{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T07:29:52Z","timestamp":1774942192118,"version":"3.50.1"},"publisher-location":"Cham","reference-count":16,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319460789","type":"print"},{"value":"9783319460796","type":"electronic"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-46079-6_34","type":"book-chapter","created":{"date-parts":[[2016,10,5]],"date-time":"2016-10-05T12:01:40Z","timestamp":1475668900000},"page":"489-507","source":"Crossref","is-referenced-by-count":41,"title":["GPU-STREAM v2.0: Benchmarking the Achievable Memory Bandwidth of Many-Core Processors Across Diverse Parallel Programming Models"],"prefix":"10.1007","author":[{"given":"Tom","family":"Deakin","sequence":"first","affiliation":[]},{"given":"James","family":"Price","sequence":"additional","affiliation":[]},{"given":"Matt","family":"Martineau","sequence":"additional","affiliation":[]},{"given":"Simon","family":"McIntosh-Smith","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,10,6]]},"reference":[{"key":"34_CR1","unstructured":"Bhat, K.: clpeak (2015). https:\/\/github.com\/krrishnarraj\/clpeak"},{"key":"34_CR2","unstructured":"Codeplay: ComputeCpp. https:\/\/www.codeplay.com\/products\/computecpp"},{"key":"34_CR3","doi-asserted-by":"crossref","unstructured":"Danalis, A., Marin, G., McCurdy, C., Meredith, J.S., Roth, P.C., Spafford, K., Tipparaju, V., Vetter, J.S.: The scalable heterogeneous computing (SHOC) benchmark suite. In: Proceedings of the 3rd Workshop on General-Purpose Computation on Graphics Processing Units, GPGPU-3, pp. 63\u201374. ACM, New York (2010). http:\/\/doi.acm.org\/10.1145\/1735688.1735702","DOI":"10.1145\/1735688.1735702"},{"key":"34_CR4","unstructured":"Deakin, T., McIntosh-Smith, S.: GPU-STREAM: benchmarking the achievable memory bandwidth of graphics processing units (poster). In: Supercomputing, Austin, Texas (2015)"},{"key":"34_CR5","doi-asserted-by":"crossref","unstructured":"Edwards, H.C., Sunderland, D.: Kokkos array performance-portable manycore programming model. In: Proceedings of the 2012 International Workshop on Programming Models and Applications for Multicores and Manycores (PMAM 2012), pp. 1\u201310. ACM (2012)","DOI":"10.1145\/2141702.2141703"},{"key":"34_CR6","unstructured":"Heroux, M., Doerfler, D., et al.: Improving performance via mini-applications. Technical report, SAND2009-5574, Sandia National Laboratories (2009)"},{"key":"34_CR7","doi-asserted-by":"crossref","unstructured":"Hornung, R.D., Keasler, J.A.: The RAJA Portability Layer: Overview and Status (2014)","DOI":"10.2172\/1169830"},{"key":"34_CR8","unstructured":"Khronos OpenCL Working Group SYCL subgroup: SYCL Provisional Specification (2016)"},{"key":"34_CR9","doi-asserted-by":"crossref","unstructured":"Martineau, M., McIntosh-Smith, S., Boulton, M., Gaudin, W.: An evaluation of emerging many-core parallel programming models. In: Proceedings of the 7th International Workshop on Programming Models and Applications for Multicores and Manycore, PMAM 2016, pp. 1\u201310. ACM, New York (2016). http:\/\/doi.acm.org\/10.1145\/2883404.2883420","DOI":"10.1145\/2883404.2883420"},{"key":"34_CR10","unstructured":"McCalpin, J.D.: Memory bandwidth and machine balance in current high performance computers. IEEE Comput. Soc. Tech. Comm. Comput. Archit. (TCCA) Newslett. 19\u201325 (1995)"},{"key":"34_CR11","unstructured":"Munshi, A.: The OpenCL Specification, Version 1.1 (2011)"},{"key":"34_CR12","unstructured":"NVIDIA: CUDA Toolkit 7.5"},{"key":"34_CR13","unstructured":"OpenACC-Standard.org: The OpenACC Application Programming Interface - Version 2.5 (2015)"},{"key":"34_CR14","unstructured":"OpenMP Architecture Review Board: OpenMP Application Program Interface, Version 4.5 (2015)"},{"key":"34_CR15","unstructured":"Reguly, I.Z., Keita, A.K., Giles, M.B.: Benchmarking the IBM Power8 processor. In: Proceedings of the 25th Annual International Conference on Computer Science and Software Engineering, pp. 61\u201369. IBM Corporation, Riverton (2015)"},{"key":"34_CR16","unstructured":"Standard Performance Evaluation Corporation: SPEC Accel (2016). https:\/\/www.spec.org\/accel\/"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-46079-6_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,14]],"date-time":"2019-09-14T04:52:00Z","timestamp":1568436720000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-46079-6_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319460789","9783319460796"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-46079-6_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016]]}}}