{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T02:38:12Z","timestamp":1762051092654,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030977580"},{"type":"electronic","value":"9783030977597"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-030-97759-7_2","type":"book-chapter","created":{"date-parts":[[2022,5,14]],"date-time":"2022-05-14T11:04:01Z","timestamp":1652526241000},"page":"22-45","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Achieving Near-Native Runtime Performance and\u00a0Cross-Platform Performance Portability for\u00a0Random Number Generation Through SYCL Interoperability"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3167-8773","authenticated-orcid":false,"given":"Vincent R.","family":"Pascuzzi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2774-0821","authenticated-orcid":false,"given":"Mehdi","family":"Goli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,5,15]]},"reference":[{"key":"2_CR1","unstructured":"AMD hipBLAS: Dense Linear Algebra on AMD GPUs. https:\/\/github.com\/ROCmSoftwarePlatform\/hipBLAS. Accessed 05 Apr 2021"},{"key":"2_CR2","unstructured":"AMD hipRAND: Random Number Generation on AMD GPUs. https:\/\/github.com\/ROCmSoftwarePlatform\/rocRAND. Accessed 05 Apr 2021"},{"key":"2_CR3","unstructured":"ComputeCpp: Codeplay\u2019s implementation of the SYCL open standard. https:\/\/developer.codeplay.com\/products\/computecpp\/ce\/home. Accessed 28 Feb 2021"},{"key":"2_CR4","unstructured":"hipSYCL RPMs. http:\/\/repo.urz.uni-heidelberg.de\/sycl\/test-plugin\/rpm\/centos7\/. Accessed 13 Mar 2021"},{"key":"2_CR5","unstructured":"Intel Math Kernel Library. https:\/\/intel.ly\/32eX1eu. Accessed 31 Aug 2020"},{"key":"2_CR6","unstructured":"Intel oneAPI DPC++\/C++ Compiler. https:\/\/github.com\/intel\/llvm\/tree\/sycl. Accessed 28 Feb 2021"},{"key":"2_CR7","unstructured":"Intel oneAPI Math Kernel Library (oneMKL). https:\/\/docs.oneapi.com\/versions\/latest\/onemkl\/index.html. Accessed 28 Feb 2021"},{"key":"2_CR8","unstructured":"NVIDIA cuBLAS: Dense Linear Algebra on GPUs. https:\/\/developer.nvidia.com\/cublas. Accessed 31 Aug 2020"},{"key":"2_CR9","unstructured":"NVIDIA CUDA programming model. http:\/\/www.nvidia.com\/CUDA. Accessed 05 Apr 2021"},{"key":"2_CR10","unstructured":"NVIDIA cuRAND: Random Number Generation on NVIDIA GPUs. https:\/\/developer.nvidia.com\/curand. Accessed 28 Feb 2021"},{"key":"2_CR11","unstructured":"NVIDIA cuSPARSE: the CUDA sparse matrix library. https:\/\/docs.nvidia.com\/cuda\/cusparse\/index.html. Accessed 05 Apr 2021"},{"key":"2_CR12","unstructured":"SYCL: C++ Single-source Heterogeneous Programming for OpenCL. https:\/\/www.khronos.org\/registry\/SYCL\/specs\/sycl-2020-provisional.pdf. Accessed 23 July 2020"},{"key":"2_CR13","unstructured":"The ARM Computer Vision and Machine Learning library. https:\/\/github.com\/ARM-software\/ComputeLibrary\/. Accessed 31 Aug 2020"},{"key":"2_CR14","doi-asserted-by":"publisher","unstructured":"Aad, G., et al.: The ATLAS Experiment at the CERN Large Hadron Collider, vol. 3, p. S08003, 437 (2008). https:\/\/doi.org\/10.1088\/1748-0221\/3\/08\/S08003, https:\/\/cds.cern.ch\/record\/1129811, also published by CERN Geneva in 2010","DOI":"10.1088\/1748-0221\/3\/08\/S08003"},{"key":"2_CR15","doi-asserted-by":"publisher","unstructured":"Agostinelli, S., et al.: GEANT4-a simulation toolkit, vol. 506, pp. 250\u2013303 (2003). https:\/\/doi.org\/10.1016\/S0168-9002(03)01368-8","DOI":"10.1016\/S0168-9002(03)01368-8"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Alpay, A., Heuveline, V.: SYCL beyond OpenCL: the architecture, current state and future direction of hipSYCL. In: Proceedings of the International Workshop on OpenCL, p. 1 (2020)","DOI":"10.1145\/3388333.3388658"},{"issue":"5","key":"2_CR17","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/j.physrep.2011.03.005","volume":"504","author":"A Buckley","year":"2011","unstructured":"Buckley, A., et al.: General-purpose event generators for LHC physics. Phys. Rep. 504(5), 145\u2013233 (2011)","journal-title":"Phys. Rep."},{"key":"2_CR18","unstructured":"Costanzo, M., Rucci, E., Sanchez, C.G., Naiouf, M.: Early Experiences Migrating CUDA codes to oneAPI (2021)"},{"key":"2_CR19","doi-asserted-by":"publisher","unstructured":"Deakin, T., McIntosh-Smith, S.: Evaluating the performance of HPC-Style SYCL applications. In: Proceedings of the International Workshop on OpenCL, IWOCL 2020. Association for Computing Machinery, New York (2020). https:\/\/doi.org\/10.1145\/3388333.3388643","DOI":"10.1145\/3388333.3388643"},{"key":"2_CR20","doi-asserted-by":"publisher","first-page":"32","DOI":"10.3389\/fdata.2021.665783","volume":"4","author":"Z Dong","year":"2021","unstructured":"Dong, Z., Gray, H., Leggett, C., Lin, M., Pascuzzi, V.R., Yu, K.: Porting HEP parameterized calorimeter simulation code to GPUs. Front. Big Data 4, 32 (2021)","journal-title":"Front. Big Data"},{"key":"2_CR21","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, 3202\u20133216 (2014)","journal-title":"J. Parallel Distrib. Comput."},{"key":"2_CR22","unstructured":"Feickert, M., Nachman, B.: A Living Review of Machine Learning for Particle Physics (2021)"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Goli, M., et al.: Towards cross-platform performance portability of DNN models using SYCL. In: 2020 IEEE\/ACM International Workshop on Performance, Portability and Productivity in HPC (P3HPC), pp. 25\u201335. IEEE (2020)","DOI":"10.1109\/P3HPC51967.2020.00008"},{"key":"2_CR24","unstructured":"Gozillon, A., Keryell, R., Yu, L.Y., Harnisch, G., Keir, P.: triSYCL for Xilinx FPGA. In: The 2020 International Conference on High Performance Computing and Simulation. IEEE (2020)"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Hornung, R.D., Keasler, J.A.: The RAJA portability layer: overview and status. Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States) (2014)","DOI":"10.2172\/1169830"},{"key":"2_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s41781-019-0034-3","volume":"4","author":"F James","year":"2020","unstructured":"James, F., Moneta, L.: Review of high-quality random number generators. Comput. Softw. Big Comput. 4, 1\u201312 (2020). https:\/\/doi.org\/10.1007\/s41781-019-0034-3","journal-title":"Comput. Softw. Big Comput."},{"key":"2_CR27","unstructured":"Larkin, J.: Performance portability through descriptive parallelism. In: Presentation at DOE Centers of Excellence Performance Portability Meeting (2016)"},{"key":"2_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1007\/978-3-319-07518-1_4","volume-title":"Supercomputing","author":"S McIntosh-Smith","year":"2014","unstructured":"McIntosh-Smith, S., Boulton, M., Curran, D., Price, J.: On the performance portability of structured grid codes on many-core computer architectures. In: Kunkel, J.M., Ludwig, T., Meuer, H.W. (eds.) ISC 2014. LNCS, vol. 8488, pp. 53\u201375. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-07518-1_4"},{"key":"2_CR29","doi-asserted-by":"publisher","first-page":"947","DOI":"10.1016\/j.future.2017.08.007","volume":"92","author":"SJ Pennycook","year":"2019","unstructured":"Pennycook, S.J., Sewall, J.D., Lee, V.W.: Implications of a metric for performance portability. Future Gener. Comput. Syst. 92, 947\u2013958 (2019)","journal-title":"Future Gener. Comput. Syst."},{"issue":"4","key":"2_CR30","first-page":"298","volume":"23","author":"C Pheatt","year":"2008","unstructured":"Pheatt, C.: Intel threading building blocks. J. Comput. Sci. Coll. 23(4), 298 (2008)","journal-title":"J. Comput. Sci. Coll."},{"key":"2_CR31","doi-asserted-by":"publisher","first-page":"042006","DOI":"10.1088\/1742-6596\/898\/4\/042006","volume":"898","author":"J Schaarschmidt","year":"2017","unstructured":"Schaarschmidt, J.: The new ATLAS fast calorimeter simulation. J. Phys. Conf. Ser. 898, 042006 (2017). https:\/\/doi.org\/10.1088\/1742-6596\/898\/4\/042006","journal-title":"J. Phys. Conf. Ser."},{"key":"2_CR32","doi-asserted-by":"publisher","unstructured":"Stauber, T., Sommerlad, P.: ReSYCLator: transforming CUDA C++ source code into SYCL. In: Proceedings of the International Workshop on OpenCL, IWOCL 2019. Association for Computing Machinery, New York (2019). https:\/\/doi.org\/10.1145\/3318170.3318190","DOI":"10.1145\/3318170.3318190"},{"issue":"3","key":"2_CR33","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1109\/MCSE.2010.69","volume":"12","author":"JE Stone","year":"2010","unstructured":"Stone, J.E., Gohara, D., Shi, G.: OpenCL: a parallel programming standard for heterogeneous computing systems. Comput. Sci. Eng. 12(3), 66 (2010)","journal-title":"Comput. Sci. Eng."},{"issue":"2","key":"2_CR34","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1007\/s10586-007-0011-1","volume":"10","author":"W Zhu","year":"2007","unstructured":"Zhu, W., Niu, Y., Gao, G.R.: Performance portability on EARTH: a case study across several parallel architectures. Cluster Comput. 10(2), 115\u2013126 (2007)","journal-title":"Cluster Comput."}],"container-title":["Lecture Notes in Computer Science","Accelerator Programming Using Directives"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-97759-7_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,14]],"date-time":"2022-05-14T11:04:35Z","timestamp":1652526275000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-97759-7_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783030977580","9783030977597"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-97759-7_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"15 May 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"WACCPD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Accelerator Programming Using Directives","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 November 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 November 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"waccpd2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/waccpd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}