references.bib

@inproceedings{Ginsbach:2018:CDS:3178372.3179515,
 author    = {Philip Ginsbach and Lewis Crawford and Michael F. P. O'Boyle},
 title     = {{CAnDL: A Domain Specific Language for Compiler Analysis}},
 booktitle = {Proceedings of the 27th International Conference on Compiler Construction},
 series    = {CC '18},
 year      = {2018},
 isbn      = {978-1-4503-5644-2},
 location  = {Vienna, Austria},
 pages     = {151--162},
 numpages  = {12},
 url       = {http://doi.acm.org/10.1145/3178372.3179515},
 doi       = {10.1145/3178372.3179515},
 acmid     = {3179515},
 publisher = {ACM},
 address   = {New York, NY, USA},
 keywords  = {LLVM, constraint programming, optimization},
}

@inproceedings{ginsbach2017discovery,
 author    = {Philip Ginsbach and Michael F. P. O'Boyle},
 title     = {{Discovery and Exploitation of General Reductions: A Constraint Based Approach}},
 booktitle = {Proceedings of the 2017 International Symposium on Code Generation and Optimization},
 series    = {CGO '17},
 year      = {2017},
 isbn      = {978-1-5090-4931-8},
 location  = {Austin, USA},
 pages     = {269--280},
 numpages  = {12},
 url       = {http://dl.acm.org/citation.cfm?id=3049832.3049862},
 acmid     = {3049862},
 publisher = {IEEE Press},
 address   = {Piscataway, NJ, USA},
 keywords  = {compiler analysis, computational idioms, constraint solver, parallelization, reduction operations},
} 

@inproceedings{Ginsbach:2018:AML:3173162.3173182,
 author    = {Philip Ginsbach and Toomas Remmelg and Michel Steuwer and Bruno Bodin and Christophe Dubach and Michael F. P. O'Boyle},
 title     = {{Automatic Matching of Legacy Code to Heterogeneous APIs: An Idiomatic Approach}},
 booktitle = {Proceedings of the Twenty-Third International Conference on Architectural Support for Programming Languages and Operating Systems},
 series    = {ASPLOS '18},
 year      = {2018},
 isbn      = {978-1-4503-4911-6},
 location  = {Williamsburg, VA, USA},
 pages     = {139--153},
 numpages  = {15},
 url       = {http://doi.acm.org/10.1145/3173162.3173182},
 doi       = {10.1145/3173162.3173182},
 acmid     = {3173182},
 publisher = {ACM},
 address   = {New York, NY, USA},
 keywords  = {computer systems organization},
}

@article{4785860,
 author   = {G. E. {Moore}},
 journal  = {IEEE Solid-State Circuits Society Newsletter},
 title    = {Cramming more components onto integrated circuits, Reprinted from Electronics, volume 38, number 8, April 19, 1965, pp.114 ff.},
 year     = {2006},
 volume   = {11},
 number   = {3},
 pages    = {33-35},
 keywords = {Integrated circuits;Computers;Silicon;Films;Heating;Microwave amplifiers;Data mining},
 doi      = {10.1109/N-SSC.2006.4785860},
 ISSN     = {},
 month    = {Sep.}
}

@article{1050511,
 author   = {R. H. {Dennard} and F. H. {Gaensslen} and V. L. {Rideout} and E. {Bassous} and A. R. {LeBlanc}},
 journal  = {IEEE Journal of Solid-State Circuits},
 title    = {Design of ion-implanted MOSFET's with very small physical dimensions},
 year     = {1974},
 volume   = {9},
 number   = {5},
 pages    = {256-268},
 keywords = {digital integrated circuits;field effect transistors;ion implantation;semiconductor device manufacture;switching circuits;Switching circuits;Ion implantation;Semiconductor device manufacture;Digital integrated circuits;Field effect transistors;Doping profiles;Semiconductor process modeling;Predictive models;Threshold voltage;Fabrication;Switching circuits;Digital integrated circuits;MOSFET circuits;Ion implantation;Length measurement},
 doi      = {10.1109/JSSC.1974.1050511},
 ISSN     = {},
 month    = {Oct}
}

@inproceedings{Hutcheson2018Moore,
 author    = {{Hutcheson}, G.~D.},
 title     = {Moore's law, lithography, and how optics drive the semiconductor industry},
 booktitle = {Society of Photo-Optical Instrumentation Engineers (SPIE) Conference Series},
 year      = {2018},
 series    = {Society of Photo-Optical Instrumentation Engineers (SPIE) Conference Series},
 volume    = {10583},
 month     = {Mar},
 eid       = {1058303},
 pages     = {1058303},
 doi       = {10.1117/12.2308299},
 adsurl    = {https://ui.adsabs.harvard.edu/abs/2018SPIE10583E..03H},
 adsnote   = {Provided by the SAO/NASA Astrophysics Data System}
}

@inproceedings{Maleki:2011:EVC:2120965.2121464,
 author = {Maleki, Saeed and Gao, Yaoqing and Garzar\'{a}n, Maria J. and Wong, Tommy and Padua, David A.},
 title = {An Evaluation of Vectorizing Compilers},
 booktitle = {Proceedings of the 2011 International Conference on Parallel Architectures and Compilation Techniques},
 series = {PACT '11},
 year = {2011},
 isbn = {978-0-7695-4566-0},
 pages = {372--382},
 numpages = {11},
 url = {https://doi.org/10.1109/PACT.2011.68},
 doi = {10.1109/PACT.2011.68},
 acmid = {2121464},
 publisher = {IEEE Computer Society},
 address = {Washington, DC, USA},
} 

@inproceedings{Murphy2014LimitsOD,
  title     = {Limits of dependence analysis for automatic parallelization},
  booktitle = {Proceedings of the 18th International Workshop on Compilers for Parallel Computing},
  series    = {CPC 2015},
  author    = {Niall Murphy and Timothy Jones and Robert Mullins},
  year      = {2015}
}

@inproceedings{Moll:2016:ISS:2892208.2892217,
 author = {Moll, Simon and Doerfert, Johannes and Hack, Sebastian},
 title = {Input Space Splitting for OpenCL},
 booktitle = {Proceedings of the 25th International Conference on Compiler Construction},
 series = {CC 2016},
 year = {2016},
 isbn = {978-1-4503-4241-4},
 location = {Barcelona, Spain},
 pages = {251--260},
 numpages = {10},
 url = {http://doi.acm.org/10.1145/2892208.2892217},
 doi = {10.1145/2892208.2892217},
 acmid = {2892217},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {Divergence, OpenCL, Polyhedral Representation, SPMD, Vectorization},
} 

@inproceedings{Cytron:1989:AGD:73141.74823,
 author = {Cytron, R. and Hind, M. and Hsieh, W.},
 title = {Automatic Generation of DAG Parallelism},
 booktitle = {Proceedings of the ACM SIGPLAN 1989 Conference on Programming Language Design and Implementation},
 series = {PLDI '89},
 year = {1989},
 isbn = {0-89791-306-X},
 location = {Portland, Oregon, USA},
 pages = {54--68},
 numpages = {15},
 url = {http://doi.acm.org/10.1145/73141.74823},
 doi = {10.1145/73141.74823},
 acmid = {74823},
 publisher = {ACM},
 address = {New York, NY, USA},
} 

@article{Karp:1967:OCU:321406.321418,
 author = {Karp, Richard M. and Miller, Raymond E. and Winograd, Shmuel},
 title = {The Organization of Computations for Uniform Recurrence Equations},
 journal = {J. ACM},
 issue_date = {July 1967},
 volume = {14},
 number = {3},
 month = jul,
 year = {1967},
 issn = {0004-5411},
 pages = {563--590},
 numpages = {28},
 url = {http://doi.acm.org/10.1145/321406.321418},
 doi = {10.1145/321406.321418},
 acmid = {321418},
 publisher = {ACM},
 address = {New York, NY, USA},
}

@inproceedings{Cook:1971:CTP:800157.805047,
 author = {Cook, Stephen A.},
 title = {The Complexity of Theorem-proving Procedures},
 booktitle = {Proceedings of the Third Annual ACM Symposium on Theory of Computing},
 series = {STOC '71},
 year = {1971},
 location = {Shaker Heights, Ohio, USA},
 pages = {151--158},
 numpages = {8},
 url = {http://doi.acm.org/10.1145/800157.805047},
 doi = {10.1145/800157.805047},
 acmid = {805047},
 publisher = {ACM},
 address = {New York, NY, USA},
}

@book{Leeuwen:1990:HTC:574797,
 author = {Leeuwen, Jan V.},
 title = {Handbook of Theoretical Computer Science: Algorithms and Complexity},
 year = {1990},
 isbn = {0262220385},
 publisher = {MIT Press},
 address = {Cambridge, MA, USA},
} 

@inproceedings{Falch:2015:MLB:2863697.2864570,
 author = {Falch, Thomas L. and Elster, Anne C.},
 title = {Machine Learning Based Auto-Tuning for Enhanced OpenCL Performance Portability},
 booktitle = {Proceedings of the 2015 IEEE International Parallel and Distributed Processing Symposium Workshop},
 series = {IPDPSW '15},
 year = {2015},
 isbn = {978-1-4673-7684-6},
 pages = {1231--1240},
 numpages = {10},
 url = {https://doi.org/10.1109/IPDPSW.2015.85},
 doi = {10.1109/IPDPSW.2015.85},
 acmid = {2864570},
 publisher = {IEEE Computer Society},
 address = {Washington, DC, USA},
 keywords = {auto-tuning, machine learning, artificial neural networks, heterogeneous computing, OpenCL},
} 

@inproceedings{Ansel:2014:OEF:2628071.2628092,
 author = {Ansel, Jason and Kamil, Shoaib and Veeramachaneni, Kalyan and Ragan-Kelley, Jonathan and Bosboom, Jeffrey and O'Reilly, Una-May and Amarasinghe, Saman},
 title = {OpenTuner: An Extensible Framework for Program Autotuning},
 booktitle = {Proceedings of the 23rd International Conference on Parallel Architectures and Compilation},
 series = {PACT '14},
 year = {2014},
 isbn = {978-1-4503-2809-8},
 location = {Edmonton, AB, Canada},
 pages = {303--316},
 numpages = {14},
 url = {http://doi.acm.org/10.1145/2628071.2628092},
 doi = {10.1145/2628071.2628092},
 acmid = {2628092},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {autotuner, optimization},
} 

@inproceedings{Baghdadi:2019:TPC:3314872.3314896,
 author = {Baghdadi, Riyadh and Ray, Jessica and Romdhane, Malek Ben and Del Sozzo, Emanuele and Akkas, Abdurrahman and Zhang, Yunming and Suriana, Patricia and Kamil, Shoaib and Amarasinghe, Saman},
 title = {{Tiramisu: A Polyhedral Compiler for Expressing Fast and Portable Code}},
 booktitle = {Proceedings of the 2019 IEEE/ACM International Symposium on Code Generation and Optimization},
 series = {CGO 2019},
 year = {2019},
 isbn = {978-1-7281-1436-1},
 location = {Washington, DC, USA},
 pages = {193--205},
 numpages = {13},
 url = {http://dl.acm.org/citation.cfm?id=3314872.3314896},
 acmid = {3314896},
 publisher = {IEEE Press},
 address = {Piscataway, NJ, USA},
 keywords = {Code Generation, Code Optimization, Deep Learning, Distributed Systems, GPU, Polyhedral Model, Tensors},
}

@inproceedings{Spampinato:2016:BLA:2854038.2854060,
 author = {Spampinato, Daniele G. and P\"{u}schel, Markus},
 title = {A Basic Linear Algebra Compiler for Structured Matrices},
 booktitle = {Proceedings of the 2016 International Symposium on Code Generation and Optimization},
 series = {CGO '16},
 year = {2016},
 isbn = {978-1-4503-3778-6},
 location = {Barcelona, Spain},
 pages = {117--127},
 numpages = {11},
 url = {http://doi.acm.org/10.1145/2854038.2854060},
 doi = {10.1145/2854038.2854060},
 acmid = {2854060},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {Basic linear algebra, DSL, Program synthesis, SIMD vectorization, Structured matrices, Tiling},
}

@inproceedings{Zhang:2016:CTG:3018843.3018849,
 author = {Zhang, Huihui and Venkat, Anand and Hall, Mary},
 title = {Compiler Transformation to Generate Hybrid Sparse Computations},
 booktitle = {Proceedings of the Sixth Workshop on Irregular Applications: Architectures and Algorithms},
 series = {$IA^3$'16},
 year = {2016},
 isbn = {978-1-5090-3867-1},
 location = {Salt Lake City, Utah},
 pages = {34--41},
 numpages = {8},
 url = {https://doi.org/10.1109/IA3.2016.11},
 doi = {10.1109/IA3.2016.11},
 acmid = {3018849},
 publisher = {IEEE Press},
 address = {Piscataway, NJ, USA},
}

@inproceedings{Steuwer:2017:LFD:3049832.3049841,
 author = {Steuwer, Michel and Remmelg, Toomas and Dubach, Christophe},
 title = {{Lift: A Functional Data-parallel IR for High-performance GPU Code Generation}},
 booktitle = {Proceedings of the 2017 International Symposium on Code Generation and Optimization},
 series = {CGO '17},
 year = {2017},
 isbn = {978-1-5090-4931-8},
 location = {Austin, USA},
 pages = {74--85},
 numpages = {12},
 url = {http://dl.acm.org/citation.cfm?id=3049832.3049841},
 acmid = {3049841},
 publisher = {IEEE Press},
 address = {Piscataway, NJ, USA},
}

@inproceedings{Wang:2013:AAG:2503210.2503219,
 author = {Wang, Qian and Zhang, Xianyi and Zhang, Yunquan and Yi, Qing},
 title = {AUGEM: Automatically Generate High Performance Dense Linear Algebra Kernels on x86 CPUs},
 booktitle = {Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis},
 series = {SC '13},
 year = {2013},
 isbn = {978-1-4503-2378-9},
 location = {Denver, Colorado},
 pages = {25:1--25:12},
 articleno = {25},
 numpages = {12},
 url = {http://doi.acm.org/10.1145/2503210.2503219},
 doi = {10.1145/2503210.2503219},
 acmid = {2503219},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {DLA code optimization, auto-tuning, code generation},
} 

@article{Lawson:1979:BLA:355841.355847,
 author = {Lawson, C. L. and Hanson, R. J. and Kincaid, D. R. and Krogh, F. T.},
 title = {Basic Linear Algebra Subprograms for Fortran Usage},
 journal = {ACM Trans. Math. Softw.},
 issue_date = {Sept. 1979},
 volume = {5},
 number = {3},
 month = sep,
 year = {1979},
 issn = {0098-3500},
 pages = {308--323},
 numpages = {16},
 url = {http://doi.acm.org/10.1145/355841.355847},
 doi = {10.1145/355841.355847},
 acmid = {355847},
 publisher = {ACM},
 address = {New York, NY, USA},
} 

@inproceedings{8719512,
 author={H. {Andrade} and I. {Crnkovic}},
 booktitle={2018 25th Asia-Pacific Software Engineering Conference (APSEC)},
 title={A Review on Software Architectures for Heterogeneous Platforms},
 year={2018},
 volume={},
 number={},
 pages={209-218},
 keywords={energy conservation;software architecture;computing performance;single processor;heterogeneous computing;software engineering;software architecture;energy efficient devices;clock frequency;transistors;Software;Computer architecture;Hardware;Heterogeneous networks;Software architecture;Systematics;software architecture;heterogeneous computing;software deployment},
 doi={10.1109/APSEC.2018.00035},
 ISSN={},
 month={Dec}
}

@inproceedings{6307773,
 author={H. {Esmaeilzadeh} and E. {Blem} and R. S. {Amant} and K. {Sankaralingam} and D. {Burger}},
 booktitle={2011 38th Annual International Symposium on Computer Architecture (ISCA)},
 title={Dark silicon and the end of multicore scaling},
 year={2011},
 volume={},
 number={},
 pages={365-376},
 keywords={graphics processing units;microprocessor chips;multiprocessing systems;network topology;parallel processing;dark silicon;processor designers;Moore's law scaling;single-core performance;Dennard scaling;multicore parts;single-core scaling;multicore scaling limits;speedup potential;parallel workloads;technology generations;ITRS projections;device scaling parameters;Pareto-optimal frontiers;performance model;upper-bound performance;lower-bound core power;multicore designs;single-threaded CPU-like multicore chip organizations;massively threaded GPU-like multicore chip organizations;asymmetric topology;dynamic topology;composed topology;chip topology;computing community;fixed-size chip;Multicore processing;Topology;Performance evaluation;Organizations;Transistors;Microarchitecture;Instruction sets;Dark Silicon;Modeling;Power;Technology Scaling;Multicore},
 doi={},
 ISSN={},
 month={June}
}

@article{7878935,
 author={Thomas N. Theis and H.-S. Philip Wong},
 journal={Computing in Science Engineering},
 title={The End of Moore's Law: A New Beginning for Information Technology},
 year={2017},
 volume={19},
 number={2},
 pages={41-50},
 keywords={information technology;research and development;Moore's law;information technology;Gordon Moore;semiconductor electronics;field effect transistor;research and development;Algorithm design and analysis;Field effect transistors;Switching circuits;Computer architecture;Random access memory;Moore's Law;Scientific computing;Memory management;introductory and survey;emerging technologies;algorithms implemented in hardware;memory technologies;neural nets;scientific computing},
 doi={10.1109/MCSE.2017.29},
 ISSN={},
 month={Mar}
} 


@misc{cudacompiler,
 author = {Nvidia},
 title  = {{NVCC}},
 year   = {2007},
 note   = {URL \href{https://developer.nvidia.com/cuda-llvm-compiler}
                    {\nolinkurl{https://developer.nvidia.com/cuda-llvm-compi}
                     \linebreak
                     \nolinkurl{ler}}}
} 

@misc{lunarglass,
 title  = {{LunarGLASS}},
 author = {LunarG},
 year   = {2015},
 note   = {URL \href{https://lunarg.com/shadercompiler-technologies/lunarglass}
                    {\nolinkurl{https://lunarg.com/shadercompiler-}
                     \linebreak
                     \nolinkurl{technologies/lunarglass}}}
} 

@misc{gfxbench,
  author = {Kishonti},
  title  = {{Gfxbench 4.0}},
  year   = {2016},
  url    = {https://gfxbench.com},
} 

@misc{polybench,
  author = {Louis-Noel Pouchet},
  title  = {{Polybench v2.0}},
  year   = {2011},
  url    = {http://web.cse.ohio-state.edu/~pouchet.2/software/polybench}
}

@inproceedings{8310168,
 author={D. {Patterson}},
 booktitle={2018 IEEE International Solid - State Circuits Conference - (ISSCC)},
 title={50 Years of computer architecture: From the mainframe CPU to the domain-specific tpu and the open RISC-V instruction set},
 year={2018},
 volume={},
 number={},
 pages={27-31},
 keywords={computer architecture;instruction sets;mainframes;microprocessor chips;reduced instruction set computing;I/O system;domain-specific TPU;mainframe CPU;computer architecture;single ISA;market niches;system software;unique instruction-set architecture;incompatible computer lines;open RISC-V instruction;time 50 year;Reduced instruction set computing;VLIW;Computer architecture;Random access memory;Microcomputers;Microprocessors;Read only memory},
 doi={10.1109/ISSCC.2018.8310168},
 ISSN={},
 month={Feb}
}

@article{Jradi2017fast,
  author    = {Walid Abdala Rfaei Jradi and
               Hugo A. D. do Nascimento and
               Wellington Martins},
  title     = {A Fast and Generic GPU-Based Parallel Reduction Implementation},
  journal   = {CoRR},
  volume    = {abs/1710.07358},
  year      = {2017},
  url       = {http://arxiv.org/abs/1710.07358},
  archivePrefix = {arXiv},
  eprint    = {1710.07358},
  timestamp = {Mon, 13 Aug 2018 16:48:40 +0200},
  biburl    = {https://dblp.org/rec/bib/journals/corr/abs-1710-07358},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@book{Torczon:2007:EC:1526330,
 author = {Torczon, Linda and Cooper, Keith},
 title = {Engineering A Compiler},
 year = {2011},
 isbn = {012088478X},
 edition = {2nd},
 publisher = {Morgan Kaufmann Publishers Inc.},
 address = {San Francisco, CA, USA},
} 

@inproceedings{Rosen:1988:GVN:73560.73562,
 author = {Rosen, B. K. and Wegman, M. N. and Zadeck, F. K.},
 title = {Global Value Numbers and Redundant Computations},
 booktitle = {Proceedings of the 15th ACM SIGPLAN-SIGACT Symposium on Principles of Programming Languages},
 series = {POPL '88},
 year = {1988},
 isbn = {0-89791-252-7},
 location = {San Diego, California, USA},
 pages = {12--27},
 numpages = {16},
 url = {http://doi.acm.org/10.1145/73560.73562},
 doi = {10.1145/73560.73562},
 acmid = {73562},
 publisher = {ACM},
 address = {New York, NY, USA},
}

@inproceedings{Lopes:2015:PCP:2737924.2737965,
 author = {Lopes, Nuno P. and Menendez, David and Nagarakatte, Santosh and Regehr, John},
 title = {Provably Correct Peephole Optimizations with Alive},
 booktitle = {Proceedings of the 36th ACM SIGPLAN Conference on Programming Language Design and Implementation},
 series = {PLDI '15},
 year = {2015},
 isbn = {978-1-4503-3468-6},
 location = {Portland, OR, USA},
 pages = {22--32},
 numpages = {11},
 url = {http://doi.acm.org/10.1145/2737924.2737965},
 doi = {10.1145/2737924.2737965},
 acmid = {2737965},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {Alive, Compiler Verification, Peephole Optimization},
}

@article{Yang:2011:FUB:1993316.1993532,
 author = {Yang, Xuejun and Chen, Yang and Eide, Eric and Regehr, John},
 title = {Finding and Understanding Bugs in C Compilers},
 journal = {SIGPLAN Not.},
 issue_date = {June 2011},
 volume = {46},
 number = {6},
 month = jun,
 year = {2011},
 issn = {0362-1340},
 pages = {283--294},
 numpages = {12},
 url = {http://doi.acm.org/10.1145/1993316.1993532},
 doi = {10.1145/1993316.1993532},
 acmid = {1993532},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {automated testing, compiler defect, compiler testing, random program generation, random testing},
}

@inproceedings{Menendez:2017:ADP:3062341.3062372,
 author = {Menendez, David and Nagarakatte, Santosh},
 title = {Alive-Infer: Data-driven Precondition Inference for Peephole Optimizations in LLVM},
 booktitle = {Proceedings of the 38th ACM SIGPLAN Conference on Programming Language Design and Implementation},
 series = {PLDI 2017},
 year = {2017},
 isbn = {978-1-4503-4988-8},
 location = {Barcelona, Spain},
 pages = {49--63},
 numpages = {15},
 url = {http://doi.acm.org/10.1145/3062341.3062372},
 doi = {10.1145/3062341.3062372},
 acmid = {3062372},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {Alive, Compilers, Inference, Learning},
}

@article{Lengauer2012Polly,
  added-at = {2013-03-01T00:00:00.000+0100},
  author = {Grosser, Tobias and Größlinger, Armin and Lengauer, Christian},
  biburl = {https://www.bibsonomy.org/bibtex/2994f0f6375a23bf37f7ad65707bc066f/dblp},
  ee = {http://dx.doi.org/10.1142/S0129626412500107},
  interhash = {c44869d500b0f606dc1c183140b85c61},
  intrahash = {994f0f6375a23bf37f7ad65707bc066f},
  journal = {Parallel Processing Letters},
  keywords = {dblp},
  number = 4,
  timestamp = {2013-08-13T13:46:02.000+0200},
  title = {Polly - Performing Polyhedral Optimizations on a Low-Level Intermediate Representation.},
  url = {http://dblp.uni-trier.de/db/journals/ppl/ppl22.html#GrosserGL12},
  volume = 22,
  year = {2012}
}

@inproceedings{Bondhugula:2008:PAP:1375581.1375595,
 author = {Bondhugula, Uday and Hartono, Albert and Ramanujam, J. and Sadayappan, P.},
 title = {A Practical Automatic Polyhedral Parallelizer and Locality Optimizer},
 booktitle = {Proceedings of the 29th ACM SIGPLAN Conference on Programming Language Design and Implementation},
 series = {PLDI '08},
 year = {2008},
 isbn = {978-1-59593-860-2},
 location = {Tucson, AZ, USA},
 pages = {101--113},
 numpages = {13},
 url = {http://doi.acm.org/10.1145/1375581.1375595},
 doi = {10.1145/1375581.1375595},
 acmid = {1375595},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {affine transformations, automatic parallelization, locality optimization, loop transformations, polyhedral model, tiling},
} 

@misc{nvidia11guide,
 author = {Nvidia},
 title = {Nvidia {OpenCL} Best Practices Guide},
 year = 2011
}

@book{Rost:2009:OSL:1696393,
 author = {Rost, Randi J. and Licea-Kane, Bill and Ginsburg, Dan and Kessenich, John M. and Lichtenbelt, Barthold and Malan, Hugh and Weiblen, Mike},
 title = {OpenGL Shading Language},
 year = {2009},
 isbn = {0321637631, 9780321637635},
 edition = {3rd},
 publisher = {Addison-Wesley Professional},
} 

@article{lee09openmp,
 author = {Lee, Seyong and Min, Seung-Jai and Eigenmann, Rudolf},
 title = {{OpenMP} to {GPGPU}: A Compiler Framework for Automatic Translation and Optimization},
 journal = {SIGPLAN Not.},
 issue_date = {April 2009},
 volume = {44},
 number = {4},
 month = feb,
 year = {2009},
 issn = {0362-1340},
 pages = {101--110},
 numpages = {10},
 url = {http://doi.acm.org/10.1145/1594835.1504194},
 doi = {10.1145/1594835.1504194},
 acmid = {1504194},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {automatic translation, compiler optimization, cuda, gpu, openmp},
}

@incollection{Franchetti09OL,
 year=2009,
 booktitle={IFIP TC 2 Working Conference on Domain-Specific Languages},
 volume2=5658,
 series2={Lecture Notes in Computer Science},
 editor2={Taha, Walid Mohamed},
 title={Operator Language: A Program Generation Framework for Fast Kernels},
 publisher={Springer},
 keywords={Library generation; program generation; automatic performance tuning; high performance software; multicore CPU},
 author={Franchetti, Franz and de Mesmay, Fr\'ed\'eric and McFarlin, Daniel and P\"uschel, Markus},
 pages2={385-409},
 language={English}
}

@article{Rompf:2012:LMS:2184319.2184345,
 author = {Rompf, Tiark and Odersky, Martin},
 title = {Lightweight Modular Staging: A Pragmatic Approach to Runtime Code Generation and Compiled {DSLs}},
 journal = {Commun. ACM},
 issue_date = {June 2012},
 volume = {55},
 number = {6},
 year = {2012},
 numpages = {10},
 acmid = {2184345},
 publisher = {ACM},
}

@inproceedings{Ragan-Kelley2013Halide,
 author = {Ragan-Kelley, Jonathan and Barnes, Connelly and Adams, Andrew and Paris, Sylvain and Durand, Fr{\'e}do and Amarasinghe, Saman},
 title = {Halide: A Language and Compiler for Optimizing Parallelism, Locality, and Recomputation in Image Processing Pipelines},
 booktitle = {Proceedings of the 34th ACM SIGPLAN Conference on Programming Language Design and Implementation},
 series = {PLDI '13},
 year = {2013},
 isbn = {978-1-4503-2014-6},
 location = {Seattle, Washington, USA},
 pages = {519--530},
 numpages = {12},
 url = {http://doi.acm.org/10.1145/2491956.2462176},
 doi = {10.1145/2491956.2462176},
 acmid = {2462176},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {autotuning, compiler, domain specific language, gpu, image processing, locality, optimization, parallelism, redundant computation, vectorization},
}

@inproceedings{jouppi2017datacenter,
  author    = {Norman P. Jouppi and
               Cliff Young and
               Nishant Patil and
               David Patterson and
               Gaurav Agrawal and
               Raminder Bajwa and
               Sarah Bates and
               Suresh Bhatia and
               Nan Boden and
               Al Borchers and
               Rick Boyle and
               Pierre{-}luc Cantin and
               Clifford Chao and
               Chris Clark and
               Jeremy Coriell and
               Mike Daley and
               Matt Dau and
               Jeffrey Dean and
               Ben Gelb and
               Tara Vazir Ghaemmaghami and
               Rajendra Gottipati and
               William Gulland and
               Robert Hagmann and
               C. Richard Ho and
               Doug Hogberg and
               John Hu and
               Robert Hundt and
               Dan Hurt and
               Julian Ibarz and
               Aaron Jaffey and
               Alek Jaworski and
               Alexander Kaplan and
               Harshit Khaitan and
               Daniel Killebrew and
               Andy Koch and
               Naveen Kumar and
               Steve Lacy and
               James Laudon and
               James Law and
               Diemthu Le and
               Chris Leary and
               Zhuyuan Liu and
               Kyle Lucke and
               Alan Lundin and
               Gordon MacKean and
               Adriana Maggiore and
               Maire Mahony and
               Kieran Miller and
               Rahul Nagarajan and
               Ravi Narayanaswami and
               Ray Ni and
               Kathy Nix and
               Thomas Norrie and
               Mark Omernick and
               Narayana Penukonda and
               Andy Phelps and
               Jonathan Ross and
               Matt Ross and
               Amir Salek and
               Emad Samadiani and
               Chris Severn and
               Gregory Sizikov and
               Matthew Snelham and
               Jed Souter and
               Dan Steinberg and
               Andy Swing and
               Mercedes Tan and
               Gregory Thorson and
               Bo Tian and
               Horia Toma and
               Erick Tuttle and
               Vijay Vasudevan and
               Richard Walter and
               Walter Wang and
               Eric Wilcox and
               Doe Hyun Yoon},
  title     = {In-Datacenter Performance Analysis of a Tensor Processing Unit},
  booktitle = {Proceedings of the 44th Annual International Symposium on Computer
               Architecture, {ISCA} 2017, Toronto, ON, Canada, June 24-28, 2017},
  pages     = {1--12},
  year      = {2017},
  url       = {http://doi.acm.org/10.1145/3079856.3080246},
  doi       = {10.1145/3079856.3080246},
  timestamp = {Mon, 19 Jun 2017 09:22:15 +0200},
  biburl    = {http://dblp.uni-trier.de/rec/bib/conf/isca/JouppiYPPABBBBB17},
  bibsource = {dblp computer science bibliography, http://dblp.org}
}

@book{nielson2015principles,
  title={Principles of program analysis},
  author={Nielson, Flemming and Nielson, Hanne R and Hankin, Chris},
  year={2015},
  publisher={Springer}
}

@inproceedings{Mendis2015Helium,
 author = {Mendis, Charith and Bosboom, Jeffrey and Wu, Kevin and Kamil, Shoaib and Ragan-Kelley, Jonathan and Paris, Sylvain and Zhao, Qin and Amarasinghe, Saman},
 title = {Helium: Lifting High-performance Stencil Kernels from Stripped x86 Binaries to {Halide} {DSL} Code},
 booktitle = {Proceedings of the 36th ACM SIGPLAN Conference on Programming Language Design and Implementation},
 series = {PLDI '15},
 year = {2015},
 isbn = {978-1-4503-3468-6},
 location = {Portland, OR, USA},
 pages = {391--402},
 numpages = {12},
 url = {http://doi.acm.org/10.1145/2737924.2737974},
 doi = {10.1145/2737924.2737974},
 acmid = {2737974},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {Helium, autotuning, dynamic analysis, image processing, reverse engineering, stencil computation, x86 binary instrumentation},
} 

@inproceedings{Kamil2016Verified,
 author = {Kamil, Shoaib and Cheung, Alvin and Itzhaky, Shachar and Solar-Lezama, Armando},
 title = {Verified Lifting of Stencil Computations},
 booktitle = {Proceedings of the 37th ACM SIGPLAN Conference on Programming Language Design and Implementation},
 series = {PLDI '16},
 year = {2016},
 isbn = {978-1-4503-4261-2},
 location = {Santa Barbara, CA, USA},
 pages = {711--726},
 numpages = {16},
 url = {http://doi.acm.org/10.1145/2908080.2908117},
 doi = {10.1145/2908080.2908117},
 acmid = {2908117},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {Domain-specific Languages, Program Synthesis, Verified Lifting},
}

@inproceedings{SteuwerRD17,
  author    = {Michel Steuwer and
    Toomas Remmelg and
      Christophe Dubach},
  title     = {Lift: a functional data-parallel {IR} for high-performance {GPU} code
    generation},
  booktitle = {{CGO}},
  pages     = {74--85},
  publisher = {{ACM}},
  year      = {2017}
}

@article{Aiken:1999:ISC:339853.339897,
 author = {Aiken, Alexander},
 title = {Introduction to Set Constraint-based Program Analysis},
 journal = {Sci. Comput. Program.},
 issue_date = {Nov.1.1999},
 volume = {35},
 number = {2-3},
 month = nov,
 year = {1999},
 pages = {79--111},
 numpages = {33},
 url = {http://dx.doi.org/10.1016/S0167-6423(99)00007-6},
 doi = {10.1016/S0167-6423(99)00007-6},
 acmid = {339897},
 publisher = {Elsevier North-Holland, Inc.},
 address = {Amsterdam, The Netherlands, The Netherlands},
 keywords = {constraints, program analysis, set constraints},
}

@inproceedings{Gulwani:2008:PAC:1375581.1375616,
 author = {Gulwani, Sumit and Srivastava, Saurabh and Venkatesan, Ramarathnam},
 title = {Program Analysis As Constraint Solving},
 booktitle = {Proceedings of the 29th ACM SIGPLAN Conference on Programming Language Design and Implementation},
 series = {PLDI '08},
 year = {2008},
 isbn = {978-1-59593-860-2},
 location = {Tucson, AZ, USA},
 pages = {281--292},
 numpages = {12},
 url = {http://doi.acm.org/10.1145/1375581.1375616},
 doi = {10.1145/1375581.1375616},
 acmid = {1375616},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {bounds analysis, constraint solving, most-general counterexamples, non-termination analysis, program verification, strongest postcondition, weakest precondition},
}

@article{Srivastava:2010:PVP:1707801.1706337,
 author = {Srivastava, Saurabh and Gulwani, Sumit and Foster, Jeffrey S.},
 title = {From Program Verification to Program Synthesis},
 journal = {SIGPLAN Not.},
 issue_date = {January 2010},
 volume = {45},
 number = {1},
 month = jan,
 year = {2010},
 issn = {0362-1340},
 pages = {313--326},
 numpages = {14},
 url = {http://doi.acm.org/10.1145/1707801.1706337},
 doi = {10.1145/1707801.1706337},
 acmid = {1706337},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {proof-theoretic program synthesis, verification},
}

@inproceedings{Zhao:2012:FLI:2103656.2103709,
 author = {Zhao, Jianzhou and Nagarakatte, Santosh and Martin, Milo M. K. and Zdancewic, Steve},
 title = {Formalizing the LLVM Intermediate Representation for Verified Program Transformations},
 booktitle = {Proceedings of the 39th Annual ACM SIGPLAN-SIGACT Symposium on Principles of Programming Languages},
 series = {POPL '12},
 year = {2012},
 isbn = {978-1-4503-1083-3},
 location = {Philadelphia, PA, USA},
 pages = {427--440},
 numpages = {14},
 url = {http://doi.acm.org/10.1145/2103656.2103709},
 doi = {10.1145/2103656.2103709},
 acmid = {2103709},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {Coq, LLVM, memory safety},
}

@inproceedings{Lerner:2005:ASP:1040305.1040335,
 author = {Lerner, Sorin and Millstein, Todd and Rice, Erika and Chambers, Craig},
 title = {Automated Soundness Proofs for Dataflow Analyses and Transformations via Local Rules},
 booktitle = {Proceedings of the 32Nd ACM SIGPLAN-SIGACT Symposium on Principles of Programming Languages},
 series = {POPL '05},
 year = {2005},
 isbn = {1-58113-830-X},
 location = {Long Beach, California, USA},
 pages = {364--377},
 numpages = {14},
 url = {http://doi.acm.org/10.1145/1040305.1040335},
 doi = {10.1145/1040305.1040335},
 acmid = {1040335},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {automated correctness proofs, compiler optimization},
}

@article{Kundu:2009:POC:1543135.1542513,
 author = {Kundu, Sudipta and Tatlock, Zachary and Lerner, Sorin},
 title = {Proving Optimizations Correct Using Parameterized Program Equivalence},
 journal = {SIGPLAN Not.},
 issue_date = {June 2009},
 volume = {44},
 number = {6},
 month = jun,
 year = {2009},
 issn = {0362-1340},
 pages = {327--337},
 numpages = {11},
 url = {http://doi.acm.org/10.1145/1543135.1542513},
 doi = {10.1145/1543135.1542513},
 acmid = {1542513},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {compiler optimization, correctness, translation validation},
}

@article{Whitfield:1997:AEC:267959.267960,
 author = {Whitfield, Deborah L. and Soffa, Mary Lou},
 title = {An Approach for Exploring Code Improving Transformations},
 journal = {ACM Trans. Program. Lang. Syst.},
 issue_date = {Nov. 1997},
 volume = {19},
 number = {6},
 month = nov,
 year = {1997},
 issn = {0164-0925},
 pages = {1053--1084},
 numpages = {32},
 url = {http://doi.acm.org/10.1145/267959.267960},
 doi = {10.1145/267959.267960},
 acmid = {267960},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {automatic generation of optimizers, code-improving transformations, enabling and disabling of optimizations, parallelizing transformations, specification of program optimizations},
}

@inproceedings{Mullen:2016:VPO:2908080.2908109,
 author = {Mullen, Eric and Zuniga, Daryl and Tatlock, Zachary and Grossman, Dan},
 title = {Verified Peephole Optimizations for CompCert},
 booktitle = {Proceedings of the 37th ACM SIGPLAN Conference on Programming Language Design and Implementation},
 series = {PLDI '16},
 year = {2016},
 isbn = {978-1-4503-4261-2},
 location = {Santa Barbara, CA, USA},
 pages = {448--461},
 numpages = {14},
 url = {http://doi.acm.org/10.1145/2908080.2908109},
 doi = {10.1145/2908080.2908109},
 acmid = {2908109},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {CompCert, Compilers, Coq, Formal Methods, Peek, Verification},
}

@inproceedings{Notzli:2016:LVP:2931021.2931024,
 author = {N\"{o}tzli, Andres and Brown, Fraser},
 title = {{LifeJacket}: Verifying Precise Floating-point Optimizations in LLVM},
 booktitle = {Proceedings of the 5th ACM SIGPLAN International Workshop on State Of the Art in Program Analysis},
 series = {SOAP 2016},
 year = {2016},
 isbn = {978-1-4503-4385-5},
 location = {Santa Barbara, CA, USA},
 pages = {24--29},
 numpages = {6},
 url = {http://doi.acm.org/10.1145/2931021.2931024},
 doi = {10.1145/2931021.2931024},
 acmid = {2931024},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {Floating-point arithmetic, LLVM, SMT, Verification},
}

@inbook{Menendez2016,
author="Menendez, David
and Nagarakatte, Santosh
and Gupta, Aarti",
title="Alive-FP: Automated Verification of Floating Point Based Peephole Optimizations in LLVM",
bookTitle="Static Analysis: 23rd International Symposium, SAS 2016, Edinburgh, UK, September 8-10, 2016, Proceedings",
year="2016",
publisher="Springer Berlin Heidelberg",
address="Berlin, Heidelberg",
pages="317--337",
abstract="Peephole optimizations optimize and canonicalize code to enable other optimizations but are error-prone. Our prior research on Alive, a domain-specific language for specifying LLVM's peephole optimizations, automatically verifies the correctness of integer-based peephole optimizations and generates C++ code for use within LLVM. This paper proposes Alive-FP, an automated verification framework for floating point based peephole optimizations in LLVM. Alive-FP handles a class of floating point optimizations and fast-math optimizations involving signed zeros, not-a-number, and infinities, which do not result in loss of accuracy. This paper provides multiple encodings for various floating point operations to account for the various kinds of undefined behavior and under-specification in the LLVM's language reference manual. We have translated all optimizations that belong to this category into Alive-FP. In this process, we have discovered seven wrong optimizations in LLVM.",
isbn="978-3-662-53413-7",
doi="10.1007/978-3-662-53413-7_16",
url="https://doi.org/10.1007/978-3-662-53413-7_16"
}

@inproceedings{Tate:2010:GCO:1706299.1706345,
 author = {Tate, Ross and Stepp, Michael and Lerner, Sorin},
 title = {Generating Compiler Optimizations from Proofs},
 booktitle = {Proceedings of the 37th Annual ACM SIGPLAN-SIGACT Symposium on Principles of Programming Languages},
 series = {POPL '10},
 year = {2010},
 isbn = {978-1-60558-479-9},
 location = {Madrid, Spain},
 pages = {389--402},
 numpages = {14},
 url = {http://doi.acm.org/10.1145/1706299.1706345},
 doi = {10.1145/1706299.1706345},
 acmid = {1706345},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {compiler optimization, explanation-based learning, proof generalization},
}

@article{Martin1998,
author="Martin, Florian",
title="PAG -- an efficient program analyzer generator",
journal="International Journal on Software Tools for Technology Transfer",
year="1998",
month="Nov",
day="01",
volume="2",
number="1",
pages="46--67",
issn="1433-2779",
doi="10.1007/s100090050017",
url="https://doi.org/10.1007/s100090050017"
}

@inproceedings{Olmos:2005:CSD:2136624.2136643,
 author = {Olmos, Karina and Visser, Eelco},
 title = {Composing Source-to-source Data-flow Transformations with Rewriting Strategies and Dependent Dynamic Rewrite Rules},
 booktitle = {Proceedings of the 14th International Conference on Compiler Construction},
 series = {CC'05},
 year = {2005},
 isbn = {3-540-25411-0, 978-3-540-25411-9},
 location = {Edinburgh, UK},
 pages = {204--220},
 numpages = {17},
 url = {http://dx.doi.org/10.1007/978-3-540-31985-6_14},
 doi = {10.1007/978-3-540-31985-6_14},
 acmid = {2136643},
 publisher = {Springer-Verlag},
 address = {Berlin, Heidelberg},
}

@inbook{Lipps1989,
author="Lipps, Peter
and M{\"o}ncke, Ulrich
and Wilhelm, Reinhard",
title="OPTRAN - A language/system for the specification of program transformations: System overview and experiences",
bookTitle="Compiler Compilers and High Speed Compilation: 2nd CCHSC Workshop Berlin, GDR, October 10--14, 1988 Proceedings",
year="1989",
publisher="Springer Berlin Heidelberg",
address="Berlin, Heidelberg",
pages="52--65",
abstract="OPTRAN is a batch-oriented system for the generation of compilers that support program transformations. Programs are represented by attributed abstract syntax trees (AAST). The transformation of AAST's is a powerful method to describe problems in compiler writing such as machine-independent optimisations, language-based editors, and source-to-source translations.",
isbn="978-3-540-46200-2",
doi="10.1007/3-540-51364-7_4",
url="https://doi.org/10.1007/3-540-51364-7_4"
}

@inproceedings{Willcock:2009:RGP:1621607.1621611,
 author = {Willcock, Jeremiah James and Lumsdaine, Andrew and Quinlan, Daniel J.},
 title = {Reusable, Generic Program Analyses and Transformations},
 booktitle = {Proceedings of the Eighth International Conference on Generative Programming and Component Engineering},
 series = {GPCE '09},
 year = {2009},
 isbn = {978-1-60558-494-2},
 location = {Denver, Colorado, USA},
 pages = {5--14},
 numpages = {10},
 url = {http://doi.acm.org/10.1145/1621607.1621611},
 doi = {10.1145/1621607.1621611},
 acmid = {1621611},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {compiler optimization, generic programming},
}

@inbook{be0fa11ddb194bde86a9dab8589b779c,
  title     = "Compiler-Assisted Test Acceleration on GPUs for Embedded Software",
  author    = "Vanya Yaneva and Ajitha Rajan and Christophe Dubach",
  year      = "2017",
  month     = "7",
  doi       = "10.1145/3092703.3092720",
  isbn      = "978-1-4503-5076-1",
  pages     = "35--45",
  booktitle = "ISSTA 2017 Proceedings of the 26th ACM SIGSOFT International Symposium on Software Testing and Analysis",
  publisher = "ACM",
}

@inbook{Assmann1996,
author="A{\ss}mann, Uwe",
title="How to uniformly specify program analysis and transformation with graph rewrite systems",
bookTitle="Compiler Construction: 6th International Conference, CC'96 Link{\"o}ping, Sweden, April 24--26, 1996 Proceedings",
year="1996",
publisher="Springer Berlin Heidelberg",
address="Berlin, Heidelberg",
pages="121--135",
abstract="Implementing program optimizers is a task which swallows an enourmous amount of man-power. To reduce development time a simple and practial specification method is highly desirable. Such a method should comprise both program analysis and transformation. However, although several frameworks for program analysis exist, none of them can be used for analysis and transformation uniformly. This paper presents such a method. For program analysis we use a simple variant of graph rewrite systems (edge addition rewrite systems). For program transformation we apply more complex graph rewrite systems. Our specification method has been implemented prototypically in the optimizer generator OPTIMIX. OPTIMIX works with arbitrary intermediate languages and generates real-life program analyses and transformations. We demonstrate this by several examples and measurements.",
isbn="978-3-540-49939-8",
doi="10.1007/3-540-61053-7_57",
url="https://doi.org/10.1007/3-540-61053-7_57"
}

@inproceedings{Assmann98optimix,
    author = {Uwe Assmann},
    title = {Optimix - A Tool For Rewriting And Optimizing Programs},
    booktitle = {Handbook of Graph Grammars and Computing by Graph Transformation. Volume 2: Applications, Languages and Tools},
    year = {1998},
    pages = {307--318},
    publisher = {World Scientific}
}

@inbook{Alt1994,
author="Alt, Martin
and A{\ss}mann, Uwe
and van Someren, Hans",
title="Cosy compiler phase embedding with the CoSy compiler model",
bookTitle="Compiler Construction: 5th International Conference, CC '94 Edinburgh, U.K., April 7--9, 1994 Proceedings",
year="1994",
publisher="Springer Berlin Heidelberg",
address="Berlin, Heidelberg",
pages="278--293",
abstract="In this article we introduce a novel model for compilation and compiler construction, the CoSY(COmpiler SYstem) model. CoSy provides a framework for flexible combination and embedding of compiler phases --- called engines in the sequel --- such that the construction of parallel and (inter-procedural) optimizing compilers is facilitated. In CoSy a compiler writer may program some phase in a target language and embed it transparently --- without source code changes --- into different compiler contexts, such as with alternative phase order, speculative evaluation, parallel evaluation, and generate-and-test evaluation. Compilers constructed with CoSy can be tuned for different host systems (the system the compiler runs on, not the system it produces code for) and are transparently scalable for (shared memory) multiprocessor host configurations.",
isbn="978-3-540-48371-7",
doi="10.1007/3-540-57877-3_19",
url="https://doi.org/10.1007/3-540-57877-3_19"
}

@inproceedings{Baskaran:2010:ACC:2175462.2175482,
 author = {Baskaran, Muthu Manikandan and Ramanujam, J. and Sadayappan, P.},
 title = {Automatic {C-to-CUDA} Code Generation for Affine Programs},
 booktitle = {Proceedings of the 19th Joint European Conference on Theory and Practice of Software, International Conference on Compiler Construction},
 series = {CC'10/ETAPS'10},
 year = {2010},
 isbn = {3-642-11969-7, 978-3-642-11969-9},
 location = {Paphos, Cyprus},
 pages = {244--263},
 numpages = {20},
 url = {http://dx.doi.org/10.1007/978-3-642-11970-5_14},
 doi = {10.1007/978-3-642-11970-5_14},
 acmid = {2175482},
 publisher = {Springer-Verlag},
 address = {Berlin, Heidelberg},
}

@inproceedings{Koeplinger:2018:SLC:3192366.3192379,
 author = {Koeplinger, David and Feldman, Matthew and Prabhakar, Raghu and Zhang, Yaqi and Hadjis, Stefan and Fiszel, Ruben and Zhao, Tian and Nardi, Luigi and Pedram, Ardavan and Kozyrakis, Christos and Olukotun, Kunle},
 title = {Spatial: A Language and Compiler for Application Accelerators},
 booktitle = {Proceedings of the 39th ACM SIGPLAN Conference on Programming Language Design and Implementation},
 series = {PLDI 2018},
 year = {2018},
 isbn = {978-1-4503-5698-5},
 location = {Philadelphia, PA, USA},
 pages = {296--311},
 numpages = {16},
 url = {http://doi.acm.org/10.1145/3192366.3192379},
 doi = {10.1145/3192366.3192379},
 acmid = {3192379},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {CGRAs, FPGAs, compilers, domain-specific languages, hardware accelerators, high-level synthesis, reconfigurable architectures},
}

@inproceedings{Spampinato:2014:BLA:2581122.2544155,
 author = {Spampinato, Daniele G. and P\"{u}schel, Markus},
 title = {A Basic Linear Algebra Compiler},
 booktitle = {Proceedings of Annual IEEE/ACM International Symposium on Code Generation and Optimization},
 series = {CGO '14},
 year = {2014},
 isbn = {978-1-4503-2670-4},
 location = {Orlando, FL, USA},
 pages = {23:23--23:32},
 articleno = {23},
 numpages = {10},
 url = {http://doi.acm.org/10.1145/2581122.2544155},
 doi = {10.1145/2581122.2544155},
 acmid = {2544155},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {Basic linear algebra, DSL, Program synthesis, SIMD vectorization, Small matrices, Tiling},
} 

@article{Verdoolaege:2013:PPC:2400682.2400713,
 author = {Verdoolaege, Sven and Carlos Juega, Juan and Cohen, Albert and Ignacio G\'{o}mez, Jos{\'e} and Tenllado, Christian and Catthoor, Francky},
 title = {Polyhedral Parallel Code Generation for CUDA},
 journal = {ACM Trans. Archit. Code Optim.},
 issue_date = {January 2013},
 volume = {9},
 number = {4},
 month = jan,
 year = {2013},
 issn = {1544-3566},
 pages = {54:1--54:23},
 articleno = {54},
 numpages = {23},
 url = {http://doi.acm.org/10.1145/2400682.2400713},
 doi = {10.1145/2400682.2400713},
 acmid = {2400713},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {C-to-CUDA, CUDA, GPU, PPCG., Par4All, Polyhedral model, code generation, compilers, loop transformations},
}

@inproceedings{Wen:2017:MSM:3038228.3038235,
 author = {Wen, Yuan and O'Boyle, Michael F.P.},
 title = {Merge or Separate?: Multi-job Scheduling for OpenCL Kernels on CPU/GPU Platforms},
 booktitle = {Proceedings of the General Purpose GPUs},
 series = {GPGPU-10},
 year = {2017},
 isbn = {978-1-4503-4915-4},
 location = {Austin, TX, USA},
 pages = {22--31},
 numpages = {10},
 url = {http://doi.acm.org/10.1145/3038228.3038235},
 doi = {10.1145/3038228.3038235},
 acmid = {3038235},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {CPU-GPU runtime system, GPU kernel scheduling, concurrent kernel, machine learning},
}

@INPROCEEDINGS{7116910,
author={Y. {Wen} and Z. {Wang} and M. F. P. {O'Boyle}},
booktitle={2014 21st International Conference on High Performance Computing (HiPC)},
title={Smart multi-task scheduling for OpenCL programs on CPU/GPU heterogeneous platforms},
year={2014},
volume={},
number={},
pages={1-10},
keywords={concurrency (computers);graphics processing units;multiprocessing programs;parallel processing;scheduling;smart multitask scheduling;OpenCL programs;CPU-GPU heterogeneous platforms;high performance computing;heterogeneous hardware resources;OpenCL task scheduling scheme;scheduling priority function;kernel speedup;static code structure;concurrent OpenCL kernels;Core i7-Nvidia GTX590 platform;Core i7-AMD Tahiti 7970 platform;Graphics processing units;Kernel;Runtime;Feature extraction;Training;Throughput;Schedules;GPU;OpenCL;task scheduling;machine learning},
doi={10.1109/HiPC.2014.7116910},
ISSN={1094-7256},
month={Dec}
}

@article{Tomusk:2016:SHC:3012405.3014165,
 author = {Tomusk, Erik and Dubach, Christophe and O'boyle, Michael},
 title = {Selecting Heterogeneous Cores for Diversity},
 journal = {ACM Trans. Archit. Code Optim.},
 issue_date = {December 2016},
 volume = {13},
 number = {4},
 month = dec,
 year = {2016},
 issn = {1544-3566},
 pages = {49:1--49:25},
 articleno = {49},
 numpages = {25},
 url = {http://doi.acm.org/10.1145/3014165},
 doi = {10.1145/3014165},
 acmid = {3014165},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {Heterogeneous, core selection, design space exploration, diversity, flexibility, power-aware, single-ISA},
}

@article{Wang:2014:IPP:2591460.2579561,
 author = {Wang, Zheng and Tournavitis, Georgios and Franke, Bj\"{o}rn and O'boyle, Michael F. P.},
 title = {Integrating Profile-driven Parallelism Detection and Machine-learning-based Mapping},
 journal = {ACM Trans. Archit. Code Optim.},
 issue_date = {February 2014},
 volume = {11},
 number = {1},
 month = feb,
 year = {2014},
 issn = {1544-3566},
 pages = {2:1--2:26},
 articleno = {2},
 numpages = {26},
 url = {http://doi.acm.org/10.1145/2579561},
 doi = {10.1145/2579561},
 acmid = {2579561},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {Auto-parallelization, OpenMP, machine-learning-based parallelism mapping, profile-driven parallelism detection},
}

@inproceedings{Tournavitis:2009:THA:1542476.1542496,
 author = {Tournavitis, Georgios and Wang, Zheng and Franke, Bj\"{o}rn and O'Boyle, Michael F.P.},
 title = {Towards a Holistic Approach to Auto-parallelization: Integrating Profile-driven Parallelism Detection and Machine-learning Based Mapping},
 booktitle = {Proceedings of the 30th ACM SIGPLAN Conference on Programming Language Design and Implementation},
 series = {PLDI '09},
 year = {2009},
 isbn = {978-1-60558-392-1},
 location = {Dublin, Ireland},
 pages = {177--187},
 numpages = {11},
 url = {http://doi.acm.org/10.1145/1542476.1542496},
 doi = {10.1145/1542476.1542496},
 acmid = {1542496},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {auto-parallelization, machine-learning based parallelism mapping, openmp, profile-driven parallelism detection},
}

@inproceedings{Manilov:2018:GPI:3178372.3179511,
 author = {Manilov, Stanislav and Vasiladiotis, Christos and Franke, Bj\"{o}rn},
 title = {Generalized Profile-guided Iterator Recognition},
 booktitle = {Proceedings of the 27th International Conference on Compiler Construction},
 series = {CC 2018},
 year = {2018},
 isbn = {978-1-4503-5644-2},
 location = {Vienna, Austria},
 pages = {185--195},
 numpages = {11},
 url = {http://doi.acm.org/10.1145/3178372.3179511},
 doi = {10.1145/3178372.3179511},
 acmid = {3179511},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {Loop iterators, loop analysis},
} 

@inproceedings{Ogilvie:2014:ALA:2628071.2628128,
 author = {Ogilvie, William F. and Petoumenos, Pavlos and Wang, Zheng and Leather, Hugh},
 title = {Active Learning Accelerated Automatic Heuristic Construction for Parallel Program Mapping},
 booktitle = {Proceedings of the 23rd International Conference on Parallel Architectures and Compilation},
 series = {PACT '14},
 year = {2014},
 isbn = {978-1-4503-2809-8},
 location = {Edmonton, AB, Canada},
 pages = {481--482},
 numpages = {2},
 url = {http://doi.acm.org/10.1145/2628071.2628128},
 doi = {10.1145/2628071.2628128},
 acmid = {2628128},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {active learning, compilers, machine learning},
} 

@inproceedings{Reddy2016Reduction,
 author = {Chandan Reddy, Michael Kruse and Albert Cohen},
 title = {Reduction Drawing: Language Constructs and Polyhedral Compilation for Reductions on {GPUs}},
 booktitle = {Proceedings of the 25rd International Conference on Parallel Architectures and Compilation},
 series = {PACT '16},
 year = {2016}
}

@inproceedings{Amdahl:1967:VSP:1465482.1465560,
 author = {Amdahl, Gene M.},
 title = {Validity of the Single Processor Approach to Achieving Large Scale Computing Capabilities},
 booktitle = {Proceedings of the April 18-20, 1967, Spring Joint Computer Conference},
 series = {AFIPS '67 (Spring)},
 year = {1967},
 location = {Atlantic City, New Jersey},
 pages = {483--485},
 numpages = {3},
 url = {http://doi.acm.org/10.1145/1465482.1465560},
 doi = {10.1145/1465482.1465560},
 acmid = {1465560},
 publisher = {ACM},
 address = {New York, NY, USA},
}

@article{Hill:2008:ALM:1449375.1449387,
 author = {Hill, Mark D. and Marty, Michael R.},
 title = {Amdahl's Law in the Multicore Era},
 journal = {Computer},
 issue_date = {July 2008},
 volume = {41},
 number = {7},
 month = jul,
 year = {2008},
 issn = {0018-9162},
 pages = {33--38},
 numpages = {6},
 url = {https://doi.org/10.1109/MC.2008.209},
 doi = {10.1109/MC.2008.209},
 acmid = {1449387},
 publisher = {IEEE Computer Society Press},
 address = {Los Alamitos, CA, USA},
 keywords = {Amdahl's law, chip multiprocessors (CMPs), multicore chips},
}

@inproceedings{johnson1994program,
 author = {Johnson, Richard and Pearson, David and Pingali, Keshav},
 title = {The Program Structure Tree: Computing Control Regions in Linear Time},
 booktitle = {Proceedings of the ACM SIGPLAN 1994 Conference on Programming Language Design and Implementation},
 series = {PLDI '94},
 year = {1994},
 isbn = {0-89791-662-X},
 location = {Orlando, Florida, USA},
 pages = {171--185},
 numpages = {15},
 url = {http://doi.acm.org/10.1145/178243.178258},
 doi = {10.1145/178243.178258},
 acmid = {178258},
 publisher = {ACM},
 address = {New York, NY, USA},
}

@article{steuwer15rewrite,
 author = {Steuwer, Michel and Fensch, Christian and Lindley, Sam and Dubach, Christophe},
 title = {Generating Performance Portable Code Using Rewrite Rules: From High-level Functional Expressions to High-performance {OpenCL} Code},
 journal = {SIGPLAN Not.},
 issue_date = {September 2015},
 volume = {50},
 number = {9},
 month = aug,
 year = {2015},
 issn = {0362-1340},
 pages = {205--217},
 numpages = {13},
 url = {http://doi.acm.org/10.1145/2858949.2784754},
 doi = {10.1145/2858949.2784754},
 acmid = {2784754},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {Algorithmic patterns, GPU, OpenCL, code generation, performance portability, rewrite rules},
}

@inproceedings{HagedornSSGD18,
  author    = {Bastian Hagedorn and
               Larisa Stoltzfus and
               Michel Steuwer and
               Sergei Gorlatch and
               Christophe Dubach},
  title     = {High Performance Stencil Code Generation with {Lift}},
  booktitle = {{CGO}},
  publisher = {{ACM}},
  year      = {2018}
}

@article{Doerfert2015Polly,
  author    = {Johannes Doerfert and
               Kevin Streit and
               Sebastian Hack and
               Zino Benaissa},
  title     = {Polly's Polyhedral Scheduling in the Presence of Reductions},
  journal   = {CoRR},
  volume    = {abs/1505.07716},
  year      = {2015},
  url       = {http://arxiv.org/abs/1505.07716},
  timestamp = {Mon, 01 Jun 2015 14:13:54 +0200},
  biburl    = {http://dblp.uni-trier.de/rec/bib/journals/corr/DoerfertSHB15},
  bibsource = {dblp computer science bibliography, http://dblp.org}
}

@inproceedings{polly-acc,
  author={Tobias Grosser and Torsten Hoefler},
  title={{Polly-ACC: Transparent compilation to heterogeneous hardware}},
  year={2016},
  month={06},
  booktitle={Proceedings of the the 30th International Conference on Supercomputing (ICS'16)},
}

@inproceedings{Doerfert:2017:OLO:3049832.3049864,
 author = {Doerfert, Johannes and Grosser, Tobias and Hack, Sebastian},
 title = {Optimistic Loop Optimization},
 booktitle = {Proceedings of the 2017 International Symposium on Code Generation and Optimization},
 series = {CGO '17},
 year = {2017},
 isbn = {978-1-5090-4931-8},
 location = {Austin, USA},
 pages = {292--304},
 numpages = {13},
 url = {http://dl.acm.org/citation.cfm?id=3049832.3049864},
 acmid = {3049864},
 publisher = {IEEE Press},
 address = {Piscataway, NJ, USA},
 keywords = {Polyhedral Model, Presburger Precondition, Program Versioning, Static Analysis},
}

@article{Hughes:1989:WFP:63410.63411,
 author = {Hughes, J.},
 title = {Why Functional Programming Matters},
 journal = {Comput. J.},
 issue_date = {April 1989},
 volume = {32},
 number = {2},
 month = apr,
 year = {1989},
 issn = {0010-4620},
 pages = {98--107},
 numpages = {10},
 url = {http://dx.doi.org/10.1093/comjnl/32.2.98},
 doi = {10.1093/comjnl/32.2.98},
 acmid = {63411},
 publisher = {Oxford University Press},
 address = {Oxford, UK},
}

@inproceedings{jablin11automatic,
 author = {Jablin, Thomas B. and Prabhu, Prakash and Jablin, James A. and Johnson, Nick P. and Beard, Stephen R. and August, David I.},
 title = {Automatic {CPU-GPU} Communication Management and Optimization},
 booktitle = {PLDI},
 booktitle2 = "{Proceedings of PLDI 32}",
 booktitle3 = PLDI,
 year = 2011
}

@inproceedings{ofenbeck13spiral,
author = {Georg Ofenbeck and Tiark Rompf and Alen Stojanov and Martin Odersky and Markus P{\"u}schel},
title = {{SPIRAL} in {S}cala: Towards the Systematic Construction of Generators for Performance Libraries},
booktitle = {International Conference on Generative Programming: Concepts \& Experiences},
booktitle3 = {Proc. of the Intl. Conf. on Generative Programming: Concepts \& Experiences},
series = {GPCE},
year = 2013
}

@article{Alnaes:2014:UFL:2594412.2566630,
 author = {Aln{\ae}s, Martin S. and Logg, Anders and Olgaard, Kristian B. and Rognes, Marie E. and Wells, Garth N.},
 title = {Unified Form Language: A Domain-specific Language for Weak Formulations of Partial Differential Equations},
 journal = {ACM Trans. Math. Softw.},
 issue_date = {February 2014},
 volume = {40},
 number = {2},
 month = mar,
 year = {2014},
 issn = {0098-3500},
 pages = {9:1--9:37},
 articleno = {9},
 numpages = {37},
 url = {http://doi.acm.org/10.1145/2566630},
 doi = {10.1145/2566630},
 acmid = {2566630},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {AD, DSEL, DSL, FEM, PDE, algorithmic differentiation, automatic functional differentiation, discretization, domain specific language, einstein notation, embedded language, finite element method, functional, implicit summation, index notation, mixed element, partial differential equation, symbolic differentiation, tensor algebra, weak form, weak formulation},
}

@inproceedings{Mullapudi:2015:PAO:2694344.2694364,
 author = {Mullapudi, Ravi Teja and Vasista, Vinay and Bondhugula, Uday},
 title = {{PolyMage}: Automatic Optimization for Image Processing Pipelines},
 booktitle = {Proceedings of the Twentieth International Conference on Architectural Support for Programming Languages and Operating Systems},
 series = {ASPLOS '15},
 year = {2015},
 isbn = {978-1-4503-2835-7},
 location = {Istanbul, Turkey},
 pages = {429--443},
 numpages = {15},
 url = {http://doi.acm.org/10.1145/2694344.2694364},
 doi = {10.1145/2694344.2694364},
 acmid = {2694364},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {domain-specific language, image processing, locality, multicores, parallelism, polyhedral optimization, tiling, vectorization},
}

@techreport{baghdadi2015PENCIL,
  TITLE = {{PENCIL Language Specification}},
  AUTHOR = {Baghdadi, Riyadh and Cohen, Albert and Grosser, Tobias and Verdoolaege, Sven and Lokhmotov, Anton and Absar, Javed and Van Haastregt, Sven and Kravets, Alexey and Donaldson, Alastair},
  URL = {https://hal.inria.fr/hal-01154812},
  TYPE = {Research Report},
  NUMBER = {RR-8706},
  PAGES = {37},
  INSTITUTION = {{INRIA}},
  YEAR = {2015},
  MONTH = May,
  KEYWORDS = {PENCIL ; DSL ; Accelerator ; Domain Specific Language ; Intermediate Language ; OpenCL},
  PDF = {https://hal.inria.fr/hal-01154812/file/RR-8706.pdf},
  HAL_ID = {hal-01154812},
  HAL_VERSION = {v3},
}

@inproceedings{Yuan:2017:TOS:3101282.3101287,
 author = {Yuan, Eric},
 title = {Towards Ontology-based Software Architecture Representations},
 booktitle = {Proceedings of the 1st International Workshop on Establishing the Community-Wide Infrastructure for Architecture-Based Software Engineering},
 series = {ECASE '17},
 year = {2017},
 isbn = {978-1-5386-0417-5},
 location = {Buenos Aires, Argentina},
 pages = {21--27},
 numpages = {7},
 url = {https://doi.org/10.1109/ECASE.2017..5},
 doi = {10.1109/ECASE.2017..5},
 acmid = {3101287},
 publisher = {IEEE Press},
 address = {Piscataway, NJ, USA},
 keywords = {OWL, architecture description languages, architecture representation, ontology, software architecture},
}

@misc{mkl,
  title  = {{Math Kernel Library}},
  author = {Intel},
  year   = {2003},
  url    = {https://software.intel.com/en-us/intel-mkl}
}

@misc{cublas,
  title  = {{cuBLAS}},
  author = {Nvidia},
  year   = {2012},
  url    = {http://developer.nvidia.com/cublas},
}

@misc{clblas,
  title  = {{clBLAS}},
  author = {AMD},
  year   = {2013},
  url    = {https://github.com/clMathLibraries/clBLAS},
}

@misc{apl,
 title  = {{Performance Libraries}},
 author = {Arm},
 year   = {2017},
 note={URL
       \href{https://developer.arm.com/tools-and-software/server-and-hpc/arm-architecture-tools/arm-performance-libraries}
             {\nolinkurl{https://developer.arm.com/tools-and-}\linebreak
              \nolinkurl{software/server-and-hpc/arm-architecture-tools/}\hfill\nolinkurl{arm-performance-libra}\linebreak
              \nolinkurl{ries}}}
}

@misc{qml,
 title  = {{Math Library}},
 author = {Qualcomm},
 year   = {2017},
 url    = {https://developer.qualcomm.com/software/qualcomm-math-library}
}

@inproceedings{PhothilimthanaARA13,
  author    = {Phitchaya Mangpo Phothilimthana and
               Jason Ansel and
               Jonathan Ragan{-}Kelley and
               Saman P. Amarasinghe},
  title     = {Portable performance on heterogeneous architectures},
  booktitle = {{ASPLOS}},
  pages     = {431--444},
  publisher = {{ACM}},
  year      = {2013}
}

@inproceedings{MuralidharanRHG16,
  author    = {Saurav Muralidharan and
               Amit Roy and
               Mary W. Hall and
               Michael Garland and
               Piyush Rai},
  title     = {Architecture-Adaptive Code Variant Tuning},
  booktitle = {{ASPLOS}},
  pages     = {325--338},
  publisher = {{ACM}},
  year      = {2016}
}

@inproceedings{chakravarty11accelerating,
 author = {Chakravarty, Manuel M.T. and Keller, Gabriele and Lee, Sean and McDonell, Trevor L. and Grover, Vinod},
 title = {Accelerating Haskell Array Codes with Multicore {GPUs}},
 booktitle = {Proceedings of the Sixth Workshop on Declarative Aspects of Multicore Programming},
 series = {DAMP '11},
 year = {2011},
 isbn = {978-1-4503-0486-3},
 location = {Austin, Texas, USA},
 pages = {3--14},
 numpages = {12},
 url = {http://doi.acm.org/10.1145/1926354.1926358},
 doi = {10.1145/1926354.1926358},
 acmid = {1926358},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {arrays, data parallelism, dynamic compilation, gpgpu, haskell, skeletons},
}

@inproceedings{mcdonell13optimising,
 author = {McDonell, Trevor L. and Chakravarty, Manuel M.T. and Keller, Gabriele and Lippmeier, Ben},
 title = {Optimising Purely Functional {GPU} Programs},
 booktitle = {Proceedings of the 18th ACM SIGPLAN International Conference on Functional Programming},
 series = {ICFP '13},
 year = {2013},
 isbn = {978-1-4503-2326-0},
 location = {Boston, Massachusetts, USA},
 pages = {49--60},
 numpages = {12},
 url = {http://doi.acm.org/10.1145/2500365.2500595},
 doi = {10.1145/2500365.2500595},
 acmid = {2500595},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {array fusion, arrays, data parallelism, dynamic compilation, embedded language, gpgpu, haskell, sharing recovery},
}

@inproceedings{Ansel:2009:PLC:1542476.1542481,
 author = {Ansel, Jason and Chan, Cy and Wong, Yee Lok and Olszewski, Marek and Zhao, Qin and Edelman, Alan and Amarasinghe, Saman},
 title = {PetaBricks: A Language and Compiler for Algorithmic Choice},
 booktitle = {Proceedings of the 30th ACM SIGPLAN Conference on Programming Language Design and Implementation},
 series = {PLDI '09},
 year = {2009},
 isbn = {978-1-60558-392-1},
 location = {Dublin, Ireland},
 pages = {38--49},
 numpages = {12},
 url = {http://doi.acm.org/10.1145/1542476.1542481},
 doi = {10.1145/1542476.1542481},
 acmid = {1542481},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {adaptive, algorithmic choice, autotuning, compiler, implicitly parallel, language},
}

@inproceedings{collins14nova,
 author = {Collins, Alexander and Grewe, Dominik and Grover, Vinod and Lee, Sean and Susnea, Adriana},
 title = {{NOVA}: A Functional Language for Data Parallelism},
 booktitle = {Proceedings of ACM SIGPLAN International Workshop on Libraries, Languages, and Compilers for Array Programming},
 series = {ARRAY'14},
 year = {2014},
 isbn = {978-1-4503-2937-8},
 location = {Edinburgh, United Kingdom},
 pages = {8:8--8:13},
 articleno = {8},
 numpages = {6},
 url = {http://doi.acm.org/10.1145/2627373.2627375},
 doi = {10.1145/2627373.2627375},
 acmid = {2627375},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {Array-oriented programming, CUDA, Code generation, Compilation, Functional programming, Multi-core CPU},
}

@techreport{catanzaro11copperhead,
    Author = {Catanzaro, Bryan and Garland, Michael and Keutzer, Kurt},
    Title = {Copperhead: Compiling an Embedded Data Parallel Language},
    Institution = {EECS Department, University of California, Berkeley},
    Year = {2010},
    Month = {Sep},
    URL = {http://www2.eecs.berkeley.edu/Pubs/TechRpts/2010/EECS-2010-124.html},
    Number = {UCB/EECS-2010-124},
    Abstract = {Modern parallel microprocessors deliver high performance on applications that expose substantial fine-grained data parallelism. Although data parallelism is widely available in many computations, implementing data parallel algorithms in low-level languages is often an unnecessarily difficult task. The characteristics of parallel microprocessors and the limitations of current programming methodologies motivate our design of Copperhead, a high-level data parallel language embedded in Python. The Copperhead programmer describes parallel computations via composition of familiar data parallel primitives supporting both flat and nested data parallel computation on arrays of data. Copperhead programs are expressed in a subset of the widely used Python programming language and interoperate with standard Python modules, including libraries for numeric computation, data visualization, and analysis.
In this paper, we discuss the language, compiler, and runtime features that enable Copperhead to efficiently execute data parallel code. We define the restricted subset of Python which Copperhead supports and introduce the program analysis techniques necessary for compiling Copperhead code into efficient low-level implementations. We also outline the runtime support by which Copperhead programs interoperate with standard Python modules. We demonstrate the effectiveness of our techniques with several examples targeting the CUDA platform for parallel programming on GPUs. Copperhead code is concise, on average requiring 3.6 times fewer lines of code than CUDA, and the compiler generates efficient code, yielding 45-100% of the performance of hand-crafted, well optimized CUDA code.}
}

@inproceedings{brown11heterogeneous,
 author = {Brown, Kevin J. and Sujeeth, Arvind K. and Lee, Hyouk Joong and Rompf, Tiark and Chafi, Hassan and Odersky, Martin and Olukotun, Kunle},
 title = {A Heterogeneous Parallel Framework for Domain-Specific Languages},
 booktitle = {Proceedings of the 2011 International Conference on Parallel Architectures and Compilation Techniques},
 series = {PACT '11},
 year = {2011},
 isbn = {978-0-7695-4566-0},
 pages = {89--100},
 numpages = {12},
 url = {http://dx.doi.org/10.1109/PACT.2011.15},
 doi = {10.1109/PACT.2011.15},
 acmid = {2121410},
 publisher = {IEEE Computer Society},
 address = {Washington, DC, USA},
 keywords = {parallel programming, multicore processing, computer languages},
}

@article{chafi11domain,
 author = {Chafi, Hassan and Sujeeth, Arvind K. and Brown, Kevin J. and Lee, HyoukJoong and Atreya, Anand R. and Olukotun, Kunle},
 title = {A Domain-specific Approach to Heterogeneous Parallelism},
 journal = {SIGPLAN Not.},
 issue_date = {August 2011},
 volume = {46},
 number = {8},
 month = feb,
 year = {2011},
 issn = {0362-1340},
 pages = {35--46},
 numpages = {12},
 url = {http://doi.acm.org/10.1145/2038037.1941561},
 doi = {10.1145/2038037.1941561},
 acmid = {1941561},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {domain-specific languages, dynamic optimizations, parallel programming, runtimes},
}

@article{Pinter:1994:POP:177492.177494,
 author = {Pinter, Shlomit S. and Pinter, Ron Y.},
 title = {Program Optimization and Parallelization Using Idioms},
 journal = {ACM Trans. Program. Lang. Syst.},
 issue_date = {May 1994},
 volume = {16},
 number = {3},
 month = may,
 year = {1994},
 issn = {0164-0925},
 pages = {305--327},
 numpages = {23},
 url = {http://doi.acm.org/10.1145/177492.177494},
 doi = {10.1145/177492.177494},
 acmid = {177494},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {array data flow analysis, computational idioms, dependence analysis, graph rewriting, intermediate program representation, parallel prefix, parallelism, reduction, scan operations},
}

@inproceedings{lattner2004llvm,
  title={LLVM: A compilation framework for lifelong program analysis \& transformation},
  author={Lattner, Chris and Adve, Vikram},
  booktitle={Code Generation and Optimization, 2004. CGO 2004. International Symposium on},
  pages={75--86},
  year={2004},
  organization={IEEE}
}

@inproceedings{benabderrahmane2010polyhedral,
  title={The polyhedral model is more widely applicable than you think},
  author={Benabderrahmane, Mohamed-Walid and Pouchet, Louis-No{\"e}l and Cohen, Albert and Bastoul, C{\'e}dric},
  booktitle={International Conference on Compiler Construction},
  pages={283--303},
  year={2010},
  organization={Springer}
}

@phdthesis{Andion2015Compilation,
  author = {José M. Andión},
  title = {Compilation Techniques for Automatic Extraction of Parallelism and Locality in Heterogeneous Architectures},
  school = {University of A Coruña},
  year      = {2015}
}

@inproceedings{fisher1994parallelizing,
  title={Parallelizing complex scans and reductions},
  author={Fisher, Allan L and Ghuloum, Anwar M},
  booktitle={ACM SIGPLAN Notices},
  volume={29},
  pages={135--146},
  year={1994},
  organization={ACM}
}

@inproceedings{pottenger1995idiom,
  title={Idiom recognition in the Polaris parallelizing compiler},
  author={Pottenger, Bill and Eigenmann, Rudolf},
  booktitle={Proceedings of the 9th international conference on Supercomputing},
  pages={444--448},
  year={1995},
  organization={ACM}
}

@inproceedings{suganuma1996detection,
  title={Detection and global optimization of reduction operations for distributed parallel machines},
  author={Suganuma, Toshio and Komatsu, Hideaki and Nakatani, Toshio},
  booktitle={Proceedings of the 10th international conference on Supercomputing},
  pages={18--25},
  year={1996},
  organization={ACM}
}

@inproceedings{jouvelot1989unified,
  title={A unified semantic approach for the vectorization and parallelization of generalized reductions},
  author={Jouvelot, Pierre and Dehbonei, Babak},
  booktitle={Proceedings of the 3rd international conference on Supercomputing},
  pages={186--194},
  year={1989},
  organization={ACM}
}

@inproceedings{redon1994scheduling,
  title={Scheduling reductions},
  author={Redon, Xavier and Feautrier, Paul},
  booktitle={Proceedings of the 8th international conference on Supercomputing},
  pages={117--125},
  year={1994},
  organization={ACM}
}

@inproceedings{Gutierrez:2000,
 author = {Guti{\'e}rrez, E. and Plata, O. and Zapata, E. L.},
 title = {A Compiler Method for the Parallel Execution of Irregular Reductions in Scalable Shared Memory Multiprocessors},
 booktitle = {Proceedings of the 14th International Conference on Supercomputing},
 series = {ICS '00},
 year = {2000},
 isbn = {1-58113-270-0},
 location = {Santa Fe, New Mexico, USA},
 pages = {78--87},
 numpages = {10},
 url = {http://doi.acm.org/10.1145/335231.335239},
 doi = {10.1145/335231.335239},
 acmid = {335239},
 publisher = {ACM},
 address = {New York, NY, USA},
}

@article{gutierrez2003optimization,
  title={Optimization techniques for parallel irregular reductions},
  author={Guti{\'e}rrez, Eladio and Plata, O and Zapata, Emilio L},
  journal={Journal of systems architecture},
  volume={49},
  number={3},
  pages={63--74},
  year={2003},
  publisher={Elsevier}
}

@article{gutierrez2008analytical,
  title={An analytical model of locality-based parallel irregular reductions},
  author={Guti{\'e}rrez, Eladio and Plata, Oscar and Zapata, Emilio L},
  journal={Parallel Computing},
  volume={34},
  number={3},
  pages={133--157},
  year={2008},
  publisher={Elsevier}
}

@article{yu2006adaptive,
  title={An adaptive algorithm selection framework for reduction parallelization},
  author={Yu, Hao and Rauchwerger, Lawrence},
  journal={IEEE Transactions on Parallel and Distributed Systems},
  volume={17},
  number={10},
  pages={1084--1096},
  year={2006},
  publisher={IEEE}
}

@inproceedings{ravi2010compiler,
  title={Compiler and runtime support for enabling generalized reduction computations on heterogeneous parallel configurations},
  author={Ravi, Vignesh T and Ma, Wenjing and Chiu, David and Agrawal, Gagan},
  booktitle={Proceedings of the 24th ACM international conference on supercomputing},
  pages={137--146},
  year={2010},
  organization={ACM}
}

@inproceedings{Huo2011HiPC,
 author = {Huo, X. and Ravi, V. and Agrawal, G.},
 title = {Porting irregular reductions on heterogeneous {CPU-GPU} configurations},
 booktitle = {Proceedings of the 18th IEEE International Conference on High Performance Computing},
 year = {2011},
}

@article{chi1997optimizing,
  title={On optimizing a class of multi-dimensional loops with reduction for parallel execution},
  author={Chi-Chung, Lam and Sadayappan, P and Wenger, Rephael},
  journal={Parallel Processing Letters},
  volume={7},
  number={02},
  pages={157--168},
  year={1997},
  publisher={World Scientific}
}

@INPROCEEDINGS{Verdoolaege12polyhedralextraction,
    author = {Sven Verdoolaege and Tobias Grosser},
    title = {Polyhedral extraction tool},
    booktitle = {In Second International Workshop on Polyhedral Compilation Techniques (IMPACT’12},
    year = {2012}
}

@inproceedings{gupta2006simplifying,
  title={Simplifying reductions.},
  author={Gupta, Gautam and Rajopadhye, Sanjay V},
  booktitle={POPL},
  volume={6},
  pages={30--41},
  year={2006}
}

@inproceedings{stock2014framework,
 author = {Stock, Kevin and Kong, Martin and Grosser, Tobias and Pouchet, Louis-No\"{e}l and Rastello, Fabrice and Ramanujam, J. and Sadayappan, P.},
 title = {A Framework for Enhancing Data Reuse via Associative Reordering},
 booktitle = {Proceedings of the 35th ACM SIGPLAN Conference on Programming Language Design and Implementation},
 series = {PLDI '14},
 year = {2014},
 isbn = {978-1-4503-2784-8},
 location = {Edinburgh, United Kingdom},
 pages = {65--76},
 numpages = {12},
 url = {http://doi.acm.org/10.1145/2594291.2594342},
 doi = {10.1145/2594291.2594342},
 acmid = {2594342},
 publisher = {ACM},
 address = {New York, NY, USA},
}

@inproceedings{Kepner2015GraphsMA,
  title={Graphs, Matrices, and the GraphBLAS: Seven Good Reasons},
  author={Jeremy Kepner and David A. Bader and Aydin Buluç and John R. Gilbert and Timothy G. Mattson and Henning Meyerhenke},
  booktitle={ICCS},
  year={2015}
}

@misc{cusparse,
  title={{NVIDIA CUDA Sparse Matrix library (cuSPARSE)}},
  year={2010},
  author={{NVIDIA}},
  howpublished = {\url{https://developer.nvidia.com/cusparse}}
}

@misc{clsparse,
  title={{clSPARSE}},
  author={{AMD}},
  year={2015},
  howpublished = {\url{https://github.com/clMathLibraries/clSPARSE}}
}

@book{doi:10.1137/1.9780898718003,
author = {Saad, Y.},
title = {Iterative Methods for Sparse Linear Systems},
publisher = {Society for Industrial and Applied Mathematics},
year = {2003},
doi = {10.1137/1.9780898718003},
address = {},
edition   = {Second},
URL = {https://epubs.siam.org/doi/abs/10.1137/1.9780898718003},
eprint = {https://epubs.siam.org/doi/pdf/10.1137/1.9780898718003}
}

@article{doi:10.1137/0910073,
author = {Saad, Y.},
title = {Krylov Subspace Methods on Supercomputers},
journal = {SIAM Journal on Scientific and Statistical Computing},
volume = {10},
number = {6},
pages = {1200-1232},
year = {1989},
doi = {10.1137/0910073},
URL = {https://doi.org/10.1137/0910073},
eprint = {https://doi.org/10.1137/0910073}
}

@article{doi:10.1080/00268970210162691,
author = {Wales,David J.},
title = {Discrete path sampling},
journal = {Molecular Physics},
volume = {100},
number = {20},
pages = {3285-3305},
year  = {2002},
publisher = {Taylor & Francis},
doi = {10.1080/00268970210162691}
}

@article{SUTHERLANDCASH2017288,
title = "Exploiting sparsity in free energy basin-hopping",
journal = "Chemical Physics Letters",
volume = "685",
pages = "288 - 293",
year = "2017",
issn = "0009-2614",
doi = "https://doi.org/10.1016/j.cplett.2017.07.081",
url = "http://www.sciencedirect.com/science/article/pii/S0009261417307583",
author = "Kyle H. Sutherland-Cash and Rosemary G. Mantell and David J. Wales"
}

@book{demetrescu2009shortest,
  title={The Shortest Path Problem: Ninth DIMACS Implementation Challenge},
  author={Demetrescu, Camil and Goldberg, Andrew V. and Johnson, David S.},
  volume={74},
  year={2009},
  publisher={American Mathematical Soc.}
}

@article{Beamer2015GAP,
author = {Beamer, Scott and Asanović, Krste and Patterson, David},
journal = {arXiv},
year = {2015},
url = {https://arxiv.org/abs/1508.03619},
pages = {},
title = {The GAP Benchmark Suite}
}

@article{doi:10.1063/1.478595,
author = {Doye,Jonathan P. K.  and Miller,Mark A.  and Wales,David J. },
title = {The double-funnel energy landscape of the 38-atom Lennard-Jones cluster},
journal = {The Journal of Chemical Physics},
volume = {110},
number = {14},
pages = {6896-6906},
year = {1999},
doi = {10.1063/1.478595}
}

@article{Davis:2011:UFS:2049662.2049663,
 author = {Davis, Timothy A. and Hu, Yifan},
 title = {The University of Florida Sparse Matrix Collection},
 journal = {ACM Trans. Math. Softw.},
 issue_date = {November 2011},
 volume = {38},
 number = {1},
 month = dec,
 year = {2011},
 issn = {0098-3500},
 pages = {1:1--1:25},
 articleno = {1},
 numpages = {25},
 url = {http://doi.acm.org/10.1145/2049662.2049663},
 doi = {10.1145/2049662.2049663},
 acmid = {2049663},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {Graph drawing, multilevel algorithms, performance evaluation, sparse matrices},
}

@inproceedings{Bailey1991NPB,
 author = {Bailey, D. H. and Barszcz, E. and Barton, J. T. and Browning, D. S. and Carter, R. L. and Dagum, L. and Fatoohi, R. A. and Frederickson, P. O. and Lasinski, T. A. and Schreiber, R. S. and Simon, H. D. and Venkatakrishnan, V. and Weeratunga, S. K.},
 title = {The {NAS} Parallel Benchmarks},
 booktitle = {Proceedings of the 1991 ACM/IEEE Conference on Supercomputing},
 series = {Supercomputing '91},
 year = {1991},
 isbn = {0-89791-459-7},
 location = {Albuquerque, New Mexico, USA},
 pages = {158--165},
 numpages = {8},
 url = {http://doi.acm.org/10.1145/125826.125925},
 doi = {10.1145/125826.125925},
 acmid = {125925},
 publisher = {ACM},
 address = {New York, NY, USA},
}

@article{Stratton2018,
  title = {Parboil: {{A Revised Benchmark Suite}} for {{Scientific}} and {{Commercial Throughput Computing}}},
  year = {2018},
  journal = {IMPACT Technical Report},
  shorttitle = {Parboil},
  abstract = {The Parboil benchmarks are a set of throughput computing applications useful for studying the performance of throughput computing architecture and compilers. The name comes from the culinary term for a partial cooking process, which represents our belief that useful throughput computing benchmarks must be "cooked", or preselected to implement a scalable algorithm with fine-grained parallel tasks. But useful benchmarks for this field cannot be "fully cooked", because the architectures and programming models and supporting tools are evolving rapidly enough that static benchmark codes will lose relevance very quickly. We have collected benchmarks from throughput computing application researchers in many different scientific and commercial fields including image processing, biomolecular simulation, fluid dynamics, and astronomy. Each benchmark includes several implementations. Some implementations we provide as readable base implementations from which new optimization efforts can begin, and others as examples of the current state-of-the-art targeting specific CPU and GPU architectures. As we continue to optimize these benchmarks for new and existing architectures ourselves, we will also gladly accept new implementations and benchmark contributions from developers to recognize those at the frontier of performance optimization on each architecture. Finally, by including versions of varying levels of optimization of the same fundamental algorithm, the bench-marks present opportunities to demonstrate tools and architectures that help programmers get the most out of their parallel hardware. Less optimized versions are presented as challenges to the compiler and architecture research communities: to develop the technology that automatically raises the performance of simpler implementations to the performance level of sophisticated programmer-optimized implementations, or demonstrate any other performance or programmability improvements. We hope that these benchmarks will facilitate effective demonstrations of such technology.},
  author = {Stratton, John and Rodrigues, Christopher and Sung, I-Jui and Obeid, Nady and Chang, Li-Wen and Anssari, Nasser and Geng, Daniel and Liu, Wen-Mei and Hwu, Wen-mei}
}

@article{Dongarra2001,
  title = {An {{Iterative Solver Benchmark}}},
  volume = {9},
  issn = {1058-9244},
  doi = {10.1155/2001/527931},
  abstract = {We present a benchmark of iterative solvers for sparse matrices. The benchmark contains several common methods and data structures, chosen to be representative of the performance of a large class of methods in current use. We give results on some high performance processors that show that performance is largely determined by memory bandwidth.},
  number = {4},
  urldate = {2018-07-06},
  journal = {Sci. Program.},
  url = {https://doi.org/10.1155/2001/527931},
  author = {Dongarra, Jack and Eijkhout, Victor and {van der Vorst}, Henk},
  month = dec,
  year = {2001},
  pages = {223--231}
}

@inproceedings{Baxter:1989:RPS:72935.72967,
 author = {Baxter, D. and Mirchandaney, R. and Saltz, J. H.},
 title = {Run-time Parallelization and Scheduling of Loops},
 booktitle = {Proceedings of the First Annual ACM Symposium on Parallel Algorithms and Architectures},
 series = {SPAA '89},
 year = {1989},
 isbn = {0-89791-323-X},
 location = {Santa Fe, New Mexico, USA},
 pages = {303--312},
 numpages = {10},
 url = {http://doi.acm.org/10.1145/72935.72967},
 doi = {10.1145/72935.72967},
 acmid = {72967},
 publisher = {ACM},
 address = {New York, NY, USA},
}

@article{rauchwerger1999lrpd,
  title={The {LRPD} test: Speculative run-time parallelization of loops with privatization and reduction parallelization},
  author={Rauchwerger, Lawrence and Padua, David A},
  journal={IEEE Transactions on Parallel and Distributed Systems},
  volume={10},
  number={2},
  pages={160--180},
  year={1999},
  publisher={IEEE}
}

@inproceedings{Zhao:2018:PCF:3178372.3179509,
 author = {Zhao, Jie and Kruse, Michael and Cohen, Albert},
 title = {A Polyhedral Compilation Framework for Loops with Dynamic Data-dependent Bounds},
 booktitle = {Proceedings of the 27th International Conference on Compiler Construction},
 series = {CC 2018},
 year = {2018},
 isbn = {978-1-4503-5644-2},
 location = {Vienna, Austria},
 pages = {14--24},
 numpages = {11},
 url = {http://doi.acm.org/10.1145/3178372.3179509},
 doi = {10.1145/3178372.3179509},
 acmid = {3179509},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {dynamic counted loop, loop nest optimization, parallelizing compiler, polyhedral model},
}

@article{pinter1994program,
  title={Program optimization and parallelization using idioms},
  author={Pinter, Shlomit S and Pinter, Ron Y},
  journal={ACM Transactions on Programming Languages and Systems (TOPLAS)},
  volume={16},
  number={3},
  pages={305--327},
  year={1994},
  publisher={ACM}
}

@article{Sujeeth:2014:DCA:2601432.2584665,
 author = {Sujeeth, Arvind K. and Brown, Kevin J. and Lee, Hyoukjoong and Rompf, Tiark and Chafi, Hassan and Odersky, Martin and Olukotun, Kunle},
 title = {Delite: A Compiler Architecture for Performance-Oriented Embedded Domain-Specific Languages},
 journal = {ACM TECS},
 issue_date = {July 2014},
 volume = {13},
 number = {4s},
 year = {2014},
 articleno = {134},
 numpages = {25},
 acmid = {2584665},
 publisher = {ACM},
 keywords = {Domain-specific languages, code generation, language virtualization, multistage programming},
}

@inproceedings{Hagedorn:2018:HPS:3179541.3168824,
 author = {Hagedorn, Bastian and Stoltzfus, Larisa and Steuwer, Michel and Gorlatch, Sergei and Dubach, Christophe},
 title = {High Performance Stencil Code Generation with Lift},
 booktitle = {Proceedings of the 2018 International Symposium on Code Generation and Optimization},
 series = {CGO 2018},
 year = {2018},
 isbn = {978-1-4503-5617-6},
 location = {Vienna, Austria},
 pages = {100--112},
 numpages = {13},
 url = {http://doi.acm.org/10.1145/3168824},
 doi = {10.1145/3168824},
 acmid = {3168824},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {Code Generation, GPU Computing, Lift, Performance Portability, Stencil},
}

@inproceedings{Pizzuti:2019:PAA:3331553.3342614,
 author = {Pizzuti, Federico and Steuwer, Michel and Dubach, Christophe},
 title = {Position-dependent Arrays and Their Application for High Performance Code Generation},
 booktitle = {Proceedings of the 8th ACM SIGPLAN International Workshop on Functional High-Performance and Numerical Computing},
 series = {FHPNC 2019},
 year = {2019},
 isbn = {978-1-4503-6814-8},
 location = {Berlin, Germany},
 pages = {14--26},
 numpages = {13},
 url = {http://doi.acm.org/10.1145/3331553.3342614},
 doi = {10.1145/3331553.3342614},
 acmid = {3342614},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {Dependent types, Irregular data structures, Lift},
}

@article{Ragan-Kelley:2013:HLC:2499370.2462176,
 author = {Ragan-Kelley, Jonathan and Barnes, Connelly and Adams, Andrew and Paris, Sylvain and Durand, Fr{\'e}do and Amarasinghe, Saman},
 title = {Halide: A Language and Compiler for Optimizing Parallelism, Locality, and Recomputation in Image Processing Pipelines},
 journal = {SIGPLAN Not.},
 issue_date = {June 2013},
 volume = {48},
 number = {6},
 month = jun,
 year = {2013},
 issn = {0362-1340},
 pages = {519--530},
 numpages = {12},
 url = {http://doi.acm.org/10.1145/2499370.2462176},
 doi = {10.1145/2499370.2462176},
 acmid = {2462176},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {autotuning, compiler, domain specific language, gpu, image processing, locality, optimization, parallelism, redundant computation, vectorization},
}

@inproceedings{Suriana:2017:PAR:3049832.3049863,
 author = {Suriana, Patricia and Adams, Andrew and Kamil, Shoaib},
 title = {Parallel Associative Reductions in Halide},
 booktitle = {Proceedings of the 2017 International Symposium on Code Generation and Optimization},
 series = {CGO '17},
 year = {2017},
 isbn = {978-1-5090-4931-8},
 location = {Austin, USA},
 pages = {281--291},
 numpages = {11},
 url = {http://dl.acm.org/citation.cfm?id=3049832.3049863},
 acmid = {3049863},
 publisher = {IEEE Press},
 address = {Piscataway, NJ, USA},
}

@article{Mullapudi:2016:ASH:2897824.2925952,
 author = {Mullapudi, Ravi Teja and Adams, Andrew and Sharlet, Dillon and Ragan-Kelley, Jonathan and Fatahalian, Kayvon},
 title = {Automatically Scheduling Halide Image Processing Pipelines},
 journal = {ACM Trans. Graph.},
 issue_date = {July 2016},
 volume = {35},
 number = {4},
 month = jul,
 year = {2016},
 issn = {0730-0301},
 pages = {83:1--83:11},
 articleno = {83},
 numpages = {11},
 url = {http://doi.acm.org/10.1145/2897824.2925952},
 doi = {10.1145/2897824.2925952},
 acmid = {2925952},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {halide, image processing, optimizing compilers},
}

@inproceedings{Kiriansky:2016:OIM:2967938.2967948,
 author = {Kiriansky, Vladimir and Zhang, Yunming and Amarasinghe, Saman},
 title = {Optimizing Indirect Memory References with Milk},
 booktitle = {Proceedings of the 2016 International Conference on Parallel Architectures and Compilation},
 series = {PACT '16},
 year = {2016},
 isbn = {978-1-4503-4121-9},
 location = {Haifa, Israel},
 pages = {299--312},
 numpages = {14},
 url = {http://doi.acm.org/10.1145/2967938.2967948},
 doi = {10.1145/2967938.2967948},
 acmid = {2967948},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {bsp, graph algorithms, indirect memory reference, irregular memory access, milk, openmp, parallel algorithms},
}

@article{2002:USB:567806.567807,
 author = {Blackford, L. Susan and Demmel, James and Dongarra, Jack and Duff, Iain and Hammarling, Sven and Henry, Greg and Heroux, Michael and Kaufman, Linda and Lumsdaine, Andrew and Petitet, Antoine and Pozo, Roland and Remington, Karin and Whaley, R. Clint},
 title = {An Updated Set of Basic Linear Algebra Subprograms (BLAS)},
 journal = {ACM Trans. Math. Softw.},
 issue_date = {June 2002},
 volume = {28},
 number = {2},
 month = jun,
 year = {2002},
 issn = {0098-3500},
 pages = {135--151},
 numpages = {17},
 url = {http://doi.acm.org/10.1145/567806.567807},
 doi = {10.1145/567806.567807},
 acmid = {567807},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {BLAS, linear algebra, standards},
 key = {{$\!\!$}} ,
}

@inproceedings{Wang:2016:BHP:2925426.2926256,
 author = {Wang, Linnan and Wu, Wei and Xu, Zenglin and Xiao, Jianxiong and Yang, Yi},
 title = {BLASX: A High Performance Level-3 BLAS Library for Heterogeneous Multi-GPU Computing},
 booktitle = {Proceedings of the 2016 International Conference on Supercomputing},
 series = {ICS '16},
 year = {2016},
 isbn = {978-1-4503-4361-9},
 location = {Istanbul, Turkey},
 pages = {20:1--20:11},
 articleno = {20},
 numpages = {11},
 url = {http://doi.acm.org/10.1145/2925426.2926256},
 doi = {10.1145/2925426.2926256},
 acmid = {2926256},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {BLAS, Cache Hierarchy, MultiGPU, Runtime Scheduler, Tile Algorithms},
}

@InProceedings{10.1007/978-3-319-64203-1_33,
author="Moreton-Fernandez, Ana
and Rodriguez-Gutiez, Eduardo
and Gonzalez-Escribano, Arturo
and Llanos, Diego R.",
editor="Rivera, Francisco F.
and Pena, Tom{\'a}s F.
and Cabaleiro, Jos{\'e} C.",
title="Supporting the Xeon Phi Coprocessor in a Heterogeneous Programming Model",
booktitle="Euro-Par 2017: Parallel Processing",
year="2017",
publisher="Springer International Publishing",
address="Cham",
pages="457--469",
abstract="Supercomputers are becoming more heterogeneous. They are composed by several machines with different computation capabilities and different kinds and families of accelerators, such as GPUs or Intel Xeon Phi coprocessors. Programming these machines is a hard task, that requires a deep study of the architectural details, in order to exploit efficiently each computational unit.",
isbn="978-3-319-64203-1"
}

@article{Diego2017Multi,
author = {Moreton-Fernandez, Ana and Gonzalez-Escribano, Arturo and Ferraris, Diego},
year = {2017},
month = {12},
pages = {},
title = {Multi-device Controllers: A Library to Simplify Parallel Heterogeneous Programming},
journal = {International Journal of Parallel Programming}
}

@article{Jablin:2011:ACC:1993316.1993516,
 author = {Jablin, Thomas B. and Prabhu, Prakash and Jablin, James A. and Johnson, Nick P. and Beard, Stephen R. and August, David I.},
 title = {Automatic CPU-GPU Communication Management and Optimization},
 journal = {SIGPLAN Not.},
 issue_date = {June 2011},
 volume = {46},
 number = {6},
 month = jun,
 year = {2011},
 issn = {0362-1340},
 pages = {142--151},
 numpages = {10},
 url = {http://doi.acm.org/10.1145/1993316.1993516},
 doi = {10.1145/1993316.1993516},
 acmid = {1993516},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {communication, gpu, management, optimization},
}

@article{Lee:2009:OGC:1594835.1504194,
 author = {Lee, Seyong and Min, Seung-Jai and Eigenmann, Rudolf},
 title = {OpenMP to GPGPU: A Compiler Framework for Automatic Translation and Optimization},
 journal = {SIGPLAN Not.},
 issue_date = {April 2009},
 volume = {44},
 number = {4},
 month = feb,
 year = {2009},
 issn = {0362-1340},
 pages = {101--110},
 numpages = {10},
 url = {http://doi.acm.org/10.1145/1594835.1504194},
 doi = {10.1145/1594835.1504194},
 acmid = {1504194},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {automatic translation, compiler optimization, cuda, gpu, openmp},
}

@article{sparsex,
  title = {{{SparseX}}: {{A Library}} for {{High}}-{{Performance Sparse Matrix}}-{{Vector Multiplication}} on {{Multicore Platforms}}},
  volume = {44},
  issn = {0098-3500},
  shorttitle = {{{SparseX}}},
  doi = {10.1145/3134442},
  abstract = {The Sparse Matrix-Vector Multiplication (SpMV) kernel ranks among the most important and thoroughly studied linear algebra operations, as it lies at the heart of many iterative methods for the solution of sparse linear systems, and often constitutes a severe performance bottleneck. Its optimization, which is intimately associated with the data structures used to store the sparse matrix, has always been of particular interest to the applied mathematics and computer science communities and has attracted further attention since the advent of multicore architectures. In this article, we present SparseX, an open source software package for SpMV targeting multicore platforms, that employs the state-of-the-art Compressed Sparse eXtended (CSX) sparse matrix storage format to deliver high efficiency through a highly usable ``BLAS-like'' interface that requires limited or no tuning. Performance results indicate that our library achieves superior performance over competitive libraries on large-scale problems.},
  number = {3},
  urldate = {2018-06-05},
  journal = {ACM Trans. Math. Softw.},
  url = {http://doi.acm.org/10.1145/3134442},
  author = {Elafrou, Athena and Karakasis, Vasileios and Gkountouvas, Theodoros and Kourtis, Kornilios and Goumas, Georgios and Koziris, Nectarios},
  month = jan,
  year = {2018},
  keywords = {high-performance computing,HPC,sparse matrix-vector multiplication,CSX,data compression,multicore,scientific applications,SpMV,SpMV library},
  pages = {26:1--26:32},
  file = {/home/bruce/Zotero/storage/E7FB22HG/Elafrou et al. - 2018 - SparseX A Library for High-Performance Sparse Mat.pdf}
}

@inproceedings{Steuwer:2016:MMB:2968455.2968521,
 author = {Steuwer, Michel and Remmelg, Toomas and Dubach, Christophe},
 title = {Matrix Multiplication Beyond Auto-tuning: Rewrite-based GPU Code Generation},
 booktitle = {Proceedings of the International Conference on Compilers, Architectures and Synthesis for Embedded Systems},
 series = {CASES '16},
 year = {2016},
 isbn = {978-1-4503-4482-1},
 location = {Pittsburgh, Pennsylvania},
 pages = {15:1--15:10},
 articleno = {15},
 numpages = {10},
 url = {http://doi.acm.org/10.1145/2968455.2968521},
 doi = {10.1145/2968455.2968521},
 acmid = {2968521},
 publisher = {ACM},
 address = {New York, NY, USA},
}

@inproceedings{das2010experiences, 
author={D. {Das} and {Peng Wu}}, 
booktitle={2010 IEEE International Symposium on Parallel Distributed Processing, Workshops and Phd Forum (IPDPSW)}, 
title={Experiences of using a dependence profiler to assist parallelization for multi-cores}, 
year={2010}, 
volume={}, 
number={}, 
pages={1-8}, 
keywords={multiprocessing programs;optimising compilers;parallel processing;dependence profiler;multi-cores parallelization;data-dependence profiling;DProf;multi-core systems parallelization;optimizing compiler;thread-level parallelism;parallelizing compilers;OpenMP;Runtime;Optimizing compilers;Concurrent computing;Prototypes;Feeds;Multicore processing;Information analysis;Data Dependence;Profiler;Multi-core;Parallelization;Compiler}, 
doi={10.1109/IPDPSW.2010.5470884}, 
ISSN={}, 
month={April}
}

@inproceedings{Johnson:2012:SSP:2254064.2254107,
 author = {Johnson, Nick P. and Kim, Hanjun and Prabhu, Prakash and Zaks, Ayal and August, David I.},
 title = {Speculative Separation for Privatization and Reductions},
 booktitle = {Proceedings of the 33rd ACM SIGPLAN Conference on Programming Language Design and Implementation},
 series = {PLDI '12},
 year = {2012},
 isbn = {978-1-4503-1205-9},
 location = {Beijing, China},
 pages = {359--370},
 numpages = {12},
 url = {http://doi.acm.org/10.1145/2254064.2254107},
 doi = {10.1145/2254064.2254107},
 acmid = {2254107},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {automatic parallelization, separation, speculation},
} 

@article{hall1996maximizing, 
author={M. W. {Hall} and J. M. {Anderson} and S. P. {Amarasinghe} and B. R. {Murphy} and {Shih-Wei Liao} and E. {Bugnion} and M. S. {Lam}}, 
journal={Computer}, 
title={Maximizing multiprocessor performance with the SUIF compiler}, 
year={1996}, 
volume={29}, 
number={12}, 
pages={84-89}, 
keywords={mathematics computing;multiprocessing systems;optimising compilers;parallelising compilers;performance evaluation;benchmark programs;SPECfp95;NAS;speedups;robust analysis techniques;memory optimization techniques;parallelizing compilers;array-based numerical programs;Stanford University Intermediate Format compiler;automatic parallelization techniques;SUIF compiler;multiprocessor performance;Parallel processing;Phased arrays;Program processors;Information analysis;Concurrent computing;Privatization;Throughput;Multiprocessing systems;Cache memory;Programming profession}, 
doi={10.1109/2.546613}, 
ISSN={0018-9162}, 
month={Dec}
}

@inproceedings{Han:2000:ILA:645678.663936,
 author = {Han, Hwansoo and Tseng, Chau-Wen},
 title = {Improving Locality for Adaptive Irregular Scientific Codes},
 booktitle = {Proceedings of the 13th International Workshop on Languages and Compilers for Parallel Computing-Revised Papers},
 series = {LCPC '00},
 year = {2001},
 isbn = {3-540-42862-3},
 pages = {173--188},
 numpages = {16},
 url = {http://dl.acm.org/citation.cfm?id=645678.663936},
 acmid = {663936},
 publisher = {Springer-Verlag},
 address = {London, UK, UK},
} 

@inproceedings{kuck1981dependence,
  title={Dependence graphs and compiler optimizations},
  author={Kuck, David J and Kuhn, Robert H and Padua, David A and Leasure, Bruce and Wolfe, Michael},
  booktitle={Proceedings of the 8th ACM SIGPLAN-SIGACT symposium on Principles of programming languages},
  pages={207--218},
  year={1981},
  organization={ACM}
}

@inproceedings{ciesko2015scaling,
  title={Scaling irregular array-type reductions in OmpSs},
  author={Ciesko, Jan and Mateo Bellido, Sergi and Teruel, Xavier and Beltran, Vicen{\c{c}}},
  booktitle={BSC Doctoral Symposium (2nd: 2015: Barcelona)},
  pages={138--140},
  year={2015},
  organization={Barcelona Supercomputing Center}
}

@inproceedings{seo2011performance,
  title={Performance characterization of the NAS Parallel Benchmarks in OpenCL},
  author={Seo, Sangmin and Jo, Gangwon and Lee, Jaejin},
  booktitle={Workload Characterization (IISWC), 2011 IEEE International Symposium on},
  pages={137--148},
  year={2011},
  organization={IEEE}
}

@article{stratton2012parboil,
  title={Parboil: A revised benchmark suite for scientific and commercial throughput computing},
  author={Stratton, John A and Rodrigues, Christopher and Sung, I-Jui and Obeid, Nady and Chang, Li-Wen and Anssari, Nasser and Liu, Geng Daniel and Hwu, Wen-mei W},
  journal={Center for Reliable and High-Performance Computing},
  volume={127},
  year={2012}
}

@inproceedings{Che2009Rodinia,
 author = {Che, Shuai and Boyer, Michael and Meng, Jiayuan and Tarjan, David and Sheaffer, Jeremy W. and Lee, Sang-Ha and Skadron, Kevin},
 title = {Rodinia: A Benchmark Suite for Heterogeneous Computing},
 booktitle = {Proceedings of the 2009 IEEE International Symposium on Workload Characterization (IISWC)},
 series = {IISWC '09},
 year = {2009},
 isbn = {978-1-4244-5156-2},
 pages = {44--54},
 numpages = {11},
 url = {http://dx.doi.org/10.1109/IISWC.2009.5306797},
 doi = {10.1109/IISWC.2009.5306797},
 acmid = {1680782},
 publisher = {IEEE Computer Society},
 address = {Washington, DC, USA},
}

@inproceedings{Han2010Speculative,
 author = {Han, Liang and Liu, Wei and Tuck, James M.},
 title = {Speculative Parallelization of Partial Reduction Variables},
 booktitle = {Proceedings of the 8th Annual IEEE/ACM International Symposium on Code Generation and Optimization},
 series = {CGO '10},
 year = {2010},
 isbn = {978-1-60558-635-9},
 location = {Toronto, Ontario, Canada},
 pages = {141--150},
 numpages = {10},
 url = {http://doi.acm.org/10.1145/1772954.1772975},
 doi = {10.1145/1772954.1772975},
 acmid = {1772975},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {multi-core architecture, parallelization, reduction variables, thread-level speculation},
}

@inproceedings{aguilar2015unified,
  title={Unified Identification of Multiple Forms of Parallelism in Embedded Applications},
  author={Aguilar, Miguel Angel and Leupers, Rainer},
  booktitle={2015 International Conference on Parallel Architecture and Compilation (PACT)},
  pages={482--483},
  year={2015},
  organization={IEEE}
}

@article{deitz2002high,
  title={High-level language support for user-defined reductions},
  author={Deitz, Steven J and Chamberlain, Bradford L and Snyder, Lawrence},
  journal={The Journal of Supercomputing},
  volume={23},
  number={1},
  pages={23--37},
  year={2002},
  publisher={Springer}
}

@phdthesis{kim2012dynamic,
  title={Dynamic program analysis algorithms to assist parallelization},
  author={Kim, Minjang},
  year={2012},
  school={Georgia Institute of Technology}
}

@article{Clarke:2001:BMC:510986.510987,
 author = {Clarke, Edmund and Biere, Armin and Raimi, Richard and Zhu, Yunshan and Zhu, Yunshan},
 title = {Bounded Model Checking Using Satisfiability Solving},
 journal = {Form. Methods Syst. Des.},
 issue_date = {July 2001},
 volume = {19},
 number = {1},
 month = jul,
 year = {2001},
 issn = {0925-9856},
 pages = {7--34},
 numpages = {28},
 url = {https://doi.org/10.1023/A:1011276507260},
 doi = {10.1023/A:1011276507260},
 acmid = {510987},
 publisher = {Kluwer Academic Publishers},
 address = {Norwell, MA, USA},
 keywords = {bounded model checking, cone of influence reduction, model checking, processor verification, satisfiability},
}

@article{DBLP:journals/pieee/WangO18,
  author    = {Zheng Wang and
               Michael F. P. O'Boyle},
  title     = {Machine Learning in Compiler Optimization},
  journal   = {Proceedings of the {IEEE}},
  volume    = {106},
  number    = {11},
  pages     = {1879--1901},
  year      = {2018},
  url       = {https://doi.org/10.1109/JPROC.2018.2817118},
  doi       = {10.1109/JPROC.2018.2817118},
  timestamp = {Fri, 02 Nov 2018 15:39:00 +0100},
  biburl    = {https://dblp.org/rec/bib/journals/pieee/WangO18},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@inproceedings{Chamberlin:1974:SSE:800296.811515,
 author = {Chamberlin, Donald D. and Boyce, Raymond F.},
 title = {SEQUEL: A Structured English Query Language},
 booktitle = {Proceedings of the 1974 ACM SIGFIDET (Now SIGMOD) Workshop on Data Description, Access and Control},
 series = {SIGFIDET '74},
 year = {1974},
 location = {Ann Arbor, Michigan},
 pages = {249--264},
 numpages = {16},
 url = {http://doi.acm.org/10.1145/800296.811515},
 doi = {10.1145/800296.811515},
 acmid = {811515},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {Data Base Management Systems, Data Manipulation Languages, Information Retrieval, Query Languages},
}

@inproceedings{Colmerauer:1993:BP:154766.155362,
 author = {Colmerauer, Alain and Roussel, Philippe},
 title = {The Birth of Prolog},
 booktitle = {The Second ACM SIGPLAN Conference on History of Programming Languages},
 series = {HOPL-II},
 year = {1993},
 isbn = {0-89791-570-4},
 location = {Cambridge, Massachusetts, USA},
 pages = {37--52},
 numpages = {16},
 url = {http://doi.acm.org/10.1145/154766.155362},
 doi = {10.1145/154766.155362},
 acmid = {155362},
 publisher = {ACM},
 address = {New York, NY, USA},
}

@book{Cole1991Algorithmic,
 author = {Cole, Murray},
 title = {Algorithmic Skeletons: Structured Management of Parallel Computation},
 year = {1991},
 isbn = {0-262-53086-4},
 publisher = {MIT Press},
 address = {Cambridge, MA, USA},
} 

@INPROCEEDINGS{Leyton2010Skandium, 
author={M. Leyton and J. M. Piquer}, 
booktitle={2010 18th Euromicro Conference on Parallel, Distributed and Network-based Processing}, 
title={Skandium: Multi-core Programming with Algorithmic Skeletons}, 
year={2010}, 
pages={289-296}, 
keywords={Application software;Clustering algorithms;Computer architecture;Distributed computing;Hardware;Libraries;Muscles;Parallel programming;Programming profession;Skeleton;algorithmic skeletons;multi-core;parallel programming;patterns}, 
doi={10.1109/PDP.2010.26}, 
ISSN={1066-6192}, 
month={Feb},}

@article{Loogen2005Parallel,
 author = {Loogen, Rita and Ortega-mall{\'e}n, Yolanda and Pe\~{n}a-mar\'{\i}, Ricardo},
 title = {Parallel Functional Programming in Eden},
 journal = {J. Funct. Program.},
 issue_date = {May 2005},
 volume = {15},
 number = {3},
 month = may,
 year = {2005},
 issn = {0956-7968},
 pages = {431--475},
 numpages = {45},
 url = {http://dx.doi.org/10.1017/S0956796805005526},
 doi = {10.1017/S0956796805005526},
 acmid = {1067409},
 publisher = {Cambridge University Press},
 address = {New York, NY, USA},
}

@article{Cole2004Bringing,
 author = {Cole, Murray},
 title = {Bringing Skeletons out of the Closet: A Pragmatic Manifesto for Skeletal Parallel Programming},
 journal = {Parallel Comput.},
 issue_date = {March 2004},
 volume = {30},
 number = {3},
 month = mar,
 year = {2004},
 issn = {0167-8191},
 pages = {389--406},
 numpages = {18},
 url = {http://dx.doi.org/10.1016/j.parco.2003.12.002},
 doi = {10.1016/j.parco.2003.12.002},
 acmid = {1007985},
 publisher = {Elsevier Science Publishers B. V.},
 address = {Amsterdam, The Netherlands, The Netherlands},
 keywords = {MPI, libraries, parallel programming, patterns, skeletons},
} 

@INPROCEEDINGS{Steuwer2011SkelCL, 
author={M. Steuwer and P. Kegel and S. Gorlatch}, 
booktitle={Parallel and Distributed Processing Workshops and Phd Forum (IPDPSW), 2011 IEEE International Symposium on}, 
title={SkelCL - A Portable Skeleton Library for High-Level GPU Programming}, 
year={2011}, 
pages={1176-1182}, 
keywords={abstract data types;coprocessors;formal specification;parallel programming;software libraries;CUDA;Mandelbrot set computation;OpenCL;SkelCL;abstract vector data type;algorithmic skeletons;data distribution specification;general-purpose programming;graphics processing units;high-level GPU programming;industrial-strength medical imaging application;parallel communication;parallel computation;portable skeleton library;Graphics processing unit;Image reconstruction;Kernel;Performance evaluation;Programming;Runtime;Skeleton}, 
doi={10.1109/IPDPS.2011.269}, 
ISSN={1530-2075}, 
month={May},}

@book{Reinders2007Intel,
 author = {Reinders, James},
 title = {Intel Threading Building Blocks},
 year = {2007},
 isbn = {9780596514808},
 edition = {First},
 publisher = {O'Reilly \& Associates, Inc.},
 address = {Sebastopol, CA, USA},
}

@TECHREPORT{Asanovic06thelandscape,
    author = {Krste Asanovic and Ras Bodik and Bryan Christopher Catanzaro and Joseph James Gebis and Parry Husbands and Kurt Keutzer and David A. Patterson and William Lester Plishker and John Shalf and Samuel Webb Williams and Katherine A. Yelick},
    title = {The Landscape of Parallel Computing Research: A View from Berkeley},
    institution = {TECHNICAL REPORT, UC BERKELEY},
    year = {2006}
}

@article{Dean2008MapReduce,
 author = {Dean, Jeffrey and Ghemawat, Sanjay},
 title = {MapReduce: Simplified Data Processing on Large Clusters},
 journal = {Commun. ACM},
 issue_date = {January 2008},
 volume = {51},
 number = {1},
 month = jan,
 year = {2008},
 issn = {0001-0782},
 pages = {107--113},
 numpages = {7},
 url = {http://doi.acm.org/10.1145/1327452.1327492},
 doi = {10.1145/1327452.1327492},
 acmid = {1327492},
 publisher = {ACM},
 address = {New York, NY, USA},
}

@phdthesis{Linton:CSD-83-164,
    Author = {Linton, Mark A.},
    Title = {Queries and Views of Programs Using a Relational Database System},
    School = {EECS Department, University of California, Berkeley},
    Year = {1983},
    Month = {Dec},
    URL = {http://www2.eecs.berkeley.edu/Pubs/TechRpts/1983/5296.html},
    Number = {UCB/CSD-83-164},
    Abstract = {Large software systems are expensive to develop and maintain.  A significant amount of programmer activity in understanding, changing, and debugging these systems is information management. To support these activities more directly, we have designed a programming environment, called OMEGA, that provides powerful mechanisms for accessing and displaying the information in a large software system.  <p>  OMEGA uses successful ideas from existing programming environments while trying to correct deficiencies. The major deficiency in these systems is that programmers can only view and manipulate a single logical representation of programs.  <p>  To support multiple representations, OMEGA uses a relational database system to manage all program information. Using a database system provides a powerful mechanism for efficient access to a variety of cross-sections of program information, as well as providing traditional database facilities such as concurrency control, data integrity, and crash recovery.  <p>  The user interface to OMEGA separates input specification from output display, relies on pointing rather than typing, and exploits interaction in semantic analysis to detect many errors as soon as they are made. By eliminating the traditional textual interface to programs, OMEGA also allows the unification of the different abstraction mechanisms present in traditional programming environments.<p>  We have experimented with the ideas in OMEGA by designing a relational schema for software written in a particular programming language, and by implementing a program that transfers existing programs, stored as text, into a database managed by an "off-the-shelf" database system. A prototype visual interface to the program database has also been implemented.  <p>The results of this thesis are new models of program representation and user interaction for software development systems. The model of program representation can be expressed in the relational data model, and software can therefore be manipulated easily and powerfully using relational calculus. Our experimental implementation demonstrates the feasibility of using a relational database system, and provides insights into potential problems and how they might be solved.}
}

@article{Stonebraker:1976:DII:320473.320476,
 author = {Stonebraker, Michael and Held, Gerald and Wong, Eugene and Kreps, Peter},
 title = {The Design and Implementation of INGRES},
 journal = {ACM Trans. Database Syst.},
 issue_date = {Sept. 1976},
 volume = {1},
 number = {3},
 month = sep,
 year = {1976},
 issn = {0362-5915},
 pages = {189--222},
 numpages = {34},
 url = {http://doi.acm.org/10.1145/320473.320476},
 doi = {10.1145/320473.320476},
 acmid = {320476},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {concurrency, data integrity, data organization, data sublanguage, database optimization, nonprocedural language, protection, query decompositon, query language, relational database},
}

@inproceedings{Hajiyev:2006:CSS:2171327.2171331,
 author = {Hajiyev, Elnar and Verbaere, Mathieu and de Moor, Oege},
 title = {CodeQuest: Scalable Source Code Queries with Datalog},
 booktitle = {Proceedings of the 20th European Conference on Object-Oriented Programming},
 series = {ECOOP'06},
 year = {2006},
 isbn = {3-540-35726-2, 978-3-540-35726-1},
 location = {Nantes, France},
 pages = {2--27},
 numpages = {26},
 url = {http://dx.doi.org/10.1007/11785477_2},
 doi = {10.1007/11785477_2},
 acmid = {2171331},
 publisher = {Springer-Verlag},
 address = {Berlin, Heidelberg},
}

@inproceedings{deMoor:2007:OQO:1244381.1244396,
 author = {de Moor, Oege and Hajiyev, Elnar and Verbaere, Mathieu},
 title = {Object-oriented Queries over Software Systems: (Abstract of Invited Talk)},
 booktitle = {Proceedings of the 2007 ACM SIGPLAN Symposium on Partial Evaluation and Semantics-based Program Manipulation},
 series = {PEPM '07},
 year = {2007},
 isbn = {978-1-59593-620-2},
 location = {Nice, France},
 pages = {91--91},
 numpages = {1},
 url = {http://doi.acm.org/10.1145/1244381.1244396},
 doi = {10.1145/1244381.1244396},
 acmid = {1244396},
 publisher = {ACM},
 address = {New York, NY, USA},
}

@article{Krings2016Constraint,
author = {Krings, Sebastian and Leuschel, Michael},
year = {2016},
month = {12},
pages = {73-87},
title = {Constraint Logic Programming over Infinite Domains with an Application to Proof},
volume = {234},
journal = {Electronic Proceedings in Theoretical Computer Science},
doi = {10.4204/EPTCS.234.6}
}

@inproceedings{CompCert-ERTS-2018,
  author = {Daniel Kästner and
            Ulrich Wünsche and
            Jörg Barrho and 
            Marc Schlickling and
            Bernhard Schommer and
            Michael Schmidt and
            Christian Ferdinand and
            Xavier Leroy and
            Sandrine Blazy},
  title = {{CompCert}: Practical experience on integrating and qualifying
           a formally verified optimizing compiler},
  booktitle = {ERTS 2018: Embedded Real Time Software and Systems},
  publisher = {SEE},
  year = 2018,
  month = jan,
  hal = {https://hal.inria.fr/hal-01643290},
  url = {http://xavierleroy.org/publi/erts2018_compcert.pdf},
  xtopic = {compcert},
  abstract = {CompCert is the first commercially available optimizing compiler that is formally verified, using machine-assisted mathematical proofs, to be exempt from mis-compilation. The executable code it produces is proved to behave exactly as specified by the semantics of the source C program. This article gives an overview of the use of CompCert to gain certification credits for a highly safety-critical industry application, certified according to IEC 60880. We will briefly introduce the target application, illustrate the process of changing the existing compiler infrastructure to CompCert, and discuss performance characteristics. The main part focuses on the tool qualification strategy, in particular on how to take advantage of the formal correctness proof in the certification process.}
}


@inproceedings{DBLP:conf/IEEEpact/CollieGO19,
  author    = {Bruce Collie and
               Philip Ginsbach and
               Michael F. P. O'Boyle},
  title     = {{Type-Directed Program Synthesis and Constraint
                Generation for Library Portability}},
  booktitle = {28th International Conference on Parallel Architectures and Compilation
               Techniques, {PACT} 2019, Seattle, WA, USA, September 23-26, 2019},
  pages     = {55--67},
  year      = {2019},
  url       = {https://doi.org/10.1109/PACT.2019.00013},
  doi       = {10.1109/PACT.2019.00013},
  timestamp = {Wed, 13 Nov 2019 18:11:57 +0100},
  biburl    = {https://dblp.org/rec/bib/conf/IEEEpact/CollieGO19},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}