{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T06:12:44Z","timestamp":1764655964387,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,6,14]],"date-time":"2017-06-14T00:00:00Z","timestamp":1497398400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100002809","name":"Generalitat de Catalunya","doi-asserted-by":"publisher","award":["2014-SGR-1051 & 2014-SGR-1272"],"award-info":[{"award-number":["2014-SGR-1051 & 2014-SGR-1272"]}],"id":[{"id":"10.13039\/501100002809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Severo Ochoa","award":["SEV2015-0493"],"award-info":[{"award-number":["SEV2015-0493"]}]},{"name":"BSC\/IBM Deep Learning Center Initiative"},{"DOI":"10.13039\/501100004837","name":"Ministerio de Ciencia e Innovaci\u00f3n","doi-asserted-by":"publisher","award":["TIN2015-65316"],"award-info":[{"award-number":["TIN2015-65316"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2017,6,14]]},"DOI":"10.1145\/3079079.3079091","type":"proceedings-article","created":{"date-parts":[[2017,5,31]],"date-time":"2017-05-31T19:31:40Z","timestamp":1496259100000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Iteration-fusing conjugate gradient"],"prefix":"10.1145","author":[{"given":"Sicong","family":"Zhuang","sequence":"first","affiliation":[{"name":"Barcelona Supercomputing Center (BSC), Barcelona, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marc","family":"Casas","sequence":"additional","affiliation":[{"name":"Barcelona Supercomputing Center (BSC), Barcelona, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2017,6,14]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2009. Intel Math Kernel Library Reference Manual. Intel Corporation.  2009. Intel Math Kernel Library Reference Manual . Intel Corporation."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1093\/imanum\/14.4.563"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"R. Barrett M. Berry T. F. Chan J. Demmel J. Donato J. Dongarra V. Eijkhout R. Pozo C. Romine and H. Van der Vorst. 1994. Templates for the Solution of Linear Systems: Building Blocks for Iterative Methods 2nd Edition. SIAM.  R. Barrett M. Berry T. F. Chan J. Demmel J. Donato J. Dongarra V. Eijkhout R. Pozo C. Romine and H. Van der Vorst. 1994. Templates for the Solution of Linear Systems: Building Blocks for Iterative Methods 2nd Edition . SIAM.","DOI":"10.1137\/1.9781611971538"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1454115.1454128"},{"key":"e_1_3_2_1_5_1","unstructured":"BSC. 2015. Programming Models Group. The Nanos++ Parallel Runtime. https:\/\/pm.bsc.es\/nanox. (2015).  BSC. 2015. Programming Models Group. The Nanos++ Parallel Runtime. https:\/\/pm.bsc.es\/nanox. (2015)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2464996.2465017"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Erin Carson and James Demmel. 2014. A Residual Replacement Strategy for Improving the Maximum Attainable Accuracy of s-Step Krylov Subspace Methods. SIAM J. Matrix Anal. Appl. 35 1 (2014).  Erin Carson and James Demmel. 2014. A Residual Replacement Strategy for Improving the Maximum Attainable Accuracy of s -Step Krylov Subspace Methods. SIAM J. Matrix Anal. Appl . 35 1 (2014).","DOI":"10.1137\/120893057"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1137\/0728088"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/0377-0427(89)90045-9"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2938615.2938621"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2049662.2049663"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Eduardo D'Azevedo Victor Eijkhout and Charles Romine. 1993. LAPACK Working Note 56: Reducing Communication Costs in the Conjugate Gradient Algorithm on Distributed Memory Multiprocessors. Technical Report. Knoxville TN USA.   Eduardo D'Azevedo Victor Eijkhout and Charles Romine. 1993. LAPACK Working Note 56: Reducing Communication Costs in the Conjugate Gradient Algorithm on Distributed Memory Multiprocessors . Technical Report. Knoxville TN USA.","DOI":"10.2172\/10176473"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/0168-9274(95)00079-A"},{"key":"e_1_3_2_1_15_1","first-page":"2","article-title":"van der Vorst. 1993. Parallel numerical linear algebra","author":"Demmel James W.","year":"1993","journal-title":"Acta Numerica"},{"key":"e_1_3_2_1_16_1","unstructured":"Kurt B. Ferreira Patrick Bridges and Ron Brightwell. Characterizing Application Sensitivity to OS Interference Using Kernel-level Noise Injection (SC '08).   Kurt B. Ferreira Patrick Bridges and Ron Brightwell. Characterizing Application Sensitivity to OS Interference Using Kernel-level Noise Injection (SC '08 )."},{"issue":"1","key":"e_1_3_2_1_17_1","article-title":"2013","volume":"35","author":"Ghysels P.","year":"2013","journal-title":"SIAM Journal on Sci. Computing"},{"key":"e_1_3_2_1_18_1","unstructured":"W. Gropp. 2010. Update on libraries for blue waters. http:\/\/jointlab-pc.ncsa.illinois.edu\/events\/workshop3\/pdf\/presentations\/Gropp-Update-on-Libraries.pdf. (2010).  W. Gropp. 2010. Update on libraries for blue waters. http:\/\/jointlab-pc.ncsa.illinois.edu\/events\/workshop3\/pdf\/presentations\/Gropp-Update-on-Libraries.pdf. (2010)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2010.12"},{"key":"e_1_3_2_1_21_1","unstructured":"M. Hoemmen. 2010. Communication-avoiding Krylov subspace methods. Ph.D. Dissertation. University of California.   M. Hoemmen. 2010. Communication-avoiding Krylov subspace methods . Ph.D. Dissertation. University of California."},{"key":"e_1_3_2_1_22_1","unstructured":"Wayne Joubert and Graham F. Carey. Parallelizable Restarted Iterative Methods for Nonsymmetric Linear Systems (SIAM PP '91).  Wayne Joubert and Graham F. Carey. Parallelizable Restarted Iterative Methods for Nonsymmetric Linear Systems (SIAM PP '91) ."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"G\u00e9rard Meurant. 1987. Multitasking the conjugate gradient method on the CRAY X-MP\/48. Parallel Comput. 5 3 (1987).  G\u00e9rard Meurant. 1987. Multitasking the conjugate gradient method on the CRAY X-MP\/48. Parallel Comput . 5 3 (1987).","DOI":"10.1016\/0167-8191(87)90037-8"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2011.84"},{"key":"e_1_3_2_1_25_1","unstructured":"OpenMP4.0 2013. Application Program Interface. (2013).  OpenMP4.0 2013. Application Program Interface. (2013)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2013.06.001"},{"key":"e_1_3_2_1_27_1","unstructured":"John Van Rosendale. 1983. Minimizing inner product data dependencies in conjugate gradient iteration. ICASE-NASA 172178 (1983).  John Van Rosendale. 1983. Minimizing inner product data dependencies in conjugate gradient iteration. ICASE-NASA 172178 (1983)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1137\/0905015"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Henk A. Van Der Vorst and Qiang Ye. 1999. Residual Replacement Strategies for Krylov Subspace Iterative Methods for the Convergence of True Residuals. Technical Report.  Henk A. Van Der Vorst and Qiang Ye. 1999. Residual Replacement Strategies for Krylov Subspace Iterative Methods for the Convergence of True Residuals . Technical Report.","DOI":"10.1137\/S1064827599353865"},{"key":"e_1_3_2_1_30_1","unstructured":"Laurence Tianruo Yang and Richard P. Brent. The Improved BiCG Method for Large and Sparse Linear Systems on Parallel Distributed Memory Architectures (PDSECA '02).  Laurence Tianruo Yang and Richard P. Brent. The Improved BiCG Method for Large and Sparse Linear Systems on Parallel Distributed Memory Architectures (PDSECA '02) ."},{"key":"e_1_3_2_1_31_1","unstructured":"Laurence Tianruo Yang and Richard P. Brent. The improved BiCGStab method for large and sparse unsymmetric linear systems on parallel distributed memory architectures (ICA3PP '02).  Laurence Tianruo Yang and Richard P. Brent. The improved BiCGStab method for large and sparse unsymmetric linear systems on parallel distributed memory architectures (ICA3PP '02) ."}],"event":{"name":"ICS '17: 2017 International Conference on Supercomputing","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"],"location":"Chicago Illinois","acronym":"ICS '17"},"container-title":["Proceedings of the International Conference on Supercomputing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3079079.3079091","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3079079.3079091","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T03:03:25Z","timestamp":1750215805000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3079079.3079091"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,6,14]]},"references-count":29,"alternative-id":["10.1145\/3079079.3079091","10.1145\/3079079"],"URL":"https:\/\/doi.org\/10.1145\/3079079.3079091","relation":{},"subject":[],"published":{"date-parts":[[2017,6,14]]},"assertion":[{"value":"2017-06-14","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}