{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T23:16:46Z","timestamp":1725664606514},"publisher-location":"Berlin, Heidelberg","reference-count":30,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540633716"},{"type":"electronic","value":"9783540695257"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[1997]]},"DOI":"10.1007\/3-540-63371-5_10","type":"book-chapter","created":{"date-parts":[[2012,2,26]],"date-time":"2012-02-26T23:23:57Z","timestamp":1330298637000},"page":"83-93","source":"Crossref","is-referenced-by-count":1,"title":["Estimating the parallel start-up overhead for parallelizing compilers"],"prefix":"10.1007","author":[{"given":"Rizos","family":"Sakellariou","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2005,6,9]]},"reference":[{"key":"10_CR1","first-page":"483","volume":"30","author":"G. Amdahl","year":"1967","unstructured":"G. Amdahl. Validity of the single-processor approach to achieving large scale computing capabilities. AFIPS Conference Proceedings, 30, 1967, pp. 483\u2013485.","journal-title":"AFIPS Conference Proceedings"},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"U. Banerjee. Loop Transformations for Restructuring Compilers: The Foundations. Kluwer Academic Publishers, 1993.","DOI":"10.1007\/b102311"},{"issue":"2","key":"10_CR3","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1109\/5.214548","volume":"81","author":"U. Banerjee","year":"1993","unstructured":"U. Banerjee, R. Eigenmann, A. Nicolau, and D. Padua. Automatic Program Parallelization. Proceedings of the IEEE, 81(2), Feb. 1993, pp. 211\u2013243.","journal-title":"Proceedings of the IEEE"},{"issue":"12","key":"10_CR4","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1109\/2.546612","volume":"29","author":"W. Blume","year":"1996","unstructured":"W. Blume, R. Doallo, R. Eigenmann, J. Grout, J. Hoeflinger, T. Lawrence, J. Lee, D. Padua, Y. Paek, B. Pottenger, L. Rauchwerger, and P. Tu. Parallel Programming with Polaris. IEEE Computer, 29(12), Dec. 1996, pp. 78\u201382.","journal-title":"IEEE Computer"},{"issue":"6","key":"10_CR5","doi-asserted-by":"crossref","first-page":"643","DOI":"10.1109\/71.180621","volume":"3","author":"W. Blume","year":"1992","unstructured":"uW. Blume and R. Eigenmann. Performance Analysis of Parallelizing Compilers on the Perfect Benchmarks Programs. IEEE Transactions on Parallel and Distributed Systems, 3(6), Nov. 1992, pp. 643\u2013656.","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"F. Bodin and M. O'Boyle. A Compiler Strategy for Shared Virtual Memories. In B. K. Szymanski and B. Sinharoy (Eds.), Languages, Compilers and Run-Time Systems for Scalable Computers, Kluwer Academic Publishers, 1996, pp. 57\u201369.","DOI":"10.1007\/978-1-4615-2315-4_5"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"F. Bodin, D. Windheiser, W. Jalby, D. Atapattu, M. Lee, and D. Gannon. Performance Evaluation and Prediction for Parallel Algorithms on the BBN GP1000. In Proceedings of the 1990 International Conference on Supercomputing, ACM Press, pp. 401\u2013413.","DOI":"10.1145\/77726.255182"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"J. M. Bull. A hierarchical classification of overheads in parallel programs. In I. Jelly, I. Gorton and P. Croll (Eds.), Software Engineering for Parallel and Distributed Systems, Chapman & Hall, 1996, pp. 208\u2013219.","DOI":"10.1007\/978-0-387-34984-8_18"},{"issue":"5","key":"10_CR9","doi-asserted-by":"crossref","first-page":"725","DOI":"10.1109\/12.24274","volume":"38","author":"H. Burkhart","year":"1989","unstructured":"H. Burkhart and R. Millen. Performance-Measurement Tools in a Multiprocessor Environment. IEEE Transactions on Computers, 38(5), May 1989, pp. 725\u2013737.","journal-title":"IEEE Transactions on Computers"},{"issue":"3","key":"10_CR10","doi-asserted-by":"crossref","first-page":"286","DOI":"10.1016\/0743-7315(91)90076-L","volume":"13","author":"E. A. Carmona","year":"1991","unstructured":"E. A. Carmona and M. D. Rice. Modeling the Serial and Parallel Fractions of a Parallel Algorithm. Journal of Parallel and Distributed Computing, 13(3), Nov. 1991, pp. 286\u2013298.","journal-title":"Journal of Parallel and Distributed Computing"},{"key":"10_CR11","unstructured":"M. E. Crovella and T. J. LeBlanc. Parallel Performance Prediction Using Lost Cycles Analysis. In Proceedings of Supercomputing '94, (Washington D. C., Nov. 1994), IEEE Computer Society Press, pp. 600\u2013609."},{"issue":"1","key":"10_CR12","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1006\/jpdc.1995.1026","volume":"25","author":"M. A. Driscoll","year":"1995","unstructured":"M. A. Driscoll and uW. R. Daasch. Accurate Predictions of Parallel Program Execution Time. Journal of Parallel and Distributed Computing, 25(1), Feb. 1995, pp. 16\u201330.","journal-title":"Journal of Parallel and Distributed Computing"},{"issue":"11","key":"10_CR13","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1109\/2.471179","volume":"28","author":"T. Fahringer","year":"1995","unstructured":"T. Fahringer. Estimating and Optimizing Performance for Parallel Programs. IEEE Computer, 28( 11), Nov. 1995, pp. 47\u201356.","journal-title":"IEEE Computer"},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"T. Fahringer. Estimating Cache Performance for Sequential and Data Parallel Programs. In B. Hertzberger and P. Sloot (Eds.), High-Performance Computing and Networking, Springer-Verlag, Lecture Notes in Computer Science 1225, 1997, pp. 840\u2013849.","DOI":"10.1007\/BFb0031655"},{"key":"10_CR15","unstructured":"T. L. Freeman and C. Phillips. Parallel Numerical Algorithms. Prentice Hall International, 1992."},{"key":"10_CR16","unstructured":"D. Grunwald and S. Vajracharya. Efficient Barriers for Distributed Shared Memory Computers. Technical Report CU-CS-703-94-93, Department of Computer Science, University of Colorado, Sep. 1993."},{"issue":"8","key":"10_CR17","doi-asserted-by":"crossref","first-page":"1161","DOI":"10.1016\/0167-8191(94)90073-6","volume":"20","author":"N. J. Higham","year":"1994","unstructured":"N. J. Higham and P. Papadimitriou. A parallel algorithm for computing the polar decomposition. Parallel Computing, 20(8), 1994, pp. 1161\u20131173.","journal-title":"Parallel Computing"},{"key":"10_CR18","unstructured":"T. Mavroudakis. Parallelisation of the Barotropic Model for Numerical Weather Prediction. MSc Thesis, Department of Mathematics, University of Manchester, 1996."},{"issue":"1","key":"10_CR19","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1155\/1996\/141895","volume":"5","author":"M. F. P. O'Boyle","year":"1996","unstructured":"M. F. P. O'Boyle and J. M. Bull. Expert Programmer versus Parallelizing Compiler: A Comparative Study of Two Approaches for Distributed Shared Memory. Scientific Programming, 5(1), Spring 1996, pp. 63\u201388.","journal-title":"Scientific Programming"},{"key":"10_CR20","unstructured":"P. Papadimitriou. Parallel Solution of SVD-Related Problems, with Applications. PhD Thesis, Department of Mathematics, University of Manchester, 1993."},{"issue":"l","key":"10_CR21","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1109\/88.481665","volume":"4","author":"M. Parashar","year":"1996","unstructured":"M. Parashar and S. Hariri. Compile-Time Performance Prediction of HPF\/Fortran 90D. IEEE Parallel & Distributed Technology, 4(l), Spring 1996, pp. 57\u201373.","journal-title":"IEEE Parallel & Distributed Technology"},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"C. D. Polychronopoulos, M. B. Girkar, M. R. Haghighat, C. L. Lee, B. P. Leung, and D. A. Schouten. Parafrase-2: An environment for parallelizing, partitioning, synchronizing and scheduling programs on multiprocessors. In Proceedings of the 1989 International Conference on Parallel Processing (Vol. II Software), The Pennsylvania State University Press, pp. 39\u201348.","DOI":"10.1142\/S0129053389000044"},{"key":"10_CR23","doi-asserted-by":"crossref","unstructured":"G. D. Riley, J. M. Bull, and J. R. Gurd. Performance Improvement Through Overhead Analysis: A Case Study in Molecular Dynamics. In Proceedings of the 1997 International Conference on Supercomputing, ACM Press.","DOI":"10.1145\/263580.263589"},{"key":"10_CR24","unstructured":"R. Sakellariou. On the Quest for Perfect Load Balance in Loop-Based Parallel Computations. PhD Thesis, Department of Computer Science, University of Manchester, 1996."},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"R. Sakellariou and J. R. Gurd. Compile-Time Minimisation of Load Imbalance in Loop Nests. In Proceedings of the 1997 International Conference on Supercomputing, ACM Press.","DOI":"10.1145\/263580.263811"},{"key":"10_CR26","doi-asserted-by":"crossref","unstructured":"E. A. St\u00f6hr and M. F. P. O'Boyle. A Graph Based Approach to Barrier Synchronisation Minimisation. In Proceedings of the 1997 International Conference on Supercomputing, ACM Press.","DOI":"10.1145\/263580.263624"},{"issue":"2","key":"10_CR27","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1016\/0167-739X(94)00064-L","volume":"11","author":"L. Vuurpijl","year":"1995","unstructured":"L. Vuurpijl, T. Schouten, and J. Vytopil. Performance Prediction of Large MIMD Systems for Parallel Neural Network Simulations. Future Generation Computer Systems, 11(2), Mar. 1995, pp. 221\u2013232.","journal-title":"Future Generation Computer Systems"},{"key":"10_CR28","unstructured":"M. Wolfe. High Performance Compilers for Parallel Computing. Addison-Wesley, 1996."},{"issue":"l","key":"10_CR29","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1109\/88.281875","volume":"2","author":"X. Zhang","year":"1994","unstructured":"X. Zhang, R. Casta\u00f1eda, and E. W. Chan. Spin-Lock Synchronization on the Butterfly and KSR1 IEEE Parallel & Distributed Technology, 2(l), Spring 1994, pp. 51\u201363.","journal-title":"IEEE Parallel & Distributed Technology"},{"key":"10_CR30","unstructured":"H. Zima and B. Chapman. Supercompilers for Parallel and Vector Computers. ACM Press & Addison-Wesley, 1990."}],"container-title":["Lecture Notes in Computer Science","Parallel Computing Technologies"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/3-540-63371-5_10.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,17]],"date-time":"2020-11-17T21:18:10Z","timestamp":1605647890000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/3-540-63371-5_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1997]]},"ISBN":["9783540633716","9783540695257"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/3-540-63371-5_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[1997]]}}}