{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T04:18:28Z","timestamp":1748405908033,"version":"3.41.0"},"publisher-location":"Cham","reference-count":20,"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_1","type":"book-chapter","created":{"date-parts":[[2015,4,30]],"date-time":"2015-04-30T09:59:39Z","timestamp":1430387979000},"page":"3-18","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Optimistic Parallelism on GPUs"],"prefix":"10.1007","author":[{"given":"Min","family":"Feng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rajiv","family":"Gupta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Laxmi N.","family":"Bhuyan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,5,1]]},"reference":[{"key":"1_CR1","unstructured":"Amini, M., Goubier, O., Guelton, S., Mcmahon, J.O., Pasquier, F.X., Pean, G., Villalon, P.: Par4All: from convex array regions to heterogeneous computing. In: IMPACT (2012)"},{"key":"1_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"851","DOI":"10.1007\/978-3-642-03869-3_79","volume-title":"Euro-Par 2009 Parallel Processing","author":"E Ayguad\u00e9","year":"2009","unstructured":"Ayguad\u00e9, E., Badia, R.M., Igual, F.D., Labarta, J., Mayo, R., Quintana-Ort\u00ed, E.S.: An extension of the StarSs programming model for platforms with multiple GPUs. In: Sips, H., Epema, D., Lin, H.-X. (eds.) Euro-Par 2009. LNCS, vol. 5704, pp. 851\u2013862. Springer, Heidelberg (2009)"},{"key":"1_CR3","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, pp. 225\u2013234 (2008)","DOI":"10.1145\/1375527.1375562"},{"issue":"1","key":"1_CR4","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1109\/99.660313","volume":"5","author":"L Dagum","year":"1998","unstructured":"Dagum, L., Menon, R.: OpenMP: an industry-standard API for shared-memory programming. IEEE Comput. Sci. Eng. 5(1), 46\u201355 (1998)","journal-title":"IEEE Comput. Sci. Eng."},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"Dang, F.H., Yu, H., Rauchwerger, L.: The R-LRPD test: speculative parallelization of partially parallel loops. In: IPDPS (2002)","DOI":"10.1109\/IPDPS.2002.1015493"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Diamos, G., Yalamanchili, S.: Speculative execution on multi-GPU systems. In: IPDPS, pp. 1\u201312 (2010)","DOI":"10.1109\/IPDPS.2010.5470427"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Ding, C., Shen, X., Kelsey, K., Tice, C., Huang, R., Zhang, C.: Software behavior oriented parallelization. In: PLDI, pp. 223\u2013234 (2007)","DOI":"10.1145\/1273442.1250760"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Feng, W., Xiao, S.: To GPU synchronize or not GPU synchronize? In: ISCAS, pp. 3801\u20133804 (2010)","DOI":"10.1109\/ISCAS.2010.5537722"},{"key":"1_CR9","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, pp. 101\u2013110 (2009)","DOI":"10.1145\/1594835.1504194"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Liu, S., Eisenbeis, C., Gaudiot, J.-L.: Speculative execution on GPU: an exploratory study. In: ICPP, pp. 453\u2013461 (2010)","DOI":"10.1109\/ICPP.2010.53"},{"issue":"5","key":"1_CR11","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1007\/s10766-010-0155-0","volume":"39","author":"S Liu","year":"2011","unstructured":"Liu, S., Eisenbeis, C., Gaudiot, J.-L.: Value prediction and speculative execution on GPU. Int. J. Parallel Program. 39(5), 533\u2013552 (2011)","journal-title":"Int. J. Parallel Program."},{"issue":"2","key":"1_CR12","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1145\/1365490.1365500","volume":"6","author":"J Nickolls","year":"2008","unstructured":"Nickolls, J., Buck, I., Garland, M., Skadron, K.: Scalable parallel programming with CUDA. Queue 6(2), 40\u201353 (2008)","journal-title":"Queue"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Rauchwerger, L., Padua, D.: The LRPD test: speculative run-time parallelization of loops with privatization and reduction parallelization. In: PLDI, pp. 218\u2013232 (1995)","DOI":"10.1145\/223428.207148"},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Samadi, M., Hormati, A., Lee, J., Mahlke, S.: Paragon: collaborative speculative loop execution on GPU and CPU. In: GPGPU, pp. 64\u201373 (2012)","DOI":"10.1145\/2159430.2159438"},{"issue":"3","key":"1_CR15","first-page":"66","volume":"12","author":"JE Stone","year":"2010","unstructured":"Stone, J.E., Gohara, D., Shi, G.: OpenCL: a parallel programming standard for heterogeneous computing systems. IEEE Des. Test 12(3), 66\u201373 (2010)","journal-title":"IEEE Des. Test"},{"key":"1_CR16","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)"},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"Wolfe, M.: Implementing the PGI accelerator model. In: GPGPU (2010)","DOI":"10.1145\/1735688.1735697"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Yang, Y., Xiang, P., Kong, J., Zhou, H.: A GPGPU compiler for memory optimization and parallelism management. In: PLDI, pp. 86\u201397 (2010)","DOI":"10.1145\/1809028.1806606"},{"key":"1_CR19","doi-asserted-by":"crossref","unstructured":"Zhang, C., Han, G., Wang, C.-L.: GPU-TLS: an efficient runtime for speculative loop parallelization on GPUs. In: CCGrid, pp. 120\u2013127 (2013)","DOI":"10.1109\/CCGrid.2013.34"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Zhang, E.Z., Jiang, Y., Guo, Z., Shen, X.: Streamlining GPU applications on the fly: thread divergence elimination through runtime thread-data remapping. In: ICS, pp. 115\u2013126 (2010)","DOI":"10.1145\/1810085.1810104"}],"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_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T18:35:26Z","timestamp":1748370926000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-17473-0_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319174723","9783319174730"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-17473-0_1","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"}}]}}