{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,12]],"date-time":"2025-07-12T01:22:40Z","timestamp":1752283360573,"version":"3.37.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319920399"},{"type":"electronic","value":"9783319920405"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-92040-5_20","type":"book-chapter","created":{"date-parts":[[2018,5,28]],"date-time":"2018-05-28T07:55:05Z","timestamp":1527494105000},"page":"389-409","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["TaskGenX: A Hardware-Software Proposal for Accelerating Task Parallelism"],"prefix":"10.1007","author":[{"given":"Kallia","family":"Chronaki","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marc","family":"Casas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miquel","family":"Moreto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaume","family":"Bosch","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rosa M.","family":"Badia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,5,29]]},"reference":[{"key":"20_CR1","unstructured":"OpenMP architecture review board. OpenMP Specification. 4.5 (2015)"},{"issue":"2","key":"20_CR2","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1002\/cpe.1631","volume":"23","author":"C Augonnet","year":"2011","unstructured":"Augonnet, C., Thibault, S., Namyst, R., Wacrenier, P.-A.: StarPU: a unified platform for task scheduling on heterogeneous multicore architectures. Concurr. Comput. Pract. Exper. 23(2), 187\u2013198 (2011)","journal-title":"Concurr. Comput. Pract. Exper."},{"issue":"5\u20136","key":"20_CR3","doi-asserted-by":"publisher","first-page":"440","DOI":"10.1007\/s10766-010-0135-4","volume":"38","author":"E Ayguad\u00e9","year":"2010","unstructured":"Ayguad\u00e9, E., Badia, R., Bellens, P., Cabrera, D., Duran, A., Ferrer, R., Gonz\u00e0lez, M., Igual, F., Jim\u00e9nez-Gonz\u00e1lez, D., Labarta, J., Martinell, L., Martorell, X., Mayo, R., P\u00e9rez, J., Planas, J., Quintana-Ort\u00ed, E.: Extending OpenMP to survive the heterogeneous multicore era. Int. J. Parallel Prog. 38(5\u20136), 440\u2013459 (2010)","journal-title":"Int. J. Parallel Prog."},{"key":"20_CR4","unstructured":"Barcelona Supercomputing Center. BSC Application Repository, 18 April 2014. https:\/\/pm.bsc.es\/projects\/bar"},{"key":"20_CR5","unstructured":"Barcelona Supercomputing Center. Nanos++"},{"key":"20_CR6","doi-asserted-by":"crossref","unstructured":"Bauer, M., Treichler, S., Slaughter, E., Aiken, A.: Legion: expressing locality and independence with logical regions. In: SC, pp. 66:1\u201366:11 (2012)","DOI":"10.1109\/SC.2012.71"},{"issue":"8","key":"20_CR7","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1145\/209937.209958","volume":"30","author":"Robert D. Blumofe","year":"1995","unstructured":"Blumofe, R.D., Joerg, C.F., Kuszmaul, B.C., Leiserson, C.E., Randall, K.H., Zhou,Y.: Cilk: an efficient multithreaded runtime system. In: PPoPP, pp. 207\u2013216 (1995)","journal-title":"ACM SIGPLAN Notices"},{"key":"20_CR8","doi-asserted-by":"crossref","unstructured":"Bueno, J., Planas, J., Duran, A., Badia, R.M., Martorell, X., Ayguad\u00e9, E., Labarta, J.: Productive programming of GPU clusters with OmpSs. In: IPDPS, pp. 557\u2013568 (2012)","DOI":"10.1109\/IPDPS.2012.58"},{"key":"20_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-540-76837-1_3","volume-title":"Advanced Parallel Processing Technologies","author":"B Chapman","year":"2007","unstructured":"Chapman, B.: The multicore programming challenge. In: Xu, M., Zhan, Y., Cao, J., Liu, Y. (eds.) APPT 2007. LNCS, vol. 4847, p. 3. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-76837-1_3"},{"key":"20_CR10","first-page":"41:1","volume":"12","author":"D Chasapis","year":"2015","unstructured":"Chasapis, D., Casas, M., Moreto, M., Vidal, R., Ayguade, E., Labarta, J., Valero, M.: PARSECSs: evaluating the impact of task parallelism in the PARSEC benchmark suite. Trans. Archit. Code Optim. 12, 41:1\u201341:22 (2015)","journal-title":"Trans. Archit. Code Optim."},{"key":"20_CR11","doi-asserted-by":"crossref","unstructured":"Chronaki, K., Rico, A., Badia, R.M., Ayguad\u00e9, E., Labarta, J., Valero, M.: Criticality-aware dynamic task scheduling for heterogeneous architectures. In: ICS, pp. 329\u2013338 (2015)","DOI":"10.1145\/2751205.2751235"},{"key":"20_CR12","doi-asserted-by":"crossref","unstructured":"Dallou, T., Engelhardt, N., Elhossini, A., Juurlink, B.: Nexus#: a distributed hardware task manager for task-based programming models. In: IPDPS, pp. 1129\u20131138 (2015)","DOI":"10.1109\/IPDPS.2015.79"},{"key":"20_CR13","doi-asserted-by":"publisher","first-page":"256","DOI":"10.1109\/JSSC.1974.1050511","volume":"9","author":"R Dennard","year":"1974","unstructured":"Dennard, R., Gaensslen, F., Rideout, V., Bassous, E., LeBlanc, A.: Design of ion-implanted MOSFET\u2019s with very small physical dimensions. IEEE J. Solid-State Circuits 9, 256\u2013268 (1974)","journal-title":"IEEE J. Solid-State Circuits"},{"key":"20_CR14","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1142\/S0129626411000151","volume":"21","author":"A Duran","year":"2011","unstructured":"Duran, A., Ayguad\u00e9, E., Badia, R.M., Labarta, J., Martinell, L., Martorell, X., Planas, J.: OmpSs: a proposal for programming heterogeneous multicore architectures. Parallel Process. Lett. 21, 173\u2013193 (2011)","journal-title":"Parallel Process. Lett."},{"key":"20_CR15","doi-asserted-by":"crossref","unstructured":"Etsion, Y., Cabarcas, F., Rico, A., Ramirez, A., Badia, R.M., Ayguade, E., Labarta, J., Valero, M.: Task superscalar: an out-of-order task pipeline. In: MICRO, pp. 89\u2013100 (2010)","DOI":"10.1109\/MICRO.2010.13"},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"Grass, T., Allande, C., Armejach, A., Rico, A., Ayguad\u00e9, E., Labarta, J., Valero, M., Casas, M., Moreto, M.: MUSA: a multi-level simulation approach for next-generation HPC machines. In: SC 2016, pp. 526\u2013537, November 2016","DOI":"10.1109\/SC.2016.44"},{"key":"20_CR17","unstructured":"Jeff, B.: big.LITTLE technology moves towards fully heterogeneous global task scheduling. ARM White Paper (2013)"},{"key":"20_CR18","doi-asserted-by":"crossref","unstructured":"Jeffrey, M.C., Subramanian, S., Yan, C., Emer, J., Sanchez, D.: A scalable architecture for ordered parallelism. In: MICRO, pp. 228\u2013241 (2015)","DOI":"10.1145\/2830772.2830777"},{"key":"20_CR19","doi-asserted-by":"crossref","unstructured":"Kumar, S., Hughes, C.J., Nguyen, A.: Carbon: architectural support for fine-grained parallelism on chip multiprocessors. In: ISCA, pp. 162\u2013173 (2007)","DOI":"10.1145\/1250662.1250683"},{"key":"20_CR20","doi-asserted-by":"crossref","unstructured":"Manivannan, M., Stenstr\u00f6m, P.: Runtime-guided cache coherence optimizations in multicore architectures. In: IPDPS (2014)","DOI":"10.1109\/IPDPS.2014.71"},{"key":"20_CR21","doi-asserted-by":"crossref","unstructured":"Papaefstathiou, V., Katevenis, M.G., Nikolopoulos, D.S., Pnevmatikatos, D.: Prefetching and cache management using task lifetimes. In: ICS 2013, pp. 325\u2013334 (2013)","DOI":"10.1145\/2464996.2465443"},{"key":"20_CR22","volume-title":"Intel Threading Building Blocks - Outfitting C++ for Multicore Processor Parallelism","author":"J Reinders","year":"2007","unstructured":"Reinders, J.: Intel Threading Building Blocks - Outfitting C++ for Multicore Processor Parallelism. O\u2019Reilly, Sebastopol (2007)"},{"issue":"4","key":"20_CR23","doi-asserted-by":"publisher","first-page":"36:1","DOI":"10.1145\/2086696.2086715","volume":"8","author":"A Rico","year":"2012","unstructured":"Rico, A., Cabarcas, F., Villavieja, C., Pavlovic, M., Vega, A., Etsion, Y., Ramirez, A., Valero, M.: On the simulation of large-scale architectures using multiple application abstraction levels. ACM Trans. Archit. Code Optim. 8(4), 36:1\u201336:20 (2012)","journal-title":"ACM Trans. Archit. Code Optim."},{"key":"20_CR24","doi-asserted-by":"crossref","unstructured":"Sanchez, D., Yoo, R.M., Kozyrakis, C.: Flexible architectural support for fine-grain scheduling. In: ASPLOS, pp. 311\u2013322 (2010)","DOI":"10.1145\/1736020.1736055"},{"key":"20_CR25","doi-asserted-by":"crossref","unstructured":"Sj\u00e4lander, M., Terechko, A., Duranton, M.: A look-ahead task management unit for embedded multicore architectures. In: EUROMICRO DSD, pp. 149\u2013157 (2008)","DOI":"10.1109\/DSD.2008.45"},{"key":"20_CR26","doi-asserted-by":"crossref","unstructured":"Tan, X., Bosch, J., Vidal, M., \u00c1lvarez, C., Jim\u00e9nez-Gonz\u00e1lez, D., Ayguad\u00e9, E., Valero, M.: General purpose task-dependence management hardware for task-based dataflow programming models. In: IPDPS, pp. 244\u2013253 (2017)","DOI":"10.1109\/IPDPS.2017.48"},{"key":"20_CR27","doi-asserted-by":"crossref","unstructured":"Vandierendonck, H., Tzenakis, G., Nikolopoulos, D.S.: A unified scheduler for recursive and task dataflow parallelism. In: PACT, pp. 1\u201311 (2011)","DOI":"10.1109\/PACT.2011.7"},{"key":"20_CR28","doi-asserted-by":"crossref","unstructured":"Castillo, E., Alvarez, L., Moret\u00f3, M., Casas, M., Vallejo, E., Bosque, J.L., Beivide, R., Valero, M.: Architectural support for task dependence management with flexible software scheduling. In: HPCA, pp. 283\u2013295 (2018)","DOI":"10.1109\/HPCA.2018.00033"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-92040-5_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,18]],"date-time":"2019-10-18T13:57:07Z","timestamp":1571407027000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-92040-5_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319920399","9783319920405"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-92040-5_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]}}}