{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,3,6]],"date-time":"2024-03-06T19:44:00Z","timestamp":1709754240661},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2013,2,21]],"date-time":"2013-02-21T00:00:00Z","timestamp":1361404800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Sign Process Syst"],"published-print":{"date-parts":[[2014,5]]},"DOI":"10.1007\/s11265-013-0732-8","type":"journal-article","created":{"date-parts":[[2013,2,20]],"date-time":"2013-02-20T09:26:51Z","timestamp":1361352411000},"page":"123-139","source":"Crossref","is-referenced-by-count":3,"title":["Message-Passing Programming for Embedded Multicore Signal-Processing Platforms"],"prefix":"10.1007","volume":"75","author":[{"given":"Shih-Hao","family":"Hung","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Po-Hsun","family":"Chiu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chia-Heng","family":"Tu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei-Ting","family":"Chou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen-Long","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,2,21]]},"reference":[{"key":"732_CR1","unstructured":"Advanced Micro Devices, Inc. (2012). AMD Opteron\u2122 6100 Series Processors. [Online]. Available: http:\/\/www.amd.com\/us\/products\/server\/processors\/6000-series-platform\/6100\/Pages\/6100-series-processors.aspx"},{"key":"732_CR2","volume-title":"Computer Architecture, Fifth Edition: A Quantitative Approach (The Morgan Kaufmann Series in Computer Architecture and Design)","author":"JL Hennessy","year":"2011","unstructured":"Hennessy, J. L., & Patterson, D. A. (2011). Computer Architecture, Fifth Edition: A Quantitative Approach (The Morgan Kaufmann Series in Computer Architecture and Design). Waltham, MA: Morgan Kaufmann."},{"issue":"5","key":"732_CR3","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1147\/rd.515.0559","volume":"51","author":"T Chen","year":"2007","unstructured":"Chen, T., Raghavan, R., Dale, J. N., & Iwata, E. (2007). CELL broadband engine architecture and its first implementation: A performance view. IBM Journal of Research and Development, 51(5), 559\u2013572.","journal-title":"IBM Journal of Research and Development"},{"key":"732_CR4","unstructured":"Texas Instruments Inc. (2012). DaVinci Digital Media System-on-Chip - TMS320DM6446. [Online]. Available: http:\/\/www.ti.com\/product\/tms320dm6446 ."},{"key":"732_CR5","doi-asserted-by":"crossref","unstructured":"Hsu, Z., Chuang, I., Su, W., Yeh, J., Yang, J., & Tseng, S. (2009). System performance analyses on PAC Duo ESL virtual platform. In Proceedings of International Conference on Intelligent Information Hiding and Multimedia Signal Processing, 406\u2013409","DOI":"10.1109\/IIH-MSP.2009.86"},{"key":"732_CR6","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1007\/s11265-010-0470-0","volume":"62","author":"D Chang","year":"2010","unstructured":"Chang, D., Lin, T., Wu, C., Lee, J., Chu, Y., & Wu, A. (2010). Parallel architecture core (PAC) - the first multicore application processor SoC in Taiwan Part I: Hardware architecture & software development tools. Journal of Signal Processing Systems, 62, 373\u2013382.","journal-title":"Journal of Signal Processing Systems"},{"key":"732_CR7","unstructured":"The Multicore Association. (2012). Multicore Communications API Working Group. [Online]. Available: http:\/\/www.multicore-association.org\/workgroup\/mcapi.php ."},{"key":"732_CR8","unstructured":"Khronos Group. (2010). The OpenCL Specification, September 2010. [Online]. Available: http:\/\/www.khronos.org\/opencl\/ ."},{"issue":"5","key":"732_CR9","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1145\/635506.605428","volume":"30","author":"MI Gordon","year":"2002","unstructured":"Gordon, M. I., Maze, D., Amarasinghe, S., Thies, T., Karczmarek, M., Lin, J., et al. (2002). A stream compiler for communication-exposed architectures. ACM SIGARCH Computer Architecture News, 30(5), 291\u2013303.","journal-title":"ACM SIGARCH Computer Architecture News"},{"key":"732_CR10","unstructured":"Dally, B., & Horowitz M. (2003). BrookGPU. [Online]. Available: http:\/\/graphics.stanford.edu\/projects\/brookgpu\/index.html ."},{"key":"732_CR11","unstructured":"NVIDIA Corp. (2012). CUDA Parallel Programming Made Easy. [Online]. Available: http:\/\/www.nvidia.com\/object\/cuda_home_new.html ."},{"issue":"6","key":"732_CR12","doi-asserted-by":"crossref","first-page":"789","DOI":"10.1016\/0167-8191(96)00024-5","volume":"22","author":"W Gropp","year":"1996","unstructured":"Gropp, W., Lusk, E., Doss, N., & Skjellum, A. (1996). A high-performance, portable implementation of the MPI, message passing interface standard. Parallel Computing, 22(6), 789\u2013828.","journal-title":"Parallel Computing"},{"key":"732_CR13","unstructured":"Yang, Q. C. (2010). Running MPI and Brook programs on embedded multi-core platforms with a portable message-passing library and code translation. Master Thesis, National Taiwan University."},{"key":"732_CR14","unstructured":"NASA Advanced Supercomputing Division. (2012). NAS Parallel Benchmarks Changes. [Online]. Available: http:\/\/www.nas.nasa.gov\/publications\/npb.html ."},{"key":"732_CR15","unstructured":"Gurhanli, A., Chen, C.C.-P., & Hung, S. H. (2010). GOP-level parallelization of the H.264 decoder without a start-code scanner. In Proceedings of the 2010 International Conference on Signal Processing Systems, 627\u2013630."},{"key":"732_CR16","unstructured":"Lawrence Livermore Nation Laboratory (LLNL). [Online]. Available: https:\/\/www.llnl.gov"},{"key":"732_CR17","unstructured":"Dierks, T., & Rescorla, E. (2008). The Transport Layer Security (TLS) Protocol, Version 1.2. [Online]. Available: http:\/\/tools.ietf.org\/html\/rfc5246 ."},{"key":"732_CR18","unstructured":"Barney, B. (2011). Introduction to Parallel Computing. [Online]. Available: https:\/\/computing.llnl.gov\/tutorials\/parallel_comp\/ ."},{"issue":"6","key":"732_CR19","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1109\/MSP.2009.934110","volume":"26","author":"G Blake","year":"2009","unstructured":"Blake, G., Dreslinski, R., & Mudge, T. (2009). A survey of multicore processors. IEEE Signal Processing Magazine, 26(6), 26\u201337.","journal-title":"IEEE Signal Processing Magazine"},{"issue":"8","key":"732_CR20","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1109\/2.84877","volume":"24","author":"B Nitzberg","year":"1991","unstructured":"Nitzberg, B., & Lo, V. (1991). Distributed Shared Memory: A Survey of Issues and Algorithms. Computer, 24(8), 52\u201360.","journal-title":"Computer"},{"issue":"2","key":"732_CR21","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1145\/1399972.1399978","volume":"36","author":"D Chang","year":"2008","unstructured":"Chang, D., Li, Q. J., Rabbah, R., & Amarasinghe, S. (2008). A lightweight streaming layer for multiore execution. ACM SIGARCH Computer Architecture News, 36(2), 18\u201327.","journal-title":"ACM SIGARCH Computer Architecture News"},{"issue":"2","key":"732_CR22","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1145\/1353535.1346319","volume":"42","author":"J Gummaraju","year":"2008","unstructured":"Gummaraju, J., Coburn, J., Turner, Y., & Rosenblum, M. (2008). Streamware: Programming gerneral-purpose multicore processor using streams. ACM SIGOPS Operating System Review, 42(2), 297\u2013307.","journal-title":"ACM SIGOPS Operating System Review"},{"key":"732_CR23","unstructured":"International Business Machines Corp. (2008). Data communication and synchronization library programmer\u2019s guide and API reference."},{"key":"732_CR24","unstructured":"Mathematics and Computer Science Division, Argonne National Laboratory. (2012). MPICH-A Portable Implementation of MPI. [Online]. Available: http:\/\/www.mcs.anl.gov\/research\/projects\/mpi\/mpich1-old\/ ."},{"issue":"1","key":"732_CR25","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1109\/99.660313","volume":"5","author":"L Dagum","year":"1998","unstructured":"Dagum, L., & Menon, R. (1998). OpenMP: an industry standard API for shared memory programming. IEEE Computational Science and Engineering, 5(1), 46\u201355.","journal-title":"IEEE Computational Science and Engineering"},{"key":"732_CR26","first-page":"40","volume":"6083","author":"JJ Li","year":"2011","unstructured":"Li, J. J., Wang, S. C., Hsu, P. C., Chen, P. Y., & Lee, J. K. (2011). A Multi-core Software API for Embedded MPSoC Environments. Lecture Notes in Computer Science, 6083, 40\u201350.","journal-title":"Lecture Notes in Computer Science"},{"issue":"2","key":"732_CR27","first-page":"193","volume":"57","author":"SH Hung","year":"2011","unstructured":"Hung, S. H., Tu, C. H., & Yang, W. L. (2011). A portable, efficient inter-core communication scheme for embedded multicore platforms. Journal of Systems Architecture - Embedded Systems Design, 57(2), 193\u2013205.","journal-title":"Journal of Systems Architecture - Embedded Systems Design"},{"key":"732_CR28","doi-asserted-by":"crossref","unstructured":"Hung, S.-H., Chiu, P.-H., Shih, C.-S. (2011). Building a Scalable and Portable Message-Passing Library for Embedded Multicore Systems. In Proceedings of the 2011 Research in Applied Computation Symposium (RACS 2011).","DOI":"10.1145\/2103380.2103387"},{"key":"732_CR29","doi-asserted-by":"crossref","unstructured":"Hung, S.-H., Tu, C.-H., Soon, T.-S. (2010). Trace-based performance analysis framework for heterogeneous multicore systems. In Proceedings of the 15th Asia South Pacific Design Automation Conference, 19\u201324.","DOI":"10.1109\/ASPDAC.2010.5419926"},{"key":"732_CR30","doi-asserted-by":"crossref","unstructured":"Hung, S., Yang, W., & Tu, C. (2010). Designing and implementing a portable, efficient inter-core communication scheme for embedded multicore platforms. In Proceedings of the 2010 IEEE 16th International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA'10), 303\u2013308.","DOI":"10.1109\/RTCSA.2010.17"},{"issue":"2","key":"732_CR31","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1016\/j.sysarc.2010.11.003","volume":"57","author":"S Hung","year":"2011","unstructured":"Hung, S., Tu, C., & Yang, W. (2011). A portable, efficient inter-core communication scheme for embedded multicore platforms. Journal of Systems Architecture, 57(2), 193\u2013205.","journal-title":"Journal of Systems Architecture"},{"key":"732_CR32","doi-asserted-by":"crossref","unstructured":"Lin, Y., Tu, C., Shih, C., & Hung, S. (2009) Zero-Buffer inter-core process communication protocol for heterogeneous multi-core platforms. In Proceedings of the 15th IEEE International Conference on Embedded and Real-time Computing Systems and Applications, 69\u201378.","DOI":"10.1109\/RTCSA.2009.14"},{"key":"732_CR33","unstructured":"Jin, H.-W., Sur, S., Chai, L., & Panda, D. (2005). Limic: support for high-performance MPI intra-node communication on Linux cluster. In Proceedings of the International Conference on in Parallel Processing, 184\u2013191."},{"key":"732_CR34","doi-asserted-by":"crossref","unstructured":"Chai, L., Hartono, A., & Panda, D. (2006). Designing high performance and scalable MPI intra-node communication support for clusters. In Proceedings of 2006 IEEE International Conference on Cluster Computing, 1\u201310.","DOI":"10.1109\/CLUSTR.2006.311850"},{"key":"732_CR35","doi-asserted-by":"crossref","unstructured":"Buntinas, D., Mercier, G., & Gropp, W. (2006). Data transfers between processes in an SMP system: Performance study and application to MPI. In Proceedings of the 2006 International Conference on Parallel Processing, 487 \u2013496.","DOI":"10.1109\/ICPP.2006.31"},{"key":"732_CR36","unstructured":"MPI over InfiniBand project. http:\/\/nowlab.cse.ohiostate.edu\/projects\/mpi-iba\/ ."},{"key":"732_CR37","unstructured":"Altevogt, P. (2008). IBM BladeCenter QS21 hardware performance. IBM Technical White Paper WP101245."},{"issue":"9","key":"732_CR38","doi-asserted-by":"crossref","first-page":"634","DOI":"10.1016\/j.parco.2007.06.003","volume":"33","author":"D Buntinas","year":"2007","unstructured":"Buntinas, D., Mercier, G., & Gropp, W. (2007). Implementation and evaluation of shared memory communication and synchronization operations in MPICH2 using the nemesis communication subsystem. Parallel Computing, 33(9), 634\u2013644.","journal-title":"Parallel Computing"},{"key":"732_CR39","doi-asserted-by":"crossref","unstructured":"Tezuka, H., O\u2019Carroll, F., Hori, A., Ishikawa, Y. (1998). Pin-down cache: a virtual memory management technique for zero-copy communication. In Proceedings of the First Merged International \u2026 and Symposium on Parallel and Distributed Processing 1998, 308\u2013314.","DOI":"10.1109\/IPPS.1998.669932"}],"container-title":["Journal of Signal Processing Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-013-0732-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11265-013-0732-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-013-0732-8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,7,9]],"date-time":"2019-07-09T23:12:05Z","timestamp":1562713925000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11265-013-0732-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,2,21]]},"references-count":39,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2014,5]]}},"alternative-id":["732"],"URL":"https:\/\/doi.org\/10.1007\/s11265-013-0732-8","relation":{},"ISSN":["1939-8018","1939-8115"],"issn-type":[{"value":"1939-8018","type":"print"},{"value":"1939-8115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,2,21]]}}}