{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T04:16:16Z","timestamp":1743135376418,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":12,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642281501"},{"type":"electronic","value":"9783642281518"}],"license":[{"start":{"date-parts":[[2012,1,1]],"date-time":"2012-01-01T00:00:00Z","timestamp":1325376000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-28151-8_25","type":"book-chapter","created":{"date-parts":[[2012,2,15]],"date-time":"2012-02-15T14:17:07Z","timestamp":1329315427000},"page":"249-259","source":"Crossref","is-referenced-by-count":3,"title":["Implementation and Evaluation of Quadruple Precision BLAS Functions on GPUs"],"prefix":"10.1007","author":[{"given":"Daichi","family":"Mukunoki","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daisuke","family":"Takahashi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"25_CR1","unstructured":"Bailey, D.H.: QD (C++\/Fortran-90 double\u2013double and quad-double package), \n                      \n                        http:\/\/crd.lbl.gov\/~dhbailey\/mpdist\/"},{"key":"25_CR2","unstructured":"Corporation, N.: CUBLAS Library (including CUDA Toolkit), \n                      \n                        http:\/\/developer.nvidia.com\/object\/cuda_download.html"},{"key":"25_CR3","unstructured":"Goto, K.: GotoBLAS2, \n                      \n                        http:\/\/www.tacc.utexas.edu\/tacc-projects\/gotoblas2\/"},{"key":"25_CR4","unstructured":"Gra\u00e7a, G.D., Defour, D.: Implementation of float-float operators on graphics hardware. In: Proc. 7th Conference on Real Numbers and Computers, RNC7 (2006)"},{"key":"25_CR5","unstructured":"Harris, M.: Optimizing Parallel Reduction in CUDA, \n                      \n                        http:\/\/developer.download.nvidia.com\/compute\/cuda\/1_1\/Website\/projects\/reduction\/doc\/reduction.pdf"},{"key":"25_CR6","unstructured":"Hasegawa, H.: Utilizing the quadruple-precision floating-point arithmetic operation for the Krylov Subspace Methods. In: Proc. SIAM Conference on Applied Linear Algebra, LA 2003 (2003)"},{"key":"25_CR7","unstructured":"Hida, Y., Li, X.S., Bailey, D.H.: Algorithms for Quad-Double Precision Floating Point Arithmetic. In: Proc. 15th Symposium on Computer Arithmetic (2001)"},{"key":"25_CR8","unstructured":"Li, X.S., Demmel, J.W., Bailey, D.H., Hida, Y., Iskandar, J., Kapur, A., Martin, M.C., Thompson, B., Tung, T., Yoo, D.J.: XBLAS \u2013 Extra Precise Basic Linear Algebra Subroutines, \n                      \n                        http:\/\/www.netlib.org\/xblas\/"},{"key":"25_CR9","doi-asserted-by":"crossref","unstructured":"Lu, M., He, B., Luo, Q.: Supporting Extended Precision on Graphics Processors. In: Proc. Sixth International Workshop on Data Management on New Hardware, DaMoN 2010 (2010)","DOI":"10.1145\/1869389.1869392"},{"key":"25_CR10","unstructured":"Nakata, M.: The MPACK; Multiple precision arithmetic BLAS (MBLAS) and LAPACK (MLAPACK), \n                      \n                        http:\/\/mplapack.sourceforge.net\/"},{"key":"25_CR11","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1007\/PL00009321","volume":"18","author":"J.R. Shewchuk","year":"1997","unstructured":"Shewchuk, J.R.: Adaptive Precision Floating-Point Arithmetic and Fast Robust Geometric Predicates. Discrete and Computational Geometry\u00a018, 305\u2013363 (1997)","journal-title":"Discrete and Computational Geometry"},{"key":"25_CR12","doi-asserted-by":"crossref","unstructured":"Thall, A.: Extended-Precision Floating-Point Numbers for GPU Computation. In: ACM SIGGRAPH 2006 Research Posters (2006)","DOI":"10.1145\/1179622.1179682"}],"container-title":["Lecture Notes in Computer Science","Applied Parallel and Scientific Computing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-28151-8_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,4,27]],"date-time":"2019-04-27T17:31:26Z","timestamp":1556386286000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-28151-8_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642281501","9783642281518"],"references-count":12,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-28151-8_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}