{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T14:57:55Z","timestamp":1770994675498,"version":"3.50.1"},"publisher-location":"Berlin, Heidelberg","reference-count":24,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642544194","type":"print"},{"value":"9783642544200","type":"electronic"}],"license":[{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"content-version":"tdm","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":[[2014]]},"DOI":"10.1007\/978-3-642-54420-0_19","type":"book-chapter","created":{"date-parts":[[2014,4,9]],"date-time":"2014-04-09T17:40:41Z","timestamp":1397065241000},"page":"188-197","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Compiler-Driven Data Layout Transformation for Heterogeneous Platforms"],"prefix":"10.1007","author":[{"given":"Deepak","family":"Majeti","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rajkishore","family":"Barik","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jisheng","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Max","family":"Grossman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vivek","family":"Sarkar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"19_CR1","unstructured":"Amd app sdk v2.8, \n                    \n                      http:\/\/developer.amd.com\/tools\/heterogeneous-Computing\/amd-accelerated-parallel-processing-app-sdk"},{"key":"19_CR2","unstructured":"Habanero-c, \n                    \n                      https:\/\/wiki.rice.edu\/confluence\/display\/HABANERO\/Habanero-C"},{"key":"19_CR3","unstructured":"Intel opencl sdk, \n                    \n                      http:\/\/software.intel.com\/en-us\/vcsource\/tools\/opencl-sdk"},{"key":"19_CR4","unstructured":"Intel thread building blocks, \n                    \n                      http:\/\/threadingbuildingblocks.org\/"},{"key":"19_CR5","unstructured":"Nvidia sdk, \n                    \n                      https:\/\/developer.nvidia.com"},{"key":"19_CR6","unstructured":"Openacc, \n                    \n                      http:\/\/www.openacc-standard.org"},{"key":"19_CR7","unstructured":"Parboil benchmark suite, \n                    \n                      http:\/\/impact.crhc.illinois.edu\/parboil.aspx"},{"key":"19_CR8","unstructured":"SIMD Parallelization of Applications that Traverse Irregular Data Structures. IEEE Computer Society (2013)"},{"key":"19_CR9","doi-asserted-by":"crossref","unstructured":"Chatterjee, et al.: Integrating asynchronous task parallelism with mpi. In: IPDPS 2013 (2013)","DOI":"10.1109\/IPDPS.2013.78"},{"key":"19_CR10","doi-asserted-by":"crossref","unstructured":"Che, et al.: Dymaxion: optimizing memory access patterns for heterogeneous systems. In: SC 2011, pp. 13:1\u201313:11. ACM, New York (2011)","DOI":"10.1145\/2063384.2063401"},{"key":"19_CR11","doi-asserted-by":"crossref","unstructured":"Che, et al.: Rodinia: A benchmark suite for heterogeneous computing. In: ISWC 2009, pp. 44\u201354 (October 2009)","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"19_CR12","unstructured":"Microsoft Corporation. C++ accelerated massive parallelism specification, \n                    \n                      http:\/\/msdn.microsoft.com\/en-us\/library\/vstudio\/hh265136.aspx"},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"Cunningham, D., Bordawekar, R., Saraswat, V.: Gpu programming in a high level language: compiling x10 to cuda. In: X10 2011, pp. 8:1\u20138:10. ACM, New York (2011)","DOI":"10.1145\/2212736.2212744"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Dubach, et al.: Compiling a high-level language for gpus: (via language support for architectures and compilers). In: PLDI 2012, pp. 1\u201312. ACM, NY (2012)","DOI":"10.1145\/2345156.2254066"},{"key":"19_CR15","unstructured":"Center for Domain Specific\u00a0Computing. Cdsc research applications"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"Liu, et al.: Data layout optimization for gpgpu architectures. In: PPoPP 2013, pp. 283\u2013284. ACM, NY (2013)","DOI":"10.1145\/2517327.2442546"},{"key":"19_CR17","unstructured":"LLNL. Rose compiler infrastructure, \n                    \n                      http:\/\/rosecompiler.org\/"},{"key":"19_CR18","unstructured":"Rodinia\u00a0Benchmark Suite. Srad wiki page"},{"key":"19_CR19","doi-asserted-by":"crossref","unstructured":"Sung, et al.: Data layout transformation exploiting memory-level parallelism in structured grid many-core applications. In: PACT 2010, pp. 513\u2013522. ACM, New York (2010)","DOI":"10.1145\/1854273.1854336"},{"key":"19_CR20","doi-asserted-by":"crossref","unstructured":"Sung, I.-J., Liu, G.D., Hwu, W.-M.W.: Dl: A data layout transformation system for heterogeneous computing. In: InPar 2012, pp. 1\u201311 (May 2012)","DOI":"10.1109\/InPar.2012.6339606"},{"key":"19_CR21","first-page":"214","volume-title":"ICS 2011","author":"D. Unat","year":"2011","unstructured":"Unat, D., Cai, X., Baden, S.B.: Mint: realizing cuda performance in 3d stencil methods with annotated c. In: ICS 2011, pp. 214\u2013224. ACM, New York (2011)"},{"key":"19_CR22","unstructured":"Vincent, C., Jisheng, Z., Jun, S., Vivek, S.: Habanero-java: the new adventures of old x10. In: PPPJ 2011 (2011)"},{"key":"19_CR23","doi-asserted-by":"crossref","unstructured":"Wu, et al.: Complexity analysis and algorithm design for reorganizing data to minimize non-coalesced memory accesses on gpu. In: PPoPP 2013, pp. 57\u201368. ACM, New York (2013)","DOI":"10.1145\/2517327.2442523"},{"key":"19_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1007\/978-3-642-38750-0_11","volume-title":"Supercomputing","author":"Y. Zhang","year":"2013","unstructured":"Zhang, Y., Sinclair II, M., Chien, A.A.: Improving performance portability in openCL programs. In: Kunkel, J.M., Ludwig, T., Meuer, H.W. (eds.) ISC 2013. LNCS, vol.\u00a07905, pp. 136\u2013150. Springer, Heidelberg (2013)"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2013: Parallel Processing Workshops"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-54420-0_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,4,19]],"date-time":"2020-04-19T20:09:04Z","timestamp":1587326944000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-54420-0_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783642544194","9783642544200"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-54420-0_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}