{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,30]],"date-time":"2025-04-30T04:20:04Z","timestamp":1745986804716,"version":"3.40.4"},"publisher-location":"Berlin, Heidelberg","reference-count":20,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642360350"},{"type":"electronic","value":"9783642360367"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-36036-7_6","type":"book-chapter","created":{"date-parts":[[2013,1,17]],"date-time":"2013-01-17T01:59:30Z","timestamp":1358387970000},"page":"76-90","source":"Crossref","is-referenced-by-count":3,"title":["OpenCL as a Programming Model for GPU Clusters"],"prefix":"10.1007","author":[{"given":"Jungwon","family":"Kim","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sangmin","family":"Seo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeongho","family":"Nah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gangwon","family":"Jo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaejin","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"6_CR1","unstructured":"AMD: AMD Accelerated Parallel Processing SDK v2.3, http:\/\/developer.amd.com\/gpu\/AMDAPPSDK\/Pages\/default.aspx"},{"key":"6_CR2","unstructured":"AMD: AMD Accelerated Parallel Processing (APP) SDK With OpenCL 1.1 Support (2011), http:\/\/developer.amd.com\/gpu\/atistreamsdk\/pages\/default.aspx"},{"key":"6_CR3","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/2.485843","volume":"29","author":"C. Amza","year":"1996","unstructured":"Amza, C., Cox, A.L., Dwarkadas, S., Keleher, P., Lu, H., Rajamony, R., Yu, W., Zwaenepoel, W.: TreadMarks: Shared Memory Computing on Networks of Workstations. Computer\u00a029, 18\u201328 (1996)","journal-title":"Computer"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Barak, A., Ben-nun, T., Levy, E., Shiloh, A.: A Package for OpenCL Based Heterogeneous Computing on Clusters with Many GPU Devices. In: Proceedings of the Workshop on Parallel Programming and Applications on Accelerator Clusters, PPAAC 2010 (2010)","DOI":"10.1109\/CLUSTERWKSP.2010.5613086"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Bienia, C., Kumar, S., Singh, J.P., Li, K.: The PARSEC benchmark suite: characterization and architectural implications. In: Proceedings of the 17th International Conference on Parallel Architectures and Compilation Techniques, PACT 2008, pp. 72\u201381 (2008)","DOI":"10.1145\/1454115.1454128"},{"key":"6_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/978-3-642-19595-2_11","volume-title":"Languages and Compilers for Parallel Computing","author":"L. Chen","year":"2011","unstructured":"Chen, L., Liu, L., Tang, S., Huang, L., Jing, Z., Xu, S., Zhang, D., Shou, B.: Unified Parallel C for GPU Clusters: Language Extensions and Compiler Implementation. In: Cooper, K., Mellor-Crummey, J., Sarkar, V. (eds.) LCPC 2010. LNCS, vol.\u00a06548, pp. 151\u2013165. Springer, Heidelberg (2011)"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Y., Cui, X., Mei, H.: Large-scale FFT on GPU clusters. In: Proceedings of the 24th ACM International Conference on Supercomputing, ICS 2010, pp. 315\u2013324 (2010)","DOI":"10.1145\/1810085.1810128"},{"key":"6_CR8","unstructured":"Fan, Z., Qiu, F., Kaufman, A., Yoakum-Stover, S.: GPU cluster for high performance computing. In: Proceedings of the 2004 ACM\/IEEE Conference on Supercomputing, SC 2004, pp. 47\u201358 (2004)"},{"key":"6_CR9","unstructured":"IBM: OpenCL Development Kit for Linux on Power (2011), http:\/\/www.alphaworks.ibm.com\/tech\/opencl"},{"key":"6_CR10","unstructured":"Intel: Intel OpenCL SDK (2011), http:\/\/software.intel.com\/en-us\/articles\/intel-opencl-sdk\/"},{"key":"6_CR11","unstructured":"Khronos OpenCL Working Group: The OpenCL Specification Version 1.1 (2010), http:\/\/www.khronos.org\/opencl"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Kim, J., Kim, H., Lee, J.H., Lee, J.: Achieving a single compute device image in OpenCL for multiple GPUs. In: Proceedings of the 16th ACM Symposium on Principles and Practice of Parallel Programming, PPoPP 2011, pp. 277\u2013288 (2011)","DOI":"10.1145\/1941553.1941591"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Lattner, C., Adve, V.: LLVM: A Compilation Framework for Lifelong Program Analysis & Transformation. In: Proceedings of the International Symposium on Code Generation and Optimization: Feedback-Directed and Runtime Optimization, CGO 2004, pp. 75\u201386 (2004)","DOI":"10.1109\/CGO.2004.1281665"},{"key":"6_CR14","unstructured":"NASA Advanced Supercomputing Division: NAS Parallel Benchmarks version 3.2, http:\/\/www.nas.nasa.gov\/Resources\/Software\/npb.html"},{"key":"6_CR15","unstructured":"NVIDIA: NVIDIA CUDA Toolkit 3.2, http:\/\/developer.nvidia.com\/cuda-toolkit-32-downloads"},{"key":"6_CR16","unstructured":"NVIDIA: NVIDIA CUDA C Programming Guide 3.2 (2010)"},{"key":"6_CR17","unstructured":"NVIDIA: NVIDIA GPU Computing Developer Home Page (2011), http:\/\/developer.nvidia.com\/object\/gpucomputing.html"},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Phillips, J.C., Stone, J.E., Schulten, K.: Adapting a message-driven parallel application to GPU-accelerated clusters. In: Proceedings of the 2008 ACM\/IEEE Conference on Supercomputing, SC 2008, pp. 8:1\u20138:9 (2008)","DOI":"10.1109\/SC.2008.5214716"},{"key":"6_CR19","unstructured":"Seoul National University and Samsung: SNU-SAMSUNG OpenCL Framework (2010), http:\/\/opencl.snu.ac.kr"},{"key":"6_CR20","unstructured":"The IMPACT Research Group: Parboil Benchmark suite, http:\/\/impact.crhc.illinois.edu\/parboil.php"}],"container-title":["Lecture Notes in Computer Science","Languages and Compilers for Parallel Computing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-36036-7_6.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T17:23:14Z","timestamp":1745947394000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-36036-7_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642360350","9783642360367"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-36036-7_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}