{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:16:28Z","timestamp":1750306588569,"version":"3.41.0"},"publisher-location":"New York, New York, USA","reference-count":14,"publisher":"ACM Press","license":[{"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.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/L016540\/1"],"award-info":[{"award-number":["EP\/L016540\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1145\/2791321.2791332","type":"proceedings-article","created":{"date-parts":[[2015,12,1]],"date-time":"2015-12-01T14:48:00Z","timestamp":1448981280000},"page":"1-7","source":"Crossref","is-referenced-by-count":11,"title":["Kernel composition in SYCL"],"prefix":"10.1145","author":[{"given":"Ralph","family":"Potter","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paul","family":"Keir","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Russell J.","family":"Bradford","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alastair","family":"Murray","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","reference":[{"unstructured":"A. W. Campagna and G. Chen. OpenCLIPP. https:\/\/github.com\/CRVI\/OpenCLIPP, 2014. [Online; accessed 4-February-2015].","key":"key-10.1145\/2791321.2791332-1"},{"unstructured":"Denis Demidov. VexCL. http:\/\/ddemidov.github.io\/vexcl\/, 2012. [Online; accessed 4-February-2015].","key":"key-10.1145\/2791321.2791332-2"},{"doi-asserted-by":"crossref","unstructured":"F. Dütsch, K. Djelassi, M. Haidl, and S. Gorlatch. Hlsf: A high-level; c++-based framework for stencil computations on accelerators. InProceedings of the Second Workshop on Optimizing Stencil Computations, WOSC '14, pages 41--4, New York, NY, USA, 2014. ACM.","key":"key-10.1145\/2791321.2791332-3","DOI":"10.1145\/2686745.2686751"},{"doi-asserted-by":"crossref","unstructured":"J. Fousek, J. Filipovič, and M. Madzin. Automatic fusions of cuda-gpu kernels for parallel map.SIGARCH Comput. Archit. News, 39(4):98--99, Dec. 2011.","key":"key-10.1145\/2791321.2791332-4","DOI":"10.1145\/2082156.2082183"},{"doi-asserted-by":"crossref","unstructured":"M. Haidl and S. Gorlatch. Pacxx: Towards a unified programming model for programming accelerators using c++14. InProceedings of the 2014 LLVM Compiler Infrastructure in HPC, LLVM-HPC '14, pages 1--11, Piscataway, NJ, USA, 2014. IEEE Press.","key":"key-10.1145\/2791321.2791332-5","DOI":"10.1109\/LLVM-HPC.2014.9"},{"unstructured":"Khronos OpenCL Working Group.The OpenCL Specification Version: 1.2 Document Revision: 19, November 2012.","key":"key-10.1145\/2791321.2791332-6"},{"unstructured":"Khronos OpenCL Working Group - SYCL subgroup.SYCL Provisional Specification.Khronos OpenCL Working Group, September 2014.","key":"key-10.1145\/2791321.2791332-7"},{"doi-asserted-by":"crossref","unstructured":"L. Kiemele, C. Berg, A. Gulliver, and Y. Coady. Kfusion: Optimizing data flow without compromising modularity. InProceedings of the 12th Annual International Conference on Aspect-oriented Software Development, AOSD '13, pages 25--36, New York, NY, USA, 2013. ACM.","key":"key-10.1145\/2791321.2791332-8","DOI":"10.1145\/2451436.2451440"},{"doi-asserted-by":"crossref","unstructured":"J. Malcolm, P. Yalamanchili, C. McClanahan, V. Venugopalakrishnan, K. Patel, and J. Melonakos. Arrayfire: a gpu acceleration platform, 2012.","key":"key-10.1145\/2791321.2791332-9","DOI":"10.1117\/12.921122"},{"doi-asserted-by":"crossref","unstructured":"E. Niebler. Proto: A compiler construction toolkit for dsels. InProceedings of the 2007 Symposium on Library-Centric Software Design, LCSD '07, pages 42--51, New York, NY, USA, 2007. ACM.","key":"key-10.1145\/2791321.2791332-10","DOI":"10.1145\/1512762.1512767"},{"unstructured":"Nvidia Corporation. NVIDIA Performance Primitives. http:\/\/developer.nvidia.com\/npp, 2011. [Online; accessed 4-February-2015].","key":"key-10.1145\/2791321.2791332-11"},{"doi-asserted-by":"crossref","unstructured":"J. Ragan-Kelley, C. Barnes, A. Adams, S. Paris, F. Durand, and S. Amarasinghe. Halide: A language and compiler for optimizing parallelism, locality, and recomputation in image processing pipelines. InProceedings of the 34th ACM SIGPLAN Conference on Programming Language Design and Implementation, PLDI '13, pages 519--530, New York, NY, USA, 2013. ACM.","key":"key-10.1145\/2791321.2791332-12","DOI":"10.1145\/2491956.2462176"},{"doi-asserted-by":"crossref","unstructured":"M. Wahib and N. Maruyama. Scalable kernel fusion for memory-bound gpu applications. InProceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC '14, pages 191--202, Piscataway, NJ, USA, 2014. IEEE Press.","key":"key-10.1145\/2791321.2791332-13","DOI":"10.1109\/SC.2014.21"},{"doi-asserted-by":"crossref","unstructured":"G. Wang, Y. Lin, and W. Yi. Kernel fusion: An effective method for better power efficiency on multithreaded gpu. InProceedings of the 2010 IEEE\/ACM Int'L Conference on Green Computing and Communications & Int'L Conference on Cyber, Physical and Social Computing, GREENCOM-CPSCOM '10, pages 344--350, Washington, DC, USA, 2010. IEEE Computer Society.","key":"key-10.1145\/2791321.2791332-14","DOI":"10.1109\/GreenCom-CPSCom.2010.102"}],"event":{"number":"3","sponsor":["AMD","Altera Corp., Altera Corporation","Auviz, Auviz Systems","Codeplay, Codeplay Software Ltd.","Imagination, Imagination Technologies Limited","hgpu.org, high performance computing on graphics processing units","QI, Qualcomm Inc.","The University of Bristol","Khronos, Khronos Group"],"acronym":"IWOCL '15","name":"the 3rd International Workshop","start":{"date-parts":[[2015,5,12]]},"location":"Palo Alto, California","end":{"date-parts":[[2015,5,13]]}},"container-title":["Proceedings of the 3rd International Workshop on OpenCL - IWOCL '15"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2791321.2791332","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/dl.acm.org\/ft_gateway.cfm?id=2791332&ftid=1648743&dwn=1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T06:16:28Z","timestamp":1750227388000},"score":1,"resource":{"primary":{"URL":"http:\/\/dl.acm.org\/citation.cfm?doid=2791321.2791332"}},"subtitle":[],"proceedings-subject":"OpenCL","short-title":[],"issued":{"date-parts":[[2015]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1145\/2791321.2791332","relation":{},"subject":[],"published":{"date-parts":[[2015]]}}}