{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T07:06:41Z","timestamp":1772867201993,"version":"3.50.1"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319075174","type":"print"},{"value":"9783319075181","type":"electronic"}],"license":[{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-3-319-07518-1_8","type":"book-chapter","created":{"date-parts":[[2014,6,3]],"date-time":"2014-06-03T06:54:08Z","timestamp":1401778448000},"page":"124-140","source":"Crossref","is-referenced-by-count":61,"title":["Sparsifying Synchronization for High-Performance Shared-Memory Sparse Triangular Solver"],"prefix":"10.1007","author":[{"given":"Jongsoo","family":"Park","sequence":"first","affiliation":[]},{"given":"Mikhail","family":"Smelyanskiy","sequence":"additional","affiliation":[]},{"given":"Narayanan","family":"Sundaram","sequence":"additional","affiliation":[]},{"given":"Pradeep","family":"Dubey","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Agullo, E., Demmel, J., Dongarra, J., Hadri, B., Kurzak, J., Langou, J., Ltaief, H., Luszczek, P., Tomov, S.: Numerical linear algebra on emerging architectures: the PLASMA and MAGMA projects. Journal of Physics: Conference Series\u00a0180 (2009)","DOI":"10.1088\/1742-6596\/180\/1\/012037"},{"key":"8_CR2","doi-asserted-by":"crossref","unstructured":"Anderson, E., Saad, Y.: Solving Sparse Triangular Linear Systems on Parallel Computers. International Journal of High Speed Computing\u00a01(1) (1989)","DOI":"10.1142\/S0129053389000056"},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Chan, E., Quintana-Orti, E.S., Quintana-Orti, G., van de Geijn, R.: SuperMatrix Out-of-Order Scheduling of Matrix Operations for SMP and Multi-Core Architectures. In: Symposium on Parallelism in Algorithms and Architectures (SPAA) (2007)","DOI":"10.1145\/1248377.1248397"},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"Chhugani, J., Satish, N., Kim, C., Sewall, J., Dubey, P.: Fast and Efficient Graph Traversal Algorithm for CPUs: Maximizing Single-Node Efficiency. In: International Symposium on Parallel and Distributed Processing (IPDPS) (2012)","DOI":"10.1109\/IPDPS.2012.43"},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"Molka, R.S.D., Hackenberg, D., M\u00fcller, M.S.: Memory Performance and Cache Coherency Effects on an Intel Nehalem Multiprocessor System. In: International Conference on Parallel Architectures and Compilation Techniques (PACT) (2009)","DOI":"10.1109\/PACT.2009.22"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Davis, T.A., Hu, Y.: The University of Florida Sparse Matrix Collection. ACM Transactions on Mathematical Software\u00a015(1) (2011), \n                      http:\/\/www.cise.ufl.edu\/research\/sparse\/matrices","DOI":"10.1145\/2049662.2049663"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Dongarra, J., Heroux, M.A.: Toward a New Metric for Ranking High Performance Computing Systems. Technical Report 4744, Sandia National Laboratories (2013)","DOI":"10.2172\/1089988"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Graham, R.L.: Bounds on Multiprocessing Timing Anomalies. SIAM Journal on Applied Mathematics\u00a017(2) (1969)","DOI":"10.1137\/0117039"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Hensgen, D., Finkel, R., Manber, U.: Two Algorithms for Barrier Synchronization. International Journal of Parallel Programming\u00a017(1) (1988)","DOI":"10.1007\/BF01379320"},{"key":"8_CR10","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1016\/S0168-9274(01)00115-5","volume":"41","author":"V.E. Henson","year":"2000","unstructured":"Henson, V.E., Yang, U.M.: Boomeramg: a parallel algebraic multigrid solver and preconditioner. Applied Numerical Mathematics\u00a041, 155\u2013177 (2000)","journal-title":"Applied Numerical Mathematics"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Hestenes, M.R., Stiefel, E.: Methods of Conjugate Gradients for Solving Linear Systems. Journal of Research of the National Bureau of Standards\u00a049(6) (1952)","DOI":"10.6028\/jres.049.044"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Hsu, H.T.: An Algorithm for Finding a Minimal Equivalent Graph of a Digraph. Journal of the ACM (JACM)\u00a022(1) (1975)","DOI":"10.1145\/321864.321866"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Hu, T.C.: Parallel Sequencing and Assembly Line Problems. Operations Research\u00a019(6) (1961)","DOI":"10.1287\/opre.9.6.841"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Iwashita, T., Nakashima, H., Takahashi, Y.: Algebraic Block Multi-Color Ordering Method for Parallel Multi-Threaded Sparse Triangular Solver in ICCG Method. In: International Symposium on Parallel and Distributed Processing (IPDPS) (2012)","DOI":"10.1109\/IPDPS.2012.51"},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Kepner, J., Gilbert, J.: Graph Algorithms in the Language of Linear Algebra. Society for Industrial & Applied Mathematics (2011)","DOI":"10.1137\/1.9780898719918"},{"key":"8_CR16","unstructured":"Kim, K., Eijkhout, V.: A Parallel Sparse Direct Solver via Hierarchical DAG Scheduling. Technical Report 5, The Texas Advanced Computing Center (2012)"},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Mayer, J.: Parallel algorithms for solving linear systems with sparse triangular matrices. Computing\u00a086(4) (2009)","DOI":"10.1007\/s00607-009-0066-3"},{"key":"8_CR18","doi-asserted-by":"crossref","unstructured":"Meijerink, J.A., van der Vorst, H.A.: An Iterative Solution Method for Linear Systems of Which the Coefficient Matrix is a Symmetric M-Matrix. Mathematics of Computation\u00a031(137) (1977)","DOI":"10.2307\/2005786"},{"key":"8_CR19","unstructured":"Naumov, M.: Parallel Solution of Sparse Triangular Linear Systems in the Preconditioned Iterative Methods on the GPU. Technical Report 001, NVIDIA Corporation (2011)"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Park, J., Dally, W.J.: Buffer-space Efficient and Deadlock-free Scheduling of Stream Applications on Multi-core Architectures. In: Symposium on Parallelism in Algorithms and Architectures (SPAA) (2010)","DOI":"10.1145\/1810479.1810481"},{"key":"8_CR21","unstructured":"Petitet, A., Whaley, R.C., Dongarra, J., Cleary, A.: HPL - A Portable Implementation of the High-Performance Linpack Benchmark for Distributed-Memory Computers, \n                      http:\/\/www.netlib.org\/benchmark\/hpl\/"},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"Poole, E.L., Ortega, J.M.: Multicolor ICCG Methods for Vector Computers. SIAM Journal on Numerical Analysis\u00a024(6) (1987)","DOI":"10.1137\/0724090"},{"key":"8_CR23","doi-asserted-by":"crossref","unstructured":"Rothberg, E., Gupta, A.: Parallel ICCG on a Hierarchical Memory Multiprocessor - Addressing the Triangular Solve Bottleneck. Parallel Computing\u00a018(7) (1992)","DOI":"10.1016\/0167-8191(92)90041-5"},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"Saltz, J.H.: Aggregation Methods for Solving Sparse Triangular Systems on Multiprocessors. SIAM Journal of Scientific and Statistical Computing\u00a011(1) (1990)","DOI":"10.1137\/0911008"},{"key":"8_CR25","unstructured":"Saltz, J.H., Mirchandaney, R., Baxter, D.: Run-Time Parallelization and Scheduling of Loops. In: Symposium on Parallelism in Algorithms and Architectures (SPAA) (1989)"},{"issue":"4","key":"8_CR26","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1177\/1094342010389857","volume":"25","author":"B. Smith","year":"2011","unstructured":"Smith, B., Zhang, H.: Sparse triangular solves for ILU revisited: Data layout crucial to better performance. International Journal of High Performance Computing Applications\u00a025(4), 386\u2013391 (2011)","journal-title":"International Journal of High Performance Computing Applications"},{"key":"8_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/978-3-642-19328-6_6","volume-title":"High Performance Computing for Computational Science \u2013 VECPAR 2010","author":"M.M. Wolf","year":"2011","unstructured":"Wolf, M.M., Heroux, M.A., Boman, E.G.: Factors Impacting Performance of Multithreaded Sparse Triangular Solve. In: Palma, J.M.L.M., Dayd\u00e9, M., Marques, O., Lopes, J.C. (eds.) VECPAR 2010. LNCS, vol.\u00a06449, pp. 32\u201344. Springer, Heidelberg (2011)"}],"container-title":["Lecture Notes in Computer Science","Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-07518-1_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T09:16:17Z","timestamp":1639732577000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-07518-1_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319075174","9783319075181"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-07518-1_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014]]}}}