bibs

@article{Nickolls08,
  author = {J. Nickolls and I. Buck and M. Garland and K. Skadron},
  title = {Scalable Parallel Programming with CUDA},
  journal = {ACM Queue},
  volume = {6},
  number = {2},
  year = {2008},
  pages = {40-53},
}
@article{wen18,
 author = {Wen, Zeyi and Shi, Jiashuai and Li, Qinbin and He, Bingsheng and Chen, Jian},
 title = {{ThunderSVM}: A Fast {SVM} Library on {GPUs} and {CPUs}},
 journal = {Journal of Machine Learning Research},
 volume={19},
 pages={1--5},
 year = {2018}
}
@article{Lindholm08,
  author = {E. Lindholm and J. Nickolls and S. Oberman and J. Montrym},
  title = {NVIDIA Tesla: A Unified Graphics and Computing Architecture},
  journal = {IEEE Micro},
  volume = {28},
  number = {2},
  year = {2008},
  pages = {39-55},
}
@article{Abraham15,
  author = { M. J. Abraham and T. Murtola and R. Schulz and S. Pall and J. C. Smith and B. Hess and E. Lindahl},
  title = {GROMACS: High Performance Molecular Simulations Through Multi-level Parallelism from Laptops to Supercomputers},
  journal = { SoftwareX},
  volume = {1-2},
  year = {2015},
  pages = {19-25},
}
@article{Brown12,
  author = { W. M. Brown and A. Kohlmeyer and S. J. Plimpton and A. N. Tharrington},
  title = {Implementing Molecular Dynamics on Hybrid High Performance Computers – Particle–particle Particle-mesh},
  journal = { Computer Physics Communications},
  volume = {183},
  number = {3},
  year = {2012},
  pages = {449-459},
}
@article{Phillips05,
  author = { J. C. Phillips and R. Braun and W. Wang and J. Gumbart and E. Tajkhorshid and E. Villa and C. Chipot and R. D. Skeel and L. Kale and K. Schulten },
  title = {Scalable Molecular Dynamics with NAMD},
  journal = {Journal of Computational Chemistry},
  volume = {26},
  number = {16},
  year = {2005},
  pages = {1781-1802},
}
@article{Wang17,
  author = { Y. Wang and P. Yangzihao and A. Davidson and Y. Wu and C. Yang and L. Wang and M. Osama and C. Yuan and W. Liua and A. T. Riffel and J. D. Owens},
  title = {Gunrock: GPU Graph Analytics},
  journal = {ACM Transactions on Parallel Computing},
  volume = {4},
  number = {2},
  year = {2017},
}
@article{Pieters07,
  author = { B. Pieters and D. Van Rijsselbergen and W. De Neve and R. Van de Walle},
  title = {Performance Evaluation of H.264/AVC Decoding and Visualization Using the GPU},
  journal = {Applications of Digital Image Processing XXX},
  volume = {6696},
  year = {2007},
}
@article{Chetlur14,
  author = {S. Chetlur and C. Woolley and P. Vandermersch and J. Cohen and J. Tran and B. Catanzaro and E. Shelhamer},
  title = {cuDNN: Efficient Primitives for Deep Learning},
  journal = {arXiv preprint arXiv:1410.0759},
  year = {2014},
}
@article{Jorda19,
  author = { M. Jorda and P. Valero-Lara and A. J. Peña },
  title = {Performance Evaluation of cuDNN Convolution Algorithms on NVIDIA Volta GPUs },
  journal = { IEEE Access},
  volume = {7},
  number = {2},
  year = {2019},
  pages = {70461 - 70473},
}









@misc{spec,
 title={SPEC CPU 2017},
 url={https://www.spec.org/cpu2017/},
 note={(2018)},
}
@misc{xmrig18,
 title={XMRig NVIDIA Miner},
 url={https://github.com/xmrig/xmrig-nvidia},
 note={(2018)},
}
@misc{RCSB,
 title={Research Collaboratory for Structural Bioinformatics (RCSB)},
 url={https://www.rcsb.org/structure/1ao6},
 note={(2018)},
}
@misc{ffmpeg18,
 title={FFmpeg: A complete, cross-platform solution to record, convert and stream audio and video},
 url={https://ffmpeg.org},
 note={(2018)},
}
@misc{racon19,
 title={Ultrafast consensus module for raw de novo genome assembly of long uncorrected reads},
 url={https://github.com/clara-genomics/racon-gpu},
 note={(2019)},
}
@misc{thunder19,
 title={ThunderSVM: A Fast SVM Library on GPUs and CPUs },
 url={https://github.com/Xtra-Computing/thundersvm},
 note={(2019)},
}
@misc{bsd,
 title={The Berkeley Segmentation Dataset and Benchmark},
 url={https://www2.eecs.berkeley.edu/Research/Projects/CS/vision/bsds},
 note={(2019)},
}
@misc{optix18,
 title={NVIDIA OptiX Rat Tracing Engine},
 url={https://developer.nvidia.com/optix},
 note={(2018)},
}
@misc{advoptix,
 title={OptiX Advanced Samples},
 url={https://github.com/nvpro-samples/optix_advanced_samples},
 note={(2018)},
}
@misc{Nsight18,
 title={NVIDIA Nsight Visual Studio Edition},
 url={https://docs.nvidia.com/gameworks/content/developertools/desktop/analysis/report/cudaexperiments/kernellevel/achievedflops.htm},
 note={(2018)},
}
@misc{shoc18,
 title={The Scalable HeterOgeneous Computing (SHOC) benchmark suite},
 url={https://github.com/vetter/shoc},
 note={(2018)},
}
@misc{3dm,
 title={The Gamer's Benhcmark},
 url={https://www.3dmark.com},
 note={(2018)},
}
@misc{passm,
 title={Benchmarking \& Diagnostic Software},
 url={https://www.passmark.com},
 note={(2018)},
}
@misc{deepb,
 title={Benchmarking Deep Learning operations on different hardware},
 url={https://github.com/baidu-research/DeepBench},
 note={(2018)},
}
@misc{mdb,
 title={MDBenchmark: Benchmark molecular dynamics simulations},
 url={https://mdbenchmark.readthedocs.io},
 note={(2018)},
}
@misc{mlperf,
 title={Fair and useful benchmarks for measuring training and inference performance of ML hardware, software, and services},
 url={https://mlperf.org},
 note={(2019)},
}
@misc{skin,
 title={ Skin Segmentation Data Set },
 url={https://archive.ics.uci.edu/ml/datasets/skin+segmentation},
 note={(2019)},
}



@techrepor{Stratton12,
  author = { J. A. Stratton and C. Rodrigues and I. Sung and N. Obeid and L. Chang and N. Anssari and G. D. Liu and W. W Hwu},
  title = {Parboil: A Revised Benchmark Suite for Scientific and Commercial Throughput Computing},
  number =  {IMPACT-12-01},
  institution = {Center for Reliable and High-Performance Computing, University of Illinois at Urbana-Champaign}
  year = {2012},
}



@inproceedings{Ferdman12,
  author = {M. Ferdman and A. Adileh and O. Kocberber and S. Volos and M. Alisafaee and D. Jevdjic and C. Kaynak and A. D. Popescu and A. Ailamaki and B. Falsafi},
  title = {Clearing the Clouds: A Study of Emerging Scale-out Workloads on Modern Hardware},
  booktitle  = {Proceeding of Conference on Architectural Support for Programming Languages and Operating Systems },
  year = {2012},
  pages = {37-48},
}
@inproceedings{Ryoo15,
  author = { J. H. Ryoo and S. J. Quirem and M. Lebeane and R. Panda and S. Song and L. K. John },
  title = {GPGPU Benchmark Suites: How Well Do They Sample the Performance Spectrum?},
  booktitle  = {Proceeding of Conference on Parallel Processing },
  year = {2015},
  pages = {320 - 329},
}
@inproceedings{Bienia08,
  author = {C. Bienia and S. Kumar and J. P. Singh and K. Li},
  title = {The PARSEC Benchmark Suite: Characterization and Architectural Implications},
  booktitle  = {Proceeding of Conference on Parallel Architectures and Compilation Techniques },
  year = {2008},
  pages = {72-81},
}
@inproceedings{Dev14,
  author = {J. A. Dev},
  title = {Bitcoin Mining Acceleration and Performance Quantification},
  booktitle  = {Proceeding of Canadian Conference on Electrical and Computer Engineering},
  year = {2014},
}
@inproceedings{Kim14,
  author = {Y. Kim},
  title = {Convolutional Neural Networks for Sentence Classification},
  booktitle  = {Proceeding of Conference on Empirical Methods in Natural Language Processing},
  year = {2014},
  pages = {1746–1751},
}
@inproceedings{Amodei16,
  author = {D. Amodei and R. Anubhai and E. Battenberg and C. Case and J. Casper and B. Catanzaro and J. Chen and M. Chrzanowski and A. Coates and G. Diamos and E. Elsen and J. Engel and L. Fan and C. Fougner and T. Han and A. Hannun and B. Jun and P. LeGresley and L. Lin and S. Narang and A. Ng and S. Ozair and R. Prenger and J. Raiman and S. Satheesh and D. Seetapun and S. Sengupta and Y. Wang and Z. Wang and C. Wang and B. Xiao and D. Yogatama and J. Zhan and Z. Zhu},
  title = {Deep Speech 2: End-to-End Speech Recognition in English and Mandarin},
  booktitle  = {Proceeding of Conference on Machine Learning},
  year = {2016},
  pages = {173-182},
}
@inproceedings{Playne09,
  author = {D. P. Playne and M. Johnson and K. A. Hawick},
  title = {Benchmarking GPU Devices with N-Body Simulations},
  booktitle  = {Proceeding of Conference on Computer Design},
  year = {2009},
  pages = {150-156},
}
@inproceedings{Dong17,
  author = {S. Dong and D. Kaeli},
  title = {DNNMark: A Deep Neural Network Benchmark Suite for GPUs},
  booktitle  = {Proceeding of the General Purpose GPUs},
  year = {2017},
  pages = {63-72},
}
@inproceedings{Burtscher12,
  author = {M. Burtscher and R. Nasre and K. Pingali},
  title = {A Quantitative Study of Irregular Programs on GPUs},
  booktitle  = {Proceedings of Symposium on Workload Characterization},
  year = {2012},
}
@inproceedings{Xu14,
  author = {Q. Xu and H. Jeon and M. Annavaram},
  title = {Graph Processing on GPUs: Where are the Bottlenecks?},
  booktitle  = {Proceedings of Symposium on Workload Characterization},
  year = {2014},
}
@inproceedings{Shi16,
  author = {S. Shi and Q. Wang and P. Xu and X. Chu},
  title = {Benchmarking State-of-the-Art Deep Learning Software Tools},
  booktitle  = {Proceedings of Conference on Cloud Computing and Big Data},
  year = {2016},
}
@inproceedings{Kulkarni09,
  author = {M. Kulkarni and M. Burtscher and C. Cascaval and K. Pingali},
  title = {Lonestar: A Suite of Parallel Irregular Programs},
  booktitle  = {Proceeding of Symposium on Performance Analysis of Systems and Software},
  year = {2009},
}
@inproceedings{Volkov10,
  author = { V. Volkov},
  title = {Better Performance at Lower Occupancy},
  booktitle  = {Proceedings of the GPU Technology Conference},
  year = {2010},
}
@inproceedings{optix10,
  author = { S. G. Parker},
  title = {OptiX: A General Purpose Ray Tracing Engine},
  booktitle  = {Proceeding of ACM SIGGRAPH},
  year = {2010},
  pages = {66:1–66:13},
}
@inproceedings{Chen15,
  author = { T. Chen and M. Li and Y. Li and M. Lin and N. Wang and M. Wang and T. Xiao and B. Xu and C. Zhang and Z. Zhang},
  title = {MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems},
  booktitle  = {Proceeding of Neural Information Processing Systems, Workshop on Machine Learning Systems},
  year = {2015},
}
@inproceedings{Paszke17,
  author = {A. Paszke and S. Gross and S. Chintala and G. Chanan and E. Yang and Z. DeVito and Z. Lin and A. Desmaison and L. Antiga and A. Lerer},
  title = {Automatic Differentiation in PyTorch},
  booktitle  = {NIPS Autodiff Workshop},
  year = {2017},
}
@inproceedings{Abadi16,
  author = { M. Abadi and P. Barham and J. Chen and Z. Chen and A. Davis and J. Dean and M. Devin and S. Ghemawat and G. Irving and M. Isard and M. Kudlur and J. Levenberg and R. Monga and S. Moore and D. G. Murray and B. Steiner and P. Tucker and V. Vasudevan and P. WardenM. Abadi and P. Barham and J. Chen and Z. Chen and A. Davis and J. Dean and M. Devin and S. Ghemawat and G. Irving and M. Isard and M. Kudlur and J. Levenberg and R. Monga and S. Moore and D. G. Murray and B. Steiner and P. Tucker and V. Vasudevan and P. Warden and M. Wicke and Y. Yu and X. Zheng M. Wicke and Y. Yu and X. Zheng},
  title = {TensorFlow: A System for Large-scale Machine Learning},
  booktitle  = {Proceedings of USENIX conference on Operating Systems Design and Implementation},
  year = {2016},
  pages = {265-283},
}
@inproceedings{Bakhoda09,
  author = { A. Bakhoda and G. Yuan and W. Fung and H. Wong and T. M. Aamodt},
  title = {Analyzing CUDA Workloads Using a Detailed GPU Simulator},
  booktitle  = {Proceedings of Symposium on Performance Analysis of Systems and Software},
  year = {2009},
  pages = {163-174},
}
@inproceedings{Che09,
  author = { S. Che and M. Boyer and J. Meng and D. Tarjan and J. W. Sheaffer and S.-H. Lee and K. Skadron},
  title = {Rodinia: A Benchmark Suite for Heterogeneous Computing},
  booktitle  = {Proceedings of Symposium on Workload Characterization},
  year = {2009},
  pages = {44-54 },
}
@inproceedings{Shi16,
  author = { W. Shi and J. Caballero and F. Huszár and J. Totz and A. P. Aitken and R. Bishop and D. Rueckert and Z. Wang },
  title = { Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network },
  booktitle  = {Proceedings of Conference on Computer Vision and Pattern Recognition},
  year = {2016},
  pages = {1874 - 1883},
}
@inproceedings{Volkov08,
  author = { V. Volkov and J. W. Demmel},
  title = {Benchmarking GPUs to Tune Dense Linear Algebra},
  booktitle  = {Proceedings of Internation Conference on Supercomputing},
  year = {2008},
  pages = { 1-11 },
}
@inproceedings{Xu16,
  author = { Y. Xu and R. Wang and T. Li and M. Song and L. Gao and Z. Luan and D. Qian},
  title = {Scheduling Tasks with Mixed Timing Constraints in GPU-Powered Real-Time Systems},
  booktitle  = {Proceedings of Conference on Supercomputing},
  year = {2016},
}
@inproceedings{Ravi11,
  author = { V. T. Ravi and M. Becchi and G. Agrawal and S. Chakradhar},
  title = {Supporting GPU Sharing in Cloud Environments with a Transparent Runtime Consolidation Framework},
  booktitle  = {Proceedings of Symposium on High Performance Distributed Computing},
  year = {2011},
  pages = { 217-228},
}
@inproceedings{Li15,
  author = { P. Li and Y. Luo and N. Zhang and Y. Cao},
  title = {HeteroSpark: A Heterogeneous CPU/GPU Spark Platform for Machine Learning Algorithms},
  booktitle  = {Proceedings of Conference on Networking, Architecture and Storage},
  year = {2015},
  pages = { 347-348 },
}
@inproceedings{Cui16,
  author = { H. Cui and H. Zhang and G. R. Ganger and P. B. Gibbons and E. P. Xing},
  title = {GeePS: scalable deep learning on distributed GPUs with a GPU-specialized parameter server},
  booktitle  = {Proceedings of European Conference on Computer Systems},
  year = {2016},
}