{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,4,2]],"date-time":"2022-04-02T04:02:19Z","timestamp":1648872139544},"reference-count":20,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2013,5,26]],"date-time":"2013-05-26T00:00:00Z","timestamp":1369526400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int J Parallel Prog"],"published-print":{"date-parts":[[2014,4]]},"DOI":"10.1007\/s10766-013-0251-z","type":"journal-article","created":{"date-parts":[[2013,5,25]],"date-time":"2013-05-25T07:22:18Z","timestamp":1369466538000},"page":"343-363","source":"Crossref","is-referenced-by-count":3,"title":["Accelerating Single Iteration Performance of CUDA-Based 3D Reaction\u2013Diffusion Simulations"],"prefix":"10.1007","volume":"42","author":[{"given":"John K.","family":"Holmen","sequence":"first","affiliation":[]},{"given":"David L.","family":"Foster","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2013,5,26]]},"reference":[{"issue":"1","key":"251_CR1","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1016\/j.chemolab.2011.03.009","volume":"108","author":"F Moln\u00e1r Jr","year":"2011","unstructured":"Moln\u00e1r Jr, F., Izs\u00e1k, F., M\u00e9sz\u00e1roa, R., Lagzi, I.: Simulation of reaction\u2013diffusion processes in three dimensions using CUDA. Chemom. Intell. Lab. Syst. 108(1), 76\u201385 (2011)","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"251_CR2","unstructured":"Giles, M.: Jacobi Iteration for a Laplace Discretisation on a 3D Structured Grid. http:\/\/people.maths.ox.ac.uk\/gilesm\/cuda\/prac3\/laplace3d.pdf"},{"key":"251_CR3","doi-asserted-by":"crossref","unstructured":"Phillips, E.H., Fatica, M.: Implementing the Himeno Benchmark with CUDA on GPU Clusters. In: Proceedings of the 24th IEEE International Symposium on Parallel and Distributed Processing (IPDPS 2010), pp. 1\u201310, April 2010","DOI":"10.1109\/IPDPS.2010.5470394"},{"key":"251_CR4","doi-asserted-by":"crossref","unstructured":"Micikevicius, P.: 3D finite difference computation on GPUs using CUDA. In: Proceedings of the 2nd Workshop on General Purpose Processing on Graphics Processing Units (GPGPU2), pp. 79\u201384, March 2009","DOI":"10.1145\/1513895.1513905"},{"key":"251_CR5","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Mueller, F.: Auto-generation and auto-tuning of 3D stencil codes on GPU clusters. In: Proceedings of the 10th IEEE\/ACM International Symposium on Code Generation and Optimization (CGO 2012), March\/April 2012","DOI":"10.1145\/2259016.2259037"},{"key":"251_CR6","doi-asserted-by":"crossref","unstructured":"Unat, D., Cai, X., Baden, S.B.: Mint: realizing CUDA performance in 3D stencil methods with annotated C. In: Proceedings of the International Conference on Supercomputing (ICS \u201911), pp. 214\u2013224, May\/June 2011","DOI":"10.1145\/1995896.1995932"},{"key":"251_CR7","doi-asserted-by":"crossref","unstructured":"Nguyen, N., Satish, Chhugani, J., Kim, C., Dubey, P.: 3.5-D blocking optimization for stencil computations on modern CPUs and GPUs. In: Proceedings of the 2010 ACM\/IEEE International Conference for High Performance Computing, Networking, Storage and, Analysis (SC\u201910), pp. 1\u201313, November 2010","DOI":"10.1109\/SC.2010.2"},{"issue":"1","key":"251_CR8","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1007\/s11390-012-1206-3","volume":"27","author":"Y Yang","year":"2012","unstructured":"Yang, Y., Cui, H.-M., Feng, X.-B., Xue, J.-L.: A hybrid circular queue method for iterative stencil computations on GPUs. J. Comput. Sci. Technol. 27(1), 57\u201374 (2012)","journal-title":"J. Comput. Sci. Technol."},{"key":"251_CR9","doi-asserted-by":"crossref","unstructured":"Holewinski, J., Pouchet, L.-N., Sadayappan, P.: High-performance code generation for stencil computations on GPU architectures. In: Proceedings of the 26th ACM International Conference on Supercomputing (ICS \u201912), pp. 311\u2013320, June 2012","DOI":"10.1145\/2304576.2304619"},{"key":"251_CR10","doi-asserted-by":"crossref","unstructured":"Meng, J., Skadron, K.: Performance Modeling and Automatic Ghost Zone Optimization for Iterative Stencil Loops on GPUs. In: Proceedings of the 23rd International Conference on Supercomputing (ICS \u201909), pp. 256\u2013265, June 2009","DOI":"10.1145\/1542275.1542313"},{"key":"251_CR11","volume-title":"Programming Massively Parallel Processors: A Hands-on Approach","author":"DB Kirk","year":"2010","unstructured":"Kirk, D.B., Hwu, W.-M.W.: Programming Massively Parallel Processors: A Hands-on Approach. Morgan Kaufmann, San Fransisco (2010)"},{"key":"251_CR12","volume-title":"CUDA by Example: An Introduction to General-Purpose GPU Programming","author":"J Sanders","year":"2010","unstructured":"Sanders, J., Kandrot, E.: CUDA by Example: An Introduction to General-Purpose GPU Programming. Addison Wesley, Reading (2010)"},{"key":"251_CR13","volume-title":"CUDA Application Design and Development","author":"R Farber","year":"2011","unstructured":"Farber, R.: CUDA Application Design and Development. Morgan Kaufmann, San Fransisco (2011)"},{"key":"251_CR14","unstructured":"NVIDIA Corporation, GeForce 8800 GTX - Specifications. http:\/\/www.geforce.com\/hardware\/desktop-gpus\/geforce-8800-gtx\/specifications"},{"key":"251_CR15","unstructured":"NVIDIA Corporation, GeForce GTX 275 - Specifications. http:\/\/www.geforce.com\/hardware\/desktop-gpus\/geforce-gtx-275\/specifications"},{"key":"251_CR16","unstructured":"EVGA, GeForce GTX 260 Core 216\u2014Product Specification Sheet. http:\/\/www.evga.com\/products\/pdf\/896-P3-1265.pdf"},{"key":"251_CR17","unstructured":"NVIDIA Corporation, Tesla C1060 Computing Processor Board Specification. http:\/\/nvidia.com\/docs\/IO\/43395\/BD-04111-001_v06.pdf"},{"key":"251_CR18","unstructured":"NVIDIA Corporation, GeForce GTX 560 Ti\u2014Specifications. http:\/\/www.geforce.com\/hardware\/desktop-gpus\/geforce-gtx-560ti\/specifications"},{"key":"251_CR19","unstructured":"Moln\u00e1r, F. Jr., Izs\u00e1k, F., M\u00e9sz\u00e1roa, R., Lagzi, I.: Simulation of Reaction-Diffusion Processes in Three Dimensions using CUDA. http:\/\/nimbus.elte.hu\/~uda\/RD\/cuda.html . 2009"},{"key":"251_CR20","unstructured":"NVIDIA Corporation, CUDA C Best Practices Guide v4.1. http:\/\/developer.download.nvidia.com\/compute\/DevZone\/docs\/html\/C\/doc\/CUDA_C_Best_Practices_Guide.pdf"}],"container-title":["International Journal of Parallel Programming"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-013-0251-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10766-013-0251-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-013-0251-z","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,7,14]],"date-time":"2019-07-14T00:34:19Z","timestamp":1563064459000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10766-013-0251-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,5,26]]},"references-count":20,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2014,4]]}},"alternative-id":["251"],"URL":"https:\/\/doi.org\/10.1007\/s10766-013-0251-z","relation":{},"ISSN":["0885-7458","1573-7640"],"issn-type":[{"value":"0885-7458","type":"print"},{"value":"1573-7640","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,5,26]]}}}