{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:19:22Z","timestamp":1740097162309,"version":"3.37.3"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319201184"},{"type":"electronic","value":"9783319201191"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-20119-1_8","type":"book-chapter","created":{"date-parts":[[2015,6,19]],"date-time":"2015-06-19T06:36:48Z","timestamp":1434695808000},"page":"96-112","source":"Crossref","is-referenced-by-count":2,"title":["Accelerating LBM and LQCD Application Kernels by In-Memory Processing"],"prefix":"10.1007","author":[{"given":"Paul F.","family":"Baumeister","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hans","family":"Boettiger","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jos\u00e9 R.","family":"Brunheroto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thorsten","family":"Hater","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thilo","family":"Maurer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrea","family":"Nobile","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dirk","family":"Pleiter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,6,20]]},"reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Ang, J.A., Barrett, R.F., Benner, R.E., Burke, D., Chan, C., Cook, J., Donofrio, D., Hammond, S.D., Hemmert, K.S., Kelly, S.M., Le, H., Leung, V.J., Resnick, D.R., Rodrigues, A.F., Shalf, J., Stark, D., Unat, D., Wright, N.J.: Abstract machine models and proxy architectures for exascale computing. In: Proceedings of the 1st International Workshop on Hardware-Software Co-Design for High Performance Computing (Co-HPC 2014), pp. 25\u201332. IEEE Press, Piscataway (2014). \n                    http:\/\/dx.doi.org\/10.1109\/Co-HPC.2014.4","DOI":"10.1109\/Co-HPC.2014.4"},{"issue":"4","key":"8_CR2","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1109\/MM.2014.55","volume":"34","author":"R Balasubramonian","year":"2014","unstructured":"Balasubramonian, R., Chang, J., Manning, T., Moreno, J.H., Murphy, R., Nair, R., Swanson, S.: Near-data processing: insights from a MICRO-46 workshop. IEEE Micro 34(4), 36\u201342 (2014)","journal-title":"IEEE Micro"},{"issue":"1","key":"8_CR3","doi-asserted-by":"publisher","first-page":"1075","DOI":"10.1016\/j.procs.2010.04.119","volume":"1","author":"L Biferale","year":"2010","unstructured":"Biferale, L., Mantovani, F., Pivanti, M., Sbragaglia, A., Schifano, S., Toschi, F., Tripiccione, R.: Lattice Boltzmann fluid-dynamics on the QPACE supercomputer. Procedia Comput. Sci. 1(1), 1075\u20131082 (2010). \n                    http:\/\/www.sciencedirect.com\/science\/article\/pii\/S1877050910001201\n                    \n                  , ICCS 2010","journal-title":"Procedia Comput. Sci."},{"key":"8_CR4","doi-asserted-by":"publisher","first-page":"994","DOI":"10.1016\/j.procs.2011.04.105","volume":"4","author":"L Biferale","year":"2011","unstructured":"Biferale, L., Mantovani, F., Pivanti, M., Pozzati, F., Sbragaglia, M., Scagliarini, A., Schifano, S.F., Toschi, F., Tripiccione, R.: Optimization of multi-phase compressible lattice Boltzmann codes on massively parallel multi-core systems. Procedia Comput. Sci. 4, 994\u20131003 (2011). \n                    http:\/\/www.sciencedirect.com\/science\/article\/pii\/S1877050911001633\n                    \n                  , Proceedings of the International Conference on Computational Science, ICCS 2011","journal-title":"Procedia Comput. Sci."},{"issue":"1\/2","key":"8_CR5","doi-asserted-by":"publisher","first-page":"13:1","DOI":"10.1147\/JRD.2012.2237149","volume":"57","author":"PA Boyle","year":"2013","unstructured":"Boyle, P.A., Christ, N.H., Kim, C.: Co-design of the IBM BlueGene\/q level 1 prefetch engine with QCD. IBM J. Res. Dev. 57(1\/2), 13:1\u201313:10 (2013)","journal-title":"IBM J. Res. Dev."},{"key":"8_CR6","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1016\/j.procs.2014.05.004","volume":"29","author":"E Calore","year":"2014","unstructured":"Calore, E., Schifano, S.F., Tripiccione, R.: A portable OpenCL lattice Boltzmann code for multi- and many-core processor architectures. Procedia Comput. Sci. 29, 40\u201349 (2014). \n                    http:\/\/www.sciencedirect.com\/science\/article\/pii\/S1877050914001811\n                    \n                  , 2014 International Conference on Computational Science","journal-title":"Procedia Comput. Sci."},{"key":"8_CR7","unstructured":"Elliott, D., Snelgrove, W., Stumm, M.: Computational ram: a memory-simd hybrid and its application to dsp. In: Proceedings of the IEEE 1992 on Custom Integrated Circuits Conference, pp. 30.6.1\u201330.6.4, May 1992"},{"key":"8_CR8","doi-asserted-by":"publisher","first-page":"A1581","DOI":"10.1137\/130919507","volume":"36","author":"A Frommer","year":"2014","unstructured":"Frommer, A., Kahl, K., Krieg, S., Leder, B., Rottmann, M.: Adaptive aggregation based domain decomposition multigrid for the lattice Wilson Dirac operator. SIAM J. Sci. Comput. 36, A1581\u2013A1608 (2014)","journal-title":"SIAM J. Sci. Comput."},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Hall, M., Kogge, P., Koller, J., Diniz, P., Chame, J., Draper, J., LaCoss, J., Granacki, J., Brockman, J., Srivastava, A., Athas, W., Freeh, V., Shin, J., Park, J.: Mapping irregular applications to DIVA, a PIM-based data-intensive architecture. In: ACM\/IEEE 1999 Conference on Supercomputing, pp. 57\u201357, November 1999","DOI":"10.1145\/331532.331589"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Heybrock, S., Jo\u00f3, B., Kalamkar, D.D., Smelyanskiy, M., Vaidyanathan, K., Wettig, T., Dubey, P.: Lattice QCD with domain decomposition on intel xeon phi co-processors. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC 2014), pp. 69\u201380. IEEE Press, Piscataway (2014). \n                    http:\/\/dx.doi.org\/10.1109\/SC.2014.11","DOI":"10.1109\/SC.2014.11"},{"key":"8_CR11","unstructured":"Hybrid Memory Cube Consortium: Hybrid Memory Cube Specification (2013)"},{"key":"8_CR12","unstructured":"Kang, Y., Huang, W., Yoo, S.M., Keen, D., Ge, Z., Lam, V., Pattnaik, P., Torrellas, J.: FlexRAM: toward an advanced intelligent memory system. In: International Conference on Computer Design (ICCD 1999), pp. 192\u2013201 (1999)"},{"key":"8_CR13","unstructured":"Koutsou, G., Krieg, S., Pleiter, D., Simma, H.: EIC co-design questionnaire: lattice QCD (unpublished, 2013)"},{"issue":"2\/3","key":"8_CR14","doi-asserted-by":"publisher","first-page":"17:1","DOI":"10.1147\/JRD.2015.2409732","volume":"59","author":"R Nair","year":"2015","unstructured":"Nair, R., Antao, S.F., Bertolli, C., Bose, P., Brunheroto, J.R., Chen, T., Cher, C.-Y., Costa, C.H.A., Evangelinos, C., Fleischer, B.M., Fox, T.W., Gallo, D.S., Grinberg, L., Gunnels, J.A., Jacob, A.C., Jacob, P., Jacobson, H.M., Karkhanis, T., Kim, C., Moreno, J.H., O\u2019Brien, J.K., Ohmacht, M., Park, Y., Prener, D.A., Rosenburg, B.S., Ryu, K.D., Sallenave, O., Serrano, M.J., Siegl, P.D.M., Sugavanam, K., Sura, Z.: Active memory cube: a processing-in-memory architecture for exascale systems. IBM J. Res. Dev. 59(2\/3), 17:1\u201317:14 (2015)","journal-title":"IBM J. Res. Dev."},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Nguyen, A., Satish, N., Chhugani, J., Kim, C., Dubey, P.: 3.5-d blocking optimization for stencil computations on modern cpus and gpus. In: International Conference for High Performance Computing, Networking, Storage and Analysis (SC 2010), pp. 1\u201313, November 2010","DOI":"10.1109\/SC.2010.2"},{"issue":"2","key":"8_CR16","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1109\/40.592312","volume":"17","author":"D Patterson","year":"1997","unstructured":"Patterson, D., Anderson, T., Cardwell, N., Fromm, R., Keeton, K., Kozyrakis, C., Thomas, R., Yelick, K.: A case for intelligent RAM. IEEE Micro 17(2), 34\u201344 (1997)","journal-title":"IEEE Micro"},{"issue":"5","key":"8_CR17","doi-asserted-by":"publisher","first-page":"055101","DOI":"10.1063\/1.3392774","volume":"22","author":"A Scagliarini","year":"2010","unstructured":"Scagliarini, A., Biferale, L., Sbragaglia, M., Sugiyama, K., Toschi, F.: Lattice Boltzmann methods for thermal flows: continuum limit and applications to compressible Rayleigh-Taylor systems. Phys. Fluids 22(5), 055101 (2010)","journal-title":"Phys. Fluids"},{"key":"8_CR18","unstructured":"Schifano, S.F., Tripiccione, R.: EIC co-design questionnaire: LBM (unpublished, 2013)"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Torrellas, J.: Flexram: toward an advanced intelligent memory system: a retrospective paper. In: IEEE 30th International Conference on Computer Design (ICCD 2012), pp. 3\u20134, September 2012","DOI":"10.1109\/ICCD.2012.6378607"},{"key":"8_CR20","unstructured":"Williams, S., Oliker, L., Carter, J., Shalf, J.: Extracting ultra-scale lattice Boltzmann performance via hierarchical and distributed auto-tuning. In: Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis (SC 2011), pp. 55:1\u201355:12. ACM, New York (2011). \n                    http:\/\/doi.acm.org\/10.1145\/2063384.2063458"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Winter, F., Clark, M., Edwards, R., Joo, B.: A framework for lattice QCD calculations on GPUs. In: 2014 IEEE 28th International Parallel and Distributed Processing Symposium, pp. 1073\u20131082, May 2014","DOI":"10.1109\/IPDPS.2014.112"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-20119-1_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,30]],"date-time":"2019-05-30T02:45:31Z","timestamp":1559184331000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-20119-1_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319201184","9783319201191"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-20119-1_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2015]]}}}