{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,9]],"date-time":"2025-06-09T14:26:40Z","timestamp":1749479200401,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":28,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642406973"},{"type":"electronic","value":"9783642406980"}],"license":[{"start":{"date-parts":[[2013,1,1]],"date-time":"2013-01-01T00:00:00Z","timestamp":1356998400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2013,1,1]],"date-time":"2013-01-01T00:00:00Z","timestamp":1356998400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-40698-0_9","type":"book-chapter","created":{"date-parts":[[2013,8,12]],"date-time":"2013-08-12T05:08:30Z","timestamp":1376284110000},"page":"114-127","source":"Crossref","is-referenced-by-count":23,"title":["OpenMP on the Low-Power TI Keystone II ARM\/DSP System-on-Chip"],"prefix":"10.1007","author":[{"given":"Eric","family":"Stotzer","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ajay","family":"Jayaraj","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Murtaza","family":"Ali","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arnon","family":"Friedmann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gaurav","family":"Mitra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alistair P.","family":"Rendell","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Th\u00e9a-Martine","family":"Gauthier","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"9_CR1","doi-asserted-by":"crossref","unstructured":"Mitra, G., Johnston, B., Rendell, A.P., McCreath, E., Zhou, J.: Use of SIMD vector operations to accelerate application code performance on low-powered ARM and Intel platforms. In: Parallel and Distributed Processing Symposium Workshops & PhD Forum (IPDPSW). IEEE (2013)","DOI":"10.1109\/IPDPSW.2013.207"},{"key":"9_CR2","doi-asserted-by":"crossref","unstructured":"Igual, F.D., Ali, M., Friedmann, A., Stotzer, E., Wentz, T., van de Geijn, R.A.: Unleashing the high-performance and low-power of multi-core dsps for general-purpose hpc. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, vol.\u00a026. IEEE Computer Society Press (2012)","DOI":"10.1109\/SC.2012.109"},{"key":"9_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1007\/978-3-642-30961-8_24","volume-title":"OpenMP in a Heterogeneous World","author":"J.M. Bull","year":"2012","unstructured":"Bull, J.M., Reid, F., McDonnell, N.: A microbenchmark suite for openMP tasks. In: Chapman, B.M., et al. (eds.) IWOMP 2012. LNCS, vol.\u00a07312, pp. 271\u2013274. Springer, Heidelberg (2012)"},{"key":"9_CR4","unstructured":"Texas Instruments Literature: SPRUGH7: TMS320C66x DSP CPU and Instruction Set Reference Guide"},{"key":"9_CR5","unstructured":"Texas Instruments Literature: SPRS691C: TMS320C6678 Multicore Fixed and Floating-Point Digital Signal Processor"},{"key":"9_CR6","volume-title":"Computer Architecture: A Quantitative Approach","author":"J.L. Hennessy","year":"2003","unstructured":"Hennessy, J.L., Patterson, D.A.: Computer Architecture: A Quantitative Approach. Morgan Kaufmann Publishers Inc., San Francisco (2003)"},{"key":"9_CR7","unstructured":"Texas Instruments Literature: SPRS866: 66AK2H12\/06 Multicore DSP+ARM Keystone II System-on-Chip (SoC)"},{"issue":"12","key":"9_CR8","doi-asserted-by":"publisher","first-page":"1193","DOI":"10.1002\/1096-9128(200010)12:12<1193::AID-CPE527>3.0.CO;2-U","volume":"12","author":"C. Brunschen","year":"2000","unstructured":"Brunschen, C., Brorsson, M.: OdinMP\/CCp - a portable implementation of OpenMP for C. Concurrency - Practice and Experience\u00a012(12), 1193\u20131203 (2000)","journal-title":"Concurrency - Practice and Experience"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"Liao, C., Hernandez, O., Chapman, B., Chen, W., Zheng, W.: OpenUH: An optimizing, portable OpenMP compiler. In: Concurrency and Computation: Practice and Experience, Special Issueon CPC 2006 selected papers (2006) (accepted)","DOI":"10.1002\/cpe.1174"},{"key":"9_CR10","unstructured":"Texas Instruments Literature: SPRU423D: DSP\/BIOS user\u2019s guide"},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Hoeflinger, J.P., de Supinski, B.R.: The openmp memory model. In: Mueller, M.S., Chapman, B.M., de Supinski, B.R., Malony, A.D., Voss, M. (eds.) IWOMP 2005\/2006. LNCS, vol.\u00a04315, pp. 167\u2013177. Springer, Heidelberg (2008)","DOI":"10.1007\/978-3-540-68555-5_14"},{"issue":"2","key":"9_CR12","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1145\/360827.360844","volume":"17","author":"L. Lamport","year":"1974","unstructured":"Lamport, L.: The parallel execution of do loops. Commun. ACM\u00a017(2), 83\u201393 (1974)","journal-title":"Commun. ACM"},{"key":"9_CR13","unstructured":"OpenMP, A.: Openmp application program interface, v. 4.0 - rc 2 (2013)"},{"key":"9_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1007\/978-3-642-21487-5_9","volume-title":"OpenMP in the Petascale Era","author":"J.C. Beyer","year":"2011","unstructured":"Beyer, J.C., Stotzer, E.J., Hart, A., de Supinski, B.R.: OpenMP for accelerators. In: Chapman, B.M., Gropp, W.D., Kumaran, K., M\u00fcller, M.S. (eds.) IWOMP 2011. LNCS, vol.\u00a06665, pp. 108\u2013121. Springer, Heidelberg (2011)"},{"key":"9_CR15","unstructured":"Texas Instruments Literature: SPRT610: TMS320TCI6612\/14 High Performance comes to small cell base stations"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"Ali, M., Stotzer, E., Igual, F.D., van de Geijn, R.A.: Level-3 blas on the ti c6678 multi-core dsp. In: 2012 IEEE 24th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD), pp. 179\u2013186. IEEE (2012)","DOI":"10.1109\/SBAC-PAD.2012.26"},{"key":"9_CR17","doi-asserted-by":"crossref","unstructured":"Ahmad, A., Ali, M., South, F., Monroy, G.L., Adie, S.G., Shemonski, N., Carney, P.S., Boppart, S.A.: Interferometric synthetic aperture microscopy implementation on a floating point multi-core digital signal processer. In: SPIE BiOS, International Society for Optics and Photonics, p. 857134 (2013)","DOI":"10.1117\/12.2006876"},{"key":"9_CR18","unstructured":"Note, F.W., Van Zee, F.G., Smith, T., Igual, F.D., Smelyanskiy, M., Zhang, X., Kistler, M., Austel, V., Gunnels, J., Low, T.M., et al.: Implementing level-3 blas with blis: Early experience (2013)"},{"key":"9_CR19","doi-asserted-by":"crossref","unstructured":"Reyes, R., Lopez, I., Fumero, J.J., de Sande, F.: Directive-based programming for gpus: A comparative study. In: 2012 IEEE 14th International Conference on High Performance Computing and Communication & 2012 IEEE 9th International Conference on Embedded Software and Systems (HPCC-ICESS), pp. 410\u2013417. IEEE (2012)","DOI":"10.1109\/HPCC.2012.62"},{"key":"9_CR20","unstructured":"Han, T.D., Abdelrahman, T.S.: hi cuda: a high-level directive-based language for gpu programming. In: Proceedings of 2nd Workshop on General Purpose Processing on Graphics Processing Units, pp. 52\u201361. ACM (2009)"},{"key":"9_CR21","doi-asserted-by":"crossref","unstructured":"Wolfe, M.: Implementing the pgi accelerator model. In: Proceedings of the 3rd Workshop on General-Purpose Computation on Graphics Processing Units, pp. 43\u201350. ACM (2010)","DOI":"10.1145\/1735688.1735697"},{"issue":"1","key":"9_CR22","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1147\/sj.451.0059","volume":"45","author":"A.E. Eichenberger","year":"2006","unstructured":"Eichenberger, A.E., O\u2019Brien, J.K., O\u2019Brien, K.M., Wu, P., Chen, T., Oden, P.H., Prener, D.A., Shepherd, J.C., So, B., Sura, Z., et al.: Using advanced compiler technology to exploit the performance of the cell broadband engine architecture. IBM Systems Journal\u00a045(1), 59\u201384 (2006)","journal-title":"IBM Systems Journal"},{"key":"9_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/978-3-642-02303-3_13","volume-title":"Evolving OpenMP in an Age of Extreme Parallelism","author":"E. Ayguade","year":"2009","unstructured":"Ayguade, E., Badia, R.M., Cabrera, D., Duran, A., Gonzalez, M., Igual, F., Jimenez, D., Labarta, J., Martorell, X., Mayo, R., Perez, J.M., Quintana-Ort\u00ed, E.S.: A proposal to extend the openMP tasking model for heterogeneous architectures. In: M\u00fcller, M.S., de Supinski, B.R., Chapman, B.M. (eds.) IWOMP 2009. LNCS, vol.\u00a05568, pp. 154\u2013167. Springer, Heidelberg (2009)"},{"key":"9_CR24","doi-asserted-by":"crossref","unstructured":"Cabrera, D., Martorell, X., Gaydadjiev, G., Ayguade, E., Jim\u00e9nez-Gonz\u00e1lez, D.: Openmp extensions for fpga accelerators. In: International Symposium on Systems, Architectures, Modeling, and Simulation, SAMOS 2009, pp. 17\u201324. IEEE (2009)","DOI":"10.1109\/ICSAMOS.2009.5289237"},{"issue":"5-6","key":"9_CR25","doi-asserted-by":"publisher","first-page":"440","DOI":"10.1007\/s10766-010-0135-4","volume":"38","author":"E. Ayguad\u00e9","year":"2010","unstructured":"Ayguad\u00e9, E., Badia, R.M., Bellens, P., Cabrera, D., Duran, A., Ferrer, R., Gonz\u00e0lez, M., Igual, F., Jim\u00e9nez-Gonz\u00e1lez, D., Labarta, J., et al.: Extending openmp to survive the heterogeneous multi-core era. International Journal of Parallel Programming\u00a038(5-6), 440\u2013459 (2010)","journal-title":"International Journal of Parallel Programming"},{"key":"9_CR26","unstructured":"Texas Instruments Literature: SPRUGO6A: SYS\/BIOS inter-processor communication (IPC) and I\/O user\u2019s guide"},{"key":"9_CR27","doi-asserted-by":"crossref","unstructured":"Chapman, B., Huang, L., Biscondi, E., Stotzer, E., Shrivastava, A., Gatherer, A.: Implementing openmp on a high performance embedded multicore mpsoc. In: IEEE International Symposium on Parallel & Distributed Processing, IPDPS 2009, pp. 1\u20138. IEEE (2009)","DOI":"10.1109\/IPDPS.2009.5161107"},{"key":"9_CR28","doi-asserted-by":"crossref","unstructured":"Jeun, W.C., Ha, S.: Effective openmp implementation and translation for multiprocessor system-on-chip without using os. In: Proceedings of the 2007 Asia and South Pacific Design Automation Conference, pp. 44\u201349. IEEE Computer Society (2007)","DOI":"10.1109\/ASPDAC.2007.357790"}],"container-title":["Lecture Notes in Computer Science","OpenMP in the Era of Low Power Devices and Accelerators"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-40698-0_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,16]],"date-time":"2024-05-16T10:59:52Z","timestamp":1715857192000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-642-40698-0_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642406973","9783642406980"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-40698-0_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}