{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T04:23:56Z","timestamp":1751862236155,"version":"3.37.3"},"reference-count":24,"publisher":"Springer Science and Business Media LLC","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int J Parallel Prog"],"published-print":{"date-parts":[[2011,2]]},"DOI":"10.1007\/s10766-010-0144-3","type":"journal-article","created":{"date-parts":[[2010,6,25]],"date-time":"2010-06-25T12:03:02Z","timestamp":1277467382000},"page":"88-114","source":"Crossref","is-referenced-by-count":27,"title":["Correlating Radio Astronomy Signals with Many-Core Hardware"],"prefix":"10.1007","volume":"39","author":[{"given":"Rob V.","family":"van Nieuwpoort","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John W.","family":"Romein","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2010,6,26]]},"reference":[{"key":"144_CR1","unstructured":"Advanced Micro Devices Corporation (AMD): AMD Stream Computing User Guide, Revision 1.1 (2008)"},{"key":"144_CR2","doi-asserted-by":"crossref","unstructured":"Barker, K.J., Davis, K., Hoisie, A., Kerbyson, D.J., Lang, M., Pakin, S., Sancho, J.C.: Entering the petaflop era: the architecture and performance of Roadrunner. In Proceedings of the 2008 ACM\/IEEE conference on Supercomputing (SC\u201908), Austin, Texas. IEEE Press. ISBN:978-1-4244-2835-9 (2008)","DOI":"10.1109\/SC.2008.5217926"},{"key":"144_CR3","doi-asserted-by":"crossref","unstructured":"Buck, I., Foley, T., Horn, D., Sugerman, J., Fatahalian, K., Houston, M., Hanrahan, P.: Brook for GPUs: Stream computing on graphics hardware. In ACM transactions on graphics, Proceedings of SIGGRAPH 2004, pp. 777\u2013786, Los Angeles, California. ACM Press (2004)","DOI":"10.1145\/1186562.1015800"},{"key":"144_CR4","doi-asserted-by":"crossref","unstructured":"de Souza, L., Bunton, J.D., Campbell-Wilson, D., Cappallo, R.J. Kincaid, B.: A radio astronomy correlator optimized for the Xilinx Virtex-4 SX FPGA. In international conference on field programmable logic and applications (FPL\u201907), pp. 62\u201367, (2007)","DOI":"10.1109\/FPL.2007.4380626"},{"issue":"2","key":"144_CR5","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1109\/MM.2006.41","volume":"26","author":"M. Gschwind","year":"2006","unstructured":"Gschwind M., Hofstee H.P., Flachs B.K., Hopkins M., Watanabe Y., Yamazaki T.: Synergistic processing in cell\u2019s multicore architecture. IEEE Micro. 26(2), 10\u201324 (2006)","journal-title":"IEEE Micro."},{"issue":"1\u20132","key":"144_CR6","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1007\/s10686-008-9114-9","volume":"22","author":"C. Harris","year":"2008","unstructured":"Harris C., Haines K., Staveley-Smith L.: GPU accelerated radio astronomy signal convolution. Exp. Astron. 22(1\u20132), 129\u2013141 (2008)","journal-title":"Exp. Astron."},{"key":"144_CR7","doi-asserted-by":"crossref","unstructured":"IBMBlue Gene team: Overview of the IBM Blue Gene\/P project. IBM J. Res. Develop. 52(1\/2), 199\u2013220 (2008)","DOI":"10.1147\/rd.521.0199"},{"issue":"3","key":"144_CR8","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1007\/s10686-008-9124-7","volume":"22","author":"S. Johnston","year":"2008","unstructured":"Johnston S., Taylor R., Bailes M. et\u00a0al.: Science with ASKAP. The Australian square-kilometre-array pathfinder. Exp. Astron. 22(3), 151\u2013273 (2008)","journal-title":"Exp. Astron."},{"key":"144_CR9","doi-asserted-by":"crossref","unstructured":"Khronos OpenCL Working Group. The opencl specification. version 1.0. See http:\/\/www.khronos.org\/opencl\/ (2009)","DOI":"10.1109\/HOTCHIPS.2009.7478338"},{"key":"144_CR10","volume-title":"Quantitative System Performance, Computer System Analysis Using Queueing Network Models","author":"E.D. Lazowska","year":"1984","unstructured":"Lazowska E.D., Zahorjana J., Graham G.S., Sevcik K.C.: Quantitative System Performance, Computer System Analysis Using Queueing Network Models. Prentice-Hall, USA (1984)"},{"key":"144_CR11","unstructured":"Mattson, T.G., der Wijngaart, R.V., Frumkin, M.: Programming the Intel 80-core network-on-a-chip terascale processor. In Proceedings of the 2008 ACM\/IEEE conference on Supercomputing (SC\u201908), pages 1\u201311, Austin, Texas, (2008)"},{"key":"144_CR12","unstructured":"NVIDIA CUDA Compute Unified Device Architecture Programming Guide Version 2.0, july (2008)"},{"issue":"1","key":"144_CR13","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1111\/j.1467-8659.2007.01012.x","volume":"26","author":"J.D. Owens","year":"2007","unstructured":"Owens J.D., Luebke D., Govindaraju N., Harris M., Kr\u00fcger J., Lefohn A.E., Purcell T.: A survey of general-purpose computation on graphics hardware. Comp. Graph. Forum 26(1), 80\u2013113 (2007)","journal-title":"Comp. Graph. Forum"},{"key":"144_CR14","doi-asserted-by":"crossref","unstructured":"Romein, J.W., Broekema, P.C., Mol, J.D., van Nieuwpoort, Rob V.: The LOFAR correlator: implementation and performance analysis. In 15th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP 2010), Bangalore, India. Accepted for for publication. See http:\/\/www.astron.nl\/~romein\/papers\/ (2010)","DOI":"10.1145\/1693453.1693477"},{"key":"144_CR15","doi-asserted-by":"crossref","unstructured":"Romein, J.W., Broekema, P.C., van Meijeren, E., van der Schaaf, K., Zwart, W.H.: Astronomical real-time streaming signal processing on a Blue Gene\/L supercomputer. In ACM Symposium on Parallel Algorithms and Srchitectures (SPAA\u201906), pp. 59\u201366, Cambridge, MA, July (2006)","DOI":"10.1145\/1148109.1148118"},{"key":"144_CR16","doi-asserted-by":"crossref","unstructured":"Schilizzi, R.T., Dewdney, P.E.F., Lazio, T.J.W.: The Square Kilometre Array. Proceedings of SPIE, 7012, july (2008)","DOI":"10.1117\/12.786780"},{"key":"144_CR17","doi-asserted-by":"crossref","unstructured":"Seiler, L., Carmean, D., Sprangle, E., Forsyth, T., Abrash, M., Dubey, P., Junkins, S., Lake, A., Sugerman, J., Cavin, R., Espasa, R., Grochowski, E., Juan, T., Hanrahan, P.: Larrabee: A many-core x86 architecture for visual computing. ACM Trans. Graph., 27(3), August (2008)","DOI":"10.1145\/1360612.1360617"},{"key":"144_CR18","doi-asserted-by":"crossref","unstructured":"Silberstein, M., Schuster, A., Geiger, D., Patney, A., Owens, J.D.: Efficient computation of sum-products on GPUs through software-managed cache. In Proceedings of the 22nd ACM International Conference on Supercomputing, pp. 309\u2013318, June (2008)","DOI":"10.1145\/1375527.1375572"},{"key":"144_CR19","unstructured":"The Karoo Array Telescope (MeerKAT). See http:\/\/www.ska.ac.za\/"},{"key":"144_CR20","doi-asserted-by":"crossref","unstructured":"van Nieuwpoort, Rob V., Romein, J.W.: Using many-core hardware to correlate radio astronomy signals. In Proceedings of the ACM International Conference on Supercomputing (ICS\u201909), pp. 440\u2013449, Yorktown Heights, New York, USA, June (2009)","DOI":"10.1145\/1542275.1542337"},{"key":"144_CR21","doi-asserted-by":"crossref","unstructured":"Varbanescu, A., van Amesfoort, A., Cornwell, T., van Diepen, G., van Nieuwpoort, R., Elmegreen, B., Sips, H.: Building high-resolution sky images using the cell\/B.E. scientific programming (accepted, to appear) Special issue on high performance computing on the cell BE, (2008)","DOI":"10.1155\/2009\/408370"},{"key":"144_CR22","doi-asserted-by":"crossref","first-page":"857","DOI":"10.1086\/605334","volume":"121","author":"R.B. Wayth","year":"2009","unstructured":"Wayth R.B., Greenhill L.J., Briggs F.H.: A GPU-based real-time software correlation system for the murchison widefield array prototype. Pub. Astron. Soc. Pacific 121, 857\u2013865 (2009)","journal-title":"Pub. Astron. Soc. Pacific"},{"key":"144_CR23","doi-asserted-by":"crossref","unstructured":"Williams, S., Datta, K., Carter, J., Oliker, L., Half, J., Yelick, K., Bailey, D.: PERI\u2013Auto-tuning memory-intensive kernels for multicore. J. Phys.: Conference Series 125(012038), (2008)","DOI":"10.1088\/1742-6596\/125\/1\/012038"},{"key":"144_CR24","doi-asserted-by":"crossref","unstructured":"Williams, S., Waterman, A., Patterson, D.: Roofline: An insightful visual performance model for floating-point programs and multicore architectures. Communications of the ACM (CACM), (2009). (to appear)","DOI":"10.2172\/1407078"}],"container-title":["International Journal of Parallel Programming"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-010-0144-3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,22]],"date-time":"2025-02-22T07:01:05Z","timestamp":1740207665000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10766-010-0144-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,6,26]]},"references-count":24,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2011,2]]}},"alternative-id":["144"],"URL":"https:\/\/doi.org\/10.1007\/s10766-010-0144-3","relation":{},"ISSN":["0885-7458","1573-7640"],"issn-type":[{"type":"print","value":"0885-7458"},{"type":"electronic","value":"1573-7640"}],"subject":[],"published":{"date-parts":[[2010,6,26]]}}}