{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T18:44:16Z","timestamp":1777574656857,"version":"3.51.4"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032076113","type":"print"},{"value":"9783032076120","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T00:00:00Z","timestamp":1763942400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T00:00:00Z","timestamp":1763942400000},"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\/978-3-032-07612-0_45","type":"book-chapter","created":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T17:57:40Z","timestamp":1763920660000},"page":"586-597","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Parallel FFTW on\u00a0RISC-V: A Comparative Study Including OpenMP, MPI, and\u00a0HPX"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9939-9044","authenticated-orcid":false,"given":"Alexander","family":"Strack","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7119-818X","authenticated-orcid":false,"given":"Christopher","family":"Taylor","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4360-0212","authenticated-orcid":false,"given":"Dirk","family":"Pfl\u00fcger","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,24]]},"reference":[{"key":"45_CR1","unstructured":"Ayala, A., et al.: FFT benchmark performance experiments on systems targeting exascale. Technical report, University of Tennessee (2022)"},{"key":"45_CR2","doi-asserted-by":"crossref","unstructured":"Brown, N., Jamieson, M., Lee, J., Wang, P.: Is RISC-V ready for HPC prime-time: evaluating the 64-core Sophon SG2042 RISC-V CPU. In: SC-W 2023, pp. 1566\u20131574. SC-W 2023. ACM (2023)","DOI":"10.1145\/3624062.3624234"},{"key":"45_CR3","unstructured":"Cai, J.: Performance evaluation of numerical libraries on RISC-V architectures with SIMD extensions. Master\u2019s thesis, Universidad Complutense de Madrid, Madrid (2024)"},{"issue":"90","key":"45_CR4","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1090\/S0025-5718-1965-0178586-1","volume":"19","author":"J Cooley","year":"1965","unstructured":"Cooley, J., Tukey, J.: An algorithm for the machine calculation of complex Fourier series. Math. Comput. 19(90), 297\u2013301 (1965)","journal-title":"Math. Comput."},{"issue":"1","key":"45_CR5","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1109\/99.660313","volume":"5","author":"L Dagum","year":"1998","unstructured":"Dagum, L., Menon, R.: OpenMP: an industry standard API for shared-memory programming. IEEE Comput. Sci. Eng. 5(1), 46\u201355 (1998)","journal-title":"IEEE Comput. Sci. Eng."},{"key":"45_CR6","doi-asserted-by":"crossref","unstructured":"Deserno, M., Holm, C.: How to mesh up Ewald sums. I. A theoretical and numerical comparison of various particle mesh routines. J. Chem. Phys. 109(18), 7678\u20137693 (1998)","DOI":"10.1063\/1.477414"},{"key":"45_CR7","doi-asserted-by":"crossref","unstructured":"Diehl, P., et\u00a0al.: Evaluating HPX and Kokkos on RISC-V using an astrophysics application octo-tiger. In: SC-W 2023, pp. 1533\u20131542. Association for Computing Machinery, New York (2023)","DOI":"10.1145\/3624062.3624230"},{"key":"45_CR8","doi-asserted-by":"crossref","unstructured":"Diehl, P., et\u00a0al.: Preparing for HPC on RISC-V: examining vectorization and distributed performance of an astrophysics application with HPX and Kokkos. In: SC-W 2024, pp. 1656\u20131665. IEEE (2024)","DOI":"10.1109\/SCW63240.2024.00207"},{"issue":"2","key":"45_CR9","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1109\/JPROC.2004.840301","volume":"93","author":"M Frigo","year":"2005","unstructured":"Frigo, M., Johnson, S.: The design and implementation of FFTW3. Proc. IEEE 93(2), 216\u2013231 (2005)","journal-title":"Proc. IEEE"},{"key":"45_CR10","unstructured":"Gabriel, E., et al.: Open MPI: goals, concept, and design of a next generation MPI implementation. In: Proceedings of the 11th European PVM\/MPI Users\u2019 Group Meeting, Budapest, Hungary, pp. 97\u2013104 (2004)"},{"key":"45_CR11","unstructured":"Gholami, A., et al.: Accfft: a library for distributed-memory FFT on CPU and GPU architectures. CoRR (2015)"},{"key":"45_CR12","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7055.001.0001","volume-title":"Using MPI: Portable Parallel Programming with the Message Passing Interface","author":"W Gropp","year":"1999","unstructured":"Gropp, W., Lusk, E., Skjellum, A.: Using MPI: Portable Parallel Programming with the Message Passing Interface, 2nd edn. MIT Press, Cambridge (1999)","edition":"2"},{"key":"45_CR13","unstructured":"Hornung, R.D., Jones, H.E.: RAJA performance suite. Technical report, Lawrence Livermore National Laboratory (LLNL), Livermore, CA, United States (2017)"},{"issue":"53","key":"45_CR14","doi-asserted-by":"publisher","first-page":"2352","DOI":"10.21105\/joss.02352","volume":"5","author":"H Kaiser","year":"2020","unstructured":"Kaiser, H., et al.: HPX - the C++ standard library for parallelism and concurrency. J. Open Source Softw. 5(53), 2352 (2020)","journal-title":"J. Open Source Softw."},{"key":"45_CR15","doi-asserted-by":"crossref","unstructured":"Li, Z., et\u00a0al.: Generating fast FFT kernels on CPUS via FFT-specific intrinsics. In: PPoPP 2023, p. 427\u2013428. Association for Computing Machinery, New York (2023)","DOI":"10.1145\/3572848.3577477"},{"key":"45_CR16","doi-asserted-by":"crossref","unstructured":"Marcello, D.C., et\u00a0al.: Octo-tiger: a new, 3D hydrodynamic code for stellar mergers that uses HPX parallelization. Mon. Notices Royal Astron. Soc. 504(4), 5345\u20135382 (2021)","DOI":"10.1093\/mnras\/stab937"},{"key":"45_CR17","unstructured":"Message Passing Interface Forum: MPI: A Message-Passing Interface Standard Version 3.0 (2021)"},{"issue":"4","key":"45_CR18","doi-asserted-by":"publisher","first-page":"C192","DOI":"10.1137\/11082748X","volume":"34","author":"D Pekurovsky","year":"2012","unstructured":"Pekurovsky, D.: P3dfft: a framework for parallel computations of Fourier transforms in three dimensions. SISC 34(4), C192\u2013C209 (2012)","journal-title":"SISC"},{"key":"45_CR19","doi-asserted-by":"crossref","unstructured":"Strack, A., Pfl\u00fcger, D.: A HPX communication benchmark: distributed FFT using collectives. In: Euro-Par 2024: Parallel Processing Workshops. LNCS. Springer, Cham (2025)","DOI":"10.1007\/978-3-031-90203-1_25"},{"key":"45_CR20","doi-asserted-by":"crossref","unstructured":"Strack, A., Taylor, C., Diehl, P., Pfl\u00fcger, D.: Experiences Porting Shared and Distributed Applications to Asynchronous Tasks: A Multidimensional FFT Case-Study, pp. 111\u2013122. Springer, Cham (2024)","DOI":"10.1007\/978-3-031-61763-8_11"},{"key":"45_CR21","doi-asserted-by":"crossref","unstructured":"Vizcaino, P., et\u00a0al.: Acceleration with long vector architectures: Implementation and evaluation of the FFT kernel on NEC SX-aurora and RISC-V vector extension. Concurr. Comput. Pract. Exp. 35 (2022)","DOI":"10.1002\/cpe.7424"},{"key":"45_CR22","doi-asserted-by":"crossref","unstructured":"Waterman, A., et\u00a0al.: The RISC-V Instruction Set Manual, Volume I: User-Level ISA. Technical report\u00a02, University of California, Berkeley (2014)","DOI":"10.21236\/ADA605735"},{"key":"45_CR23","doi-asserted-by":"crossref","unstructured":"Yan, J., Kaiser, H., Snir, M.: Design and analysis of the network software stack of an asynchronous many-task system \u2013 the LCI parcelport of HPX. In: Proceedings of the SC 2023 Workshops, pp. 1151\u20131161. ACM, New York (2023)","DOI":"10.1145\/3624062.3624598"},{"key":"45_CR24","doi-asserted-by":"crossref","unstructured":"Zhao, X., Zhang, X., Zhang, Y.: Optimization of the FFT algorithm on RISC-V CPUs. In: ISC HP 2023 Workshops, pp. 515\u2013525. Springer, Heidelberg (2023)","DOI":"10.1007\/978-3-031-40843-4_38"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-07612-0_45","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T17:57:42Z","timestamp":1763920662000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-07612-0_45"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,24]]},"ISBN":["9783032076113","9783032076120"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-07612-0_45","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,24]]},"assertion":[{"value":"24 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISC High Performance","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on High Performance Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hamburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"40","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"supercomputing2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}