{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T07:21:05Z","timestamp":1777965665338,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2016,6,1]],"date-time":"2016-06-01T00:00:00Z","timestamp":1464739200000},"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":[[2016,6]]},"DOI":"10.1145\/2925426.2926259","type":"proceedings-article","created":{"date-parts":[[2016,6,10]],"date-time":"2016-06-10T13:04:07Z","timestamp":1465563847000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":19,"title":["Fast Multiplication in Binary Fields on GPUs via Register Cache"],"prefix":"10.1145","author":[{"given":"Eli","family":"Ben-Sasson","sequence":"first","affiliation":[{"name":"Technion, Haifa, Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matan","family":"Hamilis","sequence":"additional","affiliation":[{"name":"Technion, Haifa, Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark","family":"Silberstein","sequence":"additional","affiliation":[{"name":"Technion, Haifa, Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eran","family":"Tromer","sequence":"additional","affiliation":[{"name":"Tel-Aviv University, Tel-Aviv, Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2016,6]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/1964179.1964185"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/MWSCAS.2010.5548560"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2503268"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2555243.2555253"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipl.2012.03.012"},{"key":"e_1_3_2_1_6_1","volume-title":"Newnes","author":"Kirk D. B.","year":"2012","unstructured":"D. B. Kirk , and W. W. Hwu . Programming Massively Parallel Pocessors: A Hands-on Approach . Newnes , 2012 . D. B. Kirk, and W. W. Hwu. Programming Massively Parallel Pocessors: A Hands-on Approach. Newnes, 2012."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01178683"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1137\/050646445"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/647093.716546"},{"key":"e_1_3_2_1_10_1","volume-title":"AMD and VIA CPUs.","author":"Fog A.","year":"1996","unstructured":"A. Fog . Lists of instruction latencies, throughputs and micro-operation breakdowns for Intel , AMD and VIA CPUs. Available at http:\/\/www.agner.org\/optimize\/instruction_tables.pdf, 1996 --2016. {Online; accessed 28-Mar-2016}. A. Fog. Lists of instruction latencies, throughputs and micro-operation breakdowns for Intel, AMD and VIA CPUs. Available at http:\/\/www.agner.org\/optimize\/instruction_tables.pdf, 1996--2016. {Online; accessed 28-Mar-2016}."},{"key":"e_1_3_2_1_11_1","volume-title":"Using butterfly-patterned partial sums to optimize GPU memory accesses for drawing from discrete distributions. CoRR, abs\/1505.03851","author":"Steele G. L.","year":"2015","unstructured":"G. L. Steele Jr ., and J. B. Tristan . Using butterfly-patterned partial sums to optimize GPU memory accesses for drawing from discrete distributions. CoRR, abs\/1505.03851 , 2015 . G. L. Steele Jr., and J. B. Tristan. Using butterfly-patterned partial sums to optimize GPU memory accesses for drawing from discrete distributions. CoRR, abs\/1505.03851, 2015."},{"key":"e_1_3_2_1_12_1","volume-title":"Intel(R) carry-less multiplication instruction and its usage for computing the GCM mode - rev 2.02","author":"Shay G.","year":"2014","unstructured":"G. Shay , and M. E. Kounavis . Intel(R) carry-less multiplication instruction and its usage for computing the GCM mode - rev 2.02 . Intel Corporation , April 2014 . G. Shay, and M. E. Kounavis. Intel(R) carry-less multiplication instruction and its usage for computing the GCM mode - rev 2.02. Intel Corporation, April 2014."},{"key":"e_1_3_2_1_13_1","volume-title":"AES proposal: Rijndael.","author":"Daemen J.","year":"1998","unstructured":"J. Daemen , and V. Rijmen . AES proposal: Rijndael. Available at http:\/\/jda.noekeon.org\/JDA_VRI_Rijndael_V2_1999.pdf, 1998 . {Online; accessed 28-Mar-2016}. J. Daemen, and V. Rijmen. AES proposal: Rijndael. Available at http:\/\/jda.noekeon.org\/JDA_VRI_Rijndael_V2_1999.pdf, 1998. {Online; accessed 28-Mar-2016}."},{"key":"e_1_3_2_1_14_1","volume-title":"Computational method and apparatus for finite field arithmetic. US patent number 4587627","author":"Massey J. L.","year":"1986","unstructured":"J. L. Massey , and J. K. Omura . Computational method and apparatus for finite field arithmetic. US patent number 4587627 . May 1986 . J. L. Massey, and J. K. Omura. Computational method and apparatus for finite field arithmetic. US patent number 4587627. May 1986."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2093139.2093141"},{"key":"e_1_3_2_1_16_1","first-page":"298","volume-title":"11th USENIX Conference on File and Storage Technologies","author":"Plank J. S.","year":"2013","unstructured":"J. S. Plank , K. M. Greenan , and E. L. Miller . Screaming fast Galois field arithmetic using Intel SIMD instructions . In 11th USENIX Conference on File and Storage Technologies , pages 298 -- 306 , February 2013 . J. S. Plank, K. M. Greenan, and E. L. Miller. Screaming fast Galois field arithmetic using Intel SIMD instructions. In 11th USENIX Conference on File and Storage Technologies, pages 298--306, February 2013."},{"key":"e_1_3_2_1_17_1","first-page":"93","volume-title":"IEEE International Symposium on Circuits and Systems","author":"Leboeuf K.","year":"2012","unstructured":"K. Leboeuf , R. Muscedere , and M. Ahmadi . High performance prime field multiplication for GPU . In IEEE International Symposium on Circuits and Systems , pages 93 -- 96 , May 2012 . K. Leboeuf, R. Muscedere, and M. Ahmadi. High performance prime field multiplication for GPU. In IEEE International Symposium on Circuits and Systems, pages 93--96, May 2012."},{"key":"e_1_3_2_1_18_1","volume-title":"Multiplication of Many-Digital Numbers by Automatic Computers. Doklady Akad. Nauk SSSR145, 293--294","author":"Karatsuba A.","year":"1962","unstructured":"A. Karatsuba and Y. Ofman . Multiplication of Many-Digital Numbers by Automatic Computers. Doklady Akad. Nauk SSSR145, 293--294 , 1962 . Translation in Physics-Doklady 7, 595--596, 1963. A. Karatsuba and Y. Ofman. Multiplication of Many-Digital Numbers by Automatic Computers. Doklady Akad. Nauk SSSR145, 293--294, 1962. Translation in Physics-Doklady 7, 595--596, 1963."},{"key":"e_1_3_2_1_20_1","unstructured":"nVidia. Kepler Tuning Guide. http:\/\/docs.nvidia.com\/cuda\/kepler-tuning-guide\/index.html 2015. {Online; accessed 26-Jan-2016}.  nVidia. Kepler Tuning Guide. http:\/\/docs.nvidia.com\/cuda\/kepler-tuning-guide\/index.html 2015. {Online; accessed 26-Jan-2016}."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2014.2384047"},{"key":"e_1_3_2_1_22_1","volume-title":"Finite Fields","author":"Lidl R.","year":"1997","unstructured":"R. Lidl and H. Niederreiter . Finite Fields . ( 2 nd ed.), Cambridge University Press , 1997 . R. Lidl and H. Niederreiter. Finite Fields. (2nd ed.), Cambridge University Press, 1997.","edition":"2"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2851141.2851169"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2011.40"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF02242355"},{"key":"e_1_3_2_1_26_1","volume-title":"NTL: A library for doing number theory. Avilable at http:\/\/www.shoup.net\/ntl","author":"Shoup V.","year":"2003","unstructured":"V. Shoup . NTL: A library for doing number theory. Avilable at http:\/\/www.shoup.net\/ntl , 2003 . {Online; accessed 28-Mar-2016}. V. Shoup. NTL: A library for doing number theory. Avilable at http:\/\/www.shoup.net\/ntl, 2003. {Online; accessed 28-Mar-2016}."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.5555\/1413370.1413402"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the GPU Technology Conference","author":"Volkov V.","year":"2010","unstructured":"V. Volkov . Better performance at lower occupancy . Proceedings of the GPU Technology Conference , 2010 . V. Volkov. Better performance at lower occupancy. Proceedings of the GPU Technology Conference, 2010."},{"key":"e_1_3_2_1_29_1","volume-title":"Bit slicing--- Wikipedia,. {Online","year":"2016","unstructured":"Wikipedia. Bit slicing--- Wikipedia,. {Online ; accessed 27- Mar- 2016 }. Wikipedia. Bit slicing--- Wikipedia,. {Online; accessed 27-Mar-2016}."}],"event":{"name":"ICS '16: 2016 International Conference on Supercomputing","location":"Istanbul Turkey","acronym":"ICS '16","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 2016 International Conference on Supercomputing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2925426.2926259","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2925426.2926259","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T19:04:25Z","timestamp":1750273465000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2925426.2926259"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,6]]},"references-count":28,"alternative-id":["10.1145\/2925426.2926259","10.1145\/2925426"],"URL":"https:\/\/doi.org\/10.1145\/2925426.2926259","relation":{},"subject":[],"published":{"date-parts":[[2016,6]]},"assertion":[{"value":"2016-06-01","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}