{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T19:29:33Z","timestamp":1742930973545,"version":"3.40.3"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319751771"},{"type":"electronic","value":"9783319751788"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-75178-8_52","type":"book-chapter","created":{"date-parts":[[2018,2,7]],"date-time":"2018-02-07T07:12:27Z","timestamp":1517987547000},"page":"653-663","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Accelerating the 3-D FFT Using a\u00a0Heterogeneous FPGA Architecture"],"prefix":"10.1007","author":[{"given":"Matthew","family":"Anderson","sequence":"first","affiliation":[]},{"given":"Maciej","family":"Brodowicz","sequence":"additional","affiliation":[]},{"given":"Martin","family":"Swany","sequence":"additional","affiliation":[]},{"given":"Thomas","family":"Sterling","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,2,8]]},"reference":[{"key":"52_CR1","unstructured":"Charm++. http:\/\/charm.cs.illinois.edu\/research\/charm\/"},{"key":"52_CR2","unstructured":"Datavortex. http:\/\/www.datavortex.com\/"},{"key":"52_CR3","unstructured":"HPX. http:\/\/stellar.cct.lsu.edu\/tag\/hpx\/"},{"key":"52_CR4","unstructured":"HPX-5. http:\/\/hpx.crest.iu.edu"},{"key":"52_CR5","unstructured":"Hydrodynamics Challenge Problem. Technical report LLNL-TR-490254, Lawrence Livermore National Laboratory"},{"key":"52_CR6","unstructured":"Legion programming system. http:\/\/legion.stanford.edu\/"},{"key":"52_CR7","unstructured":"Open Community Runtime. https:\/\/01.org\/open-community-runtime"},{"key":"52_CR8","unstructured":"Qthreads. http:\/\/www.cs.sandia.gov\/qthreads\/"},{"key":"52_CR9","unstructured":"Stream benchmark. https:\/\/www.cs.virginia.edu\/stream\/"},{"key":"52_CR10","unstructured":"X10. http:\/\/x10-lang.org\/"},{"key":"52_CR11","unstructured":"Alpha data (2016). www.alpha-data.com"},{"key":"52_CR12","unstructured":"Bittware (2016). www.bittware.com"},{"key":"52_CR13","unstructured":"FFTW (2016). www.fftw.org"},{"key":"52_CR14","unstructured":"GROMACS (2016). www.gromacs.org"},{"key":"52_CR15","unstructured":"NAS parallel benchmarks (2016). https:\/\/www.nas.nasa.gov\/publications\/npb.html"},{"key":"52_CR16","unstructured":"NetFPGA project (2016). netfpga.org"},{"key":"52_CR17","unstructured":"VASP (2017). www.vasp.at"},{"key":"52_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1007\/978-3-319-10214-6_7","volume-title":"High Performance Computing Systems. Performance Modeling, Benchmarking and Simulation","author":"M Anderson","year":"2014","unstructured":"Anderson, M., Brodowicz, M., Kulkarni, A., Sterling, T.: Performance modeling of gyrokinetic toroidal simulations for a many-tasking runtime system. In: Jarvis, S.A., Wright, S.A., Hammond, S.D. (eds.) PMBS 2013. LNCS, vol. 8551, pp. 136\u2013157. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10214-6_7"},{"key":"52_CR19","doi-asserted-by":"publisher","unstructured":"Deniziak, S., Tomaszewski, R.: Contention-avoiding custom topology generation for network-on-chip. In: Proceedings of the 2009 12th International Symposium on Design and Diagnostics of Electronic Circuits and Systems, DDECS 2009, pp. 234\u2013237. IEEE Computer Society, Washington, DC, USA (2009). https:\/\/doi.org\/10.1109\/DDECS.2009.5012136","DOI":"10.1109\/DDECS.2009.5012136"},{"key":"52_CR20","unstructured":"Dongarra, J.: Performance of various computers using standard linear equations software. Technical report CS-89-85, University of Tennesse Computer Science (2014). http:\/\/www.netlib.org\/benchmark\/performance.pdf"},{"key":"52_CR21","unstructured":"Hendry, G., Rodrigues, A.: SST: a simulator for exascale co-design. In: Proceedings of the ASCR\/ASC Exascale Research Conference (2012)"},{"key":"52_CR22","unstructured":"Hoefler, T.: Seventh green graph 500 list (2016). http:\/\/green.graph500.org\/"},{"key":"52_CR23","doi-asserted-by":"crossref","unstructured":"Imam, S., Sarkar, V.: Habanero-Java library: a Java 8 framework for multicore programming. In: 11th International Conference on the Principles and Practice of Programming on the Java Platform: Virtual Machines, Languages, and Tools (PPPJ 2014), September 2014","DOI":"10.1145\/2647508.2647514"},{"key":"52_CR24","doi-asserted-by":"crossref","unstructured":"Kim, J., Dally, W.J., Scott, S., Abts, D.: Technology-driven, highly-scalable Dragonfly topology. In: Proceedings of the 35th International Symposium on Compute Architecture, ISCA 2008. IEEE (2008)","DOI":"10.1109\/ISCA.2008.19"},{"key":"52_CR25","doi-asserted-by":"crossref","unstructured":"Kumar, V., Zheng, Y., Cave, V., Budimlic, Z., Sarkar, V.: HabaneroUPC++: a compiler-free PGAS library. In: 8th International Conference on Partitioned Global Address Space Programming Models (PGAS14), October 2014","DOI":"10.1145\/2676870.2676879"},{"key":"52_CR26","doi-asserted-by":"crossref","unstructured":"Leber, C., Geib, B., Litz, H.: High frequency trading acceleration using FPGAs. In: 2011 21st International Conference on Field Programmable Logic and Applications, pp. 317\u2013322, September 2011","DOI":"10.1109\/FPL.2011.64"},{"key":"52_CR27","doi-asserted-by":"crossref","unstructured":"Leon, E., Karlin, I., Grant, R.: Optimizing explicit hydrodynamics for power, energy, and performance. In: 2015 IEEE International Conference on Cluster Computing (CLUSTER), pp. 11\u201321, September 2015","DOI":"10.1109\/CLUSTER.2015.12"},{"key":"52_CR28","doi-asserted-by":"crossref","unstructured":"Lockwood, J., Gupte, A., Mehta, N., Vissers, K.A.: A low-latency library in FPGA hardware for high-frequency trading. In: IEEE 20th Annual Symposium on High-Performance Interconnects, pp. 9\u201316, August 2012","DOI":"10.1109\/HOTI.2012.15"},{"key":"52_CR29","doi-asserted-by":"crossref","unstructured":"Majeti, D., Sarkar, V.: Heterogeneous Habanero-C (H2C): a portable programming model for heterogeneous processors. In: Programming Models, Languages and Compilers for Manycore and Heterogeneous Architectures (PLC), May 2015","DOI":"10.1109\/IPDPSW.2015.81"},{"key":"52_CR30","unstructured":"Nelson, J., Holt, B., Myers, B., Briggs, P., Ceze, L., Kahan, S., Oskin, M.: Grappa: a latency-tolerant runtime for large-scale irregular applications. In: International Workshop on Rack-Scale Computing (WRSC w\/EuroSys), April 2014"},{"key":"52_CR31","doi-asserted-by":"publisher","first-page":"1781","DOI":"10.1002\/jcc.20289","volume":"26","author":"JC Phillips","year":"2005","unstructured":"Phillips, J.C., Braun, R., Wang, W., Gumbart, J., Tajkhorshid, E., Villa, E., Chipot, C., Skeel, R.D., Kale, L., Schulten, K.: Scalable molecular dynamics with NAMD. J. Comput. Chem. 26, 1781\u20131802 (2005)","journal-title":"J. Comput. Chem."},{"key":"52_CR32","unstructured":"Reed, C.: Means and apparatus for a scaleable congestion free switching system with intelligent control III, US Patent 7835278, November 2010"},{"key":"52_CR33","unstructured":"Sarkar, V.: Habanero-Scala: Async-finish programming in Scala. In: The Third Scala Workshop (Scala Days 2012), April 2012"},{"key":"52_CR34","doi-asserted-by":"publisher","unstructured":"Treichler, S., Bauer, M., Aiken, A.: Realm: an event-based low-level runtime for distributed memory architectures. In: Proceedings of the 23rd International Conference on Parallel Architectures and Compilation, PACT 2014, pp. 263\u2013276. ACM, New York, NY, USA (2014). https:\/\/doi.org\/10.1145\/2628071.2628084","DOI":"10.1145\/2628071.2628084"},{"key":"52_CR35","doi-asserted-by":"publisher","first-page":"8577","DOI":"10.1063\/1.470117","volume":"103","author":"U Essmann","year":"1995","unstructured":"Essmann, U., Perera, L., Berkowitz, M.L., Darden, T., Lee, H., Pedersen, L.G.: A smooth particle mesh Ewald method. J. Chem. Phys. 103, 8577\u20138593 (1995)","journal-title":"J. Chem. Phys."},{"key":"52_CR36","doi-asserted-by":"publisher","unstructured":"Zhao, J., Zhou, Q., Cai, Y.: Fast congestion-aware timing-driven placement for island FPGA. In: Proceedings of the 2009 12th International Symposium on Design and Diagnostics of Electronic Circuits and Systems, DDECS 2009, pp. 24\u201327. IEEE Computer Society, Washington, DC, USA (2009). https:\/\/doi.org\/10.1109\/DDECS.2009.5012092","DOI":"10.1109\/DDECS.2009.5012092"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2017: Parallel Processing Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-75178-8_52","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,8]],"date-time":"2022-02-08T01:08:33Z","timestamp":1644282513000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-75178-8_52"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319751771","9783319751788"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-75178-8_52","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"8 February 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Euro-Par","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Santiago de Compostela","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2017","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2017","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 September 2017","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2017","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/europar2017.usc.es","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}