{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T12:04:53Z","timestamp":1763467493654,"version":"3.41.0"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2001,10,1]],"date-time":"2001-10-01T00:00:00Z","timestamp":1001894400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2001,10,1]],"date-time":"2001-10-01T00:00:00Z","timestamp":1001894400000},"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":[[2001,10]]},"DOI":"10.1023\/a:1012293814832","type":"journal-article","created":{"date-parts":[[2002,12,23]],"date-time":"2002-12-23T12:42:15Z","timestamp":1040647335000},"page":"493-544","source":"Crossref","is-referenced-by-count":27,"title":["Synthesizing Transformations for Locality Enhancement of Imperfectly-Nested Loop Nests"],"prefix":"10.1007","volume":"29","author":[{"given":"Nawaaz","family":"Ahmed","sequence":"first","affiliation":[]},{"given":"Nikolay","family":"Mateev","sequence":"additional","affiliation":[]},{"given":"Keshav","family":"Pingali","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"343504_CR1","doi-asserted-by":"crossref","unstructured":"C. Ancourt and F. Irigoin, Scanning Polyhedra with DO Loops, Principle and Practice of Parallel Progr., pp. 39 50 (April 1991).","DOI":"10.1145\/109626.109631"},{"key":"343504_CR2","doi-asserted-by":"crossref","unstructured":"E. Ayguad\u00e9 and Jordi Torres, Partitioning the Statement per Iteration Space Using Nonsingular Matrices, ACM Inter. Conf. Supercomputing, Tokyo, pp. 407-415, (July 1993).","DOI":"10.1145\/165939.166021"},{"key":"343504_CR3","unstructured":"Uptal Banerjee, A Theory of Loop Permutations, Languages and Compilers for Parallel Computing, pp. 54-74 (1989)."},{"issue":"2","key":"343504_CR4","first-page":"xx","volume":"22","author":"W. Li","year":"1994","unstructured":"Wei Li and Keshav Pingali, A Singular Loop Transformation Based on Nonsingular Matrices, IJPP, 22(2): xx-xx (April 1994).","journal-title":"IJPP"},{"issue":"2","key":"343504_CR5","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1016\/0743-7315(92)90027-K","volume":"16","author":"J. Ramanujam","year":"1992","unstructured":"J. Ramanujam and P. Sadayappan, Tiling multidimensional iteration spaces for multicomputers, J. Parallel Distributed Computing, 16(2):108-120 (October 1992).","journal-title":"J. Parallel Distributed Computing"},{"key":"343504_CR6","doi-asserted-by":"crossref","unstructured":"M. E. Wolf and M. S. Lam, A Data Locality Optimizing Algorithm, SIGPLAN Conf. Progr. Lang. Design and Implementation (June 1991).","DOI":"10.1145\/113445.113449"},{"key":"343504_CR7","unstructured":"Gene Golub and Charles Van Loan, Matrix Computations, The Johns Hopkins University Press (1996)."},{"key":"343504_CR8","unstructured":"Steve Carr and K. Kennedy, Compiler Blockability of Numerical Algorithms, Supercomputing (1992)."},{"key":"343504_CR9","doi-asserted-by":"crossref","unstructured":"Yonghong Song and Zhiyuan Li, New Tiling Techniques to Improve Cache Temporal Locality, SIGPLAN Conf. Progr. Lang. Design and Implementation (June 1999).","DOI":"10.1145\/301618.301668"},{"key":"343504_CR10","unstructured":"Induprakas Kodukula, Keshav Pingali, Robert Cox, and Dror Maydan, Imperfectly Nested Loop Transformations for Memory Hierarchy Management, Intern. Conf. Supercomputing, Rhodes, Greece (June 1999)."},{"key":"343504_CR11","first-page":"323","volume-title":"ACM Int. Conf. Supercomputing","author":"K. Kennedy","year":"1992","unstructured":"K. Kennedy and K. S. McKinley, Optimizing for Parallelism and Data Locality, ACM Int. Conf. Supercomputing, ACM Press, Washington, D.C., pp. 323-334 (July 1992)."},{"key":"343504_CR12","unstructured":"M. Wolfe, High Performance Compilers for Parallel Computing, Addison-Wesley Publishing Company (1995)."},{"key":"343504_CR13","doi-asserted-by":"crossref","unstructured":"Induprakas Kodukula, Nawaaz Ahmed, and Keshav Pingali, Data-Centric Multi-Level Blocking, Progr. Lang. Design and Implementation, ACM SIGPLAN (June 1997).","DOI":"10.1145\/258915.258946"},{"key":"343504_CR14","doi-asserted-by":"crossref","unstructured":"W. Li and K. Pingali, Access Normalization: Loop Restructuring for NUMA Compilers, ACM Trans. Computer Systems (1993).","DOI":"10.1145\/143365.143541"},{"key":"343504_CR15","doi-asserted-by":"crossref","unstructured":"William Pugh, Counting Solutions to Presburger Formulas: How and Why, Technical Report, University of Maryland (1993).","DOI":"10.1145\/178243.178254"},{"key":"343504_CR16","doi-asserted-by":"crossref","unstructured":"Phillipe Claus, Counting Solutions to Linear and Nonlinear Constraints Through Erhart Polynomials, ACM Int. Conf. Supercomputing, ACM (May 1996).","DOI":"10.1145\/237578.237617"},{"key":"343504_CR17","doi-asserted-by":"crossref","unstructured":"Stephanie Coleman and Kathryn S. McKinley, The Size Selection Using Cache Organization and Data Layout, ACM SIGPLAN conf. Progr. Lang. Design and Implementation (PLDI), ACM Press (June 1995).","DOI":"10.1145\/207110.207162"},{"key":"343504_CR18","first-page":"317","volume-title":"Proc. The 11th Int. Conf. Supercomputing (ICS-97)","author":"S. Ghosh","year":"1997","unstructured":"S. Ghosh, M. Martonosi, and S. Malik, Cache Miss Equations: An Analytical Representation of Cache Misses, Proc. The 11th Int. Conf. Supercomputing (ICS-97), ACM Press, New York, pp. 317-324 (July 1997)."},{"key":"343504_CR19","doi-asserted-by":"crossref","unstructured":"Monica S. Lam, Edward E. Rothberg, and Michael E. Wolf, The Cache Performance and Optimizations of Blocked Algorithms, Fourth Int. Conf. Architectural Support for Progr. Lang. Operat. Syst., pp. 63-74 (April 1991).","DOI":"10.1145\/106972.106981"},{"key":"343504_CR20","unstructured":"Michael E. Wolf, Dror E. Maydan, and Ding-Kai Chen, Combining Loop Transformations Considering Caches and Scheduling, Silicon Graphics, Mountain View, California, MICRO 29, pp. 274-286 (1996)."},{"key":"343504_CR21","unstructured":"S. Y. Kung, VLSI Array Processors, Prentice-Hall Inc. (1988)."},{"key":"343504_CR22","doi-asserted-by":"crossref","unstructured":"Paul Feautrier, Some Efficient Solutions to the Affine Scheduling Problem-Part II: Multi-Dimensional time, I. J. P. P. (December 1992).","DOI":"10.1007\/BF01379404"},{"key":"343504_CR23","first-page":"107","volume-title":"Proc. Seventh Int. Workshop of Lang. Compilers for Parallel Computing","author":"W. Kelly","year":"1994","unstructured":"Wayne Kelly and William Pugh, Finding Legal Reordering Transformations Using Mappings, Proc. Seventh Int. Workshop of Lang. Compilers for Parallel Computing, Springer-Verlag, Ithaca, New York, pp. 107-124 (August 1994)."},{"key":"343504_CR24","doi-asserted-by":"crossref","first-page":"445","DOI":"10.1016\/S0167-8191(98)00021-0","volume":"24","author":"A. Lim","year":"1998","unstructured":"Amy Lim and Monica Lam, Maximizing Parallelism and Minimizing Synchronization with Affine Partitions, Parallel Computing\n24:445-475 (1998).","journal-title":"Parallel Computing"},{"issue":"3","key":"343504_CR25","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1142\/S0129626494000211","volume":"4","author":"W. Kelly","year":"1994","unstructured":"Wayne Kelly and William Pugh, Selecting Affine Mappings Based on Performance Estimation, Parallel Processing Letters\n4(3):205-209 (September 1994).","journal-title":"Parallel Processing Letters"},{"key":"343504_CR26","doi-asserted-by":"crossref","unstructured":"William Pugh and Evan Rosser, Iteration Space Slicing for Locality, Proc. 12th Int. Workshop of Languages and Compilers for Parallel Computing (LCPC99) (August 1999).","DOI":"10.1007\/3-540-44905-1_11"},{"key":"343504_CR27","doi-asserted-by":"crossref","unstructured":"Nikolay Mateev, Keshav Pingali, Paul Stodghill, and Vladimir Kotlyar, Next-Generation Generic Programming and Its Application to Sparse Matrix Computations, Proc. Int. Conf. Supercomputing, Santa Fe, New Mexico (May 2000).","DOI":"10.1145\/335231.335240"},{"key":"343504_CR28","doi-asserted-by":"crossref","unstructured":"Nawaaz Ahmed, Nikolay Mateev, Keshav Pingali and Paul Stodghill, A Framework for Sparse Matrix Code Synthesis from High-Level Specifications, Proc. SC2000, Dallas, Texas (November 2000).","DOI":"10.1109\/SC.2000.10033"},{"key":"343504_CR29","doi-asserted-by":"crossref","unstructured":"S. Chaterjee, V. Jain, A. Lebeck, S. Mundhra, and M. Thottethodi, Nonlinear Array Layouts for Hierarchical Memory Systems, Int. Conf. On Supercomputing (ICS'99) (June 1999).","DOI":"10.1145\/305138.305231"},{"issue":"6","key":"343504_CR30","doi-asserted-by":"crossref","first-page":"737","DOI":"10.1147\/rd.416.0737","volume":"41","author":"F. G. Gustavson","year":"1997","unstructured":"F. G. Gustavson, Recursion Leads to Automatic Variable Blocking for Dense Linear-Algebra Algorithms, IBM J. Res. Dev.\n41(6):737-755 (November 1997).","journal-title":"IBM J. Res. Dev."},{"key":"343504_CR31","doi-asserted-by":"crossref","unstructured":"Nawaaz Ahmed and Keshav Pingali, Automatic Generation of Block-Recursive Codes, Proc Euro-Par, Munich, Germany (August\/September 2000).","DOI":"10.1007\/3-540-44520-X_48"},{"key":"343504_CR32","unstructured":"Qing Yi, Vikram Adve, and Ken Kennedy, Transforming Loops to Recursion for Multi-Level Memory Hierarchies, Proc. ACM Sympos. Progr. Lang. Design and Implementation, Vancouver, Canada (June 2000)."},{"key":"343504_CR33","doi-asserted-by":"crossref","unstructured":"Nikolay Mateev, Vijay Menon, and Keshav Pingali, Left-Looking to Right-Looking and Vice Versa: An Application of Fractal Symbolic Analysis to Linear Algebra Code Restructuring, Proc. Euro-Par, Munich, Germany (August\/September 2000).","DOI":"10.1007\/3-540-44520-X_49"},{"key":"343504_CR34","doi-asserted-by":"crossref","unstructured":"Nikolay Mateev, Vijay Menon, and Keshav Pingali, Fractal Symbolic Analysis for Program Transformations, ACM Int. Conf. Supercomputing (ICS), ACM (June 2001).","DOI":"10.1145\/377792.377804"}],"container-title":["International Journal of Parallel Programming"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1012293814832.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1023\/A:1012293814832\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1012293814832.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T08:39:24Z","timestamp":1748335164000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1023\/A:1012293814832"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2001,10]]},"references-count":34,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2001,10]]}},"alternative-id":["343504"],"URL":"https:\/\/doi.org\/10.1023\/a:1012293814832","relation":{},"ISSN":["0885-7458","1573-7640"],"issn-type":[{"type":"print","value":"0885-7458"},{"type":"electronic","value":"1573-7640"}],"subject":[],"published":{"date-parts":[[2001,10]]}}}