{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:25:42Z","timestamp":1750220742213,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,8,17]],"date-time":"2020-08-17T00:00:00Z","timestamp":1597622400000},"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":[[2020,8,17]]},"DOI":"10.1145\/3409390.3409404","type":"proceedings-article","created":{"date-parts":[[2020,8,17]],"date-time":"2020-08-17T13:35:15Z","timestamp":1597671315000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Improving the Space-Time Efficiency of Matrix Multiplication Algorithms"],"prefix":"10.1145","author":[{"given":"Yuan","family":"Tang","sequence":"first","affiliation":[{"name":"Fudan University, China"}]}],"member":"320","published-online":{"date-parts":[[2020,8,17]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/341800.341801"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"R.\u00a0C. Agarwal S.\u00a0M. Balle F.\u00a0G. Gustavson M. Joshi and P. Palkar. 1995. A three-dimensional approach to parallel matrix multiplication. IBM Journal of Research and Development 39 (Sep. 1995) 575\u2013582. Issue 5.  R.\u00a0C. Agarwal S.\u00a0M. Balle F.\u00a0G. Gustavson M. Joshi and P. Palkar. 1995. A three-dimensional approach to parallel matrix multiplication. IBM Journal of Research and Development 39 (Sep. 1995) 575\u2013582. Issue 5.","DOI":"10.1147\/rd.395.0575"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Nimar\u00a0S. Arora Robert\u00a0D. Blumofe and C.\u00a0Greg Plaxton. 1998. Thread Scheduling for Multiprogrammed Multiprocessors. In SPAA \u201998. 119\u2013129.  Nimar\u00a0S. Arora Robert\u00a0D. Blumofe and C.\u00a0Greg Plaxton. 1998. Thread Scheduling for Multiprogrammed Multiprocessors. In SPAA \u201998. 119\u2013129.","DOI":"10.1145\/277651.277678"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2312005.2312021"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2312005.2312044"},{"key":"e_1_3_2_1_6_1","unstructured":"Grey Ballard James Demmel Olga Holtz Benjamin Lipshitz and Oded Schwartz. 2012. Strong Scaling of Matrix Multiplication Algorithms and Memory-Independent Communication Lower Bounds. CoRR abs\/1202.3177(2012).  Grey Ballard James Demmel Olga Holtz Benjamin Lipshitz and Oded Schwartz. 2012. Strong Scaling of Matrix Multiplication Algorithms and Memory-Independent Communication Lower Bounds. CoRR abs\/1202.3177(2012)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1137\/090769156"},{"volume-title":"Proceedings of the 20th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming(PPoPP","year":"2015","author":"R.","key":"e_1_3_2_1_8_1"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1810479.1810519"},{"volume-title":"1st Symposium on Algorithmic Principles of Computer Systems, APOCS@SODA 2020","year":"2020","author":"E.","key":"e_1_3_2_1_10_1"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/237502.237574"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/209936.209958"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/324133.324234"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1576702.1576713"},{"key":"e_1_3_2_1_15_1","unstructured":"Lynn\u00a0Elliot Cannon. 1969. A Cellular Computer to Implement the Kalman Filter Algorithm. Ph.D. Dissertation. Bozeman MT USA. AAI7010025.  Lynn\u00a0Elliot Cannon. 1969. A Cellular Computer to Implement the Kalman Filter Algorithm. Ph.D. Dissertation. Bozeman MT USA. AAI7010025."},{"volume-title":"Proceedings of ACM Symposium on Parallelism in Algorithms and Architectures (SPAA). 207\u2013216","author":"Chowdhury R.","key":"e_1_3_2_1_16_1"},{"volume-title":"Efficient Resource Oblivious Algorithms for Multicores with False Sharing. In 26th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2012","year":"2012","author":"Cole Richard","key":"e_1_3_2_1_17_1"},{"volume-title":"Revisiting the Cache Miss Analysis of Multithreaded Algorithms. In LATIN 2012: Theoretical Informatics - 10th Latin American Symposium, Arequipa, Peru, April 16-20, 2012. Proceedings. 172\u2013183","year":"2012","author":"Cole Richard","key":"e_1_3_2_1_18_1"},{"key":"e_1_3_2_1_19_1","unstructured":"Thomas\u00a0H. Cormen Charles\u00a0E. Leiserson Ronald\u00a0L. Rivest and Clifford Stein. 2009. Introduction to Algorithms(third ed.). The MIT Press.  Thomas\u00a0H. Cormen Charles\u00a0E. Leiserson Ronald\u00a0L. Rivest and Clifford Stein. 2009. Introduction to Algorithms(third ed.). The MIT Press."},{"volume-title":"Communication-Optimal Parallel Recursive Rectangular Matrix Multiplication. In 27th IEEE International Symposium on Parallel and Distributed Processing, IPDPS 2013","year":"2013","author":"Demmel James","key":"e_1_3_2_1_20_1"},{"volume-title":"SPAA\u201916.","author":"Dinh David","key":"e_1_3_2_1_21_1"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2071379.2071383"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00224-007-9098-2"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0304-3975(97)00193-X"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1137\/S009753979427491"},{"key":"e_1_3_2_1_26_1","unstructured":"Yan Gu. 2018. Improved Parallel Cache-Oblivious Algorithms for Dynamic Programming and Linear Algebra. CoRR abs\/1809.09330(2018).  Yan Gu. 2018. Improved Parallel Cache-Oblivious Algorithms for Dynamic Programming and Linear Algebra. CoRR abs\/1809.09330(2018)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Jianyu Huang Tyler\u00a0M. Smith Greg\u00a0M. Henry and Robert\u00a0A. van\u00a0de Geijn. 2016. Implementing Strassen\u2019s Algorithm with BLIS. CoRR (2016).  Jianyu Huang Tyler\u00a0M. Smith Greg\u00a0M. Henry and Robert\u00a0A. van\u00a0de Geijn. 2016. Implementing Strassen\u2019s Algorithm with BLIS. CoRR (2016).","DOI":"10.1109\/SC.2016.58"},{"key":"e_1_3_2_1_28_1","unstructured":"Intel Corporation 2010. Intel Cilk Plus Language Specification. Intel Corporation. Document Number: 324396-001US. Available from http:\/\/software.intel.com\/sites\/products\/cilk-plus\/cilk_plus_language_specification.pdf.  Intel Corporation 2010. Intel Cilk Plus Language Specification. Intel Corporation. Document Number: 324396-001US. Available from http:\/\/software.intel.com\/sites\/products\/cilk-plus\/cilk_plus_language_specification.pdf."},{"key":"e_1_3_2_1_29_1","unstructured":"Joseph J\u00e1J\u00e1. 1992. An Introduction to Parallel Algorithms. Addison-Wesley.  Joseph J\u00e1J\u00e1. 1992. An Introduction to Parallel Algorithms. Addison-Wesley."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1155\/1995\/636457"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-010-0405-3"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2012.33"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/PL00008264"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","unstructured":"Julian Shun Guy\u00a0E. Blelloch Jeremy\u00a0T. Fineman and Phillip\u00a0B. Gibbons. 2013. Reducing contention through priority updates. In SPAA. 152\u2013163.  Julian Shun Guy\u00a0E. Blelloch Jeremy\u00a0T. Fineman and Phillip\u00a0B. Gibbons. 2013. Reducing contention through priority updates. In SPAA. 152\u2013163.","DOI":"10.1145\/2486159.2486189"},{"volume-title":"Proceedings of the 2014 IEEE 28th International Parallel and Distributed Processing Symposium(IPDPS \u201914)","author":"Smith M.","key":"e_1_3_2_1_35_1"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23397-5_10"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/1583991.1584019"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF02165411"}],"event":{"name":"ICPP Workshops '20: Workshops","acronym":"ICPP Workshops '20","location":"Edmonton AB Canada"},"container-title":["49th International Conference on Parallel Processing - ICPP : Workshops"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3409390.3409404","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3409390.3409404","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:38:40Z","timestamp":1750199920000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3409390.3409404"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,17]]},"references-count":38,"alternative-id":["10.1145\/3409390.3409404","10.1145\/3409390"],"URL":"https:\/\/doi.org\/10.1145\/3409390.3409404","relation":{},"subject":[],"published":{"date-parts":[[2020,8,17]]},"assertion":[{"value":"2020-08-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}