{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T16:02:19Z","timestamp":1780675339095,"version":"3.54.1"},"reference-count":202,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T00:00:00Z","timestamp":1541030400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"},{"start":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T00:00:00Z","timestamp":1541030400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"funder":[{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["FA8750-12-2-0291"],"award-info":[{"award-number":["FA8750-12-2-0291"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["FA8750-16-2-0033"],"award-info":[{"award-number":["FA8750-16-2-0033"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["HR0011-13-2-0007"],"award-info":[{"award-number":["HR0011-13-2-0007"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"name":"DOI","award":["NBCH1050009"],"award-info":[{"award-number":["NBCH1050009"]}]},{"name":"ARO","award":["W911NF0710416"],"award-info":[{"award-number":["W911NF0710416"]}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["0325687"],"award-info":[{"award-number":["0325687"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["0702386"],"award-info":[{"award-number":["0702386"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["0931987"],"award-info":[{"award-number":["0931987"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N000141110112"],"award-info":[{"award-number":["N000141110112"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100002418","name":"Intel","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100002418","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100007065","name":"Nvidia","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007065","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Mercury"},{"DOI":"10.13039\/100000005","name":"U.S. Department of Defense","doi-asserted-by":"publisher","award":["FA8702-15-D-0002"],"award-info":[{"award-number":["FA8702-15-D-0002"]}],"id":[{"id":"10.13039\/100000005","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100008047","name":"Carnegie Mellon University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100008047","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. IEEE"],"published-print":{"date-parts":[[2018,11]]},"DOI":"10.1109\/jproc.2018.2873289","type":"journal-article","created":{"date-parts":[[2018,10,26]],"date-time":"2018-10-26T19:41:46Z","timestamp":1540582906000},"page":"1935-1968","source":"Crossref","is-referenced-by-count":87,"title":["SPIRAL: Extreme Performance Portability"],"prefix":"10.1109","volume":"106","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3529-8973","authenticated-orcid":false,"given":"Franz","family":"Franchetti","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tze Meng","family":"Low","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Doru Thom","family":"Popovici","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Richard M.","family":"Veras","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1411-7069","authenticated-orcid":false,"given":"Daniele G.","family":"Spampinato","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeremy R.","family":"Johnson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8834-8551","authenticated-orcid":false,"given":"Markus","family":"Puschel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9302-5287","authenticated-orcid":false,"given":"James C.","family":"Hoe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9822-8294","authenticated-orcid":false,"given":"Jose M. F.","family":"Moura","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref170","first-page":"169","author":"gordon","year":"2000","journal-title":"From LCF to HOL A short history"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719918"},{"key":"ref171","author":"kabacoff","year":"2010","journal-title":"R in Action"},{"key":"ref174","author":"carrara","year":"1995","journal-title":"Spotlight Synthetic Aperture Radar Signal Processing Algorithms"},{"key":"ref173","article-title":"Implementation of polar format SAR image formation on the IBM cell broadband engine","author":"rudin","year":"2007","journal-title":"High Performance Embedded Computing (HPEC)"},{"key":"ref176","first-page":"63","article-title":"A comparison of empirical and model-driven optimization","volume":"93","author":"yotov","year":"2005","journal-title":"Proc IEEE"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1109\/SFFCS.1999.814600"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1145\/2847263.2847277"},{"key":"ref177","doi-asserted-by":"crossref","first-page":"10:1","DOI":"10.1145\/1502793.1502799","article-title":"Permuting streaming data using RAMs","volume":"56","author":"p\u00fcschel","year":"2009","journal-title":"J ACM"},{"key":"ref168","author":"wolfram","year":"2003","journal-title":"The Mathematica Book"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898717952"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/1995896.1995938"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1542275.1542285"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/1837210.1837235"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2007.896116"},{"key":"ref31","article-title":"Adaptive mapping of linear DSP algorithms to fixed-point arithmetic","author":"chang","year":"2004","journal-title":"High Performance Embedded Computing (HPEC)"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2018.00048"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-69338-3_14"},{"key":"ref36","article-title":"Automatic generation of FFT libraries for GPUs","author":"angelopoulos","year":"2012","journal-title":"GPU Technical Conference NVidia Research Summit"},{"key":"ref35","first-page":"1","article-title":"Program generation with Spiral: Beyond transforms","author":"franchetti","year":"2008","journal-title":"High Performance Embedded Computing (HPEC)"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2008.4536398"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1145\/1117201.1117232"},{"key":"ref180","article-title":"Random walk SAT solver: Program generation and autotuning","author":"cui","year":"2010","journal-title":"Proc The Sixth Int Workshop Autom Perform Tuning (iWAPT)"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907342"},{"key":"ref184","article-title":"Optimizing FFT resource efficiency on FPGA using high-level synthesis","author":"xu","year":"2017","journal-title":"Proc of IEEE HPEC"},{"key":"ref183","first-page":"137","article-title":"FFT compiler: From math to efficient hardware","author":"milder","year":"2007","journal-title":"Proc IEEE Int High Level Design Validation Test Workshop (HLDVT)"},{"key":"ref182","article-title":"Discrete Fourier transform compiler: From mathematical representation to efficient hardware","author":"milder","year":"2007"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1145\/1188455.1188677"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2011.04.238"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2012.6408675"},{"key":"ref186","first-page":"171","article-title":"KeYmaera: A hybrid theorem prover for hybrid systems","author":"platzer","year":"2008","journal-title":"Proc IJCAR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2581122.2544155"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4959642"},{"key":"ref179","first-page":"887","article-title":"Learning to construct fast signal processing implementations","volume":"3","author":"singer","year":"2002","journal-title":"J Mach Learn Res"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2017.8091024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2009.934155"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2003.1213153"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2002.1015494"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2004.840491"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1202422"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-78791-4_8"},{"key":"ref25","first-page":"363","article-title":"A rewriting system for the vectorization of signal transforms","volume":"4395","author":"franchetti","year":"2006","journal-title":"High Performance Computing for Computational Science"},{"key":"ref50","article-title":"Automatic generation of 3-D FFTs","author":"duff","year":"2014","journal-title":"Rice Oil & Gas HPC Workshop"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366161"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807627"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1080\/17445760902758560"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1145\/2499370.2462176"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1145\/2491956.2462176"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-38718-0_33"},{"key":"ref152","author":"walter","year":"0","journal-title":"uBLAS"},{"key":"ref151","author":"guennebaud","year":"2017","journal-title":"Eigen"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/ICCSA.2011.41"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1145\/504210.504213"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1145\/1055531.1055532"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-38718-0_34"},{"key":"ref59","first-page":"1","article-title":"Computer generation of platform-adapted physical layer software","author":"voronenko","year":"2010","journal-title":"Proc Software Defined Radio (SDR) Tech Conf"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-11515-8_26"},{"key":"ref57","article-title":"Generation of a fast JPEG 2000 encoder using SPIRAL","author":"shen","year":"2008"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1117\/12.818399"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-79980-1_30"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-03034-5_18"},{"key":"ref53","article-title":"Automatic implementation and platform adaptation of discrete filtering and wavelet algorithms","author":"ga?i?","year":"2004"},{"key":"ref52","first-page":"541","article-title":"Fast automatic software implementations of FIR filters","volume":"2","author":"ga?i?","year":"2003","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process (ICASSP)"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/1065579.1065703"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45470-5_29"},{"key":"ref166","author":"monagan","year":"2005","journal-title":"Maple 10 Programming Guide"},{"key":"ref165","author":"abadi","year":"2015","journal-title":"TensorFlow Large-Scale"},{"key":"ref164","article-title":"Theano: A Python framework for fast computation of mathematical expressions","author":"al-rfou","year":"2016"},{"key":"ref163","doi-asserted-by":"crossref","DOI":"10.1145\/2647868.2654889","article-title":"Caffe: Convolutional architecture for fast feature embedding","author":"jia","year":"2014"},{"key":"ref162","author":"field","year":"1988","journal-title":"Functional Programming"},{"key":"ref161","author":"nilsson","year":"1995","journal-title":"Logic Programming and Prolog"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1016\/B978-044450813-3\/50011-4"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.5479\/sil.52126.39088015628399"},{"key":"ref3","article-title":"Fangcheng","year":"0","journal-title":"The Nine Chapters on the Mathematical Art"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1090\/S0025-5718-1965-0178586-1"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/BF00348431"},{"key":"ref8","year":"0","journal-title":"Product Specification Processors"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-00768-2_13"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611970999"},{"key":"ref49","first-page":"187","article-title":"Automatic generation of the HPC challenge’s global FFT benchmark for BlueGene\/P","author":"franchetti","year":"2012","journal-title":"Proc High Perform Comput Comput Sci"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1145\/3133901"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/BF01189337"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1145\/1064978.1065045"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/2159542.2159547"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495517"},{"key":"ref48","first-page":"45","article-title":"Large-scale electronic structure calculations of high-Z metals on the bluegene\/L platform","author":"gygi","year":"2006","journal-title":"Proc ACM\/IEEE Conf Supercomputing (SC)"},{"key":"ref47","doi-asserted-by":"crossref","first-page":"818","DOI":"10.1007\/11946441_74","article-title":"Automatic performance optimization of the discrete Fourier transform on distributed memory computers","volume":"4330","author":"bonelli","year":"2006","journal-title":"Proceedings of the International Symposium on Parallel and Distributed Processing and Applications"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/1391469.1391572"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2007.58"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/DATE.2009.5090831"},{"key":"ref43","article-title":"Linear transforms: From math to efficient hardware","author":"milder","year":"2008","journal-title":"Proc Workshop High-Level"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2014.7040954"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/2491956.2462187"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/2464996.2467268"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2010.5470479"},{"key":"ref76","year":"2018","journal-title":"Developer Guide for Intel Integrated Performance Primitives (Intel IPP)"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/s10766-007-0037-2"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/HASE.2017.28"},{"key":"ref75","year":"2018","journal-title":"Intel Math Kernel Library Developer Guide"},{"key":"ref78","year":"0","journal-title":"OpenSAL"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/2517208.2517228"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5946826"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/2854038.2854060"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2015.112"},{"key":"ref63","first-page":"327","article-title":"Program generation for small-scale linear algebra applications","author":"spampinato","year":"2018","journal-title":"Proc Int Symp Code Generation Optimization (CGO)"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.4105"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2016.2643244"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2009.11"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2002.800394"},{"key":"ref68","first-page":"887","article-title":"Learning to construct fast signal processing implementations","volume":"3","author":"singer","year":"2002","journal-title":"J Mach Learn Res"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553468"},{"key":"ref197","article-title":"Automatic generation of adaptive libraries for matrix-multiplication","author":"de mesmay","year":"2008","journal-title":"Proc Parallel Matrix Algorithms Appl (PMAA)"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2016.7761646"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2017.8091046"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1967.1054010"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2006.1657823"},{"key":"ref195","author":"karn","year":"2007","journal-title":"DSP & FEC library version 3 0 1"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2015.7322445"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1145\/1836543.1836554"},{"key":"ref94","doi-asserted-by":"crossref","first-page":"14:1","DOI":"10.1145\/2764454","article-title":"BLIS: A framework for rapidly instantiating BLAS functionality","volume":"41","author":"van zee","year":"2015","journal-title":"ACM Trans Math Softw"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1063\/1.1839852"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719604"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2014.09.019"},{"key":"ref92","author":"goto","year":"2008","journal-title":"Gotoblas 1 26"},{"key":"ref192","article-title":"Implementation of polar format SAR image formation on the IBM cell broadband engine","author":"rudin","year":"2007","journal-title":"High Performance Embedded Computing (HPEC)"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1145\/77626.79170"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1145\/42288.42291"},{"key":"ref98","first-page":"1","article-title":"PLuTo: A practical and fully automatic polyhedral program optimization system","author":"bondhugula","year":"2008","journal-title":"Proc of the ACM SIGPLAN Conf on Prog Lang Design and Implementation (PLDI)"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1142\/S0129626412500107"},{"key":"ref96","article-title":"CHiLL: A framework for composing high-level loop transformations","author":"chen","year":"2008"},{"key":"ref97","article-title":"R-Stream compiler","author":"meister","year":"2011","journal-title":"Encyclopedia of Parallel Computing"},{"key":"ref82","first-page":"162","article-title":"Programming for locality and parallelism with hierarchically tiled arrays","author":"almasi","year":"2003","journal-title":"Proc 16th Int Workshop Lang Compil Parallel Comput (LCPC)"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1145\/3136040.3136056"},{"key":"ref84","year":"1997","journal-title":"GAP Groups Algorithms and Programming"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/1122971.1122981"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/3136040.3136060"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1145\/355841.355847"},{"key":"ref85","article-title":"FFTX and SpectralPack: A first look","author":"franchetti","year":"2018","journal-title":"Proc PFFT Workshop HiPC"},{"key":"ref86","year":"2009","journal-title":"AMD Core Math Library"},{"key":"ref87","year":"2009","journal-title":"Cray Scientific Libraries"},{"key":"ref88","year":"2003","journal-title":"Engineering and Scientific Subroutine Library for AIX Version 4 Release 2"},{"key":"ref200","year":"2009","journal-title":"The Coq Proof Assistant Reference Manual"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1145\/2400682.2400713"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1145\/2925426.2926286"},{"key":"ref201","article-title":"Reasoning about sparse vectors for loops code generation","author":"zaliva","year":"2017","journal-title":"Proc ICFP Student Res Competition"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1145\/3264738.3264739"},{"key":"ref127","author":"czarnecki","year":"2000","journal-title":"Generative Programming Methods Tools and Applications"},{"key":"ref126","year":"0","journal-title":"ACM Conference on Generative Programming and Component Engineering"},{"key":"ref125","doi-asserted-by":"crossref","DOI":"10.1109\/JPROC.2018.2870284","article-title":"Japanese auto-tuning research: Auto-tuning languages and FFT","volume":"106","author":"katagiri","year":"2018","journal-title":"Proc IEEE"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2009.5161004"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2002.1114997"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1145\/505145.505147"},{"key":"ref130","article-title":"Mechanizing the development of software","author":"smith","year":"1999","journal-title":"Calculational System Design"},{"key":"ref133","author":"hudak","year":"1997","journal-title":"Domain Specific Languages"},{"key":"ref134","article-title":"Domain-specific languages","author":"taha","year":"2008","journal-title":"Proc Int Conf Comput Eng Syst (ICCES)"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1145\/989293.989301"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1145\/6424.315691"},{"key":"ref136","article-title":"SEJITS: Getting productivity and performance with selective embedded JIT specialization","author":"catanzaro","year":"2010"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-25935-0_4"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1145\/2184319.2184345"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1145\/2584665"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1145\/2491956.2462166"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2915244"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3196893"},{"key":"ref142","first-page":"100","article-title":"High performance stencil code generation with Lift","author":"hagedorn","year":"2018","journal-title":"Proc Int Symp Code Generation Optimization (CGO)"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2008.4536183"},{"key":"ref2","year":"0","journal-title":"Elements"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1145\/2629698"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2004.840306"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23568-9_12"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1145\/289918.289920"},{"key":"ref108","article-title":"UPC language specifications, V1.2","year":"2005","journal-title":"Tech Rep LBNL-59208"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1145\/1094811.1094852"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1177\/1094342007078442"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1145\/1238844.1238851"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8191(99)00074-5"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1145\/1048935.1050201"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1145\/331963.331970"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2006.55"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1145\/1542275.1542301"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1145\/1353445.1353451"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/BF00127843"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsc.2002.06.001"},{"key":"ref12","article-title":"Spiral: Automatic implementation of signal processing algorithms","author":"moura","year":"2000","journal-title":"Proc Conf High Perform Extreme Comput (HPEC)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/378795.378860"},{"key":"ref14","first-page":"97","article-title":"Fast automatic generation of DSP algorithms","author":"p\u00fcschel","year":"2001","journal-title":"Proc Int Conf Comput Sci (ICCS)"},{"key":"ref15","author":"p\u00fcschel","year":"2011","journal-title":"Encyclopedia of Parallel Computing"},{"key":"ref16","article-title":"The landscape of parallel computing research: A view from Berkeley","author":"asanovic","year":"2006"},{"key":"ref118","article-title":"Automatically tuned linear algebra software (ATLAS)","author":"whaley","year":"1998","journal-title":"Proc Supercomput"},{"key":"ref17","first-page":"315","article-title":"Loop merging for signal transforms","author":"franchetti","year":"2005","journal-title":"Proc Program Lang Design Implement (PLDI)"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2004.840301"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2009.33"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2006.31"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8191(00)00087-9"},{"key":"ref114","first-page":"1","article-title":"MILEPOST GCC: Machine learning based research compiler","author":"fursin","year":"2008","journal-title":"GCC Summit Proceedings"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2004.1342537"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1145\/301618.301661"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1145\/1862876.1862877"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1177\/1094342004041296"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2004.840848"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2004.840311"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2002.10062"}],"container-title":["Proceedings of the IEEE"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielaam\/5\/8510998\/8510983-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5\/8510998\/08510983.pdf?arnumber=8510983","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T18:55:55Z","timestamp":1649444155000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8510983\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11]]},"references-count":202,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/jproc.2018.2873289","relation":{},"ISSN":["0018-9219","1558-2256"],"issn-type":[{"value":"0018-9219","type":"print"},{"value":"1558-2256","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,11]]}}}