last_paper_bibliography.bib

@misc{beau_johnston_2017_1134175,
  author       = {Beau Johnston and
                  James Price and
                  Moritz Pflanzer and
                  Petros Kalos and
                  Tom Deakin and
                  Nido Media and
                  Daniel Saier},
  title        = {{BeauJoh/Oclgrind: Adding AIWC -- An Architecture 
                   Independent Workload Characterisation Plugin}},
  month        = dec,
  year         = 2017,
  doi          = {10.5281/zenodo.1134175},
  howpublished          = {https://doi.org/10.5281/zenodo.1134175}
}

@inproceedings{CaparrosCabezas:2011:PDM:1989493.1989506,
 author = {Caparr\'{o}s Cabezas, Victoria and Stanley-Marbell, Phillip},
 title = {Parallelism and Data Movement Characterization of Contemporary Application Classes},
 booktitle = {Proceedings of the Twenty-third Annual {ACM} Symposium on Parallelism in Algorithms and Architectures},
 series = {SPAA '11},
 year = {2011},
 isbn = {978-1-4503-0743-7},
 location = {San Jose, California, USA},
 pages = {95--104},
 numpages = {10},
 url = {http://doi.acm.org/10.1145/1989493.1989506},
 doi = {10.1145/1989493.1989506},
 acmid = {1989506},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {basic-block-level parallelism, berkeley computational motifs, data movement, instruction-level parallelism},
}

@article{spafford2010maestro,
  title={Maestro: data orchestration and tuning for {OpenCL} devices},
  author={Spafford, Kyle and Meredith, Jeremy and Vetter, Jeffrey},
  journal={Euro-Par 2010-Parallel Processing},
  pages={275--286},
  year={2010},
  publisher={Springer}
}

@inproceedings{price2017analyzing,
   title={Analyzing and improving performance portability of {OpenCL} applications via auto-tuning},
   author={Price, James and McIntosh-Smith, Simon},
   booktitle={Proceedings of the 5th International Workshop on {OpenCL}},
   pages={14},
   year={2017},
   organization={ACM}
}

@InProceedings{ansel:pact:2014,
   author    = "Jason Ansel and Shoaib Kamil and Kalyan Veeramachaneni and Jonathan Ragan-Kelley and Jeffrey Bosboom and Una-May O'Reilly and Saman Amarasinghe",
   title     = "OpenTuner: An Extensible Framework for Program Autotuning",
   url       = "http://groups.csail.mit.edu/commit/papers/2014/ansel-pact14-opentuner.pdf",
   slides    = "http://groups.csail.mit.edu/commit/papers/2014/ansel-pact14-opentuner-slides.pdf",
   keywords  = "OpenTuner",
   month     = "August",
   year      = "2014",
   address   = "Edmonton, Canada",
   booktitle = "International Conference on Parallel Architectures and Compilation Techniques ({PACT})",
}

@inproceedings{chaimov2014toward,
   title={Toward multi-target autotuning for accelerators},
   author={Chaimov, Nick and Norris, Boyana and Malony, Allen},
   booktitle={IEEE International Conference on Parallel and Distributed Systems ({ICPADS})},
   pages={534--541},
   year={2014},
   organization={IEEE}
}

@inproceedings{nugteren2015cltune,
   title={CLTune: A generic auto-tuner for {OpenCL} kernels},
   author={Nugteren, Cedric and Codreanu, Valeriu},
   booktitle={IEEE International Symposium on Embedded Multicore/Many-core Systems-on-Chip ({MCSoC})},
   pages={195--202},
   year={2015},
   organization={IEEE}
}

@inproceedings{meajil1997architecture,
    title={An architecture-independent workload characterization model for parallel computer architectures},
    author={Meajil, Abdullah I and El-Ghazawi, Tarek and Sterling, Thomas},
    booktitle={Second Aizu International Symposium on Parallel Algorithms/Architecture Synthesis},
    pages={143--150},
    year={1997},
    organization={IEEE}
}

@article{chen1996analysis,
    title={Analysis of branch prediction via data compression},
    author={Chen, I-Cheng K and Coffey, John T and Mudge, Trevor N},
    journal={ACM SIGPLAN Notices},
    volume={31},
    number={9},
    pages={128--137},
    year={1996},
    publisher={ACM}
}

@inproceedings{yokota2007introducing,
  title={Introducing entropies for representing program behavior and branch predictor performance},
  author={Yokota, Takashi and Ootsu, Kanemitsu and Baba, Takanobu},
  booktitle={Proceedings of the 2007 workshop on Experimental computer science},
  pages={17},
  year={2007},
  organization={ACM}
}

@inproceedings{Hammerstrom:1977:ICC:800255.810669,
    author = {Hammerstrom, D. W. and Davidson, E. S.},
    title = {Information Content of {CPU} Memory Referencing Behavior},
    booktitle = {Proceedings of the $4^{th}$ Annual Symposium on Computer Architecture},
    series = {ISCA '77},
    year = {1977},
    pages = {184--192},
    numpages = {9},
    url = {http://doi.acm.org/10.1145/800255.810669},
    doi = {10.1145/800255.810669},
    acmid = {810669},
    publisher = {ACM},
    address = {New York, NY, USA},
} 

@inproceedings{shao2013isa,
    title={ISA-independent workload characterization and its implications for specialized architectures},
    author={Shao, Yakun Sophia and Brooks, David},
    booktitle={IEEE International Symposium on Performance Analysis of Systems and Software {(ISPASS)}},
    pages={245--255},
    year={2013},
    organization={IEEE}
}

@inproceedings{johnston18opendwarfs,
    author = {Johnston, Beau and Milthorpe, Josh},
    title = {{Dwarfs} on Accelerators: Enhancing {OpenCL} Benchmarking for Heterogeneous Computing Architectures},
    booktitle = {Proceedings of the $47^{th}$ International Conference on Parallel Processing Companion},
    series = {ICPP '18},
    year = {2018},
    isbn = {978-1-4503-6523-9},
    location = {Eugene, OR, USA},
    pages = {4:1--4:10},
    articleno = {4},
    numpages = {10},
    url = {http://doi.acm.org/10.1145/3229710.3229729},
    doi = {10.1145/3229710.3229729},
    acmid = {3229729},
    publisher = {ACM},
    address = {New York, NY, USA},
} 

@misc{johnston18predicting,
    title={{OpenCL} Performance Prediction using Architecture-Independent Features},
    author={Johnston, Beau and Falzon, Greg and Milthorpe, Josh},
    journal={International Workshop on High Performance and Dynamic Reconfigurable Systems and Networks (DRSN-2018) (in press)},
    howpublished={http://www.milthorpe.org/pubs/aiwc-perf-prediction},
    year={2018}
}

@article{declerck2016cori,
    title={Cori - A system to support data-intensive computing},
    author={Declerck, Tina and Antypas, Katie and Bard, Deborah and Bhimji, Wahid and Canon, Shane and Cholia, Shreyas and He, Helen Yun and Jacobsen, Douglas and Prabhat, Nicholas J Wright},
    journal={Proceedings of the Cray User Group},
    pages={8},
    year={2016}
}

@misc{bainville2010fft,
    title={{OpenCL} Fast {Fourier} Transform},
    author={Bainville, Eric},
    year={2010},
    url={http://www.bealto.com/gpu-fft.html}
}

@inproceedings{che2009rodinia,
    title={{Rodinia}: A benchmark suite for heterogeneous computing},
    author={Che, Shuai and Boyer, Michael and Meng, Jiayuan and Tarjan, David and Sheaffer, Jeremy W and Lee, Sang-Ha and Skadron, Kevin},
    booktitle={Workload Characterization, 2009. IISWC 2009. IEEE International Symposium on},
    pages={44--54},
    year={2009},
    organization={Ieee}
}

@inproceedings{ganesan2008performance,
    title={A performance counter based workload characterization on {Blue Gene/P}},
    author={Ganesan, Karthik and John, Lizy and Salapura, Valentina and Sexton, James},
    booktitle={International Conference on Parallel Processing ({ICPP})},
    pages={330--337},
    year={2008},
    organization={IEEE}
}

@article{depestel2017linear,
    author = {De Pestel, Sander and Eyerman, Stijn and Eeckhout, Lieven},
    title = {Linear Branch Entropy: Characterizing and Optimizing Branch Behavior in a Micro-Architecture Independent Way},
    journal = {IEEE Transactions on Computers},
    issue_date = {March 2017},
    volume = {66},
    number = {3},
    month = mar,
    year = {2017},
    issn = {0018-9340},
    pages = {458--472},
    numpages = {15},
    url = {https://doi.org/10.1109/TC.2016.2601323},
    doi = {10.1109/TC.2016.2601323},
    acmid = {3057908},
    publisher = {IEEE Computer Society},
    address = {Washington, DC, USA},
}
@article{prakash2008performance,
    title={Performance characterization of {SPEC CPU2006} benchmarks on {Intel Core 2 Duo} processor},
    author={Prakash, Tribuvan Kumar and Peng, Lu},
    journal={ISAST Trans. Comput. Softw. Eng},
    volume={2},
    number={1},
    pages={36--41},
    year={2008}
}


@inproceedings{price:15,
    title = {Oclgrind: An extensible {OpenCL} device simulator},
    author = {Price, James and McIntosh-Smith, Simon},
    booktitle = {Proceedings of the 3rd International Workshop on {OpenCL}},
    pages = {12},
    year = {2015},
    organization = {ACM}
}

@misc{kessenich2015,
    title={{A Khronos-Defined Intermediate Language for Native Representation of Graphical Shaders and Compute Kernels}},
    author={Kessenich, John},
    year={2015},
    url={https://www.khronos.org/registry/spir-v/papers/WhitePaper.html}
}



@article{hoste2007microarchitecture,
    title={Microarchitecture-independent workload characterization},
    author={Hoste, Kenneth and Eeckhout, Lieven},
    journal={IEEE Micro},
    volume={27},
    number={3},
    year={2007},
    publisher={IEEE}
}

@inproceedings{luk2005pin,
    title={Pin: building customized program analysis tools with dynamic instrumentation},
    author={Luk, Chi-Keung and Cohn, Robert and Muth, Robert and Patil, Harish and Klauser, Artur and Lowney, Geoff and Wallace, Steven and Reddi, Vijay Janapa and Hazelwood, Kim},
    booktitle={{ACM SIGPLAN} notices},
    volume={40},
    number={6},
    pages={190--200},
    year={2005},
    organization={ACM}
}

@inproceedings{hoste2006performance,
    title={Performance prediction based on inherent program similarity},
    author={Hoste, Kenneth and Phansalkar, Aashish and Eeckhout, Lieven and Georges, Andy and John, Lizy K and De Bosschere, Koen},
    booktitle={International Conference on Parallel Architectures and Compilation Techniques ({PACT})},
    pages={114--122},
    year={2006},
    organization={IEEE}
}

@article{lively2011energy,
    title={Energy and performance characteristics of different parallel implementations of scientific applications on multicore systems},
    author={Lively, Charles and Wu, Xingfu and Taylor, Valerie and Moore, Shirley and Chang, Hung-Ching and Cameron, Kirk},
    journal={International Journal of High Performance Computing Applications},
    volume={25},
    number={3},
    pages={342--350},
    year={2011},
    publisher={SAGE Publications Sage UK: London, England}
}



@article{krommydas2016opendwarfs,
    title={Opendwarfs: Characterization of dwarf-based benchmarks on fixed and reconfigurable architectures},
    author={Krommydas, Konstantinos and Feng, Wu-chun and Antonopoulos, Christos D and Bellas, Nikolaos},
    journal={Journal of Signal Processing Systems},
    volume={85},
    number={3},
    pages={373--392},
    year={2016},
    publisher={Springer}
}

@techreport{asanovic2006landscape,
    title={The landscape of parallel computing research: A view from berkeley},
    author={Asanovic, Krste and Bodik, Ras and Catanzaro, Bryan Christopher and Gebis, Joseph James and Husbands, Parry and Keutzer, Kurt and Patterson, David A and Plishker, William Lester and Shalf, John and Williams, Samuel Webb and others},
    year={2006},
    institution={Technical Report UCB/EECS-2006-183, EECS Department, University of California, Berkeley}
}

@inproceedings{johnston2017embedded,
  title={Embedded Accelerators for Scientific High-Performance Computing: An Energy Study of {OpenCL} {Gaussian} Elimination Workloads},
  author={Johnston, Beau and Lee, Brian and Angove, Luke and Rendell, Alistair},
  booktitle={International Conference on Parallel Processing Workshops ({ICPPW})},
  pages={59--68},
  year={2017},
  organization={IEEE}
}

@inproceedings{mitra2014implementation,
  title={Implementation and optimization of the {OpenMP} accelerator model for the {TI Keystone II} architecture},
  author={Mitra, Gaurav and Stotzer, Eric and Jayaraj, Ajay and Rendell, Alistair P},
  booktitle={International Workshop on OpenMP},
  pages={202--214},
  year={2014},
  organization={Springer}
}

@article{bailey1991parallel,
	title={The {NAS} parallel benchmarks},
	author={Bailey, David H and Barszcz, Eric and Barton, John T and Browning, David S and Carter, Robert L and Dagum, Leonardo and Fatoohi, Rod A and Frederickson, Paul O and Lasinski, Thomas A and Schreiber, Rob S and others},
	journal={International Journal of Supercomputing Applications},
	volume={5},
	number={3},
	pages={63--73},
	year={1991},
	publisher={Sage Publications Sage CA: Thousand Oaks, CA}
}

@inproceedings{barnes2016evaluating,
    title={Evaluating and optimizing the {NERSC} workload on {Knights Landing}},
    author={Barnes, Taylor and Cook, Brandon and Deslippe, Jack and Doerfler, Douglas and Friesen, Brian and He, Yun and Kurth, Thorsten and Koskela, Tuomas and Lobet, Mathieu and Malas, Tareq and others},
    booktitle={International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS},
    pages={43--53},
    year={2016},
    organization={IEEE}
}

@inproceedings{martineau2016performance,
    title={Performance analysis and optimization of {Clang}'s {OpenMP} 4.5 {GPU} support},
    author={Martineau, Matt and McIntosh-Smith, Simon and Bertolli, Carlo and Jacob, Arpith C and Antao, Samuel F and Eichenberger, Alexandre and Bercea, Gheorghe-Teodor and Chen, Tong and Jin, Tian and O'Brien, Kevin and others},
    booktitle={International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS)},
    pages={54--64},
    year={2016},
    organization={IEEE}
}

@inproceedings{marjanovic2016hpc,
    title={{HPC} benchmarking: problem size matters},
    author={Marjanovi{\'c}, Vladimir and Gracia, Jos{\'e} and Glass, Colin W},
    booktitle={International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS)},
    pages={1--10},
    year={2016},
    organization={IEEE}
}

@article{feldman_2017,
    title={TOP500 Meanderings: Supercomputers Take Big Green Leap in 2017},
    url={https://www.top500.org/news/top500-meanderings-supercomputers-take-big-green-leap-in-2017/},
    journal={TOP500 Supercomputer Sites},
    publisher={Top500.org},
    author={Feldman, Michael},
    year={2017},
    month={Sep}
}



@article{feldman_2017_isambard,
	title={Cray to Deliver {ARM}-Powered Supercomputer to {UK} Consortium},
	url={https://www.top500.org/news/cray-to-deliver-arm-powered-supercomputer-to-uk-consortium/},
	journal={TOP500 Supercomputer Sites},
	publisher={Top500.org},
	author={Feldman, Michael},
	year={2017},
	month={Jan}
}

@article{morgan_2016,
    title={{NVLink} Takes {GPU} Acceleration To The Next Level},
    url={https://www.nextplatform.com/2016/05/04/nvlink-takes-gpu-acceleration-next-level/},
    journal={The Next Platform},
    author={Morgan, Timothy},
    publisher={Stackhouse Publishing Inc.},
    year={2016},
    month={May}
}

@article{morgan_2017,
    title={The {Power9} Rollout Begins With {Summit} And {Sierra} Supercomputers},
    url={https://www.nextplatform.com/2017/09/19/power9-rollout-begins-summit-sierra/},
    journal={The Next Platform},
    author={Morgan, Timothy},
    publisher={Stackhouse Publishing Inc.},
    year={2017},
    month={Sep}
}

@misc{morgan_2016_postk,
    title={Inside {Japan}'s Future Exascale {ARM} Supercomputer},
    url={https://www.nextplatform.com/2016/06/23/inside-japans-future-exaflops-arm-supercomputer/},
    journal={The Next Platform},
    publisher={Stackhouse Publishing Inc.},
    author={Morgan, Timothy},
    year={2016},
    month={Jun}}


@inproceedings{lopez2015examining,
    title={Examining recent many-core architectures and programming models using {SHOC}},
    author={Lopez, M Graham and Young, Jeffrey and Meredith, Jeremy S and Roth, Philip C and Horton, Mitchel and Vetter, Jeffrey S},
    booktitle={International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS},
    pages={3},
    year={2015},
    organization={ACM}
}

@inproceedings{hoefler2015scientific,
  title={Scientific benchmarking of parallel computing systems: Twelve ways to tell the masses when reporting performance results},
  author={Hoefler, Torsten and Belli, Roberto},
  booktitle={Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis},
  pages={73},
  year={2015},
  organization={ACM}
}

@inproceedings{mucci1999papi,
  title={{PAPI}: A portable interface to hardware performance counters},
  author={Mucci, Philip J and Browne, Shirley and Deane, Christine and Ho, George},
  booktitle={Proceedings of the Department of Defense HPCMP users group conference},
  volume={710},
  year={1999}
}


@misc{johnston2017,
  author = {Johnston, B.},
  title = {{OpenDwarfs}},
  year = {2017},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/BeauJoh/OpenDwarfs}}
}

@misc{opendwarfs2017base,
  title={{OpenDwarfs} (base version)},
  day={26},
  month={Feb},
  year={2017},
  howpublished={\url{https://github.com/vtsynergy/OpenDwarfs/commit/31c099aff5343e93ba9e8c3cd42bee5ec536aa93}}
}

@article{hager2013exploring,
  title={Exploring performance and power properties of modern multi-core chips via simple machine models},
  author={Hager, Georg and Treibig, Jan and Habich, Johannes and Wellein, Gerhard},
  journal={Concurrency and Computation: Practice and Experience},
  volume={28},
  number={2},
  pages={189--210},
  year={2013},
  publisher={Wiley Online Library}
}

@article{williams2009roofline,
  title={Roofline: An insightful visual performance model for floating-point programs and multicore architectures},
  author={Williams, Samuel and Waterman, Andrew and Patterson, David},
  journal={Communications of the Association for Computing Machinery},
  year={2009}
}