{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T05:53:16Z","timestamp":1747806796915},"publisher-location":"Berlin, Heidelberg","reference-count":24,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642360350"},{"type":"electronic","value":"9783642360367"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-36036-7_16","type":"book-chapter","created":{"date-parts":[[2013,1,17]],"date-time":"2013-01-17T01:59:30Z","timestamp":1358387970000},"page":"237-251","source":"Crossref","is-referenced-by-count":6,"title":["Static Compilation Analysis for Host-Accelerator Communication Optimization"],"prefix":"10.1007","author":[{"given":"Mehdi","family":"Amini","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fabien","family":"Coelho","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fran\u00e7ois","family":"Irigoin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ronan","family":"Keryell","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"16_CR1","unstructured":"Amini, M., Ancourt, C., Coelho, F., Creusillet, B., Guelton, S., Irigoin, F., Jouvelot, P., Keryell, R., Villalon, P.: PIPS is not (just) polyhedral software. In: 1st International Workshop on Polyhedral Compilation Techniques, Impact (in Conjunction with CGO 2011) (April 2011)"},{"issue":"1","key":"16_CR2","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1155\/1997\/195689","volume":"6","author":"C. Ancourt","year":"1997","unstructured":"Ancourt, C., Coelho, F., Irigoin, F., Keryell, R.: A linear algebra framework for static High Performance Fortran code distribution. Scientific Programming\u00a06(1), 3\u201327 (1997)","journal-title":"Scientific Programming"},{"key":"16_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"874","DOI":"10.1007\/978-3-642-01970-8_88","volume-title":"Computational Science \u2013 ICCS 2009","author":"D. Aubert","year":"2009","unstructured":"Aubert, D., Amini, M., David, R.: A Particle-Mesh Integrator for Galactic Dynamics Powered by GPGPUs. In: Allen, G., Nabrzyski, J., Seidel, E., van Albada, G.D., Dongarra, J., Sloot, P.M.A. (eds.) ICCS 2009, Part I. LNCS, vol.\u00a05544, pp. 874\u2013883. Springer, Heidelberg (2009)"},{"key":"16_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"863","DOI":"10.1007\/978-3-642-03869-3_80","volume-title":"Euro-Par 2009 Parallel Processing","author":"C. Augonnet","year":"2009","unstructured":"Augonnet, C., Thibault, S., Namyst, R., Wacrenier, P.-A.: StarPU: A unified platform for task scheduling on heterogeneous multicore architectures. Concurrency and Computation: Practice and Experience 23, 187\u2013198 (2011); Special Issue: Sips, H., Epema, D., Lin, H.-X. (eds.) Euro-Par 2009. LNCS, vol.\u00a05704, pp. 863\u2013874. Springer, Heidelberg (2009)"},{"key":"16_CR5","first-page":"325","volume":"17","author":"F. Bodin","year":"2009","unstructured":"Bodin, F., Bihan, S.: Heterogeneous multicore parallel programming for graphics processing units. Sci. Program.\u00a017, 325\u2013336 (2009)","journal-title":"Sci. Program."},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Che, S., Boyer, M., Meng, J., Tarjan, D., Sheaffer, J.W., Lee, S.H., Skadron, K.: Rodinia: A benchmark suite for heterogeneous computing. In: IEEE International Symposium on Workload Characterization (2009)","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Y., Cui, X., Mei, H.: Large-scale FFT on GPU clusters. In: 24th ACM International Conference on Supercomputing, ICS 2010 (2010)","DOI":"10.1145\/1810085.1810128"},{"issue":"6","key":"16_CR8","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1007\/BF03356758","volume":"24","author":"B. Creusillet","year":"1996","unstructured":"Creusillet, B., Irigoin, F.: Interprocedural array region analyses. Int. J. Parallel Program.\u00a024(6), 513\u2013546 (1996)","journal-title":"Int. J. Parallel Program."},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Datta, K., Murphy, M., Volkov, V., Williams, S., Carter, J., Oliker, L., Patterson, D., Shalf, J., Yelick, K.: Stencil computation optimization and auto-tuning on state-of-the-art multicore architectures. In: Proceedings of the 2008 ACM\/IEEE Conference on Supercomputing (2008)","DOI":"10.1109\/SC.2008.5222004"},{"key":"16_CR10","doi-asserted-by":"crossref","first-page":"670","DOI":"10.14778\/1920841.1920927","volume":"3","author":"W. Fang","year":"2010","unstructured":"Fang, W., He, B., Luo, Q.: Database compression on graphics processors. Proc. VLDB Endow.\u00a03, 670\u2013680 (2010)","journal-title":"Proc. VLDB Endow."},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Feautrier, P.: Parametric integer programming. RAIRO Recherche Op\u00e9rationnelle\u00a022 (1988)","DOI":"10.1051\/ro\/1988220302431"},{"key":"16_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1007\/3-540-53065-7_109","volume-title":"CONPAR 90 - VAPP IV","author":"H.M. Gerndt","year":"1990","unstructured":"Gerndt, H.M., Zima, H.P.: Optimizing Communication in SUPERB. In: Burkhart, H. (ed.) CONPAR 1990 and VAPP 1990. LNCS, vol.\u00a0457, pp. 300\u2013311. Springer, Heidelberg (1990)"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Gong, C., Gupta, R., Melhem, R.: Compilation techniques for optimizing communication on distributed-memory systems. In: ICPP 1993 (1993)","DOI":"10.1109\/ICPP.1993.58"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Han, T.D., Abdelrahman, T.S.: hiCUDA: a high-level directive-based language for GPU programming. In: Proceedings of GPGPU-2. ACM (2009)","DOI":"10.1145\/1513895.1513902"},{"key":"16_CR15","unstructured":"HPC Project. Par4All automatic parallelization, \n                  \n                    http:\/\/www.par4all.org"},{"key":"16_CR16","unstructured":"Huang, W., Ghosh, S., Velusamy, S., Sankaranarayanan, K., Skadron, K., Stan, M.R.: Hotspot: acompact thermal modeling methodology for early-stage VLSI design. IEEE Trans. Very Large Scale Integr. Syst. (May 2006)"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Irigoin, F., Jouvelot, P., Triolet, R.: Semantical interprocedural parallelization: an overview of the PIPS project. In: ICS 1991, pp. 244\u2013251 (1991)","DOI":"10.1145\/109025.109086"},{"key":"16_CR18","first-page":"142","volume-title":"Proceedings of the 32nd ACM SIGPLAN Conference on Programming Language Design and Implementation, PLDI 2011","author":"T.B. Jablin","year":"2011","unstructured":"Jablin, T.B., Prabhu, P., Jablin, J.A., Johnson, N.P., Beard, S.R., August, D.I.: Automatic CPU-GPU communication management and optimization. In: Proceedings of the 32nd ACM SIGPLAN Conference on Programming Language Design and Implementation, PLDI 2011, pp. 142\u2013151. ACM, New York (2011)"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Lee, S., Eigenmann, R.: OpenMPC: Extended OpenMP programming and tuning for GPUs. In: SC 2010, pp. 1\u201311 (2010)","DOI":"10.1109\/SC.2010.36"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Lee, S., Min, S.-J., Eigenmann, R.: OpenMP to GPGPU: a compiler framework for automatic translation and optimization. In: PPoPP (2009)","DOI":"10.1145\/1504176.1504194"},{"key":"16_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1007\/978-3-642-13217-9_13","volume-title":"Beyond Loop Level Parallelism in OpenMP: Accelerators, Tasking and More","author":"S. Ohshima","year":"2010","unstructured":"Ohshima, S., Hirasawa, S., Honda, H.: OMPCUDA: OpenMP Execution Framework for CUDA Based on Omni OpenMP Compiler. In: Sato, M., Hanawa, T., M\u00fcller, M.S., Chapman, B.M., de Supinski, B.R. (eds.) IWOMP 2010. LNCS, vol.\u00a06132, pp. 161\u2013173. Springer, Heidelberg (2010)"},{"key":"16_CR22","unstructured":"Pouchet, L.-N.: The Polyhedral Benchmark suite 2.0 (March 2011)"},{"key":"16_CR23","doi-asserted-by":"crossref","unstructured":"Wolfe, M.: Implementing the PGI accelerator model. In: GPGPU (2010)","DOI":"10.1145\/1735688.1735697"},{"key":"16_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"887","DOI":"10.1007\/978-3-642-03869-3_82","volume-title":"Euro-Par 2009 Parallel Processing","author":"Y. Yan","year":"2009","unstructured":"Yan, Y., Grossman, M., Sarkar, V.: JCUDA: A Programmer-Friendly Interface for Accelerating Java Programs with CUDA. In: Sips, H., Epema, D., Lin, H.-X. (eds.) Euro-Par 2009. LNCS, vol.\u00a05704, pp. 887\u2013899. Springer, Heidelberg (2009)"}],"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\/978-3-642-36036-7_16.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T13:34:33Z","timestamp":1620135273000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-36036-7_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642360350","9783642360367"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-36036-7_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}