{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T03:22:47Z","timestamp":1787368967033,"version":"build-2736575974"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032024350","type":"print"},{"value":"9783032024367","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-02436-7_1","type":"book-chapter","created":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T06:50:16Z","timestamp":1761893416000},"page":"1-19","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SEER: An On-node Performance-Portable C++ Library for\u00a0Heterogeneous Systems"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1479-4310","authenticated-orcid":false,"given":"Pedro","family":"Valero-Lara","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2449-6720","authenticated-orcid":false,"given":"Jeffrey S.","family":"Vetter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,1]]},"reference":[{"key":"1_CR1","doi-asserted-by":"publisher","unstructured":"Beckingsale, D., Hornung, R.D., Scogland, T., Vargas, A.: Performance portable C++ programming with RAJA. In: Hollingsworth, J.K., Keidar, I. (eds.) Proceedings of the 24th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPoPP 2019, Washington, DC, USA, 16\u201320 February 2019, pp. 455\u2013456. ACM (2019). https:\/\/doi.org\/10.1145\/3293883.3302577","DOI":"10.1145\/3293883.3302577"},{"key":"1_CR2","doi-asserted-by":"publisher","unstructured":"Bosch, J., et al.: Application acceleration on fpgas with ompss@fpga. In: International Conference on Field-Programmable Technology, FPT 2018, Naha, Okinawa, Japan, 10\u201314 December 2018, pp. 70\u201377. IEEE (2018). https:\/\/doi.org\/10.1109\/FPT.2018.00021","DOI":"10.1109\/FPT.2018.00021"},{"key":"1_CR3","doi-asserted-by":"publisher","unstructured":"Catal\u00e1n, S., Martorell, X., Labarta, J., Usui, T., D\u00edaz, L.A.T., Valero-Lara, P.: Accelerating conjugate gradient using ompss. In: 20th International Conference on Parallel and Distributed Computing, Applications and Technologies, PDCAT 2019, Gold Coast, Australia, 5\u20137 December 2019, pp. 121\u2013126. IEEE (2019).https:\/\/doi.org\/10.1109\/PDCAT46702.2019.00033","DOI":"10.1109\/PDCAT46702.2019.00033"},{"key":"1_CR4","doi-asserted-by":"publisher","unstructured":"Chetlur, S., et al.: cudnn: Efficient primitives for deep learning (2014). https:\/\/doi.org\/10.48550\/ARXIV.1410.0759. https:\/\/arxiv.org\/abs\/1410.0759","DOI":"10.48550\/ARXIV.1410.0759"},{"key":"1_CR5","doi-asserted-by":"publisher","unstructured":"Dongarra, J.J., Hammarling, S., Higham, N.J., Relton, S.D., Valero-Lara, P., Zounon, M.: The design and performance of batched BLAS on modern high-performance computing systems. In: Koumoutsakos, P., Lees, M., Krzhizhanovskaya, V.V., Dongarra, J.J., Sloot, P.M.A. (eds.) International Conference on Computational Science, ICCS 2017, Zurich, Switzerland, 12\u201314 June 2017. Procedia Computer Science, vol.\u00a0108, pp. 495\u2013504. Elsevier (2017).https:\/\/doi.org\/10.1016\/j.procs.2017.05.138","DOI":"10.1016\/j.procs.2017.05.138"},{"key":"1_CR6","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1145\/356044.356047","volume":"9","author":"IS Duff","year":"1983","unstructured":"Duff, I.S., Reid, J.K.: The multifrontal solution of indefinite sparse symmetric linear. ACM Trans. Math. Softw. 9, 302\u2013325 (1983)","journal-title":"ACM Trans. Math. Softw."},{"issue":"12","key":"1_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."},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Greenbaum, A.: Iterative Methods for Solving Linear Systems. Society for Industrial and Applied Mathematics (1997)","DOI":"10.1137\/1.9781611970937"},{"issue":"3\u20134","key":"1_CR9","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1016\/j.ocemod.2003.10.002","volume":"7","author":"GR Halliwell","year":"2004","unstructured":"Halliwell, G.R.: Evaluation of vertical coordinate and vertical mixing algorithms in the hybrid-coordinate ocean model (hycom). Ocean Model. 7(3\u20134), 285\u2013322 (2004)","journal-title":"Ocean Model."},{"key":"1_CR10","doi-asserted-by":"publisher","unstructured":"Huang, T., Lin, Y., Lin, C., Guo, G., Wong, M.D.F.: Cpp-taskflow: a general-purpose parallel task programming system at scale. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 40(8), 1687\u20131700 (2021).https:\/\/doi.org\/10.1109\/TCAD.2020.3025075","DOI":"10.1109\/TCAD.2020.3025075"},{"key":"1_CR11","doi-asserted-by":"publisher","unstructured":"Khuvis, S., Tomko, K., Hashmi, J.M., Panda, D.K.: Exploring hybrid mpi+kokkos tasks programming model. In: 3rd IEEE\/ACM Annual Parallel Applications Workshop: Alternatives To MPI+X, PAW-ATM@SC 2020, Atlanta, GA, USA, 12 November 2020, pp. 66\u201373. IEEE (2020). https:\/\/doi.org\/10.1109\/PAWATM51920.2020.00011","DOI":"10.1109\/PAWATM51920.2020.00011"},{"key":"1_CR12","doi-asserted-by":"publisher","unstructured":"Korakitis, O., Gonzalo, S.G.D., Guidotti, N., Barreto, J.P., Monteiro, J.C., Pe\u00f1a, A.J.: Towards ompss-2 and openacc interoperation. In: Lee, J., Agrawal, K., Spear, M.F. (eds.) PPoPP \u201922: 27th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, Seoul, Republic of Korea, 2\u20136 April 2022, pp. 433\u2013434. ACM (2022). https:\/\/doi.org\/10.1145\/3503221.3508401","DOI":"10.1145\/3503221.3508401"},{"key":"1_CR13","unstructured":"Kraus, J.: Multi gpu programming with mpi and openacc (2015). https:\/\/on-demand.gputechconf.com\/gtc\/2015\/presentation\/S5711-Jiri-Kraus.pdf, GPU Technology Conference (GTC)"},{"key":"1_CR14","doi-asserted-by":"publisher","unstructured":"Matsumura, K., de\u00a0Gonzalo, S.G., Pe\u00f1a, A.J.: JACC: an openacc runtime framework with kernel-level and multi-gpu parallelization. In: 28th IEEE International Conference on High Performance Computing, Data, and Analytics, HiPC 2021, Bengaluru, India, 17\u201320 December 2021, pp. 182\u2013191. IEEE (2021). https:\/\/doi.org\/10.1109\/HiPC53243.2021.00032","DOI":"10.1109\/HiPC53243.2021.00032"},{"key":"1_CR15","doi-asserted-by":"publisher","unstructured":"Miniskar, N.R., Monil, M.A.H., Valero-Lara, P., Liu, F.Y., Vetter, J.S.: IRIS-BLAS: towards a performance portable and heterogeneous BLAS library. In: 29th IEEE International Conference on High Performance Computing, Data, and Analytics, HiPC 2022, Bengaluru, India, 18\u201321 December 2022, pp. 256\u2013261. IEEE (2022). https:\/\/doi.org\/10.1109\/HiPC56025.2022.00042","DOI":"10.1109\/HiPC56025.2022.00042"},{"key":"1_CR16","doi-asserted-by":"publisher","unstructured":"Monil, M.A.H., Miniskar, N.R., Liu, F.Y., Vetter, J.S., Valero-Lara, P.: Laris: targeting portability and productivity for LAPACK codes on extreme heterogeneous systems by using IRIS. In: IEEE\/ACM Redefining Scalability for Diversely Heterogeneous Architectures Workshop, RSDHA@SC 2022, Dallas, TX, USA, 13\u201318 November 2022, pp. 12\u201321. IEEE (2022). https:\/\/doi.org\/10.1109\/RSDHA56811.2022.00007","DOI":"10.1109\/RSDHA56811.2022.00007"},{"key":"1_CR17","first-page":"1","volume":"8","author":"EE Papalexakis","year":"2016","unstructured":"Papalexakis, E.E., Faloutsos, C., Sidiropoulos, N.: Tensors for data mining and data fusion. ACM Trans. Intell. Syst. Technol. (TIST) 8, 1\u201344 (2016)","journal-title":"ACM Trans. Intell. Syst. Technol. (TIST)"},{"issue":"8","key":"1_CR18","doi-asserted-by":"publisher","first-page":"1247","DOI":"10.1109\/JPROC.2008.925411","volume":"96","author":"JR Powell","year":"2008","unstructured":"Powell, J.R.: The quantum limit to Moore\u2019s law. Proc. IEEE 96(8), 1247\u20131248 (2008). https:\/\/doi.org\/10.1109\/JPROC.2008.925411","journal-title":"Proc. IEEE"},{"key":"1_CR19","doi-asserted-by":"publisher","unstructured":"Reyes, R., Brown, G., Burns, R., Wong, M.: SYCL 2020: more than meets the eye. In: McIntosh-Smith, S. (ed.) IWOCL \u201920: International Workshop on OpenCL, Virtual Event\/Munich, Germany, 27\u201329 April 2020, p.\u00a04:1. ACM (2020). https:\/\/doi.org\/10.1145\/3388333.3388649","DOI":"10.1145\/3388333.3388649"},{"key":"1_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1007\/978-3-030-49943-3_7","volume-title":"Accelerator Programming Using Directives","author":"D Sahasrabudhe","year":"2020","unstructured":"Sahasrabudhe, D., Phipps, E.T., Rajamanickam, S., Berzins, M.: A portable SIMD primitive using kokkos for heterogeneous architectures. In: Wienke, S., Bhalachandra, S. (eds.) WACCPD 2019. LNCS, vol. 12017, pp. 140\u2013163. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-49943-3_7"},{"key":"1_CR21","unstructured":"Shewchuk, J.R.: An introduction to the conjugate gradient method without the agonizing pain. Technical report, USA (1994)"},{"key":"1_CR22","doi-asserted-by":"publisher","unstructured":"Toledo, L., Valero-Lara, P., Vetter, J.S., Pe\u00f1a, A.J.: Static graphs for coding productivity in openacc. In: 28th IEEE International Conference on High Performance Computing, Data, and Analytics, HiPC 2021, Bengaluru, India, 17\u201320 December 2021, pp. 364\u2013369. IEEE (2021). https:\/\/doi.org\/10.1109\/HiPC53243.2021.00050","DOI":"10.1109\/HiPC53243.2021.00050"},{"key":"1_CR23","doi-asserted-by":"publisher","unstructured":"Trott, C., et al.: The kokkos ecosystem: comprehensive performance portability for high performance computing. Comput. Sci. Eng. 23(5), 10\u201318 (2021). https:\/\/doi.org\/10.1109\/MCSE.2021.3098509","DOI":"10.1109\/MCSE.2021.3098509"},{"key":"1_CR24","doi-asserted-by":"publisher","first-page":"23365","DOI":"10.1109\/ACCESS.2019.2900122","volume":"7","author":"P Valero-Lara","year":"2019","unstructured":"Valero-Lara, P., Andrade, D., Sirvent, R., Labarta, J., Fraguela, B.B., Doallo, R.: A fast solver for large tridiagonal systems on multi-core processors (lass library). IEEE Access 7, 23365\u201323378 (2019). https:\/\/doi.org\/10.1109\/ACCESS.2019.2900122","journal-title":"IEEE Access"},{"key":"1_CR25","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1016\/j.jocs.2015.07.002","volume":"10","author":"P Valero-Lara","year":"2015","unstructured":"Valero-Lara, P., Igual, F.D., Prieto-Mat\u00edas, M., Pinelli, A., Favier, J.: Accelerating fluid-solid simulations (lattice-boltzmann & immersed-boundary) on heterogeneous architectures. J. Comput. Sci. 10, 249\u2013261 (2015). https:\/\/doi.org\/10.1016\/j.jocs.2015.07.002","journal-title":"J. Comput. Sci."},{"key":"1_CR26","doi-asserted-by":"publisher","unstructured":"Valero-Lara, P., Jansson, J.: Heterogeneous CPU+GPU approaches for mesh refinement over lattice-boltzmann simulations. Concurr. Comput. Pract. Exp. 29(7) (2017). https:\/\/doi.org\/10.1002\/cpe.3919","DOI":"10.1002\/cpe.3919"},{"key":"1_CR27","doi-asserted-by":"publisher","unstructured":"Valero-Lara, P., Kim, J., Hernandez, O., Vetter, J.S.: Openmp target task: tasking and target offloading on heterogeneous systems. In: Chaves, R., et al. (eds.) Euro-Par 2021: Parallel Processing Workshops - Euro-Par 2021 International Workshops, Lisbon, Portugal, 30\u201331 August 2021, Revised Selected Papers. Lecture Notes in Computer Science, vol. 13098, pp. 445\u2013455. Springer, Heidelberg (2021). https:\/\/doi.org\/10.1007\/978-3-031-06156-1_35","DOI":"10.1007\/978-3-031-06156-1_35"},{"key":"1_CR28","doi-asserted-by":"publisher","unstructured":"Valero-Lara, P., Kim, J., Vetter, J.S.: A portable and heterogeneous LU factorization on IRIS. In: Singer, J., Elkhatib, Y., Heras, D.B., Diehl, P., Brown, N., Ilic, A. (eds.) Euro-Par 2022: Parallel Processing Workshops - Euro-Par 2022 International Workshops, Glasgow, UK, 22\u201326 August 2022, Revised Selected Papers. Lecture Notes in Computer Science, vol. 13835, pp. 17\u201331. Springer, Heidleberg (2022). https:\/\/doi.org\/10.1007\/978-3-031-31209-0_2","DOI":"10.1007\/978-3-031-31209-0_2"},{"key":"1_CR29","doi-asserted-by":"publisher","unstructured":"Valero-Lara, P., Lee, S., Tallada, M.G., Denny, J.E., Vetter, J.S.: Kokkacc: enhancing kokkos with openacc. In: 9th Workshop on Accelerator Programming Using Directives, WACCPD@SC 2022, Dallas, TX, USA, 13\u201318 November 2022, pp. 32\u201342. IEEE (2022).https:\/\/doi.org\/10.1109\/WACCPD56842.2022.00009","DOI":"10.1109\/WACCPD56842.2022.00009"},{"key":"1_CR30","doi-asserted-by":"publisher","unstructured":"Valero-Lara, P., et al.: Variable batched DGEMM. In: Merelli, I., Li\u00f2, P., Kotenko, I.V. (eds.) 26th Euromicro International Conference on Parallel, Distributed and Network-based Processing, PDP 2018, Cambridge, United Kingdom, 21\u201323 March 2018, pp. 363\u2013367. IEEE Computer Society (2018). https:\/\/doi.org\/10.1109\/PDP2018.2018.00065","DOI":"10.1109\/PDP2018.2018.00065"},{"key":"1_CR31","doi-asserted-by":"publisher","unstructured":"Valero-Lara, P., Mart\u00ednez-P\u00e9rez, I., Pe\u00f1a, A.J., Martorell, X., Sirvent, R., Labarta, J.: cuhinesbatch: solving multiple hines systems on gpus human brain project$$ ^{\\text{*}}$$. In: Koumoutsakos, P., Lees, M., Krzhizhanovskaya, V.V., Dongarra, J.J., Sloot, P.M.A. (eds.) International Conference on Computational Science, ICCS 2017, Zurich, Switzerland, 12\u201314 June 2017. Procedia Computer Science, vol.\u00a0108, pp. 566\u2013575. Elsevier (2017). https:\/\/doi.org\/10.1016\/j.procs.2017.05.145","DOI":"10.1016\/j.procs.2017.05.145"},{"key":"1_CR32","doi-asserted-by":"crossref","unstructured":"Valero-Lara, P., Mart\u00ednez-P\u00e9rez, I., Sirvent, R., Martorell, X., Pe\u00f1a, A.J.: cuthomasbatch and cuthomasvbatch, CUDA routines to compute batch of tridiagonal systems on NVIDIA gpus. Concurr. Comput. Pract. Exp. 30(24) (2018)","DOI":"10.1002\/cpe.4909"},{"key":"1_CR33","doi-asserted-by":"crossref","unstructured":"Valero-Lara, P., Pinelli, A., Favier, J., Matias, M.P.: Block tridiagonal solvers on heterogeneous architectures. In: IEEE 10th International Symposium on Parallel and Distributed Processing with Applications, ISPA \u201912, pp. 609\u2013616 (2012)","DOI":"10.1109\/ISPA.2012.91"},{"issue":"4","key":"1_CR34","doi-asserted-by":"publisher","first-page":"1265","DOI":"10.1016\/j.cpc.2013.12.026","volume":"185","author":"P Valero-Lara","year":"2014","unstructured":"Valero-Lara, P., Pinelli, A., Prieto-Mat\u00edas, M.: Fast finite difference poisson solvers on heterogeneous architectures. Comput. Phys. Commun. 185(4), 1265\u20131272 (2014). https:\/\/doi.org\/10.1016\/j.cpc.2013.12.026","journal-title":"Comput. Phys. Commun."},{"key":"1_CR35","doi-asserted-by":"publisher","unstructured":"Wolf, M.M., Edwards, H.C., Olivier, S.L.: Kokkos\/qthreads task-parallel approach to linear algebra based graph analytics. In: 2016 IEEE High Performance Extreme Computing Conference, HPEC 2016, Waltham, MA, USA, 13\u201315 September 2016, pp.\u00a01\u20137. IEEE (2016).https:\/\/doi.org\/10.1109\/HPEC.2016.7761649","DOI":"10.1109\/HPEC.2016.7761649"}],"container-title":["Lecture Notes in Computer Science","Languages and Compilers for Parallel Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-02436-7_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T02:22:48Z","timestamp":1787365368000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-02436-7_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,1]]},"ISBN":["9783032024350","9783032024367"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-02436-7_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,1]]},"assertion":[{"value":"1 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"LCPC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Languages and Compilers for Parallel Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lexington, KY","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"36","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"lcpc2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.lcpcworkshop.org\/LCPC23\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}