{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,19]],"date-time":"2025-03-19T16:50:49Z","timestamp":1742403049864,"version":"3.32.0"},"publisher-location":"Berlin, Heidelberg","reference-count":23,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540309369"},{"type":"electronic","value":"9783540324270"}],"license":[{"start":{"date-parts":[[2005,1,1]],"date-time":"2005-01-01T00:00:00Z","timestamp":1104537600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2005]]},"DOI":"10.1007\/11602569_13","type":"book-chapter","created":{"date-parts":[[2006,10,17]],"date-time":"2006-10-17T23:57:31Z","timestamp":1161129451000},"page":"83-94","source":"Crossref","is-referenced-by-count":5,"title":["Performance Study of LU Decomposition on the Programmable GPU"],"prefix":"10.1007","author":[{"given":"Fumihiko","family":"Ino","sequence":"first","affiliation":[]},{"given":"Manabu","family":"Matsui","sequence":"additional","affiliation":[]},{"given":"Keigo","family":"Goda","sequence":"additional","affiliation":[]},{"given":"Kenichi","family":"Hagihara","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"volume-title":"GPU Gems: Programming Techniques, Tips and Tricks for Real-Time Graphics","year":"2004","key":"13_CR1","unstructured":"Fernando, R. (ed.): GPU Gems: Programming Techniques, Tips and Tricks for Real-Time Graphics. Addison-Wesley, Reading (2004)"},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"Fatahalian, K., Sugerman, J., Hanrahan, P.: Understanding the efficiency of GPU algorithms for matrix-matrix multiplication. In: Proc. SIGGRAPH\/EUROGRAPHICS Workshop Graphics Hardware (GH 2004), pp. 133\u2013137 (2004)","DOI":"10.1145\/1058129.1058148"},{"key":"13_CR3","doi-asserted-by":"crossref","unstructured":"Thompson, C.J., Hahn, S., Oskin, M.: Using modern graphics architectures for general-purpose computing: A framework and analysis. In: Proc. 35th IEEE\/ACM Int\u2019l Symp. Microarchitecture (MICRO 2002), pp. 306\u2013317 (2002)","DOI":"10.1109\/MICRO.2002.1176259"},{"key":"13_CR4","doi-asserted-by":"crossref","unstructured":"Larsen, E.S., McAllister, D.: Fast matrix multiplies using graphics hardware. In: Proc. High Performance Networking and Computing Conf., SC 2001 (2001)","DOI":"10.1145\/582034.582089"},{"key":"13_CR5","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/S0167-8191(00)00087-9","volume":"27","author":"R.C. Whaley","year":"2001","unstructured":"Whaley, R.C., Petitet, A., Dongarra, J.J.: Automated empirical optimizations of software and the ATLAS project. Parallel Computing\u00a027, 3\u201335 (2001)","journal-title":"Parallel Computing"},{"key":"13_CR6","unstructured":"Hall, J.D., Carr, N.A., Hart, J.C.: Cache and bandwidth aware matrix multiplication on the GPU. Technical Report UIUCDCS-R-2003-2328, University of Illinois (2003)"},{"key":"13_CR7","doi-asserted-by":"publisher","first-page":"908","DOI":"10.1145\/882262.882363","volume":"22","author":"J. Kr\u00fcger","year":"2003","unstructured":"Kr\u00fcger, J., Westermann, R.: Linear algebra operators for GPU implementation of numerical algorithms. ACM Trans. Graphics\u00a022, 908\u2013916 (2003)","journal-title":"ACM Trans. Graphics"},{"key":"13_CR8","doi-asserted-by":"publisher","first-page":"917","DOI":"10.1145\/882262.882364","volume":"22","author":"J. Bolz","year":"2003","unstructured":"Bolz, J., Farmer, I., Grinspun, E., Schr\u00f6der, P.: Sparse matrix solvers on the GPU: Conjugate gradients and multigrid. ACM Trans. Graphics\u00a022, 917\u2013924 (2003)","journal-title":"ACM Trans. Graphics"},{"key":"13_CR9","unstructured":"Morav\u00e1nszky, A.: Dense Matrix Algebra on the GPU (2003), http:\/\/www.shaderx2.com\/shaderx.PDF"},{"key":"13_CR10","unstructured":"Moreland, K., Angel, E.: The FFT on a GPU. In: Proc. SIGGRAPH\/EUROGRAPHICS Workshop Graphics Hardware (GH 2003), pp. 112\u2013119 (2003)"},{"key":"13_CR11","unstructured":"Fernando, R., Harris, M., Wloka, M., Zeller, C.: Programming graphics hardware. In: EUROGRAPHICS 2004 Tutorial Note, (2004), http:\/\/download.nvidia.com\/developer\/presentations\/2004\/Eurographics\/EG_04_TutorialNotes.pdf"},{"volume-title":"GPU Gems 2: Programming Techniques for High-Performance Graphics and General-Purpose Computation","year":"2005","key":"13_CR12","unstructured":"Pharr, M., Fernando, R. (eds.): GPU Gems 2: Programming Techniques for High-Performance Graphics and General-Purpose Computation. Addison-Wesley, Reading (2005)"},{"key":"13_CR13","volume-title":"Introduction to Parallel Computing","author":"A. Grama","year":"2003","unstructured":"Grama, A., Gupta, A., Karypis, G., Kumar, V.: Introduction to Parallel Computing, 2nd edn. Addison-Wesley, Reading (2003)","edition":"2"},{"key":"13_CR14","volume-title":"OpenGL Programming Guide","year":"2003","unstructured":"Shreiner, D., Woo, M., Neider, J., Davis, T. (eds.): OpenGL Programming Guide, 4th edn. Addison-Wesley, Reading (2003)","edition":"4"},{"key":"13_CR15","unstructured":"Microsoft Corporation: DirectX (2005), http:\/\/www.microsoft.com\/directx\/"},{"key":"13_CR16","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1109\/C-M.1981.220377","volume":"14","author":"D. Stevenson","year":"1981","unstructured":"Stevenson, D.: A proposed standard for binary floating-point arithmetic. IEEE Computer\u00a014, 51\u201362 (1981)","journal-title":"IEEE Computer"},{"volume-title":"Solving Linear Systems on Vector and Shared Memory Computers","year":"1991","key":"13_CR17","unstructured":"Dongarra, J.J., Duff, I.S., Sorensen, D.C., Vorst, H.V.D. (eds.): Solving Linear Systems on Vector and Shared Memory Computers. SIAM, Philadelphia (1991)"},{"key":"13_CR18","doi-asserted-by":"publisher","first-page":"896","DOI":"10.1145\/882262.882362","volume":"22","author":"W.R. Mark","year":"2003","unstructured":"Mark, W.R., Glanville, R.S., Akeley, K., Kilgard, M.J.: Cg: A system for programming graphics hardware in a C-like language. ACM Trans. Graphics\u00a022, 896\u2013897 (2003)","journal-title":"ACM Trans. Graphics"},{"key":"13_CR19","first-page":"62","volume":"45","author":"A. Naruse","year":"2004","unstructured":"Naruse, A., Sumimoto, S., Kumon, K.: Optimization and evaluation of linpack benchmark for Xeon processor. IPSJ Trans. Advanced Computing Systems\u00a045, 62\u201370 (2004) (in Japanese)","journal-title":"IPSJ Trans. Advanced Computing Systems"},{"key":"13_CR20","unstructured":"Goto, K., van de Geijn, R.: On reducing TLB misses in matrix multiplication. Technical Report CS-TR-02-55, The University of Texas at Austin (2002)"},{"key":"13_CR21","doi-asserted-by":"publisher","first-page":"803","DOI":"10.1002\/cpe.728","volume":"15","author":"J.J. Dongarra","year":"2003","unstructured":"Dongarra, J.J., Luszczek, P., Petitet, A.: The LINPACK benchmark: past, present and future. Concurrency and Computation: Practice and Experience\u00a015, 803\u2013820 (2003)","journal-title":"Concurrency and Computation: Practice and Experience"},{"key":"13_CR22","unstructured":"Hillesland, K.E., Lastra, A.: In: GPU floating point paranoia. In: Proc. 1st ACM Workshop General-Purpose Computing on Graphics Processors (GP2 2004), vol.\u00a0C\u20138 (2004), http:\/\/www.cs.unc.edu\/~ibr\/projects\/paranoia\/"},{"key":"13_CR23","first-page":"114","volume":"38","author":"G.E. Moore","year":"1965","unstructured":"Moore, G.E.: Cramming more components onto integrated circuits. Electronics\u00a038, 114\u2013117 (1965)","journal-title":"Electronics"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing \u2013 HiPC 2005"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11602569_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,11]],"date-time":"2025-01-11T15:50:11Z","timestamp":1736610611000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11602569_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2005]]},"ISBN":["9783540309369","9783540324270"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/11602569_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2005]]}}}