{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T19:26:49Z","timestamp":1777058809439,"version":"3.51.4"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031856990","type":"print"},{"value":"9783031857003","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-85700-3_10","type":"book-chapter","created":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T04:57:41Z","timestamp":1743569861000},"page":"134-147","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Performance Portability of\u00a0SpMV for\u00a0CSR and\u00a0BSR Storage Formats Implemented Using OpenACC and\u00a0SYCL"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-6562-8954","authenticated-orcid":false,"given":"Kinga","family":"Stec","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8661-414X","authenticated-orcid":false,"given":"Przemys\u0142aw","family":"Stpiczy\u0144ski","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,4,1]]},"reference":[{"key":"10_CR1","doi-asserted-by":"publisher","unstructured":"Beckingsale, D., et al.: RAJA: portable performance for large-scale scientific applications. In: 2019 IEEE\/ACM International Workshop on Performance, Portability and Productivity in HPC, P3HPC@SC 2019, Denver, CO, USA, November 22, 2019, pp. 71\u201381. IEEE (2019). https:\/\/doi.org\/10.1109\/P3HPC49587.2019.00012","DOI":"10.1109\/P3HPC49587.2019.00012"},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"Boisvert, R.F., Pozo, R., Remington, K.A., Barrett, R.F., Dongarra, J.: Matrix Market: a web resource for test matrix collections. In: Boisvert, R.F. (ed.) Quality of Numerical Software - Assessment and Enhancement, Proceedings of the IFIP TC2\/WG2.5 Working Conference on the Quality of Numerical Software, Assessment and Enhancement, Oxford, UK, 8\u201312 July 1996. IFIP Conference Proceedings, vol.\u00a076, pp. 125\u2013137. Chapman & Hall (1997)","DOI":"10.1007\/978-1-5041-2940-4_9"},{"key":"10_CR3","unstructured":"Chandrasekaran, S., Juckeland, G. (eds.): OpenACC for Programmers: Concepts and Strategies. Addison-Wesley (2018)"},{"key":"10_CR4","unstructured":"Cheng, J., Grossman, M., McKercher, T. (eds.): Professional CUDA C Programming. Wiley and Sons (2014)"},{"issue":"1","key":"10_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2049662.2049663","volume":"38","author":"TA Davis","year":"2011","unstructured":"Davis, T.A., Hu, Y.: The University of Florida sparse matrix collection. ACM Trans. Math. Softw. 38(1), 1\u201325 (2011). https:\/\/doi.org\/10.1145\/2049662.2049663","journal-title":"ACM Trans. Math. Softw."},{"key":"10_CR6","doi-asserted-by":"publisher","unstructured":"Eberl, H.J., Sudarsan, R.: OpenACC parallelisation for diffusion problems, applied to temperature distribution on a honeycomb around the bee brood: A worked example using BiCGSTAB. In: Parallel Processing and Applied Mathematics - 10th International Conference, PPAM 2013, Warsaw, Poland, September 8-11, 2013, Revised Selected Papers, Part II. pp. 311\u2013321 (2013). https:\/\/doi.org\/10.1007\/978-3-642-55195-6_29","DOI":"10.1007\/978-3-642-55195-6_29"},{"issue":"12","key":"10_CR7","doi-asserted-by":"publisher","first-page":"3202","DOI":"10.1016\/j.jpdc.2014.07.003","volume":"74","author":"HC Edwards","year":"2014","unstructured":"Edwards, H.C., Trott, C.R., Sunderland, D.: Kokkos: enabling manycore performance portability through polymorphic memory access patterns. J. Parallel Distrib. Comput. 74(12), 3202\u20133216 (2014). https:\/\/doi.org\/10.1016\/j.jpdc.2014.07.003","journal-title":"J. Parallel Distrib. Comput."},{"issue":"1","key":"10_CR8","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1002\/cpe.2978","volume":"26","author":"X Feng","year":"2014","unstructured":"Feng, X., Jin, H., Zheng, R., Shao, Z., Zhu, L.: A segment-based sparse matrix-vector multiplication on CUDA. Concurrency Comput. Practice Exp. 26(1), 271\u2013286 (2014). https:\/\/doi.org\/10.1002\/cpe.2978","journal-title":"Concurrency Comput. Practice Exp."},{"issue":"15","key":"10_CR9","doi-asserted-by":"publisher","first-page":"3584","DOI":"10.1016\/j.cam.2011.04.025","volume":"236","author":"R Helfenstein","year":"2012","unstructured":"Helfenstein, R., Koko, J.: Parallel preconditioned conjugate gradient algorithm on GPU. J. Comput. Appl. Math. 236(15), 3584\u20133590 (2012). https:\/\/doi.org\/10.1016\/j.cam.2011.04.025","journal-title":"J. Comput. Appl. Math."},{"issue":"2","key":"10_CR10","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1007\/s11227-012-0825-3","volume":"63","author":"R Li","year":"2013","unstructured":"Li, R., Saad, Y.: GPU-accelerated preconditioned iterative linear solvers. J. Supercomput. 63(2), 443\u2013466 (2013). https:\/\/doi.org\/10.1007\/s11227-012-0825-3","journal-title":"J. Supercomput."},{"key":"10_CR11","doi-asserted-by":"publisher","unstructured":"Marowka, A.: On the performance portability of OpenACC, OpenMP, Kokkos and RAJA. In: HPC Asia 2022: International Conference on High Performance Computing in Asia-Pacific Region, Virtual Event, Japan, 12\u201314 January, 2022, pp. 103\u2013114. ACM (2022). https:\/\/doi.org\/10.1145\/3492805.3492806","DOI":"10.1145\/3492805.3492806"},{"key":"10_CR12","doi-asserted-by":"publisher","unstructured":"Marowka, A.: Reformulation of the performance portability metric. Softw. Practice Exp. 52(1), 154\u2013171 (2022). https:\/\/doi.org\/10.1002\/spe.3002","DOI":"10.1002\/spe.3002"},{"key":"10_CR13","doi-asserted-by":"publisher","unstructured":"Marowka, A.: A comparison of two performance portability metrics. Concurr. Comput. Practice Exp. 35 (2023). https:\/\/doi.org\/10.1002\/CPE.7868","DOI":"10.1002\/CPE.7868"},{"key":"10_CR14","doi-asserted-by":"publisher","unstructured":"Marowka, A.: Inferential statistical analysis of performance portability. In: Parallel Processing and Applied Mathematics, pp. 39\u201350. Springer (2023). https:\/\/doi.org\/10.1007\/978-3-031-30445-3_4","DOI":"10.1007\/978-3-031-30445-3_4"},{"key":"10_CR15","doi-asserted-by":"publisher","unstructured":"Marowka, A.: New insights on the revised definition of the performance portability metric. In: Parallel Processing and Applied Mathematics, pp. 27\u201338. Springer (2023). https:\/\/doi.org\/10.1007\/978-3-031-30445-3_2","DOI":"10.1007\/978-3-031-30445-3_2"},{"key":"10_CR16","doi-asserted-by":"publisher","unstructured":"Marowka, A.: Toward open repository of performance portability of applications, benchmarks and models. In: 35th IEEE International Symposium on Computer Architecture and High Performance Computing, SBAC-PAD 2023, Porto Alegre, Brazil, October 17-20, 2023, pp. 160\u2013169. IEEE (2023). https:\/\/doi.org\/10.1109\/SBAC-PAD59825.2023.00025","DOI":"10.1109\/SBAC-PAD59825.2023.00025"},{"key":"10_CR17","doi-asserted-by":"publisher","unstructured":"Matam, K.K., Kothapalli, K.: Accelerating sparse matrix vector multiplication in iterative methods using GPU. In: International Conference on Parallel Processing, ICPP 2011, Taipei, Taiwan, 13\u201316 September 2011, pp. 612\u2013621 (2011). https:\/\/doi.org\/10.1109\/ICPP.2011.82","DOI":"10.1109\/ICPP.2011.82"},{"key":"10_CR18","unstructured":"van der Pas, R., Stotzer, E., Terboven, C.: Using OpenMP \u2013 The Next Step, Affinity, Accelerators, Tasking, and SIMD. MIT Press, Cambridge MA (2017)"},{"key":"10_CR19","doi-asserted-by":"publisher","unstructured":"Pennycook, S.J., Sewall, J.D.: Revisiting a metric for performance portability. In: International Workshop on Performance, Portability and Productivity in HPC, P3HPC@SC 2021, St. Louis, MO, USA, November 14, 2021, pp.\u00a01\u20139. IEEE (2021). https:\/\/doi.org\/10.1109\/P3HPC54578.2021.00004","DOI":"10.1109\/P3HPC54578.2021.00004"},{"issue":"1","key":"10_CR20","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1002\/cpe.2949","volume":"26","author":"JC Pichel","year":"2014","unstructured":"Pichel, J.C., Lorenzo, J.A., Rivera, F.F., Heras, D.B., Pena, T.F.: Using sampled information: is it enough for the sparse matrix-vector product locality optimization? Concurrency Comput. Practice Exp. 26(1), 98\u2013117 (2014). https:\/\/doi.org\/10.1002\/cpe.2949","journal-title":"Concurrency Comput. Practice Exp."},{"key":"10_CR21","doi-asserted-by":"publisher","unstructured":"Reinders, J., Ashbaugh, B., Brodman, J., Kinsner, M., Pennycook, J., Tian, X.: Data Parallel C++. Apress Berkeley, CA (2021). https:\/\/doi.org\/10.1007\/978-1-4842-5574-2","DOI":"10.1007\/978-1-4842-5574-2"},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"Saad, Y.: Iterative methods for sparse linear systems. SIAM (2003)","DOI":"10.1137\/1.9780898718003"},{"issue":"2","key":"10_CR23","first-page":"130","volume":"8","author":"R Shahnaz","year":"2011","unstructured":"Shahnaz, R., Usman, A.: Blocked-based sparse matrix-vector multiplication on distributed memory parallel computers. Int. Arab J. Inf. Technol. 8(2), 130\u2013136 (2011)","journal-title":"Int. Arab J. Inf. Technol."},{"key":"10_CR24","doi-asserted-by":"publisher","unstructured":"Stec, K., Stpiczy\u0144ski, P.: Performance of portable sparse matrix-vector product implemented using OpenACC. In: Proceedings of the 18th Conference on Computer Science and Intelligence Systems, pp. 1155\u20131160. IEEE (2023). https:\/\/doi.org\/10.15439\/2023F9640","DOI":"10.15439\/2023F9640"},{"key":"10_CR25","doi-asserted-by":"publisher","unstructured":"Stpiczy\u0144ski, P.: Semiautomatic acceleration of sparse matrix-vector product using OpenACC. In: Parallel Processing and Applied Mathematics, 11th International Conference, PPAM 2015, Kracow, Poland, September 6-9, 2015, Revised Selected Papers, Part II. Lecture Notes in Computer Science, vol.\u00a09574, pp. 143\u2013152. Springer (2016). https:\/\/doi.org\/10.1007\/978-3-319-32152-3_14","DOI":"10.1007\/978-3-319-32152-3_14"},{"key":"10_CR26","doi-asserted-by":"publisher","first-page":"238","DOI":"10.1016\/j.jpdc.2019.12.004","volume":"137","author":"P Stpiczy\u0144ski","year":"2020","unstructured":"Stpiczy\u0144ski, P.: Algorithmic and language-based optimization of Marsa-LFIB4 pseudorandom number generator using OpenMP, OpenACC and CUDA. J. Parallel Distribut. Comput. 137, 238\u2013245 (2020). https:\/\/doi.org\/10.1016\/j.jpdc.2019.12.004","journal-title":"J. Parallel Distribut. Comput."},{"key":"10_CR27","doi-asserted-by":"publisher","unstructured":"Stylianou, C., Weiland, M.: Exploiting dynamic sparse matrices for performance portable linear algebra operations. In: IEEE\/ACM International Workshop on Performance, Portability and Productivity in HPC, P3HPC@SC 2022, Dallas, TX, USA, 13\u201318 November 2022, pp. 47\u201357. IEEE (2022). https:\/\/doi.org\/10.1109\/P3HPC56579.2022.00010","DOI":"10.1109\/P3HPC56579.2022.00010"},{"key":"10_CR28","doi-asserted-by":"publisher","unstructured":"Vuduc, R.W., Moon, H.J.: Fast sparse matrix-vector multiplication by exploiting variable block structure. In: High Performance Computing and Communications, First International Conference, HPCC 2005, Sorrento, Italy, September 21-23, 2005, Proceedings. LNCS, vol.\u00a03726, pp. 807\u2013816. Springer (2005). https:\/\/doi.org\/10.1007\/11557654_91","DOI":"10.1007\/11557654_91"},{"issue":"3","key":"10_CR29","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1016\/j.parco.2008.12.006","volume":"35","author":"S Williams","year":"2009","unstructured":"Williams, S., Oliker, L., Vuduc, R.W., Shalf, J., Yelick, K.A., Demmel, J.: Optimization of sparse matrix-vector multiplication on emerging multicore platforms. Parallel Comput. 35(3), 178\u2013194 (2009). https:\/\/doi.org\/10.1016\/j.parco.2008.12.006","journal-title":"Parallel Comput."}],"container-title":["Lecture Notes in Computer Science","Parallel Processing and Applied Mathematics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-85700-3_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T04:57:44Z","timestamp":1743569864000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-85700-3_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031856990","9783031857003"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-85700-3_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"1 April 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PPAM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Parallel Processing and Applied Mathematics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ostrava","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ppam2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ppam.edu.pl\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}