory Hierarchy Performance for Irregular Applications Using Data and Computation Reorderings"],"prefix":"10.1007","volume":"29","author":[{"given":"John","family":"Mellor-Crummey","sequence":"first","affiliation":[]},{"given":"David","family":"Whalley","sequence":"additional","affiliation":[]},{"given":"Ken","family":"Kennedy","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"301717_CR1","doi-asserted-by":"crossref","unstructured":"D. Callahan, S. Carr, and K. Kennedy, Improving Register Allocation for Subscripted Variables, Proc. ACM SIGPLAN Conf. Progr. Lang. Design Implementation, pp. 53-65 (June 1990).","DOI":"10.1145\/93542.93553"},{"key":"301717_CR2","doi-asserted-by":"crossref","first-page":"587","DOI":"10.1016\/0743-7315(88)90014-7","volume":"5","author":"D. Gannon","year":"1988","unstructured":"D. Gannon, W. Jalby, and K. Gallivan, Strategies for Cache and Local Memory Management by Global Program Transformation, J. Parallel Distributed Computing, 5:587-616 (1988).","journal-title":"J. Parallel Distributed Computing"},{"key":"301717_CR3","doi-asserted-by":"crossref","unstructured":"M. S. Lam, E. E. Rothberg, and M. E. Wolf, The Cache Performance and Optimizations of Blocked Algorithms, Proc. Fourth Int'l. Conf. Architectural Support Progr. Lang. Oper. Syst., pp. 63-74 (April 1991).","DOI":"10.1145\/106972.106981"},{"key":"301717_CR4","volume-title":"Software Methods for Improvement of Cache Performance on Super-computer Applications","author":"A. K. Porterfield","year":"1989","unstructured":"A. K. Porterfield, Software Methods for Improvement of Cache Performance on Super-computer Applications, Ph.D. Dissertation, Rice University, Houston, Texas (May 1989)."},{"key":"301717_CR5","doi-asserted-by":"crossref","unstructured":"M. E. Wolf and M. S. Lam, A Data Locality Optimizing Algorithm, Proc. SIGPLAN Conf. Progr. Lang. Design and Implementation, pp. 30-44 (June 1991).","DOI":"10.1145\/113445.113449"},{"key":"301717_CR6","unstructured":"J. Ferrante, V. Sarkar, and W. Thrash, On Estimating and Enhancing Cache Effective-ness, Proc. Fourth Workshop on Lang. Compilers for Parallel Computing (August 1991)."},{"issue":"1","key":"301717_CR7","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1145\/200912.201006","volume":"13","author":"D. M. Tullsen","year":"1995","unstructured":"D. M. Tullsen and S. J. Eggers, Effective Cache Prefetching on Bus-Based Multipro-cessors, ACM Trans. Computer Syst., 13(1):57-88 (February 1995).","journal-title":"ACM Trans. Computer Syst."},{"key":"301717_CR8","doi-asserted-by":"crossref","unstructured":"T. C. Mowry, M. S. Lam, and A. Gupta, Design and Evaluation of a Compiler Algorithm for Prefetching, Proc. Fifth Int'l. Conf. Architectural Support Progr. Lang. Oper. Syst., pp. 62-73 (October 1992).","DOI":"10.1145\/143365.143488"},{"issue":"3","key":"301717_CR9","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1145\/362875.362879","volume":"12","author":"A. C. McKeller","year":"1969","unstructured":"A. C. McKeller and E. G. Coffman, The Organization of Matrices and Matrix Operations in a Paged Multiprogramming Environment, Commun. ACM, 12(3):153-165 (1969).","journal-title":"Commun. ACM"},{"key":"301717_CR10","doi-asserted-by":"crossref","unstructured":"W. Abu-Sufah, D. J. Kuck, and D. H. Lawrie, Automatic Program Transformations for Virtual Memory Computers, Proc. Nat'l. Computer Conf., pp. 969-974 (June 1979).","DOI":"10.1109\/MARK.1979.8817192"},{"key":"301717_CR11","unstructured":"J. J. Navarro, E. Garcia, and J. R. Herrero, Proc. Tenth ACM Int'l. Conf. Supercomputing (ICS) (1996)."},{"key":"301717_CR12","doi-asserted-by":"crossref","unstructured":"I. Kodukula, N. Ahmed, and K. Pingali, Data-Centric Multi-level Blocking, Proc. ACM SIGPLAN Conf. Progr. Lang. Design Implementation, pp. 346-357 (June 1997).","DOI":"10.1145\/258915.258946"},{"issue":"6","key":"301717_CR13","first-page":"233","volume":"19","author":"J. R. Allen","year":"1984","unstructured":"J. R. Allen and K. Kennedy, Automatic Loop Interchange, Proc. SIGPLAN Symp. Compiler Construction SIGPLAN Notices, 19(6):233-246 (June 1984).","journal-title":"Proc. SIGPLAN Symp. Compiler Construction SIGPLAN Notices"},{"issue":"4","key":"301717_CR14","doi-asserted-by":"crossref","first-page":"424","DOI":"10.1145\/233561.233564","volume":"18","author":"K. S. McKinley","year":"1996","unstructured":"K. S. McKinley, S. Carr, and C.-W. Tseng, Improving Data Locality with Loop Transformations, ACM Trans. Progr. Lang. Syst., 18(4):424-453 (July 1996).","journal-title":"ACM Trans. Progr. Lang. Syst."},{"key":"301717_CR15","doi-asserted-by":"crossref","unstructured":"C. Ding and K. Kennedy, Improving Cache Performance of Dynamic Applications with Computation and Data Layout Transformations, Proc. ACM SIGPLAN Conf. Progr. Lang. Design Implementation, pp. 229-241 (May 1999).","DOI":"10.1145\/301618.301670"},{"key":"301717_CR16","doi-asserted-by":"crossref","first-page":"489","DOI":"10.2514\/3.12012","volume":"32","author":"R. Das","year":"1994","unstructured":"R. Das, D. Mavriplis, J. Saltz, S. Gupta, and R. Ponnusamy, The Design and Implemen-tation of a Parallel Unstructured Euler Solver Using Software Primitives, AIAA J., 32:489-496 (1994).","journal-title":"AIAA J."},{"key":"301717_CR17","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4612-0871-6","volume-title":"Space-Filling Curves","author":"H. Sagan","year":"1994","unstructured":"H. Sagan, Space-Filling Curves, Springer-Verlag, New York (1994)."},{"key":"301717_CR18","volume-title":"Applications of Spatial Data Structures: Computer Graphics, Image Processing and GIS","author":"H. Samet","year":"1989","unstructured":"H. Samet, Applications of Spatial Data Structures: Computer Graphics, Image Processing and GIS, Addison-Wesley, New York (1989)."},{"key":"301717_CR19","doi-asserted-by":"crossref","unstructured":"J. P Singh, C. Holt, T. Totsuka, A. Gupta, and J. Hennessy, Load Balancing and Data Locality in Adaptive Hierarhcical N-body Methods: Barnes-Hut, Fast Multipole, and Radiosity, J. Parallel Distributed Computing (June 1995).","DOI":"10.1006\/jpdc.1995.1077"},{"key":"301717_CR20","doi-asserted-by":"crossref","unstructured":"M. S. Warren and J. K. Salmon, A Parallel Hashed Oct-Tree N-Body Algorithm, Proc. Supercomputing (November 1993).","DOI":"10.1145\/169627.169640"},{"key":"301717_CR21","doi-asserted-by":"crossref","unstructured":"C. Ou, M. Gunwani, and S. Ranka, Architecture-Independent Locality-Improving Transformations of Computational Graphs Embedded in k-Dimensions, Proc. Int'l. Conf. Supercomputing (1995).","DOI":"10.1145\/224538.224573"},{"key":"301717_CR22","doi-asserted-by":"crossref","unstructured":"M. Parashar and J. C. Browne, On Partitioning Dynamic Adaptive Grid Hierarchies, Proc. Hawaii Conf. Syst. Sci. (January 1996).","DOI":"10.1109\/HICSS.1996.495511"},{"key":"301717_CR23","doi-asserted-by":"crossref","unstructured":"M. Thottethodi, S. Chatterjee, and A. R. Lebeck, Tuning Strassen's Matrix Multiplication Algorithm for Memory Efficiency, Proc. SC98: High Performance Computing and Networking (November 1998).","DOI":"10.1109\/SC.1998.10045"},{"key":"301717_CR24","doi-asserted-by":"crossref","unstructured":"J. Frens and D. Wise, Auto-blocking Matrix Multiplication or Tracking BLAS3 Performance from Source Code, Proc. ACM SIGPLAN Conf. Progr. Lang. Design Implementation, pp. 206-216 (June 1997).","DOI":"10.1145\/263764.263789"},{"key":"301717_CR25","unstructured":"I. Al-Furaih and S. Ranka, Memory Hierarchy Management for Iterative Graph Structures, Proc. Int'l. Parallel Processing Symp. (March 1998)."},{"key":"301717_CR26","volume-title":"Computer Solution of Large Sparse Positive Definite Systems","author":"A. George","year":"1981","unstructured":"A. George and G. Liu, Computer Solution of Large Sparse Positive Definite Systems, Prentice Hall, Englewood Cliffs, New Jersey (1981)."},{"key":"301717_CR27","doi-asserted-by":"crossref","unstructured":"E. Cuthill and J. McKee, Reducing the Bandwidth of Sparse Symmetric Matrices, Proc. ACM National Conf., Association of Computing Machinery (1969).","DOI":"10.1145\/800195.805928"},{"key":"301717_CR28","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1002\/nme.1620230208","volume":"23","author":"S. Sloan","year":"1986","unstructured":"S. Sloan, An Algorithm for Profile and Wavefront Reduction of Sparse Matrices, Int'l. J. Numerical Methods Engng., 23:239-251 (1986).","journal-title":"Int'l. J. Numerical Methods Engng."},{"key":"301717_CR29","unstructured":"N. Mitchell, L. Carter, and J. Ferrante, Localizing Nonaffine Array References, Proc. Parallel Architectures and Compilation Techniques (October 1999)."},{"key":"301717_CR30","doi-asserted-by":"crossref","unstructured":"J. Mellor-Crummey, D. Whalley, and K. Kennedy, Improving Memory Hierarchy Performance for Irregular Applications, Proc. ACM Int'l. Conf. Supercomputing, pp. 425-433 (June 1999).","DOI":"10.1145\/305138.305228"},{"key":"301717_CR31","unstructured":"H. Prokop, Cache-Oblivious Algorithms, Master's thesis, MIT Department of Electrical Engineering and Computer Science (June 1999)."},{"key":"301717_CR32","volume-title":"The Art of Computer Programming Volume 3: Sorting and Searching","author":"D. Knuth","year":"1973","unstructured":"D. Knuth, The Art of Computer Programming Volume 3: Sorting and Searching, Addison-Wesley, New York (1973)."},{"key":"301717_CR33","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1002\/jcc.540040211","volume":"4","author":"B. R. Brooks","year":"1983","unstructured":"B. R. Brooks, R. E. Bruccoleri, B. D. Olafson, D. J. States, S. Swaminathan, and M. Karplus, CHARMM: A Program for Macromolecular Energy, Minimization and Dynamics Calculations, J. Computational Chemistry, 4:187-217 (1983).","journal-title":"J. Computational Chemistry"},{"key":"301717_CR34","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1137\/S0036144598334138","volume":"41","author":"G. Karypis","year":"1999","unstructured":"G. Karypis and V. Kumar, Parallel Multilevel k-way Partition Scheme for Irregular Graphs, SIAM Review, 41: 278-300 (1999).","journal-title":"SIAM Review"},{"key":"301717_CR35","unstructured":"R. Robey, Personal Communication (September 2000)."},{"key":"301717_CR36","unstructured":"Y. C. Hu, A. Cox, and W. Zwaenepoel, Improving Fine-Grained Irregular Shared-Memory Benchmarks by Data Reordering, Proc. Supercomputing (November 2000)."},{"key":"301717_CR37","unstructured":"V. Pai and S. Adve, Code Transformations to Improve Memory Parallelism, Proc. MICRO-32 (November 1999)."}],"container-title":["International Journal of Parallel Programming"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1011119519789.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1023\/A:1011119519789\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1011119519789.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T08:23:21Z","timestamp":1748334201000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1023\/A:1011119519789"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2001,6]]},"references-count":37,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2001,6]]}},"alternative-id":["301717"],"URL":"https:\/\/doi.org\/10.1023\/a:1011119519789","relation":{},"ISSN":["0885-7458","1573-7640"],"issn-type":[{"value":"0885-7458","type":"print"},{"value":"1573-7640","type":"electronic"}],"subject":[],"published":{"date-parts":[[2001,6]]}}}