{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,19]],"date-time":"2025-03-19T10:48:51Z","timestamp":1742381331870},"publisher-location":"Berlin, Heidelberg","reference-count":32,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540575023"},{"type":"electronic","value":"9783540482017"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[1993]]},"DOI":"10.1007\/3-540-57502-2_38","type":"book-chapter","created":{"date-parts":[[2012,2,26]],"date-time":"2012-02-26T13:03:29Z","timestamp":1330261409000},"page":"31-48","source":"Crossref","is-referenced-by-count":13,"title":["Using profile information to assist advanced compiler optimization and scheduling"],"prefix":"10.1007","author":[{"given":"W.","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"R.","family":"Bringmann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S.","family":"Mahlke","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S.","family":"Anik","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"T.","family":"Kiyohara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"N.","family":"Warter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"D.","family":"Lavery","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"W. -M.","family":"Hwu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"R.","family":"Hank","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J.","family":"Gyllenhaal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2005,6,3]]},"reference":[{"key":"3_CR1","volume-title":"Compilers: Principles, Techniques, and Tools","author":"A. Aho","year":"1986","unstructured":"A. Aho, R. Sethi, and J. Ullman, Compilers: Principles, Techniques, and Tools. Reading, MA: Addison-Wesley, 1986."},{"issue":"2","key":"3_CR2","doi-asserted-by":"crossref","first-page":"396","DOI":"10.1145\/17356.17402","volume":"14","author":"S. McFarling","year":"1986","unstructured":"S. McFarling and J. Hennessy, \u201cReducing the cost of branches,\u201d in Proceedings of the 13th International Symposium on Computer Architecture, pp. 396\u2013403, June 1986.","journal-title":"ACM SIGARCH Computer Architecture News"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"W. W. Hwu, T. M. Conte, and P. P. Chang, \u201cComparing software and hardware schemes for reducing the cost of branches,\u201d in Proceedings of the 16th International Symposium on Computer Architecture, pp. 224\u2013233, May 1989.","DOI":"10.1109\/ISCA.1989.714557"},{"key":"3_CR4","doi-asserted-by":"crossref","first-page":"478","DOI":"10.1109\/TC.1981.1675827","volume":"c-30","author":"J. A. Fisher","year":"1981","unstructured":"J. A. Fisher, \u201cTrace scheduling: A technique for global microcode compaction,\u201d IEEE Transactions on Computers, vol. c-30, pp. 478\u2013490, July 1981.","journal-title":"IEEE Transactions on Computers"},{"key":"3_CR5","volume-title":"Bulldog: A Compiler for VLIW Architectures","author":"J. Ellis","year":"1985","unstructured":"J. Ellis, Bulldog: A Compiler for VLIW Architectures. Cambridge, MA: The MIT Press, 1985."},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"P. P. Chang and W. W. Hwu, \u201cTrace selection for compiling large C application programs to microcode,\u201d in Proceedings of the 21st International Workshop on Microprogramming and Microarchitecture, pp. 188\u2013198, November 1988.","DOI":"10.1109\/MICRO.1988.639244"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"W. W. Hwu and P. P. Chang, \u201cAchieving high instruction cache performance with an optimizing compiler,\u201d in Proceedings of the 16th International Symposium on Computer Architecture, pp. 242\u2013251, May 1989.","DOI":"10.1145\/74926.74953"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"K. Pettis and R. C. Hansen, \u201cProfile guided code positioning,\u201d in Proceedings of the ACM SIGPLAN 1990 Conference on Programming Language Design and Implementation, pp. 16\u201327, June 1990.","DOI":"10.1145\/93542.93550"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"D. W. Wall, \u201cGlobal register allocation at link time,\u201d in Proceedings of the 1986 SIGPLAN Symposium on Compiler Construction, pp. 264\u2013275, June 1986.","DOI":"10.1145\/12276.13338"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"W. W. Hwu and P. P. Chang, \u201cInline function expansion for compiling realistic C programs,\u201d in Proceedings of the ACM SIGPLAN 1989 Conference on Programming Language Design and Implementation, pp. 246\u2013257, June 1989.","DOI":"10.1145\/74818.74840"},{"key":"3_CR11","doi-asserted-by":"crossref","first-page":"1301","DOI":"10.1002\/spe.4380211204","volume":"21","author":"P. P. Chang","year":"1991","unstructured":"P. P. Chang, S. A. Mahlke, and W. W. Hwu, \u201cUsing profile information to assist classic code optimizations,\u201d Software Practice and Experience, vol. 21, pp. 1301\u20131321, December 1991.","journal-title":"Software Practice and Experience"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"P. P. Chang, S. A. Mahlke, W. Y. Chen, N. J. Warter, and W. W. Hwu, \u201cIMPACT: An architectural framework for multiple-instruction-issue processors,\u201d in Proceedings of the 18th International Symposium on Computer Architecture, pp. 266\u2013275, May 1991.","DOI":"10.1145\/115952.115979"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"D. J. Kuck, R. H. Kuhn, D. A. Padua, B. Leasure, and M. Wolfe, \u201cDependence graphs and compiler optimizations,\u201d in Proceedings of the 8th ACM Symposium on Principles of Programming Languages, pp. 207\u2013218, January 1981.","DOI":"10.1145\/567532.567555"},{"key":"3_CR14","unstructured":"S. A. Mahlke, W. Y. Chen, J. C. Gyllenhaal, W. W. Hwu, P. P. Chang, and T. Kiyohara, \u201cCompiler code transformations for superscalar-based high-performance systems,\u201d Proceeding of Supercomputing '92, Nov, 1992."},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"T. Nakatani and K. Ebcioglu, \u201cCombining as a compilation technique for VLIW architectures,\u201d in Proceedings of the 22nd International Workshop on Microprogramming and Microarchitecture, pp. 43\u201355, September 1989.","DOI":"10.1145\/75362.75401"},{"key":"3_CR16","volume-title":"The Structure of Computers and Computations","author":"D. J. Kuck","year":"1978","unstructured":"D. J. Kuck, The Structure of Computers and Computations. New York, NY: John Wiley and Sons, 1978."},{"issue":"4","key":"3_CR17","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1145\/36204.36201","volume":"21","author":"Robert P. Colwell","year":"1987","unstructured":"R. P. Colwell, R. P. Nix, J. J. O'Donnell, D. B. Papworth, and P. K. Rodman, \u201cA VLIW architecture for a trace scheduling compiler,\u201d in Proceedings of the 2nd International Conference on Architectural Support for Programming Languages and Operating Systems, pp. 180\u2013192, April 1987.","journal-title":"ACM SIGOPS Operating Systems Review"},{"key":"3_CR18","volume-title":"MIPS R2000 RISC Architecture","author":"G. Kane","year":"1987","unstructured":"G. Kane, MIPS R2000 RISC Architecture. Englewood Cliffs, NJ: Prentice-Hall, Inc., 1987."},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"A. Aiken and A. Nicolau, \u201cOptimal loop parallelization,\u201d in Proceedings of the ACM SIGPLAN 1988 Conference on Programming Language Design and Implementation, pp. 308\u2013317, June 1988.","DOI":"10.1145\/53990.54021"},{"key":"3_CR20","first-page":"69","volume":"20","author":"K. Ebcioglu","year":"1987","unstructured":"K. Ebcioglu, \u201cA compilation technique for software pipelining of loops with conditional jumps,\u201d in Micro 20, pp. 69\u201379, December 1987.","journal-title":"Micro"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"M. S. Lam, \u201cSoftware pipelining: An effective scheduling technique for VLIW machines,\u201d in Proceedings of the ACM SIGPLAN 1988 Conference on Programming Language Design and Implementation, pp. 318\u2013328, June 1988.","DOI":"10.1145\/53990.54022"},{"key":"3_CR22","first-page":"212","volume":"24","author":"B. Su","year":"1991","unstructured":"B. Su and J. Wang, \u201cGurpr*: A new global software pipelining algorithm,\u201d in Micro 24, pp. 212\u2013216, November 1991.","journal-title":"Micro"},{"issue":"4","key":"3_CR23","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1145\/1014192.802449","volume":"12","author":"B. R. Rau","year":"1981","unstructured":"B. R. Rau and C. D. Glaeser, \u201cSome scheduling techniques and an easily schedulable horizontal architecture for high performance scientific computing,\u201d in Proceedings of the 20th Annual Workshop on Microprogramming and Microarchitecture, pp. 183\u2013198, October 1981.","journal-title":"ACM SIGMICRO Newsletter"},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"J. R. Allen, K. Kennedy, C. Porterfield, and J. Warren, \u201cConversion of control dependence to data dependence,\u201d in Proceedings of the 10th ACM Symposium on Principles of Programming Languages, pp. 177\u2013189, January 1983.","DOI":"10.1145\/567067.567085"},{"issue":"1","key":"3_CR25","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1109\/2.19820","volume":"22","author":"B.R. Rau","year":"1989","unstructured":"B. R. Rau, D. W. L. Yen, W. Yen, and R. A. Towle, \u201cThe Cydra 5 departmental supercomputer,\u201d IEEE Computer, pp. 12\u201335, January 1989.","journal-title":"Computer"},{"key":"3_CR26","volume-title":"PhD thesis","author":"R. Towle","year":"1976","unstructured":"R. Towle, Control and Data Dependence for Program Transformations. PhD thesis, Department of Computer Science, University of Illinois, Urbana, IL, 1976."},{"key":"3_CR27","volume-title":"tech. rep.","author":"N. J. Warter","year":"1992","unstructured":"N. J. Warter, D. M. Lavery, and W. W. Hwu, \u201cUsing profile information to assist modulo scheduling,\u201d tech. rep., Center for Reliable and High-Performance Computing, University of Illinois, Urbana, IL, May 1992."},{"key":"3_CR28","volume-title":"Tech. Rep. CSRD-827","author":"M. Berry","year":"1989","unstructured":"M. Berry, D. Chen, P. Koss, D. Kuck, S. Lo, Y. Pang, R. Roloff, A. Sameh, E. Clementi, S. Chin, D. Schneider, G. Fox, P. Messina, D. Walker, C. Hsiung, J. Schwarzmeier, K. Lue, S. Orzag, F. Seidl, O. Johnson, G. Swanson, R. Goodrum, and J. Martin, \u201cThe PERFECT club benchmarks: Effective performance evaluation of supercomputers,\u201d Tech. Rep. CSRD-827, Center for Supercomputing Research and Development, University of Illinois, Urbana, IL, May 1989."},{"key":"3_CR29","unstructured":"Intel, i860 64-Bit Microprocessor. Santa Clara, CA, 1989."},{"key":"3_CR30","unstructured":"N. J. Warter, D. M. Lavery, and W. W. Hwu, \u201cThe benefit of Predicated Execution for software pipelining,\u201d in Proceedings of the 23rd Hawaii International Conference on System Sci ences, to appear January 1993."},{"key":"3_CR31","doi-asserted-by":"crossref","first-page":"663","DOI":"10.1109\/12.24269","volume":"38","author":"A. Nicolau","year":"1989","unstructured":"A. Nicolau, \u201cRun-time disambiguation: coping with statically unpredictable dependencies,\u201d IEEE Transactions on Computers, vol. 38, pp. 663\u2013678, May 1989.","journal-title":"IEEE Transactions on Computers"},{"key":"3_CR32","volume-title":"tech. rep.","author":"W. Y. Chen","year":"1992","unstructured":"W. Y. Chen, S. A. Mahlke, W. W. Hwu, and T. Kiyohara, \u201cAssisting compile-time code reordering with the memory conflict buffer,\u201d tech. rep., Center for Reliable and High-Performance Computing, University of Illinois, Urbana, IL, May 1992."}],"container-title":["Lecture Notes in Computer Science","Languages and Compilers for Parallel Computing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/3-540-57502-2_38.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,17]],"date-time":"2020-11-17T21:12:31Z","timestamp":1605647551000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/3-540-57502-2_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1993]]},"ISBN":["9783540575023","9783540482017"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/3-540-57502-2_38","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[1993]]}}}