{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T17:44:34Z","timestamp":1771955074150,"version":"3.50.1"},"publisher-location":"Berlin, Heidelberg","reference-count":30,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783540929895","type":"print"},{"value":"9783540929901","type":"electronic"}],"license":[{"start":{"date-parts":[[2009,1,1]],"date-time":"2009-01-01T00:00:00Z","timestamp":1230768000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009]]},"DOI":"10.1007\/978-3-540-92990-1_8","type":"book-chapter","created":{"date-parts":[[2008,12,23]],"date-time":"2008-12-23T11:36:15Z","timestamp":1230032175000},"page":"80-94","source":"Crossref","is-referenced-by-count":8,"title":["Software Pipelining in Nested Loops with Prolog-Epilog Merging"],"prefix":"10.1007","author":[{"given":"Mohammed","family":"Fellahi","sequence":"first","affiliation":[]},{"given":"Albert","family":"Cohen","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"8_CR1","volume-title":"Optimizing Compilers for Modern Architectures","author":"R. Allen","year":"2002","unstructured":"Allen, R., Kennedy, K.: Optimizing Compilers for Modern Architectures. Morgan Kaufman, San Francisco (2002)"},{"key":"8_CR2","series-title":"Software Technology and Architecture","volume-title":"Proceedings of the 29th Hawaii Intl. Conf. on System Sciences (HICSS 1996)","author":"S. Carr","year":"1996","unstructured":"Carr, S., Ding, C., Sweany, P.: Improving software pipelining with unroll-and-jam. In: Proceedings of the 29th Hawaii Intl. Conf. on System Sciences (HICSS 1996). Software Technology and Architecture, vol.\u00a01. IEEE, Los Alamitos (1996)"},{"issue":"4","key":"8_CR3","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1145\/115372.115320","volume":"13","author":"R. Cytron","year":"1991","unstructured":"Cytron, R., Ferrante, J., Rosen, B.K., Wegman, M.N., Zadeck, F.K.: Efficiently computing static single assignment form and the control dependence graph. ACM Trans. on Programming Languages and Systems\u00a013(4), 451\u2013490 (1991)","journal-title":"ACM Trans. on Programming Languages and Systems"},{"issue":"5","key":"8_CR4","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1023\/A:1007506711786","volume":"28","author":"A. Darte","year":"2000","unstructured":"Darte, A., Huard, G.: Loop shifting for loop parallelization. Intl. J. of Parallel Programming\u00a028(5), 499\u2013534 (2000)","journal-title":"Intl. J. of Parallel Programming"},{"issue":"4","key":"8_CR5","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1142\/S0129626497000383","volume":"7","author":"A. Darte","year":"1997","unstructured":"Darte, A., Silber, G.-A., Vivien, F.: Combining Retiming and Scheduling Techniques for Loop Parallelization and Loop Tiling. Parallel Processing Letters\u00a07(4), 379\u2013392 (1997)","journal-title":"Parallel Processing Letters"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Dehnert, J.C., Hsu, P.Y., Bratt, J.P.: Overlapped loop support in the Cydra 5. In: Intl Conf. on Architectural Support for Programming Languages and Operating Systems (ASPLOS 1989), pp. 26\u201338 (April 1989)","DOI":"10.1145\/70082.68185"},{"key":"8_CR7","unstructured":"Dulong, C., Krishnaiyer, R., Kulkarni, D., Lavery, D., Li, W., Ng, J., Sehr, D.: An overview of the Intel IA-64 compiler. Intel. Technical Journal\u00a0Q4 (1999)"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Feautrier, P.: Array expansion. In: Intl. Conf. on Supercomputing (ICS 1988), St. Malo, France, pp. 429\u2013441 (July 1988)","DOI":"10.1145\/55364.55406"},{"issue":"6","key":"8_CR9","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1007\/BF01379404","volume":"21","author":"P. Feautrier","year":"1992","unstructured":"Feautrier, P.: Some efficient solutions to the affine scheduling problem, part I, multidimensional time. Intl. J. of Parallel Programming\u00a021(6), 315\u2013348 (1992)","journal-title":"Intl. J. of Parallel Programming"},{"key":"8_CR10","volume-title":"Parallel Architectures and Compilation Techniques (PACT 1999)","author":"P. Feautrier","year":"1999","unstructured":"Feautrier, P., Griebl, M., Lengauer, C.: On index set splitting. In: Parallel Architectures and Compilation Techniques (PACT 1999). IEEE Computer Society, Los Alamitos (1999)"},{"issue":"1","key":"8_CR11","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1145\/200994.201003","volume":"17","author":"M.P. Gerlek","year":"1995","unstructured":"Gerlek, M.P., Stoltz, E., Wolfe, M.J.: Beyond induction variables: detecting and classifying sequences using a demand-driven ssa form. ACM Trans. on Programming Languages and Systems\u00a017(1), 85\u2013122 (1995)","journal-title":"ACM Trans. on Programming Languages and Systems"},{"key":"#cr-split#-8_CR12.1","doi-asserted-by":"crossref","unstructured":"Girbal, S., Vasilache, N., Bastoul, C., Cohen, A., Parello, D., Sigler, M., Temam, O.: Semi-automatic composition of loop transformations for deep parallelism and memory hierarchies. Intl. J. of Parallel Programming, 57 (2006);","DOI":"10.1007\/s10766-006-0012-3"},{"key":"#cr-split#-8_CR12.2","unstructured":"Special issue on Microgrids"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Karczmarek, M., Thies, W., Amarasinghe, S.: Phased scheduling of stream programs. In: LCTES 2003 (June 2003)","DOI":"10.1145\/780732.780747"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Lam, M.S.: Software pipelining: An effective scheduling technique for vliw machines. In: ACM Principles, Logics, and Implementations of High-Level Programming Languages (1988)","DOI":"10.1145\/53990.54022"},{"issue":"1","key":"8_CR15","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1007\/BF01759032","volume":"6","author":"C.E. Leiserson","year":"1991","unstructured":"Leiserson, C.E., Saxe, J.B.: Retiming synchronous circuitry. Algorithmica\u00a06(1), 5\u201335 (1991)","journal-title":"Algorithmica"},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Maydan, D.E., Amarasinghe, S.P., Lam, M.S.: Array dataflow analysis and its use in array privatization. In: Principles of Programming Languages (PoPL 1993), Charleston, South Carolina, pp. 2\u201315 (January 1993)","DOI":"10.1145\/158511.158515"},{"issue":"4","key":"8_CR17","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1145\/233561.233564","volume":"18","author":"K. McKinley","year":"1996","unstructured":"McKinley, K., Carr, S., Tseng, C.-W.: Improving data locality with loop transformations. ACM Transactions on Programming Languages and Systems\u00a018(4), 424\u2013453 (1996)","journal-title":"ACM Transactions on Programming Languages and Systems"},{"key":"8_CR18","doi-asserted-by":"crossref","unstructured":"McNairy, C., Soltis, D.: Itanium 2 processor microarchitecture. IEEE Micro., 44\u201355 (March 2003)","DOI":"10.1109\/MM.2003.1196114"},{"key":"8_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45306-7_12","volume-title":"Compiler Construction","author":"K. Muthukumar","year":"2001","unstructured":"Muthukumar, K., Doshi, G.: Software pipelining of nested loops. In: Wilhelm, R. (ed.) CC 2001. LNCS, vol.\u00a02027. Springer, Heidelberg (2001)"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Parra-Hermandez, R., Dimopoulos, N.J.: A new heuristic for solving the multichoice multidimensional knapsack problem. IEEE Transactions on Systems, Man, and Cybernetics \u2014 Part A: Systems and Humans\u00a035(5) (September 2005)","DOI":"10.1109\/TSMCA.2005.851140"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Petkov, D., Harr, R.E., Amarasinghe, S.P.: Efficient pipelining of nested loops: Unroll-and-squash. In: Proc. of the 16th Intl. Parallel and Distributed Processing Symp. (IPDPS 2002), Washington, DC (2002)","DOI":"10.1109\/IPDPS.2002.1015491"},{"key":"8_CR22","unstructured":"Puchinger, J., Raidl, G.R., Pfershy, U.: The multidimensional knapsack problem: Structure and algorithms. Technical Report No. 006149 INFORMS Journal of Computing (March 2007)"},{"key":"8_CR23","doi-asserted-by":"crossref","unstructured":"Ramanujam, J.: Optimal software pipelining of nested loops. In: International Symposium on Parallel Processing, Washington, D.C, pp. 335\u2013342 (1994)","DOI":"10.1109\/IPPS.1994.288280"},{"key":"8_CR24","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1145\/192724.192731","volume-title":"MICRO 27: Proceedings of the 27th annual international symposium on Microarchitecture","author":"B.R. Rau","year":"1994","unstructured":"Rau, B.R.: Iterative modulo scheduling: an algorithm for software pipelining loops. In: MICRO 27: Proceedings of the 27th annual international symposium on Microarchitecture, pp. 63\u201374. ACM Press, New York (1994)"},{"key":"8_CR25","unstructured":"Rong, H., Tang, Z., Govindarajan, R., Douillet, A., Gao, G.R.: Code generation for single-dimension software pipelining for multi-dimensional loops. In: Proceedings of the International Symposium on Code generation and Optimization(CGO 2004), pp. 175\u2013186 (March 2004)"},{"key":"8_CR26","unstructured":"Rong, H., Tang, Z., Govindarajan, R., Douillet, A., Gao, G.R.: Single-dimension software pipelining for multi-dimensional loops. In: Proceedings of the International Symposium on Code generation and Optimization(CGO 2004), pp. 163\u2013184 (2004)"},{"key":"8_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1007\/3-540-36579-6_2","volume-title":"Compiler Construction","author":"S. Touati","year":"2003","unstructured":"Touati, S., Eisenbeis, C.: Early Control of Register Pressure for Software Pipelined Loops. In: Hedin, G. (ed.) CC 2003. LNCS, vol.\u00a02622, pp. 17\u201332. Springer, Heidelberg (2003)"},{"key":"8_CR28","series-title":"Lecture Notes in Computer Science","volume-title":"Parallel Computing Technologies","author":"N. Vasilache","year":"2007","unstructured":"Vasilache, N., Cohen, A., Pouchet, L.-N.: Automatic correction of loop transformations. In: Malyshkin, V.E. (ed.) PaCT 2007. LNCS, vol.\u00a04671. Springer, Heidelberg (2007)"},{"key":"8_CR29","doi-asserted-by":"crossref","unstructured":"Verdoolaege, S., Bruynooghe, M., Janssens, G., Catthoor, F.: Multi-dimentsional incremetal loops fusion for data locality. In: ASAP, pp. 17\u201327 (2003)","DOI":"10.1109\/ASAP.2003.1212826"}],"container-title":["Lecture Notes in Computer Science","High Performance Embedded Architectures and Compilers"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-92990-1_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T10:24:49Z","timestamp":1738837489000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-92990-1_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009]]},"ISBN":["9783540929895","9783540929901"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-92990-1_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2009]]}}}