{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:33:41Z","timestamp":1742913221261,"version":"3.40.3"},"publisher-location":"Cham","reference-count":19,"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_3","type":"book-chapter","created":{"date-parts":[[2015,4,30]],"date-time":"2015-04-30T09:59:39Z","timestamp":1430387979000},"page":"36-50","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["GLES: A Practical GPGPU Optimizing Compiler Using Data Sharing and Thread Coarsening"],"prefix":"10.1007","author":[{"given":"Zhen","family":"Lin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaopeng","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han","family":"Wan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,5,1]]},"reference":[{"key":"3_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1007\/978-3-642-11970-5_14","volume-title":"Compiler Construction","author":"MM Baskaran","year":"2010","unstructured":"Baskaran, M.M., Ramanujam, J., Sadayappan, P.: Automatic C-to-CUDA code generation for affine programs. In: Gupta, R. (ed.) CC 2010. LNCS, vol. 6011, pp. 244\u2013263. Springer, Heidelberg (2010)"},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Baskaran, M.M., Bondhugula, U., Krishnamoorthy, S., Ramanujam, J., Rountev, A., Sadayappan, P.: A compiler framework for optimization of affine loop nests for gpgpus. In: ICS (2008)","DOI":"10.1145\/1375527.1375562"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Baskaran, M.M., Bondhugula, U., Krishnamoorthy, S., Ramanujam, J., Rountev, A., Sadayappan, P.: Automatic data movement and computation mapping for multi-level parallel architectures with explicitly managed memories. In: PPOPP (2008)","DOI":"10.1145\/1345206.1345210"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Chakrabarti, G., Grover, V., Aarts, B., Kong, X., Kudlur, M., Lin, Y., Marathe, J., Murphy, M., Wang, J.-Z.: Cuda: compiling and optimizing for a gpu platform. In: ICCS (2012)","DOI":"10.1016\/j.procs.2012.04.209"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Coutinho, B., Sampaio, D., Pereira, F.M.Q., Meira Jr., W.: Divergence analysis and optimizations (2011)","DOI":"10.1109\/PACT.2011.63"},{"key":"3_CR6","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1109\/MC.2009.385","volume":"42","author":"C Dave","year":"2009","unstructured":"Dave, C., Bae, H., Min, S.-J., Lee, S., Eigenmann, R., Midkiff, S.P.: Cetus: a source-to-source compiler infrastructure for multicores. IEEE Comput. 42, 36\u201342 (2009)","journal-title":"IEEE Comput."},{"issue":"5","key":"3_CR7","first-page":"686","volume":"73","author":"J Gai","year":"2013","unstructured":"Gai, J., Obeid, N., Holtrop, J.L., Wu, X.-L., Lam, F., Fu, M., Haldar, J.P., Hwu, W.-M.W., Liang, Z.-P., Sutton, B.P.: More impatient: a gridding-accelerated toeplitz-based strategy for non-cartesian high-resolution 3d mri on gpus. JPDC 73(5), 686\u2013697 (2013)","journal-title":"JPDC"},{"key":"3_CR8","first-page":"78","volume":"22","author":"TD Han","year":"2011","unstructured":"Han, T.D., Abdelrahman, T.S.: hiCUDA: High-Level GPGPU Programming. TPDS 22, 78\u201390 (2011)","journal-title":"TPDS"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Lee, S., Eigenmann, R.: OpenMPC: extended OpenMP programming and tuning for gpus. In: SC (2010)","DOI":"10.1109\/SC.2010.36"},{"key":"3_CR10","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":"3_CR11","unstructured":"NVIDIA Corporation. CUDA C Programming Guide (2012)"},{"key":"3_CR12","unstructured":"OpenAcc. The OpenACC Application Programming Interface (2013)"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Rodrigues, C.I., Hardy, D.J., Stone, J.E., Schulten, K., Hwu, W.-M.W.: Gpu acceleration of cutoff pair potentials for molecular modeling applications. In: CF (2008)","DOI":"10.1145\/1366230.1366277"},{"key":"3_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-540-89740-8_1","volume-title":"Languages and Compilers for Parallel Computing","author":"S-Z Ueng","year":"2008","unstructured":"Ueng, S.-Z., Lathara, M., Baghsorkhi, S.S., Hwu, W.W.: CUDA-lite: reducing gpu programming complexity. In: Amaral, J.N. (ed.) LCPC 2008. LNCS, vol. 5335, pp. 1\u201315. Springer, Heidelberg (2008)"},{"key":"3_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-642-28652-0_2","volume-title":"Compiler Construction","author":"S Unkule","year":"2012","unstructured":"Unkule, S., Shaltz, C., Qasem, A.: Automatic restructuring of gpu kernels for exploiting inter-thread data locality. In: O\u2019Boyle, M. (ed.) CC 2012. LNCS, vol. 7210, pp. 21\u201340. Springer, Heidelberg (2012)"},{"key":"3_CR16","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1145\/2400682.2400713","volume":"9","author":"S Verdoolaege","year":"2013","unstructured":"Verdoolaege, S., Carlos Juega, J., Cohen, A., Ignacio G\u00f3mez, J., Tenllado, C., Catthoor, F.: Polyhedral parallel code generation for CUDA. TACO 9, 54 (2013)","journal-title":"TACO"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Wong, H., Papadopoulou, M.-M., Sadooghi-Alvandi, M., Moshovos, A.: Demystifying GPU microarchitecture through microbenchmarking. In: ISPASS (2010)","DOI":"10.1109\/ISPASS.2010.5452013"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Wu, X.-L., Gai, J., Lam, F., Fu, M., Haldar, J.P., Zhuo, Y., Liang, Z.-P., Hwu, W.-M., Sutton, B.P.: Impatient mri: Illinois massively parallel acceleration toolkit for image reconstruction with enhanced throughput in mri. In: IEEE International Symposium on Biomedical Imaging: From Nano to Macro (2011)","DOI":"10.1109\/ISBI.2011.5872356"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Yang, Y., Xiang, P., Kong, J., Zhou, H.: A GPGPU compiler for memory optimization and parallelism management. In: PLDI (2010)","DOI":"10.1145\/1806596.1806606"}],"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_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,10]],"date-time":"2023-02-10T08:11:59Z","timestamp":1676016719000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-17473-0_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319174723","9783319174730"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-17473-0_3","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"}}]}}