{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,20]],"date-time":"2025-03-20T21:10:14Z","timestamp":1742505014737,"version":"3.40.1"},"publisher-location":"Berlin, Heidelberg","reference-count":14,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642243219"},{"type":"electronic","value":"9783642243226"}],"license":[{"start":{"date-parts":[[2011,1,1]],"date-time":"2011-01-01T00:00:00Z","timestamp":1293840000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011]]},"DOI":"10.1007\/978-3-642-24322-6_5","type":"book-chapter","created":{"date-parts":[[2012,2,15]],"date-time":"2012-02-15T04:26:16Z","timestamp":1329279976000},"page":"40-51","source":"Crossref","is-referenced-by-count":0,"title":["Implementing a GPU Programming Model on a Non-GPU Accelerator Architecture"],"prefix":"10.1007","author":[{"given":"Stephen M.","family":"Kofsky","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel R.","family":"Johnson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John A.","family":"Stratton","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen-mei W.","family":"Hwu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sanjay J.","family":"Patel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Steven S.","family":"Lumetta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"5_CR1","unstructured":"Diamos, G.: The design and implementation ocelot\u2019s dynamic binary translator from ptx to multi-core x86. Technical Report GIT-CERCS-09-18, Georgia Institute of Technology (2009)"},{"key":"5_CR2","doi-asserted-by":"crossref","unstructured":"Frigo, M., Johnson, S.: FFTW: an adaptive software architecture for the fft, vol.\u00a03, pp. 1381\u20131384 (May 1998)","DOI":"10.1109\/ICASSP.1998.681704"},{"key":"5_CR3","unstructured":"Dongarra, R.C.J.: Automatically tuned linear algebra software. Technical report, Knoxville, TN, USA (1997)"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Kelm, J.H., Johnson, D.R., Johnson, M.R., Crago, N.C., Tuohy, W., Mahesri, A., Lumetta, S.S., Frank, M.I., Patel, S.J.: Rigel: An architecture and scalable programming interface for a 1000-core accelerator. In: Proceedings of the International Symposium on Computer Architecture, pp. 140\u2013151 (June 2009)","DOI":"10.1145\/1555815.1555774"},{"key":"5_CR5","unstructured":"Khronos OpenCL Working Group. OpenCL Specification, 1.0 edn. (December 2008)"},{"key":"5_CR6","unstructured":"Kofsky, S.M.: Achieving performance portability across parallel accelerator architectures. Technical Report (to Appear), Center for Reliable and High-Performance Computing, University of Illinois, Urbana, IL (2010)"},{"key":"5_CR7","unstructured":"Lin, C.: The portability of parallel programs across MIMD computers. PhD thesis, Seattle, WA, USA (1992)"},{"issue":"2","key":"5_CR8","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1109\/MM.2008.31","volume":"28","author":"E. Lindholm","year":"2008","unstructured":"Lindholm, E., Nickolls, J., Oberman, S., Montrym, J.: NVIDIA Tesla: A unified graphics and computing architecture. IEEE Micro\u00a028(2), 39\u201355 (2008)","journal-title":"IEEE Micro"},{"key":"5_CR9","unstructured":"Moura, J.M.F., Johnson, J., Johnson, R.W., Padua, D., Prasanna, V.K., P\u00fcschel, M., Veloso, M.: SPIRAL: Automatic implementation of signal processing algorithms. In: High Performance Embedded Computing, HPEC (2000)"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Nickolls, J., Buck, I., Garland, M., Skadron, K.: Scalable parallel programming with CUDA. Queue\u00a06(2) (2008)","DOI":"10.1145\/1365490.1365500"},{"key":"5_CR11","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1145\/1356058.1356084","volume-title":"CGO 2008: Proceedings of the Sixth Annual IEEE\/ACM International Symposium on Code Generation and Optimization","author":"S. Ryoo","year":"2008","unstructured":"Ryoo, S., Rodrigues, C.I., Stone, S.S., Baghsorkhi, S.S., Ueng, S.-Z., Stratton, J.A., mei, W., Hwu, W.: Program optimization space pruning for a multithreaded GPU. In: CGO 2008: Proceedings of the Sixth Annual IEEE\/ACM International Symposium on Code Generation and Optimization, pp. 195\u2013204. ACM, New York (2008)"},{"key":"5_CR12","first-page":"8","volume-title":"HOPL III: Proceedings of the third ACM SIGPLAN conference on History of programming languages","author":"L. Snyder","year":"2007","unstructured":"Snyder, L.: The design and development of ZPL. In: HOPL III: Proceedings of the third ACM SIGPLAN conference on History of programming languages, pp. 8\u20131\u20138\u201337. ACM, New York (2007)"},{"issue":"10","key":"5_CR13","doi-asserted-by":"publisher","first-page":"1307","DOI":"10.1016\/j.jpdc.2008.05.013","volume":"68","author":"S.S. Stone","year":"2008","unstructured":"Stone, S.S., Haldar, J.P., Tsao, S.C., Hwu, W.W., Sutton, B.P., Liang, Z.P.: Accelerating advanced mri reconstructions on GPUs. J. Parallel Distrib. Comput.\u00a068(10), 1307\u20131318 (2008)","journal-title":"J. Parallel Distrib. Comput."},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Stratton, J.A., Stone, S.S., Hwu, W.-M.W.: MCUDA: An efficient implementation of CUDA kernels for multi-core CPUs, pp. 16\u201330 (2008)","DOI":"10.1007\/978-3-540-89740-8_2"}],"container-title":["Lecture Notes in Computer Science","Computer Architecture"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-24322-6_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,20]],"date-time":"2025-03-20T20:34:05Z","timestamp":1742502845000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-24322-6_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011]]},"ISBN":["9783642243219","9783642243226"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-24322-6_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2011]]}}}