{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T21:18:46Z","timestamp":1725743926702},"publisher-location":"Berlin, Heidelberg","reference-count":29,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642404467"},{"type":"electronic","value":"9783642404474"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-40447-4_18","type":"book-chapter","created":{"date-parts":[[2013,8,6]],"date-time":"2013-08-06T01:00:39Z","timestamp":1375750839000},"page":"279-294","source":"Crossref","is-referenced-by-count":8,"title":["Towards Heterogeneous Computing without Heterogeneous Programming"],"prefix":"10.1007","author":[{"given":"Miguel","family":"Diogo","sequence":"first","affiliation":[]},{"given":"Clemens","family":"Grelck","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"issue":"4","key":"18_CR1","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1007\/s10766-006-0018-x","volume":"34","author":"C. Grelck","year":"2006","unstructured":"Grelck, C., et al.: SAC: a functional array language for efficient multi-threaded execution. International Journal of Parallel Programming\u00a034(4), 383\u2013427 (2006)","journal-title":"International Journal of Parallel Programming"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Wieser, V., et al.: Combining High Productivity and High Performance in Image Processing Using Single Assignment C on Multi-core CPUs and Many-core GPUs. Journal of Electronic Imaging\u00a021(2) (2012)","DOI":"10.1117\/1.JEI.21.2.021116"},{"issue":"4","key":"18_CR3","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1016\/j.parco.2008.03.001","volume":"34","author":"R. Chamberlain","year":"2008","unstructured":"Chamberlain, R., et al.: Visions for application development on hybrid computing systems. Parallel Computing\u00a034(4), 201\u2013216 (2008)","journal-title":"Parallel Computing"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Kumar, R., et al.: Heterogeneous chip multiprocessors. Computer\u00a038(11) (2005)","DOI":"10.1109\/MC.2005.379"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Guo, Z., et al.: A quantitative analysis of the speedup factors of FPGAs over processors. In: Field Programmable Gate Arrays, Monterrey, CA, USA (2004)","DOI":"10.1145\/968280.968304"},{"issue":"10","key":"18_CR6","doi-asserted-by":"publisher","first-page":"1370","DOI":"10.1016\/j.jpdc.2008.05.014","volume":"68","author":"S. Che","year":"2008","unstructured":"Che, S., et al.: A performance study of general-purpose applications on graphics processors using CUDA. Journal of Parallel and Distributed Computing\u00a068(10), 1370\u20131380 (2008)","journal-title":"Journal of Parallel and Distributed Computing"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Williams, S., et al.: The potential of the cell processor for scientific computing. In: 3rd Conference on Computing Frontiers, Ischia, Italy. ACM (2006)","DOI":"10.1145\/1128022.1128027"},{"key":"18_CR8","unstructured":"RapidMind Inc.: Writing Applications for the GPU Using the RapidMindTM Development Platform (2006)"},{"key":"18_CR9","unstructured":"Papakipos, M.: The PeakStream platform: High-Productivity software development for multi-core processors. Technical report, PeakStream Inc. (2007)"},{"key":"18_CR10","unstructured":"Dolbeau, R., et al.: HMPPTM: A hybrid multi-core parallel programming environment. In: General Purpose Processing on Graphics Processing Units, Boston, MA, USA (2007)"},{"key":"18_CR11","unstructured":"Tomov, S., et al.: MAGMA Users\u2019 Guide. University of Tennessee (2010)"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Horton, M., et al.: A Class of Hybrid LAPACK Algorithms for Multicore and GPU Architectures. In: Application Accelerators in High-Performance Computing, Knoxville, TN, USA (2011)","DOI":"10.1109\/SAAHPC.2011.18"},{"issue":"5","key":"18_CR13","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1002\/cpe.1848","volume":"24","author":"V. Ravi","year":"2011","unstructured":"Ravi, V., et al.: Compiler and runtime support for enabling reduction computations on heterogeneous systems. Concurrency and Computation: Practice and Experience\u00a024(5), 463\u2013480 (2011)","journal-title":"Concurrency and Computation: Practice and Experience"},{"issue":"3","key":"18_CR14","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1017\/S0956796805005538","volume":"15","author":"C. Grelck","year":"2005","unstructured":"Grelck, C.: Shared memory multiprocessor support for functional array processing in SAC. Journal of Functional Programming\u00a015(3), 353\u2013401 (2005)","journal-title":"Journal of Functional Programming"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Guo, J., et al.: Breaking the GPU programming barrier with the auto-parallelising SAC compiler. In: Declarative Aspects of Multicore Programming, Austin, TX, USA (2011)","DOI":"10.1145\/1926354.1926359"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Hummel, S., et al.: Load-sharing in heterogeneous systems via weighted factoring. In: Parallel Algorithms and Architectures, Padua, Italy, pp. 318\u2013328. ACM (1996)","DOI":"10.1145\/237502.237576"},{"key":"18_CR17","unstructured":"Boyer, M., et al.: Automatic Intra-Application Load Balancing for Heterogeneous Systems. In: AMD Fusion\u00ae Developer Summit 2011, Bellevue, Washington, USA (2011)"},{"key":"18_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1007\/978-3-642-32096-5_5","volume-title":"Central European Functional Programming School","author":"C. Grelck","year":"2012","unstructured":"Grelck, C.: Single Assignment C (SAC): High Productivity meets High Performance. In: Zs\u00f3k, V., Horv\u00e1th, Z., Plasmeijer, R. (eds.) CEFP. LNCS, vol.\u00a07241, pp. 207\u2013278. Springer, Heidelberg (2012)"},{"issue":"7+8","key":"18_CR19","doi-asserted-by":"publisher","first-page":"507","DOI":"10.1016\/j.parco.2006.08.003","volume":"32","author":"C. Grelck","year":"2006","unstructured":"Grelck, C., Scholz, S.B.: Merging compositions of array skeletons in SAC. Journal of Parallel Computing\u00a032(7+8), 507\u2013522 (2006)","journal-title":"Journal of Parallel Computing"},{"key":"18_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1007\/10722298_5","volume-title":"Implementation of Functional Languages","author":"C. Grelck","year":"2000","unstructured":"Grelck, C., et al.: On code generation for multi-generator with-loops in SAC. In: Koopman, P., Clack, C. (eds.) IFL 1999. LNCS, vol.\u00a01868, pp. 77\u201394. Springer, Heidelberg (2000)"},{"key":"18_CR21","unstructured":"Guo, J.: Compilation of SAC to CUDA. PhD thesis, University of Hertfordshire, Hatfield, UK (2012)"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Augonnet, C., et al.: A unified runtime system for heterogeneous multi-core architectures. In: Euro-Par 2008, Las Palmas, Spain (2008)","DOI":"10.1007\/978-3-642-00955-6_22"},{"issue":"3","key":"18_CR23","doi-asserted-by":"publisher","first-page":"348","DOI":"10.1145\/773453.808204","volume":"12","author":"M. Papamarcos","year":"1984","unstructured":"Papamarcos, M., et al.: A low-overhead coherence solution for multiprocessors with private cache memories. Computer Architecture News\u00a012(3), 348\u2013354 (1984)","journal-title":"Computer Architecture News"},{"key":"18_CR24","unstructured":"DAS-4: Distributed ASCI Supercomputer 4, \n \n http:\/\/www.cs.vu.nl\/das4\/"},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"Chakravarty, M., et al.: Accelerating Haskell array codes with multicore GPUs. In: Declarative Aspects of Multicore Programming, Austin, TX, USA (2011)","DOI":"10.1145\/1926354.1926358"},{"key":"18_CR26","unstructured":"Microsoft Research: An Introduction to Microsoft Accelerator v2 (July 2012)"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Luk, C.K., et al.: Qilin: exploiting parallelism on heterogeneous multiprocessors with adaptive mapping. In: Microarchitecture, New York, NY, USA (2009)","DOI":"10.1145\/1669112.1669121"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Augonnet, C., et al.: StarPU: A unified platform for task scheduling on heterogeneous multicore architectures. In: Euro-Par 2009, Delft, Netherlands (2009)","DOI":"10.1007\/978-3-642-03869-3_80"},{"key":"18_CR29","doi-asserted-by":"crossref","unstructured":"Song, F., et al.: Efficient Support for Matrix Computations on Heterogeneous Multi-core and Multi-GPU Architectures, University of Tennessee (2011)","DOI":"10.2172\/1173287"}],"container-title":["Lecture Notes in Computer Science","Trends in Functional Programming"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-40447-4_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,16]],"date-time":"2019-05-16T12:22:09Z","timestamp":1558009329000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-40447-4_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642404467","9783642404474"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-40447-4_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}