{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T07:57:25Z","timestamp":1725868645356},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319491080"},{"type":"electronic","value":"9783319491097"}],"license":[{"start":{"date-parts":[[2016,10,22]],"date-time":"2016-10-22T00:00:00Z","timestamp":1477094400000},"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":[[2017]]},"DOI":"10.1007\/978-3-319-49109-7_34","type":"book-chapter","created":{"date-parts":[[2016,10,21]],"date-time":"2016-10-21T05:03:15Z","timestamp":1477026195000},"page":"361-372","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive Modular Mapping to Reduce Shared Memory Bank Conflicts on GPUs"],"prefix":"10.1007","author":[{"given":"Innocenzo","family":"Mungiello","sequence":"first","affiliation":[]},{"given":"Francesco","family":"De Rosa","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,10,22]]},"reference":[{"key":"34_CR1","unstructured":"CUDA C Programming Guide"},{"key":"34_CR2","doi-asserted-by":"crossref","unstructured":"Amato, F., Fasolino, A., Mazzeo, A., Moscato, V., Picariello, A., Romano, S., Tramontana, P.: Ensuring semantic interoperability for e-health applications. In: Proceedings of the International Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2011, pp. 315\u2013320 (2011)","DOI":"10.1109\/CISIS.2011.52"},{"key":"34_CR3","doi-asserted-by":"crossref","unstructured":"Amato, F., Mazzeo, A., Penta, A., Picariello, A.: Building RDF ontologies from semistructured legal documents. pp. 997\u20131002 (2008)","DOI":"10.1109\/CISIS.2008.146"},{"key":"34_CR4","unstructured":"Amato, F., Moscato, F.: A model driven approach to data privacy verification in e-health systems. Transactions on Data Privacy 8(3), 273\u2013296 (2015)"},{"key":"34_CR5","doi-asserted-by":"crossref","unstructured":"Barbareschi, M.: Implementing hardware decision tree prediction: a scalable approach. In: 2016 30th International Conference on Advanced Information Networking and Applications Workshops (WAINA), pp. 87\u201392. IEEE (2016)","DOI":"10.1109\/WAINA.2016.171"},{"key":"34_CR6","doi-asserted-by":"crossref","unstructured":"Barbareschi, M., Battista, E., Mazzocca, N., Venkatesan, S.: A hardware accelerator for data classification within the sensing infrastructure. In: Information Reuse and Integration (IRI), 2014 IEEE 15th International Conference on, pp. 400\u2013405. IEEE (2014)","DOI":"10.1109\/IRI.2014.7051917"},{"key":"34_CR7","unstructured":"Barbareschi, M., De Benedictis, A., Mazzeo, A., Vespoli, A.: Providing mobile traffic analysis as-a-service: Design of a service-based infrastructure to offer high-accuracy traffic classifiers based on hardware accelerators. Journal of Digital Information Management 13(4), 257 (2015)"},{"key":"34_CR8","doi-asserted-by":"crossref","unstructured":"Che, S., Sheaffer, J.W., Skadron, K.: Dymaxion: optimizing memory access patterns for heterogeneous systems. In: Proceedings of 2011 international conference for high performance computing, networking, storage and analysis, p. 13. ACM (2011)","DOI":"10.1145\/2063384.2063401"},{"key":"34_CR9","unstructured":"Cheng, J., Grossman, M., McKercher, T.: Professional Cuda C Programming. John Wiley & Sons (2014)"},{"key":"34_CR10","doi-asserted-by":"crossref","unstructured":"Cilardo, A.: Efficient bit-parallel GF(2m) multiplier for a large class of irreducible pentanomials. IEEE Transactions on Computers 58(7), 1001\u20131008 (2009)","DOI":"10.1109\/TC.2009.16"},{"key":"34_CR11","doi-asserted-by":"crossref","unstructured":"Cilardo, A.: Exploring the potential of threshold logic for cryptography-related operations. IEEE Transactions on Computers 60(4), 452\u2013462 (2011)","DOI":"10.1109\/TC.2010.116"},{"key":"34_CR12","doi-asserted-by":"crossref","unstructured":"Cilardo, A., Fusella, E., Gallo, L., Mazzeo, A.: Exploiting concurrency for the automated synthesis of MPSoC interconnects. ACM Transactions on Embedded Computing Systems 14(3) (2015)","DOI":"10.1145\/2700075"},{"key":"34_CR13","doi-asserted-by":"crossref","unstructured":"Cilardo, A., Gallo, L.: Improving multibank memory access parallelism with lattice-based partitioning. ACM Transactions on Architecture and Code Optimization 11(4) (2014)","DOI":"10.1145\/2675359"},{"key":"34_CR14","doi-asserted-by":"crossref","unstructured":"Darte, A., Dion, M., Robert, Y.: A characterization of one-to-one modular mappings. Parallel Processing Letters 6(01), 145\u2013157 (1996)","DOI":"10.1142\/S0129626496000157"},{"key":"34_CR15","doi-asserted-by":"crossref","unstructured":"Darte, A., Schreiber, R., Villard, G.: Lattice-based memory allocation. IEEE Transactions on Computers 54(10), 1242\u20131257 (2005)","DOI":"10.1109\/TC.2005.167"},{"key":"34_CR16","doi-asserted-by":"crossref","unstructured":"Escobar, F.A., Chang, X., Valderrama, C.: Suitability analysis of fpgas for heterogeneous platforms in hpc. IEEE Transactions on Parallel and Distributed Systems 27(2), 600\u2013612 (2016)","DOI":"10.1109\/TPDS.2015.2407896"},{"key":"34_CR17","doi-asserted-by":"crossref","unstructured":"Fusella, E., Cilardo, A.: H2ONoC: A hybrid optical-electronic NoC based on hybrid topology. IEEE Transactions on Very Large Scale Integration (VLSI) Systems (2016)","DOI":"10.1109\/TVLSI.2016.2581486"},{"key":"34_CR18","doi-asserted-by":"crossref","unstructured":"Fusella, E., Cilardo, A.: Minimizing power loss in optical networks-on-chip through application-specific mapping. Microprocessors and Microsystems (2016)","DOI":"10.1016\/j.micpro.2016.01.014"},{"key":"34_CR19","unstructured":"Gao, S., Peterson, G.D.: Optimizing cuda shared memory usage"},{"key":"34_CR20","doi-asserted-by":"crossref","unstructured":"Grun, P., Dutt, N., Nicolau, A.: Apex: access pattern based memory architecture exploration. In: Proceedings of the 14th international symposium on Systems synthesis, pp. 25\u201332. ACM (2001)","DOI":"10.1145\/500001.500007"},{"key":"34_CR21","doi-asserted-by":"crossref","unstructured":"Hallmans, D., A\u02da sberg, M., Nolte, T.: Towards using the graphics processing unit (gpu) for embedded systems. In: Proceedings of 2012 IEEE 17th International Conference on Emerging Technologies & Factory Automation (ETFA 2012), pp. 1\u20134. IEEE (2012)","DOI":"10.1109\/ETFA.2012.6489715"},{"key":"34_CR22","doi-asserted-by":"crossref","unstructured":"Khan, A., Al-Mouhamed, M., Fatayar, A., Almousa, A., Baqais, A., Assayony, M.: Padding free bank conflict resolution for cuda-based matrix transpose algorithm. In: Software Engineering, Artificial Intelligence, Networking and Parallel\/Distributed Computing (SNPD), 2014 15th IEEE\/ACIS International Conference on, pp. 1\u20136. IEEE (2014)","DOI":"10.1109\/SNPD.2014.6888709"},{"key":"34_CR23","doi-asserted-by":"crossref","unstructured":"Kim, Y., Shrivastava, A.: Cumapz: a tool to analyze memory access patterns in cuda. In: Proceedings of the 48th Design Automation Conference, pp. 128\u2013133. ACM (2011)","DOI":"10.1145\/2024724.2024754"},{"key":"34_CR24","unstructured":"Kirk, D.B., Wen-mei, W.H.: Programming massively parallel processors: a hands-on approach. Newnes (2012)"},{"key":"34_CR25","doi-asserted-by":"crossref","unstructured":"Luebke, D.: Cuda: Scalable parallel programming for high-performance scientific computing. In: 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, pp. 836\u2013838. IEEE (2008)","DOI":"10.1109\/ISBI.2008.4541126"},{"key":"34_CR26","doi-asserted-by":"crossref","unstructured":"Lustig, D., Martonosi, M.: Reducing gpu offload latency via fine-grained cpu-gpu synchronization. In: HPCA, vol. 13, pp. 354\u2013365 (2013)","DOI":"10.1109\/HPCA.2013.6522332"},{"key":"34_CR27","doi-asserted-by":"crossref","unstructured":"Mungiello, I.: Experimental evaluation of memory optimizations on an embedded gpu platform. In: 2015 10th International Conference on P2P, Parallel, Grid, Cloud and Internet Computing (3PGCIC), pp. 169\u2013174. IEEE (2015)","DOI":"10.1109\/3PGCIC.2015.136"},{"key":"34_CR28","doi-asserted-by":"crossref","unstructured":"Sung, I.J., Liu, G.D., Hwu, W.M.W.: Dl: A data layout transformation system for heterogeneous computing. In: Innovative Parallel Computing (InPar), 2012, pp. 1\u201311. IEEE (2012)","DOI":"10.1109\/InPar.2012.6339606"},{"key":"34_CR29","doi-asserted-by":"crossref","unstructured":"Ueng, S.Z., Lathara, M., Baghsorkhi, S.S., Wen-mei, W.H.: Cuda-lite: Reducing gpu programming complexity. In: International Workshop on Languages and Compilers for Parallel Computing, pp. 1\u201315. Springer (2008)","DOI":"10.1007\/978-3-540-89740-8_1"},{"key":"34_CR30","doi-asserted-by":"crossref","unstructured":"Wang, Z., Grewe, D., Oboyle, M.F.: Automatic and portable mapping of data parallel programs to opencl for gpu-based heterogeneous systems. ACM Transactions on Architecture and Code Optimization (TACO) 11(4), 42 (2015)","DOI":"10.1145\/2677036"},{"key":"34_CR31","unstructured":"Zhang, Z., Fan, Y., Jiang, W., Han, G., Yang, C., Cong, J.: High-level synthesis: From algorithm to digital circuit (2008)"}],"container-title":["Lecture Notes on Data Engineering and Communications Technologies","Advances on P2P, Parallel, Grid, Cloud and Internet Computing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-49109-7_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,14]],"date-time":"2019-09-14T18:00:58Z","timestamp":1568484058000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-49109-7_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,10,22]]},"ISBN":["9783319491080","9783319491097"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-49109-7_34","relation":{},"ISSN":["2367-4512","2367-4520"],"issn-type":[{"type":"print","value":"2367-4512"},{"type":"electronic","value":"2367-4520"}],"subject":[],"published":{"date-parts":[[2016,10,22]]}}}