{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T20:31:08Z","timestamp":1790973068945,"version":"4.1.0"},"publisher-location":"New York, NY, USA","reference-count":23,"publisher":"ACM","license":[{"start":{"date-parts":[[2011,5,3]],"date-time":"2011-05-03T00:00:00Z","timestamp":1304380800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2011,5,3]]},"DOI":"10.1145\/2016604.2016637","type":"proceedings-article","created":{"date-parts":[[2011,8,10]],"date-time":"2011-08-10T16:16:32Z","timestamp":1312992992000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":16,"title":["Bounding the effect of partition camping in GPU kernels"],"prefix":"10.1145","author":[{"given":"Ashwin M.","family":"Aji","sequence":"first","affiliation":[{"name":"Virginia Tech, Blacksburg, Virginia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mayank","family":"Daga","sequence":"additional","affiliation":[{"name":"Virginia Tech, Blacksburg, Virginia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wu-chun","family":"Feng","sequence":"additional","affiliation":[{"name":"Virginia Tech, Blacksburg, Virginia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2011,5,3]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Virginia Tech","author":"Aji A. M.","year":"2010","unstructured":"A. M. Aji , M. Daga , and W. Feng . CampProf: A Visual Performance Analysis Tool for Memory Bound GPU Kernels. Technical report , Virginia Tech , 2010 . A. M. Aji, M. Daga, and W. Feng. CampProf: A Visual Performance Analysis Tool for Memory Bound GPU Kernels. Technical report, Virginia Tech, 2010."},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of High Performance Computing Conference","author":"Bader M.","year":"2009","unstructured":"M. Bader , H.-J. Bungartz , D. Mudigere , S. Narasimhan , and B. Narayanan . Fast GPGPU Data Rearrangement Kernels using CUDA . In Proceedings of High Performance Computing Conference , 2009 . M. Bader, H.-J. Bungartz, D. Mudigere, S. Narasimhan, and B. Narayanan. Fast GPGPU Data Rearrangement Kernels using CUDA. In Proceedings of High Performance Computing Conference, 2009."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1693453.1693470"},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of 3rd Workshop on Software Tools for MultiCore Systems","author":"Boyer M.","year":"2010","unstructured":"M. Boyer , K. Skadron , and W. Weimer . Automated Dynamic Analysis of CUDA Programs . In Proceedings of 3rd Workshop on Software Tools for MultiCore Systems , 2010 . M. Boyer, K. Skadron, and W. Weimer. Automated Dynamic Analysis of CUDA Programs. In Proceedings of 3rd Workshop on Software Tools for MultiCore Systems, 2010."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCABS.2011.5729946"},{"key":"e_1_3_2_1_6_1","author":"Gordon J. C.","year":"2008","unstructured":"J. C. Gordon , A. T. Fenley , and A. Onufriev . An Analytical Approach to Computing Biomolecular Electrostatic Potential, II: Validation and Applications. Journal of Chemical Physics , 2008 . J. C. Gordon, A. T. Fenley, and A. Onufriev. An Analytical Approach to Computing Biomolecular Electrostatic Potential, II: Validation and Applications. Journal of Chemical Physics, 2008.","journal-title":"Journal of Chemical Physics"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1555754.1555775"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1815961.1815998"},{"key":"e_1_3_2_1_9_1","volume-title":"The OpenCL Specification","author":"Munshi A.","year":"2008","unstructured":"A. Munshi . The OpenCL Specification , 2008 . http:\/\/www.khronos.org\/registry\/cl\/specs\/opencl-1.0.29.pdf. A. Munshi. The OpenCL Specification, 2008. http:\/\/www.khronos.org\/registry\/cl\/specs\/opencl-1.0.29.pdf."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/GREENCOMP.2010.5598315"},{"key":"e_1_3_2_1_11_1","volume-title":"CUDA Occupancy Calculator","author":"NVIDIA.","year":"2008","unstructured":"NVIDIA. CUDA Occupancy Calculator , 2008 . http:\/\/developer.download.nvidia.com\/compute\/cuda\/CUDA_Occupancy_calculator.xls. NVIDIA. CUDA Occupancy Calculator, 2008. http:\/\/developer.download.nvidia.com\/compute\/cuda\/CUDA_Occupancy_calculator.xls."},{"key":"e_1_3_2_1_12_1","volume-title":"GeForce GTX 280 Specifications","author":"NVIDIA.","year":"2008","unstructured":"NVIDIA. GeForce GTX 280 Specifications , 2008 . http:\/\/www.nvidia.com\/object\/product_ geforce_gtx_280_us.html. NVIDIA. GeForce GTX 280 Specifications, 2008. http:\/\/www.nvidia.com\/object\/product_ geforce_gtx_280_us.html."},{"key":"e_1_3_2_1_13_1","volume-title":"NVIDIA Fermi Compute Acrhitecture","author":"NVIDIA.","year":"2008","unstructured":"NVIDIA. NVIDIA Fermi Compute Acrhitecture , 2008 . http:\/\/www.nvidia.com\/content\/PDF\/fermi_white_papers\/NVIDIA_Fermi_Compute_Architecture_Whitepaper.pdf. NVIDIA. NVIDIA Fermi Compute Acrhitecture, 2008. http:\/\/www.nvidia.com\/content\/PDF\/fermi_white_papers\/NVIDIA_Fermi_Compute_Architecture_Whitepaper.pdf."},{"key":"e_1_3_2_1_14_1","volume-title":"The CUDA Compiler Driver NVCC","author":"NVIDIA.","year":"2008","unstructured":"NVIDIA. The CUDA Compiler Driver NVCC , 2008 . http:\/\/www.nvidia.com\/object\/io_1213955090354.html. NVIDIA. The CUDA Compiler Driver NVCC, 2008. http:\/\/www.nvidia.com\/object\/io_1213955090354.html."},{"key":"e_1_3_2_1_15_1","volume-title":"CUDA Visual Profiler","author":"NVIDIA.","year":"2009","unstructured":"NVIDIA. CUDA Visual Profiler , 2009 . http:\/\/developer.download.nvidia.com\/compute\/cuda\/2_2\/toolkit\/docs\/cudaprof_1.2_readme.html. NVIDIA. CUDA Visual Profiler, 2009. http:\/\/developer.download.nvidia.com\/compute\/cuda\/2_2\/toolkit\/docs\/cudaprof_1.2_readme.html."},{"key":"e_1_3_2_1_16_1","volume-title":"NVIDIA CUDA Programming Guide-2.3","author":"NVIDIA.","year":"2009","unstructured":"NVIDIA. NVIDIA CUDA Programming Guide-2.3 , 2009 . http:\/\/developer.download.nvidia.com\/compute\/cuda\/2_3\/toolkit\/docs\/NVIDIA_CUDA_Programming_Guide_2.3.pdf. NVIDIA. NVIDIA CUDA Programming Guide-2.3, 2009. http:\/\/developer.download.nvidia.com\/compute\/cuda\/2_3\/toolkit\/docs\/NVIDIA_CUDA_Programming_Guide_2.3.pdf."},{"key":"e_1_3_2_1_17_1","volume-title":"Optimizing Matrix Transpose in CUDA","author":"NVIDIA.","year":"2009","unstructured":"NVIDIA. Optimizing Matrix Transpose in CUDA , 2009 . NVIDIA _CUDA_SDK\/C\/src\/transposeNew\/doc\/MatrixTranspose.pdf. NVIDIA. Optimizing Matrix Transpose in CUDA, 2009. NVIDIA_CUDA_SDK\/C\/src\/transposeNew\/doc\/MatrixTranspose.pdf."},{"key":"e_1_3_2_1_18_1","volume-title":"Workshop on General Purpose Processing on Graphics Processing","author":"Ryoo S.","year":"2008","unstructured":"S. Ryoo , C. I. Rodrigues , S. S. Stone , S. S. Baghsorkhi , S.-Z. Ueng , and W. mei Hwu . Program Optimization Study on a 128-Core GPU . In Workshop on General Purpose Processing on Graphics Processing , 2008 . S. Ryoo, C. I. Rodrigues, S. S. Stone, S. S. Baghsorkhi, S.-Z. Ueng, and W. mei Hwu. Program Optimization Study on a 128-Core GPU. In Workshop on General Purpose Processing on Graphics Processing, 2008."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/1356058.1356084"},{"key":"e_1_3_2_1_20_1","volume-title":"Proc. of the IEEE International Symposium on Parallel and Distributed Computing","author":"Schaa D.","year":"2009","unstructured":"D. Schaa and D. Kaeli . Exploring the Multi-GPU Design Space . In Proc. of the IEEE International Symposium on Parallel and Distributed Computing , 2009 . D. Schaa and D. Kaeli. Exploring the Multi-GPU Design Space. In Proc. of the IEEE International Symposium on Parallel and Distributed Computing, 2009."},{"key":"e_1_3_2_1_21_1","unstructured":"W. van der Laan. Decuda 2008. http:\/\/wiki.github.com\/laanwj\/decuda.  W. van der Laan. Decuda 2008. http:\/\/wiki.github.com\/laanwj\/decuda."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.5555\/1413370.1413402"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2010.5452013"}],"event":{"name":"CF'11: Computing Frontiers Conference","location":"Ischia Italy","acronym":"CF'11","sponsor":["SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing"]},"container-title":["Proceedings of the 8th ACM International Conference on Computing Frontiers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2016604.2016637","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2016604.2016637","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T11:06:14Z","timestamp":1750244774000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2016604.2016637"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,5,3]]},"references-count":23,"alternative-id":["10.1145\/2016604.2016637","10.1145\/2016604"],"URL":"https:\/\/doi.org\/10.1145\/2016604.2016637","relation":{},"subject":[],"published":{"date-parts":[[2011,5,3]]},"assertion":[{"value":"2011-05-03","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}