{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T06:49:37Z","timestamp":1743058177361,"version":"3.40.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319174723"},{"type":"electronic","value":"9783319174730"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-17473-0_2","type":"book-chapter","created":{"date-parts":[[2015,4,30]],"date-time":"2015-04-30T09:59:39Z","timestamp":1430387979000},"page":"19-35","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Directive-Based Compilers for GPUs"],"prefix":"10.1007","author":[{"given":"Swapnil","family":"Ghike","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rub\u00e9n","family":"Gran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mar\u00eda J.","family":"Garzar\u00e1n","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Padua","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,5,1]]},"reference":[{"key":"2_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1007\/978-3-642-36036-7_16","volume-title":"Languages and Compilers for Parallel Computing","author":"M Amini","year":"2013","unstructured":"Amini, M., Coelho, F., Irigoin, F., Keryell, R.: Static compilation analysis for host-accelerator communication optimization. In: Rajopadhye, S., Mills Strout, M. (eds.) LCPC 2011. LNCS, vol. 7146, pp. 237\u2013251. Springer, Heidelberg (2013)"},{"key":"2_CR2","unstructured":"Bordawekar, R., Bondhugula, U., Rao, R.: Can CPUs match GPUs on performance with productivity?: Experiences with optimizing a flop-intensive application on CPUs and GPU. Technical report RC25033, IBM, August 2010"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Boyer, M., Tarjan, D., Acton, S.T., Skadron, K.: Accelerating leukocyte tracking using cuda: a case study in leveraging manycore coprocessors. In: Proceedings of IPDPS, pp. 1\u201312 (2009)","DOI":"10.1109\/IPDPS.2009.5160984"},{"key":"2_CR4","unstructured":"CAPS Enterprise: HMPP workbench (2011). http:\/\/www.caps-entreprise.com\/technology\/hmpp\/"},{"key":"2_CR5","unstructured":"CAPS Enterprise and Cray Inc. and NVIDIA and the Portland Group: The openacc application programming interface, v1.0, November 2011. http:\/\/www.openacc-standard.org\/"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Che, S., et al.: Rodinia: a benchmark suite for heterogeneous computing. In: IISWC 2009. pp. 44\u201354, October 2009","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Che, S., et al.: A characterization of the rodinia benchmark suite with comparison to contemporary CMP workloads. In: Proceedings of IISWC, pp. 1\u201311 (2010)","DOI":"10.1109\/IISWC.2010.5650274"},{"key":"2_CR8","unstructured":"Cloutier, B., Muite, B.K., Rigge, P.: A comparison of CPU and GPU performance for fourier pseudospectral simulations of the navier-stokes, cubic nonlinear schrodinger and sine gordon equations. ArXiv e-prints, June 2012"},{"key":"2_CR9","unstructured":"CRAY: Cray Compiler Environment (2011). http:\/\/docs.cray.com\/books\/S-2179-52\/html-S-2179-52\/index.html"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Grauer Gray, S., Xu, L., Searles, R., Ayalasomayajula, S., Cavazos, J.: Auto-tuning a high-level language targeted to GPU codes. In: Proceedings of InPar, pp. 1\u201310 (2012)","DOI":"10.1109\/InPar.2012.6339595"},{"key":"2_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1007\/978-3-642-16233-6_13","volume-title":"Facing the Multicore-challenge","author":"H Hacker","year":"2010","unstructured":"Hacker, H., Trinitis, C., Weidendorfer, J., Brehm, M.: Considering GPGPU for HPC Centers: Is It Worth the effort? In: Keller, R., Kramer, D., Weiss, J.-P. (eds.) Facing the Multicore-Challenge. LNCS, vol. 6310, pp. 118\u2013130. Springer, Heidelberg (2010)"},{"issue":"1","key":"2_CR12","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1109\/TPDS.2010.62","volume":"22","author":"T Han","year":"2011","unstructured":"Han, T., Abdelrahman, T.: HiCUDA: high-level GPGPU programming. IEEE Trans. Parallel Distrib. Syst. 22(1), 78\u201390 (2011)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Henderson, T., Middlecoff, J., Rosinski, J., Govett, M., Madden, P.: Experience applying fortran GPU compilers to numerical weather prediction. In: Proceedings of SAAHPC, pp. 34\u201341, July 2011","DOI":"10.1109\/SAAHPC.2011.9"},{"key":"2_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1007\/978-3-642-30397-5_9","volume-title":"Facing the Multicore - Challenge II","author":"O Hernandez","year":"2012","unstructured":"Hernandez, O., Ding, W., Chapman, B., Kartsaklis, C., Sankaran, R., Graham, R.: Experiences with high-level programming directives for porting applications to GPUs. In: Keller, R., Kramer, D., Weiss, J.-P. (eds.) Facing the Multicore - Challenge II. LNCS, vol. 7174, pp. 96\u2013107. Springer, Heidelberg (2012)"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Enos, J., et al.: Quantifying the impact of GPUs on performance and energy efficiency in HPC clusters. In: Internatioanl Green Computing Conference, pp. 317\u2013324, August 2010","DOI":"10.1109\/GREENCOMP.2010.5598297"},{"issue":"6","key":"2_CR16","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1145\/2345156.1993516","volume":"47","author":"TB Jablin","year":"2011","unstructured":"Jablin, T.B., et al.: Automatic CPU-GPU communication management and optimization. SIGPLAN Not. 47(6), 142\u2013151 (2011)","journal-title":"SIGPLAN Not."},{"key":"2_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/978-3-642-30961-8_12","volume-title":"OpenMP in a Heterogeneous World","author":"H Jin","year":"2012","unstructured":"Jin, H., Kellogg, M., Mehrotra, P.: Using compiler directives for accelerating CFD applications on GPUs. In: Chapman, B.M., Massaioli, F., M\u00fcller, M.S., Rorro, M. (eds.) IWOMP 2012. LNCS, vol. 7312, pp. 154\u2013168. Springer, Heidelberg (2012)"},{"key":"2_CR18","volume-title":"Optimizing Compilers for Modern Architectures: A Dependence-Based Approach","author":"K Kennedy","year":"2002","unstructured":"Kennedy, K., Allen, J.R.: Optimizing Compilers for Modern Architectures: A Dependence-Based Approach. Morgan Kaufmann Publishers Inc., San Francisco (2002)"},{"key":"2_CR19","unstructured":"Khronos Group: Opencl - the open standard for parallel programming of heterogeneous systems (2011). http:\/\/www.khronos.org\/opencl"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Lee, S., Eigenmann, R.: OpenMPC: extended OpenMP programming and tuning for GPUs. In: Proceedings of SC 2010 (2010)","DOI":"10.1109\/SC.2010.36"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Lee, S., Min, S.J., Eigenmann, R.: OpenMP to GPGPU: a compiler framework for automatic translation and optimization. In: Proceedings of PPoPP 2009 (2010)","DOI":"10.1145\/1504176.1504194"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Lee, S., Vetter, J.S.: Early evaluation of directive-based GPU programming models for productive exascale computing. In: Proceedings of SC2012. IEEE Press, Salt Lake City (2012)","DOI":"10.1109\/SC.2012.51"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Leung, A., Vasilache, N., Meister, B., Baskaran, M., Wohlford, D., Bastoul, C., Lethin, R.: A mapping path for multi-GPGPU accelerated computers from a portable high level programming abstraction. In: Proceedings of GPGPU (2010)","DOI":"10.1145\/1735688.1735698"},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"Membarth, R., Hannig, F., Teich, J., Korner, M., Eckert, W.: Frameworks for GPU accelerators: a comprehensive evaluation using 2D\/3D image registration. In: Proceedings of SASP, pp. 78\u201381, June 2011","DOI":"10.1109\/SASP.2011.5941083"},{"key":"2_CR25","unstructured":"NVIDIA: Compute Command Line Profiler. NVIDIA Whitepaper"},{"key":"2_CR26","unstructured":"NVIDIA: The Benefits of Multiple CPU Cores in Mobile Devices. NVIDIA Whitepaper. http:\/\/www.nvidia.com\/content\/PDF\/tegra_white_papers\/Benefits-of-Multi-core-CPUs-in-Mobile-Devices_Ver1.2.pdf"},{"key":"2_CR27","unstructured":"NVIDIA: Bring high-end graphics to handheld devices. NVIDIA White Paper (2011). http:\/\/www.nvidia.com\/content\/PDF\/tegra_white_papers\/Bringing_High-End_Graphics_to_Handheld_Devices.pdf"},{"key":"2_CR28","unstructured":"NVIDIA Corporation: NVIDIA CUDA programming guide version 4.0 (2011). http:\/\/developer.download.nvidia.com"},{"key":"2_CR29","unstructured":"OpenMP: Openmp: Complete specification v4.0 (2013). http:\/\/openmp.org\/wp\/resources\/"},{"key":"2_CR30","unstructured":"The Portland Group: PGI compiler reference manual (2011). http:\/\/www.pgroup.com\/doc\/pgiref.pdf"},{"key":"2_CR31","unstructured":"Website, B.W.: (2011). http:\/\/www.ncsa.illinois.edu\/BlueWaters\/"},{"key":"2_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"859","DOI":"10.1007\/978-3-642-32820-6_85","volume-title":"Euro-Par 2012 Parallel Processing","author":"S Wienke","year":"2012","unstructured":"Wienke, S., Springer, P., Terboven, C., an Mey, D.: OpenACC \u2014 first experiences with real-world applications. In: Kaklamanis, C., Papatheodorou, T., Spirakis, P.G. (eds.) Euro-Par 2012. LNCS, vol. 7484, pp. 859\u2013870. Springer, Heidelberg (2012)"}],"container-title":["Lecture Notes in Computer Science","Languages and Compilers for Parallel Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-17473-0_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,15]],"date-time":"2023-02-15T07:29:43Z","timestamp":1676446183000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-17473-0_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319174723","9783319174730"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-17473-0_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2015]]},"assertion":[{"value":"1 May 2015","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}