{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,5]],"date-time":"2025-04-05T04:04:12Z","timestamp":1743825852643,"version":"3.40.3"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2012,7,17]],"date-time":"2012-07-17T00:00:00Z","timestamp":1342483200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int J Parallel Prog"],"published-print":{"date-parts":[[2013,2]]},"DOI":"10.1007\/s10766-012-0203-z","type":"journal-article","created":{"date-parts":[[2012,7,16]],"date-time":"2012-07-16T09:53:48Z","timestamp":1342432428000},"page":"1-58","source":"Crossref","is-referenced-by-count":2,"title":["Minimal Unroll Factor for Code Generation of Software Pipelining"],"prefix":"10.1007","volume":"41","author":[{"given":"Mounira","family":"Bachir","sequence":"first","affiliation":[]},{"given":"Sid-Ahmed-Ali","family":"Touati","sequence":"additional","affiliation":[]},{"given":"Frederic","family":"Brault","sequence":"additional","affiliation":[]},{"given":"David","family":"Gregg","sequence":"additional","affiliation":[]},{"given":"Albert","family":"Cohen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2012,7,17]]},"reference":[{"issue":"10","key":"203_CR1","doi-asserted-by":"crossref","first-page":"1242","DOI":"10.1109\/TC.2005.167","volume":"54","author":"A. Darte","year":"2005","unstructured":"Darte A., Schreiber R., Villard G.: Lattice-based memory allocation. IEEE Trans. Comput. 54(10), 1242\u20131257 (2005)","journal-title":"IEEE Trans. Comput."},{"key":"203_CR2","doi-asserted-by":"crossref","unstructured":"Bachir, M., Touati, S.-A.-A., Cohen, A.: Post-pass periodic register allocation to minimise loop unrolling degree. In: LCTES \u201908: Proceedings of the 2008 ACM SIGPLAN-SIGBED Conference on Languages, Compilers, and Tools for Embedded Systems, pp. 141\u2013150. ACM, New York, NY, USA (2008)","DOI":"10.1145\/1375657.1375677"},{"key":"203_CR3","unstructured":"Bachir, M., Touati, S.-A.-A., Cohen, A.: Decomposing meeting graph circuits to minimise kernel loop unrolling. In: 9th Workshop on Optimizations for DSP and Embedded Systems (ODES\u201911, associated with CGO), Chamonix, France, April (2011)"},{"key":"203_CR4","doi-asserted-by":"crossref","unstructured":"Bastoul, C\u00e9dric: Code generation in the polyhedral model is easier than you think. In: PACT\u201913 IEEE International Conference on Parallel Architecture and Compilation Techniques, pp. 7\u201316. Juan-les-Pins, France, September (2004)","DOI":"10.1109\/PACT.2004.1342537"},{"key":"203_CR5","doi-asserted-by":"crossref","unstructured":"Beno\u00eet Dupont de Dinechin: A unified software pipeline construction scheme for modulo scheduled loops. In: PaCT \u201997: Proceedings of the 4th International Conference on Parallel Computing Technologies, pp. 189\u2013200. Springer, London, UK (1997)","DOI":"10.1007\/3-540-63371-5_20"},{"issue":"2\u20133","key":"203_CR6","first-page":"191","volume":"93","author":"W. Dominique de","year":"1999","unstructured":"Dominique de W., Christine E., Sylvain L., Bruno M.: On a graph-theoretical model for cyclic register allocation. Discret. Appl. Math. 93(2\u20133), 191\u2013203 (1999)","journal-title":"Discret. Appl. Math."},{"key":"203_CR7","doi-asserted-by":"crossref","unstructured":"Dehnert, J.C., Hsu Peter, Y.-T., Bratt J.P.: Overlapped loop support in the Cydra~5. In: ASPLOS-III: Proceedings of the Third International Conference on Architectural Support for Programming Languages and Operating Systems, pp. 26\u201338. ACM, New York, NY, USA (1989)","DOI":"10.1145\/70082.68185"},{"issue":"1-2","key":"203_CR8","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1007\/BF01205184","volume":"7","author":"J.C. Dehnert","year":"1993","unstructured":"Dehnert J.C., Towle R.A.: Compiling for the Cydra 5. J. Supercomput. 7(1-2), 181\u2013227 (1993)","journal-title":"J. Supercomput."},{"key":"203_CR9","unstructured":"Eisenbeis, C., Lelait, S.: LoRA a Package for Loop Optimal Register Allocation. Technical report, INRIA, France (1999)"},{"key":"203_CR10","unstructured":"Eisenbeis, C., Lelait S., Marmol B.: The meeting graph: a new model for loop cyclic register allocation. In: PACT \u201995: Proceedings of the IFIP WG10.3 Working Conference on Parallel Architectures and Compilation Techniques, pp. 264\u2013267. IFIP Working Group on Algol, Manchester, UK (1995)"},{"key":"203_CR11","doi-asserted-by":"crossref","unstructured":"Faraboschi,P., Brown, G., Fisher,J. A., Desoli,G., Homewood F.: Lx: a technology platform for customizable VLIW embedded processing. In: ISCA \u201900: Proceedings of the 27th Annual International Symposium on Computer Architecture, pp. 203\u2013213. ACM, New York, NY, USA (2000)","DOI":"10.1145\/339647.339682"},{"key":"203_CR12","volume-title":"Embedded Computing: A VLIW Approach to Architecture, Compilers and Tools","author":"J.A. Fisher","year":"2005","unstructured":"Fisher J.A., Faraboschi P., Young C.: Embedded Computing: A VLIW Approach to Architecture, Compilers and Tools. Morgan Kaufmann Publishers, San Francisco, CA (2005)"},{"key":"203_CR13","doi-asserted-by":"crossref","unstructured":"Hendren, L., Gao, G. R., Altman, E. R., Mukerji, C.: A register allocation framework based on hierarchical cyclic interval graphs. In: CC \u201992: Proceedings of the 4th International Conference on Compiler Construction, pp 176\u2013191. Springer, London, UK (1992)","DOI":"10.1007\/3-540-55984-1_17"},{"key":"203_CR14","doi-asserted-by":"crossref","unstructured":"Howgrave-Graham, N.: Approximate integer common divisors. In: Cryptography and Lattices, International Conference (CaLC), volume 2146 of Lecture Notes in Computer Science, pp. 51\u201366 (2001)","DOI":"10.1007\/3-540-44670-2_6"},{"issue":"6","key":"203_CR15","doi-asserted-by":"crossref","first-page":"258","DOI":"10.1145\/173262.155115","volume":"28","author":"R.A. Huff","year":"1993","unstructured":"Huff R.A.: Lifetime-sensitive modulo scheduling. SIGPLAN Not. 28(6), 258\u2013267 (1993)","journal-title":"SIGPLAN Not."},{"issue":"7","key":"203_CR16","doi-asserted-by":"crossref","first-page":"318","DOI":"10.1145\/960116.54022","volume":"23","author":"L. Monica","year":"1988","unstructured":"Monica L.: Software pipelining: an effective scheduling technique for VLIW machines. SIGPLAN Not. 23(7), 318\u2013328 (1988)","journal-title":"SIGPLAN Not."},{"key":"203_CR17","doi-asserted-by":"crossref","unstructured":"Nicolau, A., Potasman, R., Wang, H.: Register allocation, renaming and their impact on fine-grain parallelism. In: Proceedings of the Fourth International Workshop on Languages and Compilers for Parallel Computing, pp. 218\u2013235. Springer, London, UK (1992)","DOI":"10.1007\/BFb0038667"},{"issue":"2","key":"203_CR18","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1109\/12.73588","volume":"40","author":"K.K. Parhi","year":"1991","unstructured":"Parhi K.K., Messerschmitt D.G.: Static rate-optimal scheduling of iterative data-flow programs via optimum unfolding. Trans. Comput. 40(2), 178\u2013195 (1991)","journal-title":"Trans. Comput."},{"key":"203_CR19","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1145\/1014192.802449","volume":"12","author":"B.R. Rau","year":"1981","unstructured":"Rau B.R., Glaeser C.D.: Some scheduling techniques and an easily schedulable horizontal architecture for high performance scientific computing. SIGMICRO Newsl. 12, 183\u2013198 (1981)","journal-title":"SIGMICRO Newsl."},{"key":"203_CR20","doi-asserted-by":"crossref","unstructured":"Rau, B.R., Schlansker, M.S., Timmalai P.P.: Code generation schema for modulo scheduled loops. In: Proceedings of the 25th Annual International Symposium on Microarchitecture, pp. 158\u2013169. (1992)","DOI":"10.1109\/MICRO.1992.697012"},{"issue":"4","key":"203_CR21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1377492.1377498","volume":"30","author":"H. Rong","year":"2008","unstructured":"Rong H., Douillet A., Gao G.R.: Register allocation for software pipelined multidimensional loops. ACM Trans. Program. Lang. Syst. 30(4), 1\u201368 (2008)","journal-title":"ACM Trans. Program. Lang. Syst."},{"key":"203_CR22","unstructured":"Schlansker, M., Rau, B., Mahlke, S.: Achieving High Levels of Instruction-Level Parallelism with Reduced Hardware Complexity. Technical Report HPL-96-120, Hewlett Packard (1994)"},{"key":"203_CR23","unstructured":"ST231 Core and Instruction Set Architecture Manual (2005)"},{"key":"203_CR24","doi-asserted-by":"crossref","unstructured":"Touati, S.-A.-A., Brault, F., Deschinkel, K., de~Dinechin, B.D.: Efficient Spilling Reduction for Software Pipelined Loops in Presence of Multiple Register Types in Embedded VLIW Processors. ACM Trans. Embed. Comput. Syst. 10(4) (2011)","DOI":"10.1145\/2043662.2043671"},{"issue":"2","key":"203_CR25","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1142\/S012962640400188X","volume":"14","author":"S.-A.-A. Touati","year":"2004","unstructured":"Touati S.-A.-A., Eisenbeis C.: Early periodic register allocation on ILP processors. Parallel Process. Lett. 14(2), 287\u2013313 (2004)","journal-title":"Parallel Process. Lett."},{"key":"203_CR26","doi-asserted-by":"crossref","unstructured":"Vasilache N., Bastoul, C., Cohen, A.: Polyhedral code generation in the real world. In: Proceedings of the International Conference on Compiler Construction (ETAPS CC\u201906), LNCS 3923, pp. 185\u2013201. Springer, Vienna, Austria (2006)","DOI":"10.1007\/11688839_16"},{"issue":"3","key":"203_CR27","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1007\/BF02577737","volume":"22","author":"J. Wang","year":"1994","unstructured":"Wang J., Eisenbeis C., Jourdan M., Su B.: Decomposed software pipelining: a new perspective and a new approach. Int. J. Parallel Program. 22(3), 351\u2013373 (1994)","journal-title":"Int. J. Parallel Program."}],"container-title":["International Journal of Parallel Programming"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-012-0203-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10766-012-0203-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-012-0203-z","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T06:23:38Z","timestamp":1743747818000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10766-012-0203-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,7,17]]},"references-count":27,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2013,2]]}},"alternative-id":["203"],"URL":"https:\/\/doi.org\/10.1007\/s10766-012-0203-z","relation":{},"ISSN":["0885-7458","1573-7640"],"issn-type":[{"type":"print","value":"0885-7458"},{"type":"electronic","value":"1573-7640"}],"subject":[],"published":{"date-parts":[[2012,7,17]]}}}