{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T07:09:56Z","timestamp":1768028996667,"version":"3.49.0"},"reference-count":124,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2016,2,1]],"date-time":"2016-02-01T00:00:00Z","timestamp":1454284800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100002924","name":"FEDER project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002924","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2016,2,1]]},"DOI":"10.1109\/tpds.2015.2407896","type":"journal-article","created":{"date-parts":[[2015,2,27]],"date-time":"2015-02-27T14:28:43Z","timestamp":1425047323000},"page":"600-612","source":"Crossref","is-referenced-by-count":34,"title":["Suitability Analysis of FPGAs for Heterogeneous Platforms in HPC"],"prefix":"10.1109","volume":"27","author":[{"given":"Fernando A.","family":"Escobar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Chang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carlos","family":"Valderrama","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2554688.2554785"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2011.08.003"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1137\/S00361445003820"},{"key":"ref32","article-title":"Block krylov space methods for linear systems with multiple right-hand sides: An introduction","year":"2006"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1007\/978-3-642-36812-7_14","article-title":"Performance modeling of pipelined linear algebra architectures on fpgas","volume":"7806","author":"skalicky","year":"0","journal-title":"Proc Reconfigurable Comput Architectures Tools Appl"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2012.03.001"},{"key":"ref37","article-title":"SuperLU users’ guide","year":"1999"},{"key":"ref36","article-title":"Communication-avoiding Krylov subspace methods","year":"2010"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-012-0825-3"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.5402\/2012\/127647"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2010.278"},{"key":"ref27","article-title":"Avoiding communication in dense linear algebra","year":"2013"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.micpro.2012.06.008"},{"key":"ref20","first-page":"35","article-title":"Fcuda: Enabling efficient compilation of cuda kernels onto FPGAS","year":"0","journal-title":"Proc IEEE 7th Symp Appl Specific Process"},{"key":"ref22","first-page":"288","article-title":"BLAS comparison on FPGA, CPU and GPU","year":"2010"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/DATE.2012.6176720"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2004.21"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s00450-011-0191-z"},{"key":"ref101","article-title":"Parallel heterogeneous branch and bound algorithms for multi-core and multi-gpu environments","year":"2013"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2381056.2381076"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.2007.4429974"},{"key":"ref25","first-page":"8","article-title":"Adaptive Strassen and Atlas's dgemm: A fast square-matrix multiply for modern high-performance systems","year":"0","journal-title":"Proc 8th Int Conf High-Perform Comput Asia-Pacific Region"},{"key":"ref50","first-page":"58:1","article-title":"A massively parallel adaptive fast-multipole method on heterogeneous architectures","year":"0","journal-title":"Proc Conf High Perform Comput Netw Storage Anal"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40047-6_57"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/2554688.2554774"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-1791-0_4"},{"key":"ref57","first-page":"447","article-title":"A comparative study on asic, FPGAS, GPUs and general purpose processors in the o(n2) gravitational n-body simulation","year":"0","journal-title":"Proc NASA\/ESA Conf Adaptive Hardware Syst"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CSE.2010.25"},{"key":"ref55","first-page":"5:1","article-title":"4.45 pflops astrophysical n-body simulation on k computer: The gravitational trillion-body problem","year":"0","journal-title":"Proc Int Conf High Perform Comput Netw Storage Anal"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1177\/1094342011429952"},{"key":"ref53","first-page":"36","article-title":"Scalable fast multipole methods on distributed heterogeneous architectures","year":"0","journal-title":"Proc Int Conf High Perform Comput Netw Storage Anal"},{"key":"ref52","first-page":"4","article-title":"Highly portable and efficient implementations of parallel adaptive n-body methods","year":"0","journal-title":"Proc Supercomput Conf"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2014.6"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1155\/2012\/241439"},{"key":"ref3","first-page":"50","article-title":"Achieving high performance with FPGA-based computing","year":"0","journal-title":"NIH Public Access"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1155\/2012\/439141"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1145\/1562764.1562783","article-title":"The landscape of parallel computing research: A view from berkeley","volume":"52","author":"krste","year":"2009","journal-title":"Commun ACM"},{"key":"ref8","first-page":"339","article-title":"Direct GPU\/FPGA communication via PCI express","volume":"17","year":"2013","journal-title":"Cluster Comput"},{"key":"ref49","first-page":"68","article-title":"3d FFTs on a single FPGA","year":"0","journal-title":"Proc IEEE Int Symp Field-Programm Custom Comput Mach"},{"key":"ref7","first-page":"833","article-title":"The recoblock SOC platform: A flexible array of reusable run-time-reconfigurable ip-blocks","year":"0","journal-title":"Proc Design Autom Test Eur Conf Exhib"},{"key":"ref9","first-page":"229","article-title":"Streams on wires: A query compiler for FPGAS","volume":"2","year":"0","journal-title":"Proc VLDB Endowment"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ReConFig.2010.13"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-90-481-2261-5_4"},{"key":"ref48","first-page":"92","article-title":"Accelerating 3d-fft using hard embedded blocks in FPGAS","year":"0","journal-title":"Proc 26th Int Conf VLSI Design 12th Int Conf Embedded Syst"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s11265-010-0500-y"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2012.121"},{"key":"ref41","first-page":"1:1","article-title":"A high throughput FPGA-based floating point conjugate gradient implementation for dense matrices","volume":"3","year":"2010","journal-title":"ACM Trans Reconfigurable Technol Syst"},{"key":"ref44","first-page":"1","article-title":"Spectral methods for partial differential equations","volume":"6","author":"costa","year":"2004","journal-title":"CUBO Math J"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2013.162"},{"key":"ref124","article-title":"The FPGA is half full","year":"0"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32820-6_19"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2012.6339277"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2014.07.001"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/FPGA.2002.1106658"},{"key":"ref76","article-title":"Hadoop+aparapi: Making heterogenous mapreduce programming easier","year":"2012"},{"key":"ref77","first-page":"6","article-title":"An implementation of GPU accelerated mapreduce: Using hadoop with opencl for data- and compute-intensive jobs","year":"0","journal-title":"Proc Int Joint Conf Serv Sci"},{"key":"ref74","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1007\/978-3-642-32686-8_26","article-title":"Scalable mapreduce framework on FPGA accelerated commodity hardware","volume":"7469","author":"yin","year":"0","journal-title":"Internet of Things, Smart Spaces, and Next Generation Networking"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2010.158"},{"key":"ref78","first-page":"93","article-title":"Fpmr: Mapreduce framework on FPGA","year":"0","journal-title":"Proc 18th Annu ACM\/SIGDA Int Symp Field Programm Gate Arrays"},{"key":"ref79","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1007\/978-3-642-32686-8_26","article-title":"Scalable mapreduce framework on FPGA accelerated commodity hardware","volume":"7469","author":"yin","year":"0","journal-title":"Internet of Things, Smart Spaces, and Next Generation Networking"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/1723112.1723134"},{"key":"ref62","first-page":"311","article-title":"High-performance code generation for stencil computations on gpu architectures","year":"0","journal-title":"Proc 26th ACM Int Conf Supercomput"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/COMPSAC.2009.82"},{"key":"ref63","first-page":"11:1","article-title":"Physis: An implicitly parallel programming model for stencil computations on large-scale GPU-accelerated supercomputers","year":"0","journal-title":"Proc Int Conf High Perform Comput Netw Storage Anal"},{"key":"ref64","first-page":"1","article-title":"Automatic efficient data layout for multithreaded stencil codes on CPU sand GPUs","year":"0","journal-title":"Proc 19th Int Conf High Perform Comput"},{"key":"ref65","first-page":"30:1","article-title":"Understanding stencil code performance on multicore architectures","year":"0","journal-title":"Proc 8th ACM Int Conf Comput Frontiers"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/2458523.2458526"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/2641361.2641369"},{"key":"ref68","first-page":"343","article-title":"Towards a low-power accelerator of many FPGAS for stencil computations","year":"0","journal-title":"Proc 3rd Int Conf Netw Comput"},{"key":"ref2","first-page":"13","article-title":"Examining the viability of FPGA supercomputing","volume":"2007","year":"2007","journal-title":"EURASIP J Embedded Syst"},{"key":"ref69","first-page":"695","article-title":"Multi-FPGA accelerator for scalable stencil computation with constant memory bandwidth","volume":"25","year":"0","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"ref1","article-title":"Platform-based design for embedded systems","author":"carloni","year":"2005","journal-title":"Embedded Systems Handbook"},{"key":"ref109","first-page":"342","article-title":"A parallel algorithm for exact Bayesian network inference","year":"0","journal-title":"Proc Int Conf on High Perf Comput"},{"key":"ref95","first-page":"460","article-title":"Efficient nonserial polyadic dynamic programming on the cell processor","year":"0","journal-title":"Proc IEEE Int Symp Parallel Distrib Process Workshops PhD Forum"},{"key":"ref108","first-page":"323","article-title":"Fpga-accelerated Bayesian learning for reconstruction of gene regulatory networks","year":"0","journal-title":"Proc Int Conf Field Programm Logic Appl"},{"key":"ref94","first-page":"96","article-title":"Optimizing dynamic programming on graphics processing units via adaptive thread-level parallelism","year":"0","journal-title":"Proc IEEE 17th Int Parallel Distrib Syst Conf"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijar.2011.08.003"},{"key":"ref93","first-page":"452","article-title":"Automatically tuned dynamic programming with an algorithm-by-blocks","year":"0","journal-title":"Proc IEEE 16th Int Parallel Distrib Syst Conf"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44687-7_33"},{"key":"ref92","first-page":"515","article-title":"Chapter 12: Dynamic programming","author":"grama","year":"0","journal-title":"Introduction to Parallel Computing"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/FPT.2006.270325"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2014.30"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30117-2_53"},{"key":"ref90","first-page":"1","article-title":"A framework for FPGA acceleration of large graph problems: Graphlet counting case study","year":"0","journal-title":"Proc Int Conf Field-Programm Technol"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2013.178"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1287\/opre.42.6.1042"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1007\/s10766-013-0246-9"},{"key":"ref112","first-page":"73","article-title":"High-throughput bayesian computing machine with reconfigurable hardware","year":"0","journal-title":"Proc 18th Annu ACM\/SIGDA Int Symp Field Programm Gate Arrays"},{"key":"ref110","article-title":"A novel learning algorithm for Bayesian network and its efficient implementation on gpu","author":"wang","year":"0","journal-title":"CoRR"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2013.6610096"},{"key":"ref99","article-title":"High performance dynamic programming on FPGAS with opencl","year":"0","journal-title":"Proc IEEE High Perform Extreme Comput Conf"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS.2009.110"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2013.208"},{"key":"ref10","first-page":"910","article-title":"Data processing on FPGAS","volume":"2","year":"0","journal-title":"Proc VLDB Endowment"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/3PGCIC.2011.25"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-0061-5_3"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2007.4380625"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1155\/2012\/872610"},{"key":"ref15","first-page":"1","article-title":"Confetti : A reconfigurable hardware platform for prototyping cellular architectures","year":"0","journal-title":"Proc IEEE Int Int Symp Parallel Distrib Process"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2013.31"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2007.62"},{"key":"ref82","volume":"197","year":"2001","journal-title":"Advanced Encryption Standard (AES)"},{"key":"ref117","article-title":"Finding the minimal DFA of very large finite state automata with an application to token passing networks","author":"slavici","year":"0","journal-title":"CoRR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-28365-9_27"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1949.tb00928.x"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2008.80"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1016\/j.mejo.2014.05.004"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-02979-0_9"},{"key":"ref19","first-page":"51","article-title":"Cube: A 512-FPGA cluster","year":"0","journal-title":"Proc Southern Conf Programmable Logic"},{"key":"ref83","first-page":"147","article-title":"Data encryption on GPU for high-performance database systems","volume":"19","year":"0","journal-title":"Proc Journal of Computer Science"},{"key":"ref114","first-page":"5:1","article-title":"A fully pipelined FPGA architecture of a factored restricted boltzmann machine artificial neural network","volume":"7","year":"2014","journal-title":"ACM Trans Reconfigurable Technol Syst"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2013.2294137"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-36265-7_4"},{"key":"ref80","first-page":"66","article-title":"Accelerating iterative algorithms with asynchronous accumulative updates on FPGAS","year":"0","journal-title":"Proc Int Conf Field-Programm Technol"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2001.0184"},{"key":"ref120","first-page":"33","article-title":"Design and implementation of parallel hierarchical finite state machines","year":"0","journal-title":"Proc 2nd Int Conf Commun Electron"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1587\/elex.11.20130987"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2013.51"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495538"},{"key":"ref123","article-title":"Xilinx delivers the industry's first 4m logic cell device","year":"2015"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1016\/j.vlsi.2014.02.004"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2011.04.006"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/s00450-012-0207-3"},{"key":"ref88","first-page":"378","article-title":"Fast and efficient graph traversal algorithm for cpus: Maximizing single-node efficiency","year":"0","journal-title":"Proc IEEE 26th Int Parallel Distrib Process Symp"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/7383375\/7051218.pdf?arnumber=7051218","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:46:40Z","timestamp":1641988000000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7051218\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,2,1]]},"references-count":124,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2015.2407896","relation":{},"ISSN":["1045-9219"],"issn-type":[{"value":"1045-9219","type":"print"}],"subject":[],"published":{"date-parts":[[2016,2,1]]}}}