{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T15:40:10Z","timestamp":1748533210638,"version":"3.41.0"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2015,7,23]],"date-time":"2015-07-23T00:00:00Z","timestamp":1437609600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Parallel Prog"],"published-print":{"date-parts":[[2016,8]]},"DOI":"10.1007\/s10766-015-0372-7","type":"journal-article","created":{"date-parts":[[2015,7,22]],"date-time":"2015-07-22T07:22:01Z","timestamp":1437549721000},"page":"735-771","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Performance Estimation of Task Graphs Based on Path Profiling"],"prefix":"10.1007","volume":"44","author":[{"given":"Marco","family":"Lattuada","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christian","family":"Pilato","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fabrizio","family":"Ferrandi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,7,23]]},"reference":[{"key":"372_CR1","doi-asserted-by":"crossref","unstructured":"Wolf, W.: The future of multiprocessor systems-on-chips. In: Proceedings of the 41st Annual Design Automation Conference, DAC \u201904, pp. 681\u2013685 (2004)","DOI":"10.1145\/996566.996753"},{"issue":"2","key":"372_CR2","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1023\/A:1008832202436","volume":"2","author":"R Niemann","year":"1997","unstructured":"Niemann, R., Marwedel, P.: An algorithm for hardware\/software partitioning using mixed integer linear programming. Des. Autom. Embed. Syst. 2(2), 165\u2013193 (1997)","journal-title":"Des. Autom. Embed. Syst."},{"key":"372_CR3","volume-title":"Embedded System Design: Embedded Systems Foundations of Cyber-Physical Systems","author":"P Marwedel","year":"2010","unstructured":"Marwedel, P.: Embedded System Design: Embedded Systems Foundations of Cyber-Physical Systems, 2nd edn. Springer, Berlin (2010)","edition":"2"},{"key":"372_CR4","doi-asserted-by":"crossref","unstructured":"Ferrandi, F., Pilato, C., Tumeo, A., Sciuto, D.: Mapping and scheduling of parallel C applications with ant colony optimization onto Heterogeneous reconfigurable MPSoCs. In: Proceedings of the 15th IEEE Asia and South Pacific Design Automation Conference, ASP-DAC \u201910, pp. 799\u2013804, January 2010 (2010)","DOI":"10.1109\/ASPDAC.2010.5419782"},{"issue":"6","key":"372_CR5","doi-asserted-by":"crossref","first-page":"911","DOI":"10.1109\/TCAD.2010.2048354","volume":"29","author":"F Ferrandi","year":"2010","unstructured":"Ferrandi, F., Lanzi, P.L., Pilato, C., Sciuto, D., Tumeo, A.: Ant colony heuristic for mapping and scheduling task and communications on heterogeneous embedded systems. IEEE Trans. Comput. Aided Des. Integ. Circ. Syst. 29(6), 911\u2013924 (2010)","journal-title":"IEEE Trans. Comput. Aided Des. Integ. Circ. Syst."},{"issue":"2","key":"372_CR6","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1007\/s11265-005-6648-1","volume":"41","author":"L Benini","year":"2005","unstructured":"Benini, L., Bertozzi, D., Bogliolo, A., Menichelli, F., Olivieri, M.: MPARM: Exploring the Multi-Processor SoC Design Space with SystemC. J. VLSI Sign. Process. 41(2), 169\u2013182 (2005)","journal-title":"J. VLSI Sign. Process."},{"issue":"12","key":"372_CR7","doi-asserted-by":"crossref","first-page":"1857","DOI":"10.1109\/TCAD.2009.2030268","volume":"28","author":"G Beltrame","year":"2009","unstructured":"Beltrame, G., Fossati, L., Sciuto, D.: ReSP: A Nonintrusive Transaction-Level Reflective MPSoC Simulation Platform for Design Space Exploration. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 28(12), 1857\u20131869 (2009)","journal-title":"IEEE Trans. Comput. Aided Des. Integr. Circuits Syst."},{"key":"372_CR8","doi-asserted-by":"crossref","unstructured":"Li, Y.A., Antonio, J.K.: Estimating the execution time distribution for a task graph in a heterogeneous computing system. In Proceedings of the 6th Heterogeneous Computing Workshop, HCW \u201997, pp. 172\u2013184, (1997)","DOI":"10.1109\/HCW.1997.581419"},{"key":"372_CR9","unstructured":"Manolache, S.: Analysis and optimisation of real-time systems with stochastic behaviour. Technical report, Linkoping University (2005)"},{"key":"372_CR10","doi-asserted-by":"crossref","unstructured":"Poplavko, P., Basten, T., Bekooij, M., van Meerbergen, J., Mesman, B.: Task-level timing models for guaranteed performance in multiprocessor networks-on-chip. In: Proceedings of the 2003 international conference on Compilers, architecture and synthesis for embedded systems, CASES \u201903, pp. 63\u201372, (2003)","DOI":"10.1145\/951710.951721"},{"key":"372_CR11","volume-title":"Computer and Job Shop Scheduling Theory","author":"EG Coffman","year":"1976","unstructured":"Coffman, E.G.: Computer and Job Shop Scheduling Theory. Wiley, New York (1976)"},{"key":"372_CR12","doi-asserted-by":"crossref","unstructured":"Sahu, A., Balakrishnan, M., Panda, P.R.: A generic platform for estimation of multi-threaded program performance on heterogeneous multiprocessors. In: Proceedings of the Conference on Design, Automation and Test in Europe, DATE \u201909, pp. 1018\u20131023 (2009)","DOI":"10.1109\/DATE.2009.5090813"},{"key":"372_CR13","doi-asserted-by":"crossref","unstructured":"Yaldiz, S., Demir, A., Tasiran, S., Ienne, P., Leblebici, Y.: Characterizing and exploiting task-load variability and correlation for energy management in multi-core systems. In: ESTImedia, pp. 135\u2013140 (2005)","DOI":"10.1109\/ESTMED.2005.1518092"},{"key":"372_CR14","doi-asserted-by":"crossref","unstructured":"Hubert, H., Stabernack, B., Wels, K.-I.: Performance and memory profiling for embedded system design. In: Proceedings of the International Symposium on Industrial Embedded Systems, SIES \u201907, pp. 94\u2013101 (July 2007)","DOI":"10.1109\/SIES.2007.4297322"},{"key":"372_CR15","doi-asserted-by":"crossref","unstructured":"Ball, T., Larus, J. R.: Efficient path profiling. In: MICRO-29: Proceedings of the 29th Annual ACM\/IEEE International Symposium on Microarchitecture, pp. 46\u201357 (1996)","DOI":"10.1109\/MICRO.1996.566449"},{"key":"372_CR16","doi-asserted-by":"crossref","unstructured":"Lattuada, M., Ferrandi, F.: Performance modeling of embedded applications with zero architectural knowledge. In: Proceedings of the Eighth IEEE\/ACM\/IFIP International Conference on Hardware\/Software Codesign and Cystem Cynthesis, CODES\/ISSS \u201910, pp. 277\u2013286 (2010)","DOI":"10.1145\/1878961.1879010"},{"key":"372_CR17","doi-asserted-by":"crossref","unstructured":"Ferrandi, F., Lattuada, M., Pilato, C., Tumeo, A.: Performance modeling of parallel applications on MPSoCs. In: IEEE International Symposium on System-on-Chip, SOC \u201909, pp. 64\u201367 (2009)","DOI":"10.1109\/SOCC.2009.5335675"},{"key":"372_CR18","unstructured":"OpenMP. Application Program Interface, version 2.5 (May 2005)"},{"key":"372_CR19","doi-asserted-by":"crossref","unstructured":"Satish, N.R., Ravindran, K., Keutzer, K.: Scheduling task dependence graphs with variable task execution times onto heterogeneous multiprocessors. In: Proceedings of the 8th ACM international conference on Embedded software, EMSOFT \u201908, pp. 149\u2013158, New York, NY, USA. ACM (2008)","DOI":"10.1145\/1450058.1450079"},{"key":"372_CR20","unstructured":"Zhu, X., Malik, S.: Using a communication architecture specification in an application-driven retargetable prototyping platform for multiprocessing. In: Proceedings of the Conference on Design, Automation and Test in Europe, DATE \u201904, pp. 1244\u20131249 (2004)"},{"issue":"2","key":"372_CR21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2024716.2024718","volume":"39","author":"N Binkert","year":"2011","unstructured":"Binkert, N., Beckmann, B., Black, G., Reinhardt, S.K., Saidi, A., Basu, A., Hestness, J., Hower, D.R., Krishna, T., Sardashti, S., Sen, R., Sewell, K., Shoaib, M., Vaish, N., Hill, M.D., Wood, D.A.: The Gem5 simulator. SIGARCH Comput. Archit. News 39(2), 1\u20137 (2011)","journal-title":"SIGARCH Comput. Archit. News"},{"issue":"1","key":"372_CR22","doi-asserted-by":"crossref","first-page":"22","DOI":"10.4018\/jertcs.2013010102","volume":"4","author":"A Miele","year":"2013","unstructured":"Miele, A., Pilato, C., Sciuto, D.: A simulation-based framework for the exploration of mapping solutions on heterogeneous MPSoCs. Int. J. Embed. Real Time Commun. Syst. 4(1), 22\u201341 (2013)","journal-title":"Int. J. Embed. Real Time Commun. Syst."},{"key":"372_CR23","unstructured":"Lin, K.-L., Lo, C.-K., Tsay, R.-S.: Source-level timing annotation for fast and accurate tlm computation model generation. In: Design Automation Conference (ASP-DAC), 2010 15th Asia and South Pacific, pp. 235\u2013240, (2010)"},{"key":"372_CR24","doi-asserted-by":"crossref","unstructured":"Wilson, R., French, R., Wilson, C., Amarasinghe, S., Anderson, J., T. S., Liao, S., Tseng, C., Hall, M., Lam, M., Hennessy, J.: The SUIF Compiler System: a Parallelizing and Optimizing Research Compiler. Technical report, Stanford, CA, USA (1994)","DOI":"10.1145\/193209.193217"},{"key":"372_CR25","doi-asserted-by":"crossref","unstructured":"Kreku, J., Tiensyrj\u00e4, K., Vanmeerbeeck, G.: Automatic workload generation for system-level exploration based on modified GCC compiler. In: Proceedings of the Conference on Design, Automation and Test in Europe, Date \u201910, pp. 369\u2013374, (2010)","DOI":"10.1109\/DATE.2010.5457175"},{"key":"372_CR26","doi-asserted-by":"crossref","unstructured":"Javaid, H., Janapsatya, A., Haque, M.S., Parameswaran, S.: Rapid runtime estimation methods for pipelined MPSoCs. In: Proceedings of the Conference on Design, Automation and Test in Europe, DATE \u201910, pp. 363\u2013368 (2010)","DOI":"10.1109\/DATE.2010.5457178"},{"key":"372_CR27","doi-asserted-by":"crossref","unstructured":"Cordes, D., Marwedel, P., Mallik, A.: Automatic parallelization of embedded software using hierarchical task graphs and integer linear programming. In: Proceedings of the Eighth IEEE\/ACM\/IFIP International Conference on Hardware\/Software Codesign and System Synthesis, CODES\/ISSS \u201910, pp. 267\u2013276 (2010)","DOI":"10.1145\/1878961.1879009"},{"key":"372_CR28","doi-asserted-by":"crossref","unstructured":"Kim, S., Ha, S.: System-level performance analysis of multiprocessor system-on-chips by combining analytical model and execution time variation. Microprocess. Microsyst. 38(3), 233\u2013245 (2014)","DOI":"10.1016\/j.micpro.2014.02.003"},{"issue":"4","key":"372_CR29","doi-asserted-by":"crossref","first-page":"538","DOI":"10.1109\/TCAD.2010.2042887","volume":"29","author":"A Kumar","year":"2010","unstructured":"Kumar, A., Mesman, B., Corporaal, H., Ha, Y.: Iterative probabilistic performance prediction for multi-application multiprocessor systems. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 29(4), 538\u2013551 (2010)","journal-title":"IEEE Trans. Comput. Aided Des. Integr. Circuits Syst."},{"key":"372_CR30","doi-asserted-by":"crossref","unstructured":"Xu, Y., Wang, B., Hasholzner, R., Rosales, R., Teich, J.: On robust task-accurate performance estimation. In: Proceedings of the 50th Annual Design Automation Conference, DAC \u201913, ACM, New York, NY, USA, pp. 171:1\u2013171:6 (2013)","DOI":"10.1145\/2463209.2488945"},{"key":"372_CR31","doi-asserted-by":"crossref","unstructured":"Ernst, R., Ye, W.: Embedded program timing analysis based on path clustering and architecture classification. In: Proceedings of the 1997 IEEE\/ACM International Conference on Computer-Aided Design, ICCAD \u201997, pp. 598\u2013604, (1997)","DOI":"10.1109\/ICCAD.1997.643600"},{"key":"372_CR32","doi-asserted-by":"crossref","unstructured":"Malik, S., Martonosi, M., Li, Y.S.: Static timing analysis of embedded software. In Proceedings of the 34th Annual Design Automation Conference, DAC \u201997, pp. 147\u2013152 (1997)","DOI":"10.1109\/DAC.1997.597134"},{"key":"372_CR33","doi-asserted-by":"crossref","unstructured":"Zhai, A., Colohan, C.B., Steffan, J.G., Mowry, T.C.: Compiler optimization of scalar value communication between speculative threads. In: Proceedings of the 10th International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS-X, pp. 171\u2013183 (2002)","DOI":"10.1145\/605432.605416"},{"key":"372_CR34","doi-asserted-by":"crossref","unstructured":"Ferrandi, F., Lattuada, M., Pilato, C., Tumeo, A.: Performance estimation for task graphs combining sequential path profiling and control dependence regions. In: Proceedings of the 7th IEEE\/ACM International Conference on Formal Methods and Models for Codesign, MEMOCODE \u201909, pp. 131\u2013140 (2009)","DOI":"10.1109\/MEMCOD.2009.5185389"},{"key":"372_CR35","volume-title":"Compilers: Principles, Techniques, and Tools","author":"AV Aho","year":"1986","unstructured":"Aho, A.V., Sethi, R., Ullman, J.D.: Compilers: Principles, Techniques, and Tools. Addison-Wesley Longman Publishing Co., Inc, Melbourne (1986)"},{"issue":"6","key":"372_CR36","doi-asserted-by":"crossref","first-page":"649","DOI":"10.1145\/236114.236115","volume":"18","author":"VC Sreedhar","year":"1996","unstructured":"Sreedhar, V.C., Gao, G.R., Lee, Y.: Identifying loops using DJ graphs. ACM Trans. Program. Lang. Syst. 18(6), 649\u2013658 (1996)","journal-title":"ACM Trans. Program. Lang. Syst."},{"issue":"3","key":"372_CR37","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1145\/24039.24041","volume":"9","author":"J Ferrante","year":"1987","unstructured":"Ferrante, J., Ottenstein, K.J., Warren, J.D.: The program dependence graph and its use in optimization. ACM Trans. Program. Lang. Syst. 9(3), 319\u2013349 (1987)","journal-title":"ACM Trans. Program. Lang. Syst."},{"issue":"2","key":"372_CR38","doi-asserted-by":"crossref","first-page":"166","DOI":"10.1109\/71.127258","volume":"3","author":"M Girkar","year":"1992","unstructured":"Girkar, M., Polychronopoulos, C.: Automatic extraction of functional parallelism from ordinary programs. IEEE Trans. Parallel Distrib. Syst. 3(2), 166\u2013178 (1992)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"372_CR39","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1109\/MM.2010.91","volume":"30","author":"K Bertels","year":"2010","unstructured":"Bertels, K., Sima, V., Yankova, Y., Kuzmanov, G., Luk, W., Coutinho, G., Ferrandi, F., Pilato, C., Lattuada, M., Sciuto, D., Michelotti, A.: Hartes: Hardware-software codesign for heterogeneous multicore platforms. IEEE Micro. 30, 88\u201397 (2010)","journal-title":"IEEE Micro."},{"key":"372_CR40","doi-asserted-by":"crossref","unstructured":"Thompson, M., Nikolov, H., Stefanov, T., Pimentel, A.D., Erbas, C., Polstra, S., Deprettere, E.F.: A framework for rapid system-level exploration, synthesis, and programming of multimedia MP-SoCs. In: Proceedings of the IEEE\/ACM\/IFIP International Conference on Hardware\/Software Codesign and System Synthesis, CODES+ISSS \u201907, pp. 9\u201314 (2007)","DOI":"10.1145\/1289816.1289823"},{"key":"372_CR41","unstructured":"Atmel Corporation. DIOPSIS 940HF. http:\/\/www.atmel.com (2009)"},{"key":"372_CR42","unstructured":"Texas Instruments. TI OMAP 4. http:\/\/www.ti.com (2011)"},{"key":"372_CR43","unstructured":"Xilinx. Vivado Design Suite. http:\/\/www.xilinx.com (2013)"},{"key":"372_CR44","doi-asserted-by":"crossref","unstructured":"Gerstlauer, A.: Host-compiled simulation of multi-core platforms. In: Proceedings of the IEEE International Symposium on Rapid System Prototyping (RSP), pp. 1\u20136 (June 2010)","DOI":"10.1109\/RSP.2010.5656355"},{"key":"372_CR45","unstructured":"Synopsys Inc. Platform Architect. http:\/\/www.synopsys.com\/Systems\/ArchitectureDesign (2012)"},{"issue":"1\u20132","key":"372_CR46","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1016\/j.sysarc.2007.06.005","volume":"54","author":"MS Oyamada","year":"2008","unstructured":"Oyamada, M.S., Zschornack, F., Wagner, F.R.: Applying neural networks to performance estimation of embedded software. J. Syst. Architect. 54(1\u20132), 224\u2013240 (2008)","journal-title":"J. Syst. Architect."},{"key":"372_CR47","unstructured":"PandA. PandA framework. http:\/\/trac.ws.dei.polimi.it\/panda"},{"key":"372_CR48","unstructured":"GNU Compiler Collection. GCC, version 4.3. http:\/\/gcc.gnu.org\/"},{"key":"372_CR49","doi-asserted-by":"crossref","unstructured":"Guthaus, M.R., Ringenberg, J.S., Ernst, D., Austin, T.M., Mudge, T., Brown. R.B.: MiBench: A free, commercially representative embedded benchmark suite. In: Proceedings of the IEEE International Workshop on Workload Characterization, WWC \u201901, pp. 3\u201314 (2001)","DOI":"10.1109\/WWC.2001.990739"},{"key":"372_CR50","doi-asserted-by":"crossref","unstructured":"Dorta, A.J., Rodriguez, C., de Sande, F., Gonzalez-Escribano, A.: The OpenMP Source Code Repository. In: Proceedings of the 13th Euromicro Conference on Parallel, Distributed and Network-Based Processing, PDP \u201905, pp. 244\u2013250 (2005)","DOI":"10.1109\/EMPDP.2005.41"},{"key":"372_CR51","doi-asserted-by":"crossref","unstructured":"Woo, S.C., Ohara, M., Torrie, E., Singh, J.P., Gupta, A.: The SPLASH-2 programs: characterization and methodological considerations. In: Proceedings of the 22nd Annual International Symposium on Computer Architecture, ISCA \u201995, pp. 24\u201336 (1995)","DOI":"10.1145\/223982.223990"},{"key":"372_CR52","unstructured":"ARM922T. Technical Reference Manual. http:\/\/infocenter.arm.com"},{"key":"372_CR53","unstructured":"Politecnico di Milano. ReSP web-site. http:\/\/code.google.com\/p\/resp-sim\/ (2010)"}],"container-title":["International Journal of Parallel Programming"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-015-0372-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10766-015-0372-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-015-0372-7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T14:59:04Z","timestamp":1748530744000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10766-015-0372-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,7,23]]},"references-count":53,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2016,8]]}},"alternative-id":["372"],"URL":"https:\/\/doi.org\/10.1007\/s10766-015-0372-7","relation":{},"ISSN":["0885-7458","1573-7640"],"issn-type":[{"type":"print","value":"0885-7458"},{"type":"electronic","value":"1573-7640"}],"subject":[],"published":{"date-parts":[[2015,7,23]]}}}