{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T07:24:52Z","timestamp":1768029892481,"version":"3.49.0"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319676296","type":"print"},{"value":"9783319676302","type":"electronic"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"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\/978-3-319-67630-2_29","type":"book-chapter","created":{"date-parts":[[2017,10,19]],"date-time":"2017-10-19T00:33:17Z","timestamp":1508373197000},"page":"389-403","source":"Crossref","is-referenced-by-count":3,"title":["KART \u2013 A Runtime Compilation Library for Improving HPC Application Performance"],"prefix":"10.1007","author":[{"given":"Matthias","family":"Noack","sequence":"first","affiliation":[]},{"given":"Florian","family":"Wende","sequence":"additional","affiliation":[]},{"given":"Georg","family":"Zitzlsberger","sequence":"additional","affiliation":[]},{"given":"Michael","family":"Klemm","sequence":"additional","affiliation":[]},{"given":"Thomas","family":"Steinke","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,10,20]]},"reference":[{"key":"29_CR1","unstructured":"OpenMP Compilers, September 2016. \nhttp:\/\/openmp.org\/wp\/openmp-compilers\/"},{"key":"29_CR2","unstructured":"OpenMP\u00ae: Support for the OpenMP language, April 2016. \nhttp:\/\/openmp.llvm.org\/"},{"key":"29_CR3","unstructured":"Bezanson, J., Edelman, A., Karpinski, S., Shah, V.B.: Julia: a fresh approach to numerical computing, November 2014"},{"key":"29_CR4","unstructured":"Bezanson, J., Karpinski, S., Shah, V.B., Edelman, A.: Julia: a fast dynamic language for technical computing. \nhttp:\/\/julialang.org"},{"key":"29_CR5","unstructured":"Heinecke, A., Henry, G., Hutchinson, M., Pabst, H.: LIBXSMM: accelerating small matrix multiplications by runtime code generation. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 84:1\u201384:11, SC 2016. IEEE Press, Piscataway (2016). \nhttp:\/\/dl.acm.org\/citation.cfm?id=3014904.3015017"},{"key":"29_CR6","series-title":"Lecture Notes in Computer Science","volume-title":"Parallel Processing Workshops, Euro-Par 2011","author":"A Heinecke","year":"2011","unstructured":"Heinecke, A., Klemm, M., Pfl\u00fcger, D., Bode, A., Bungartz, H.J.: Extending a highly parallel data mining algorithm to the Intel\n            $$^{\\textregistered }$$\n           many integrated core architecture. In: Alexander, M., et al. (eds.) Parallel Processing Workshops, Euro-Par 2011. LNCS, vol. 7156. Springer, Heidelberg (2011)"},{"key":"29_CR7","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1016\/B978-0-12-803819-2.00016-1","volume-title":"High Performance Parallelism Pearls","author":"T Henderson","year":"2015","unstructured":"Henderson, T., Michalakes, J., Gokhale, I., Jha, A.: Chapter 2 - Numerical weather prediction optimization. In: Reinders, J., Jeffers, J. (eds.) High Performance Parallelism Pearls, pp. 7\u201323. Morgan Kaufmann, Boston (2015)"},{"key":"29_CR8","unstructured":"Jo\u00f3, B.: LLVM and QDP-JIT. In: iXPUG Workshop, Berkeley (2015). \nhttps:\/\/www.ixpug.org\/events\/ixpug-annual-meeting-2015"},{"key":"29_CR9","unstructured":"Khronos OpenCL Working Group: The OpenCL Specification, Version 2.2. \nhttps:\/\/www.khronos.org\/registry\/cl\/specs\/opencl-2.2.pdf"},{"issue":"9","key":"29_CR10","doi-asserted-by":"crossref","first-page":"4045","DOI":"10.1021\/ct500629s","volume":"10","author":"C Kreisbeck","year":"2014","unstructured":"Kreisbeck, C., Kramer, T., Aspuru-Guzik, A.: Scalable high-performance algorithm for the simulation of exciton dynamics. Application to the light-harvesting Complex II in the presence of resonant vibrational modes. J. Chem. Theory Comput. 10(9), 4045\u20134054 (2014). pMID: 26588548. \nhttp:\/\/dx.doi.org\/10.1021\/ct500629s","journal-title":"J. Chem. Theory Comput."},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Lattner, C., Adve, V.: LLVM: a compilation framework for lifelong program analysis and transformation. In: CGO, pp. 75\u201388, San Jose, CA, USA, March 2004. \nllvm.org","DOI":"10.1109\/CGO.2004.1281665"},{"issue":"2","key":"29_CR12","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1145\/1365490.1365500","volume":"6","author":"J Nickolls","year":"2008","unstructured":"Nickolls, J., Buck, I., Garland, M., Skadron, K.: Scalable parallel programming with CUDA. Queue 6(2), 40\u201353 (2008). \nhttp:\/\/doi.acm.org\/10.1145\/1365490.1365500","journal-title":"Queue"},{"key":"29_CR13","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1016\/B978-0-12-803819-2.00001-X","volume-title":"High Performance Parallelism Pearls","author":"M Noack","year":"2015","unstructured":"Noack, M., Wende, F., Oertel, K.D.: Chapter 19 - OpenCL: there and back again. In: Reinders, J., Jeffers, J. (eds.) High Performance Parallelism Pearls, pp. 355\u2013378. Morgan Kaufmann, Boston (2015)"},{"key":"29_CR14","doi-asserted-by":"crossref","unstructured":"Noack, M., Wende, F., Steinke, T., Cordes, F.: A unified programming model for intra- and inter-node offloading on xeon phi clusters. In: International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2014, New Orleans, LA, USA, 16\u201321 November 2014, pp. 203\u2013214 (2014). \nhttp:\/\/dx.doi.org\/10.1109\/SC.2014.22","DOI":"10.1109\/SC.2014.22"},{"key":"29_CR15","unstructured":"NVIDIA: NVRTC - CUDA Runtime Compilation User Guide. \nhttp:\/\/docs.nvidia.com\/cuda\/pdf\/NVRTC_User_Guide.pdf"},{"key":"29_CR16","unstructured":"OpenMP Architecture Review Board: OpenMP Application Program Interface, Version 4.5 (2015). \nhttp:\/\/www.openmp.org\/"},{"key":"29_CR17","volume-title":"The Boost C++ Libraries","author":"B Schling","year":"2011","unstructured":"Schling, B.: The Boost C++ Libraries. XML Press, Fort Collins (2011)"},{"key":"29_CR18","doi-asserted-by":"crossref","unstructured":"Schneider, T., Kjolstad, F., Hoefler, T.: MPI datatype processing using runtime compilation. In: Proceedings of the 20th European MPI Users\u2019 Group Meeting, pp. 19\u201324. ACM, September 2013","DOI":"10.1145\/2488551.2488552"},{"key":"29_CR19","unstructured":"Siso, S.: DL_MESO Code Modernization. Intel Xeon Phi Users Group (IXPUG). IXPUG Workshop, Ostrava, March 2016"},{"key":"29_CR20","doi-asserted-by":"crossref","unstructured":"Winter, F.T., Clark, M.A., Edwards, R.G., Jo\u00f3, B.: A framework for lattice QCD calculations on GPUs. In: Proceedings of the 2014 IEEE 28th International Parallel and Distributed Processing Symposium, pp. 1073\u20131082, IPDPS 2014 (2014). \nhttp:\/\/dx.doi.org\/10.1109\/IPDPS.2014.112","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\/978-3-319-67630-2_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,1,5]],"date-time":"2018-01-05T20:00:34Z","timestamp":1515182434000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-67630-2_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319676296","9783319676302"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-67630-2_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017]]}}}