{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,5,14]],"date-time":"2024-05-14T00:27:01Z","timestamp":1715646421351},"reference-count":17,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"12","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2023,12,1]]},"DOI":"10.1587\/transinf.2023pap0008","type":"journal-article","created":{"date-parts":[[2023,11,30]],"date-time":"2023-11-30T22:36:24Z","timestamp":1701383784000},"page":"2015-2025","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive Lossy Data Compression Extended Architecture for Memory Bandwidth Conservation in SpMV"],"prefix":"10.1587","volume":"E106.D","author":[{"given":"Siyi","family":"HU","sequence":"first","affiliation":[{"name":"The University of Tokyo"}]},{"given":"Makiko","family":"ITO","sequence":"additional","affiliation":[{"name":"Fujitsu Ltd."}]},{"given":"Takahide","family":"YOSHIKAWA","sequence":"additional","affiliation":[{"name":"Fujitsu Ltd."}]},{"given":"Yuan","family":"HE","sequence":"additional","affiliation":[{"name":"Keio University"}]},{"given":"Hiroshi","family":"NAKAMURA","sequence":"additional","affiliation":[{"name":"The University of Tokyo"}]},{"given":"Masaaki","family":"KONDO","sequence":"additional","affiliation":[{"name":"Keio University"},{"name":"RIKEN"}]}],"member":"532","reference":[{"key":"1","unstructured":"[1] HPCG Ranking June 2021: https:\/\/www.top500.org\/lists\/hpcg\/2021\/06\/."},{"key":"2","doi-asserted-by":"publisher","unstructured":"[2] K. Kourtis, V. Karakasis, G. Goumas, and N. Koziris, \u201cCSX: an extended compression format for spmv on shared memory systems,\u201d SIGPLAN Not., vol.46, no.8, pp.247-256, 2011. 10.1145\/2038037.1941587","DOI":"10.1145\/2038037.1941587"},{"key":"3","doi-asserted-by":"publisher","unstructured":"[3] K. Ahmad, H. Sundar, and M. Hall, \u201cData-driven mixed precision sparse matrix vector multiplication for GPUs,\u201d ACM Trans. TACO, vol.16, no.4, pp.1-24, 2019. 10.1145\/3371275","DOI":"10.1145\/3371275"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] R. Sakamoto, M. Kondo, K. Fujita, T. Ichimura, and K. Nakajima, \u201cThe Effectiveness of Low-Precision Floating Arithmetic on Numerical Codes: A Case Study on Power Consumption,\u201d Proc. HPCAsia2020, pp.199-206, 2020. 10.1145\/3368474.3368492","DOI":"10.1145\/3368474.3368492"},{"key":"5","unstructured":"[5] FUJITSU Processor A64FX Datasheet. https:\/\/www.fujitsu.com\/downloads\/SUPER\/a64fx\/a64fx_datasheet_en.pdf"},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] F. V\u00e1zquez, G. Ortega, J.J. Fern\u00e1ndez, and E.M. Garz\u00f3n, \u201cImproving the performance of the sparse matrix vector product with GPUs,\u201d Proc. 10th IEEE ICCIT, ser. CIT, pp.1146-1151, 2010. 10.1109\/cit.2010.208","DOI":"10.1109\/CIT.2010.208"},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] W.T. Tang, W.J. Tan, R. Ray, Y.W. Wong, W. Chan, S.-H. Kuo, R.S.M. Goh, S.J. Turner, and W.-F. Wong, \u201cAccelerating sparse matrix-vector multiplication on GPUs using bit-representation optimized schemes,\u201d Proc. ICHPC, 2013. 10.1145\/2503210.2503234","DOI":"10.1145\/2503210.2503234"},{"key":"8","doi-asserted-by":"publisher","unstructured":"[8] W. Yang, K. Li, Z. Mo, and K. Li, \u201cPerformance optimization using partitioned SpMV on GPUs and multicore CPUs,\u201d IEEE Trans. Comput., vol.64, no.9, pp.2623-2636, 2015. 10.1109\/tc.2014.2366731","DOI":"10.1109\/TC.2014.2366731"},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] A. Ashari, N. Sedaghati, J. Eisenlohr, and P. Sadayappan, \u201cAn Efficient Two-Dimensional Blocking Strategy for Sparse Matrix-vector Multiplication on GPUs,\u201d Proc. ICS '14, pp.273-282, 2014. 10.1145\/2597652.2597678","DOI":"10.1109\/SC.2014.69"},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] P. Grigoras, P. Burovskiy, E. Hung, and W. Luk, \u201cAccelerating SpMV on FPGAs by Compressing Nonzero Values,\u201d 2015 IEEE 23rd Annual International Symposium on Field-Programmable Custom Computing Machines, pp.64-67, 2015. 10.1109\/fccm.2015.30","DOI":"10.1109\/FCCM.2015.30"},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] W. Liu and B. Vinter, \u201cCSR5: An Efficient Storage Format for Cross-Platform Sparse Matrix-Vector Multiplication,\u201d Proc. ICS'15, pp.339-350, 2015. 10.1145\/2751205.2751209","DOI":"10.1145\/2751205.2751209"},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] B. Bian, J. Huang, R. Dong, L. Liu, and X. Wang, \u201cCSR2: A New Format for SIMD-accelerated SpMV,\u201d CCGRID, pp.350-359, 2020. 10.1109\/ccgrid49817.2020.00-58","DOI":"10.1109\/CCGrid49817.2020.00-58"},{"key":"13","unstructured":"[13] B., David, T. Harris, W. Saphir, R.V.D. Wijngaart, A. Woo, and M. Yarrow, \u201cThe NAS parallel benchmarks 2.0,\u201d Technical Report NAS-95-020, vol.156, NASA Ames Research Center, 1995."},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] J. Dongarra, M.A. Heroux, and P. Luszczek, \u201cHPCG Benchmark: A new metric for ranking high performance computing systems,\u201d Knoxville, Tennessee, 2015.","DOI":"10.1177\/1094342015593158"},{"key":"15","doi-asserted-by":"publisher","unstructured":"[15] T.A. Davis and Y. Hu, \u201cThe University of Florida Sparse Matrix Collection,\u201d ACM Trans. on Mathematical Software, vol.38, no.1, Article 1, pp.1-25, Dec. 2011. 10.1145\/2049662.2049663","DOI":"10.1145\/2049662.2049663"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] N.E. Jerger, A. Kannan, Z. Li, and G.H. Loh, \u201cNoC Architectures for Silicon Interposer Systems: Why Pay for more Wires when you Can Get them (from your interposer) for Free,\u201d 47th Annual IEEE\/ACM International Symposium on Microarchitecture, pp.458-470, Dec. 2014. 10.1109\/micro.2014.61","DOI":"10.1109\/MICRO.2014.61"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] J. Jayabalan, V. Chidambaram, S.L.PSiang, W. Xiangyu, J.M. Chinq, S. Bhattacharya, \u201cActive Through-Silicon Interposer Based 2.5D IC Design, Fabrication, Assembly and Test,\u201d IEEE 69th Electronic Components and Technology Conference, pp.587-593, May 2019. 10.1109\/ectc.2019.00094","DOI":"10.1109\/ECTC.2019.00094"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E106.D\/12\/E106.D_2023PAP0008\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T04:59:14Z","timestamp":1715576354000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E106.D\/12\/E106.D_2023PAP0008\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,1]]},"references-count":17,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2023]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2023pap0008","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,1]]},"article-number":"2023PAP0008"}}