{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T13:26:21Z","timestamp":1770297981572,"version":"3.49.0"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[1994,4,1]],"date-time":"1994-04-01T00:00:00Z","timestamp":765158400000},"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":[[1994,4]]},"DOI":"10.1007\/bf02577873","type":"journal-article","created":{"date-parts":[[2007,3,22]],"date-time":"2007-03-22T23:30:25Z","timestamp":1174606225000},"page":"151-181","source":"Crossref","is-referenced-by-count":17,"title":["Profile-assisted instruction scheduling"],"prefix":"10.1007","volume":"22","author":[{"given":"William Y.","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Scott A.","family":"Mahlke","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nancy J.","family":"Warter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sadun","family":"Anik","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen-Mei W.","family":"Hwu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"BF02577873_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, Massachusetts, Addison-Wesley (1986)."},{"key":"BF02577873_CR2","doi-asserted-by":"crossref","first-page":"478","DOI":"10.1109\/TC.1981.1675827","volume":"30","author":"J. A. Fisher","year":"1981","unstructured":"J. A. Fisher, Trace scheduling: A technique for global microcode compaction,IEEE Trans. on Computers, C-30:478\u2013490 (July 1981).","journal-title":"IEEE Trans. on Computers"},{"key":"BF02577873_CR3","volume-title":"Bulldog: A Compiler for VLIW Architectures","author":"J. Ellis","year":"1985","unstructured":"J. Ellis,Bulldog: A Compiler for VLIW Architectures, Cambridge, Massachusetts, MIT Press (1985)."},{"key":"BF02577873_CR4","doi-asserted-by":"crossref","unstructured":"M. D. Smith, M. S. Lam, and M. A. Horowitz, Boosting beyond static scheduling in a superscalar processor,Proc. of the 17th Int'l. Symp. on Computer Archit., pp. 344\u2013354 (May 1990).","DOI":"10.1145\/325096.325160"},{"key":"BF02577873_CR5","doi-asserted-by":"crossref","unstructured":"P. P. Chang, S. A. Mahlke, W. Y. Chen, N. J. Warter, and W. W. Hwu, IMPACT: An architectural framework for multiple-instruction-issue processors,Proc. of the 18th Int'l. Symp. on Computer Archit., pp. 266\u2013275 (May 1991).","DOI":"10.1145\/115952.115979"},{"key":"BF02577873_CR6","doi-asserted-by":"crossref","unstructured":"S. A. Mahlke, W. Y. Chen, W. W. Hwu, B. R. Rau, and M. S. Schlansker, Sentinel scheduling for superscalar and VLIW processors,Proc. of the 5th Int'l. Conf. on Archit. Support for Programming Languages and Oper. Syst., pp. 238\u2013247 (October 1992).","DOI":"10.1145\/143365.143529"},{"key":"BF02577873_CR7","unstructured":"D. Weaver,SPARC-V9 Architecture Specification, SPARC International Inc. (1992)."},{"key":"BF02577873_CR8","doi-asserted-by":"crossref","unstructured":"R. P. Colwell, R. P. Nix, J. J. O'Donnell, D. B. Papworth, and P. K. Rodman, A. VLIW architecture for a trace scheduling complier,Proc. of the 2nd Int'l. Conf. on Archit. Support for Programming Languages and Oper. Syst., pp. 180\u2013192 (April 1987).","DOI":"10.1145\/36204.36201"},{"key":"BF02577873_CR9","doi-asserted-by":"crossref","unstructured":"B. R. Rau, D. W. L. Yen, W. Yen, and R. A. Towle, the Cydra 5 departmental super-computer,IEEE Computer, pp. 12\u201335 (January 1989).","DOI":"10.1109\/2.19820"},{"key":"BF02577873_CR10","doi-asserted-by":"crossref","unstructured":"B. R. Rau and C. D. Glaeser, Some Scheduling techniques and an easily schedulable horizontal architecture for high performance scientific computing.Proc. of the 20th Ann. Workshop on Microprogramming and Microarchitecture, pp. 183\u2013198 (October 1981).","DOI":"10.1145\/1014192.802449"},{"key":"BF02577873_CR11","doi-asserted-by":"crossref","unstructured":"M. S. Lam, Software pipelining: An effective scheduling technique for VLIW machines,Proc. of the ACM SIGPLAN Conf. on Programming Language Design and Implemention, pp. 318\u2013328 (June 1988).","DOI":"10.1145\/53990.54022"},{"key":"BF02577873_CR12","doi-asserted-by":"crossref","unstructured":"J. C. Dehnert, P. Y. Hsu, and J. P. Bratt, Overlapped loop support in the Cydra 5,Proc. of the Third Int'l. Conf. on Archit. Support for Programming Languages and Oper. Syst., pp. 26\u201338 (April 1989).","DOI":"10.1145\/68182.68185"},{"key":"BF02577873_CR13","doi-asserted-by":"crossref","unstructured":"B. Su and J. Wang, GURPR*: A new global software pipelining algorithm,Proc. of the 24th Int'l. Conf. on Microarchitecture, pp. 212\u2013216 (November 1991).","DOI":"10.1145\/123465.123509"},{"key":"BF02577873_CR14","doi-asserted-by":"crossref","unstructured":"B. R. Rau, M. S. Schlansker, and P. P. Tirumalai, Code generation schema for modulo scheduled loops,Proc. of the 25th Ann. Int'l. Symp. on Microarchitteture, pp. 158\u2013169 (December 1992).","DOI":"10.1109\/MICRO.1992.697012"},{"key":"BF02577873_CR15","doi-asserted-by":"crossref","unstructured":"N. J. Warter, G. E. Haab, K. Subramanian, and J. W. Bockhaus, Enhanced modulo scheduling for loops with conditional branches, inProc. of the 25th Ann. Int'l. Symp. on Microarchitecture, pp. 170\u2013179 (December 1992).","DOI":"10.1145\/144965.145796"},{"key":"BF02577873_CR16","doi-asserted-by":"crossref","first-page":"663","DOI":"10.1109\/12.24269","volume":"38","author":"A. Nicolau","year":"1989","unstructured":"A. Nicolau, Run-time disambiguation: coping with statically unpredictable dependencies.IEEE Trans. on Computers,38:663\u2013678 (May 1989).","journal-title":"IEEE Trans. on Computers"},{"key":"BF02577873_CR17","doi-asserted-by":"crossref","unstructured":"W. W. Hwu, S. A. Mahlke, W. Y. Chen, P. P. Chang, N. J. Warter, R. A. Brigmann, R. G. Ouellette, R. E. Hank, T. Kiyohara, G. E. Haab, J. G. Holm, and D. M. Lavery, The superblock: An effective structure for VLIW and superscalar compilation,J. of Supercomputing (February 1993).","DOI":"10.1007\/BF01205185"},{"key":"BF02577873_CR18","doi-asserted-by":"crossref","unstructured":"P. P. Chang and W. W. Hwu, Trace selection for compiling large C application programs to microcode,Proc. of the 21st Int'l. Workshop, on Microprogramming and Microarchitecture, pp. 188\u2013198 (November 1988).","DOI":"10.1109\/MICRO.1988.639244"},{"key":"BF02577873_CR19","volume-title":"MIPS R2000 RISC Architecture","author":"G. Kane","year":"1987","unstructured":"G. Kane,MIPS R2000 RISC Architecture, Englewood Cliffs, New Jersey, Prentice-Hall, Inc. (1987)."},{"key":"BF02577873_CR20","series-title":"Tech. Rep.","volume-title":"Assisting compile-time code reordering with the memory conflict buffer","author":"W. Y. Chen","year":"1992","unstructured":"W. Y. Chen, S. A. Mahlke, W. W. Hwu, and T. Kiyohara, Assisting compile-time code reordering with the memory conflict buffer, Tech. Rep., Center for Reliable and High-Performance Computing, University of Illinois, Urbana, Illinois (May 1992)."},{"key":"BF02577873_CR21","doi-asserted-by":"crossref","unstructured":"J. R. Allen, K. Kennedy, C. Porterfield, and J. Warren, Conversion of control dependence to data dependence,Proc. of the 10th ACM Symp. on Principles of Programming Languages, pp. 177\u2013189 (January 1983).","DOI":"10.1145\/567067.567085"},{"key":"BF02577873_CR22","series-title":"Tech. Rep.","volume-title":"Enhanced modulo scheduling","author":"N. J. Warter","year":"1993","unstructured":"N. J. Warter and W. W. Hwu, Enhanced modulo scheduling, Tech. Rep. in preparation, Center for Reliable and High-Performance Computing, University of Illinois, Urbana, Illinois (1993)."},{"key":"BF02577873_CR23","series-title":"Tech. Rep. CSRD-827","volume-title":"The PERFECT club benchmarks: Effective performance evaluation of supercomputers","author":"M. Berry","year":"1989","unstructured":"M. Berryet al., The PERFECT club benchmarks: Effective performance evaluation of supercomputers, Tech. Rep. CSRD-827, Center for Supercomputing Research and Development, University of Illinois, Urbana, Illinois (May 1989)."},{"key":"BF02577873_CR24","volume-title":"i860 64-Bit Microprocessor","author":"Intel","year":"1989","unstructured":"Intel,i860 64-Bit Microprocessor, Santa Clara, California (1989)."},{"key":"BF02577873_CR25","doi-asserted-by":"crossref","unstructured":"N. J. Warter, D. M. Lavery, and W. W. Hwu, The benefit of predicated execution for software pipelining,Proc. of the 26rd Hawaii Int'l. Conf. on Syst. Sci., pp. 497\u2013506 (January 1993).","DOI":"10.1109\/HICSS.1993.283949"},{"key":"BF02577873_CR26","doi-asserted-by":"crossref","unstructured":"S. McFarling and J. Hennessy, Reducing the cost of branches,Proc. of the 13th Int'l. Symp. on Computer Archit., pp. 396\u2013403 (June 1986).","DOI":"10.1145\/17356.17402"},{"key":"BF02577873_CR27","doi-asserted-by":"crossref","unstructured":"W. W. Hwu, T. M. Conte, and P. P. Chang, Comparing software and hardware schemes for reducing the cost of branches,Proc. of the 16th Int'l. Symp. on Computer Archit, pp. 224\u2013233 (May 1989).","DOI":"10.1145\/74925.74951"},{"key":"BF02577873_CR28","doi-asserted-by":"crossref","unstructured":"W. W. Hwu, and P. P. Chang, Achieving high instruction cache performance with an optimizing compiler,Proc. of the 16th Int'l. Symp. on Computer Archit., pp. 242\u2013251 (May 1989).","DOI":"10.1145\/74925.74953"},{"key":"BF02577873_CR29","doi-asserted-by":"crossref","unstructured":"K. Pettis and R. C. Hansen, Profile guided code positioning,Proc. of the ACM SIGPLAN Conf. on Programming Language Design and Implementation, pp. 16\u201327 (June 1990).","DOI":"10.1145\/93548.93550"},{"key":"BF02577873_CR30","doi-asserted-by":"crossref","unstructured":"D. W. Wall, Global register allocation at, link time,Proc. of the SIGPLAN Symp. on Compiler Construction, pp. 264\u2013275 (June 1986).","DOI":"10.1145\/12276.13338"},{"key":"BF02577873_CR31","doi-asserted-by":"crossref","unstructured":"W. W. Hwu and P. P. Chang, Inline function expansion for compiling realistic C programs,Proc. of the ACM SIGPLAN Conf. on Programming Language Design and Implementation, pp. 246\u2013257 (June 1989).","DOI":"10.1145\/74818.74840"},{"key":"BF02577873_CR32","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, Using profile information to assist classic code optimizations,Software Practice and Experience,21:1301\u20131321 (December 1991).","journal-title":"Software Practice and Experience"}],"container-title":["International Journal of Parallel Programming"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/BF02577873.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/BF02577873\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/BF02577873","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T05:16:01Z","timestamp":1736918161000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/BF02577873"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1994,4]]},"references-count":32,"journal-issue":{"issue":"2","published-print":{"date-parts":[[1994,4]]}},"alternative-id":["BF02577873"],"URL":"https:\/\/doi.org\/10.1007\/bf02577873","relation":{},"ISSN":["0885-7458","1573-7640"],"issn-type":[{"value":"0885-7458","type":"print"},{"value":"1573-7640","type":"electronic"}],"subject":[],"published":{"date-parts":[[1994,4]]}}}