Paper.bib

@misc{nvidia_cuda, title={CUDA Zone}, url={https://developer.nvidia.com/cuda-zone}, journal={NVIDIA Developer}, year={2017}, month={Sep}}

@inproceedings{yang2010gpgpu,
  title={A GPGPU compiler for memory optimization and parallelism management},
  author={Yang, Yi and Xiang, Ping and Kong, Jingfei and Zhou, Huiyang},
  booktitle={ACM Sigplan Notices},
  volume={45},
  number={6},
  pages={86--97},
  year={2010},
  organization={ACM}
}

@article{lee2010debunking,
  title={Debunking the 100X GPU vs. CPU myth: an evaluation of throughput computing on CPU and GPU},
  author={Lee, Victor W and Kim, Changkyu and Chhugani, Jatin and Deisher, Michael and Kim, Daehyun and Nguyen, Anthony D and Satish, Nadathur and Smelyanskiy, Mikhail and Chennupaty, Srinivas and Hammarlund, Per and others},
  journal={ACM SIGARCH computer architecture news},
  volume={38},
  number={3},
  pages={451--460},
  year={2010},
  publisher={ACM}
}

@misc{nvidia_gtx_1080, title={GeForce GTX 1080 Graphics Cards from NVIDIA GeForce}, url={https://www.nvidia.com/en-us/geforce/products/10series/geforce-gtx-1080/}, journal={NVIDIA}}

@misc{nvidia_gtx_1080_whitepaper, title={GeForce GTX 1080 Graphics Cards from NVIDIA GeForce}, url={https://international.download.nvidia.com/geforce-com/international/pdfs/GeForce\_GTX\_108\_Whitepaper\_FINAL.pdf}, journal={NVIDIA Developer}, year={2016}}

@misc{nvidia_developer_2017, title={GPU Accelerated Computing with C and C }, url={https://developer.nvidia.com/how-to-cuda-c-cpp}, journal={NVIDIA Developer}, year={2017}, month={Sep}}

@misc{nvidia_developer_documentation, title={CUDA C Programming Guide}, url={http://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html}, journal={NVIDIA Developer Documentation}}

@inproceedings{ueng2008cuda,
  title={CUDA-Lite: Reducing GPU Programming Complexity.},
  author={Ueng, Sain-Zee and Lathara, Melvin and Baghsorkhi, Sara S and Wen-mei, W Hwu},
  booktitle={Languages and Compilers for Parallel Computing},
  volume={8},
  pages={1--15},
  year={2008},
  organization={Springer}
}

@inproceedings{bakkum2010accelerating,
  title={Accelerating SQL database operations on a GPU with CUDA},
  author={Bakkum, Peter and Skadron, Kevin},
  booktitle={Proceedings of the 3rd Workshop on General-Purpose Computation on Graphics Processing Units},
  pages={94--103},
  year={2010},
  organization={ACM}
}

@inproceedings{aji2011bounding,
  title={Bounding the effect of partition camping in GPU kernels},
  author={Aji, Ashwin M and Daga, Mayank and Feng, Wu-chun},
  booktitle={Proceedings of the 8th ACM International Conference on Computing Frontiers},
  pages={27},
  year={2011},
  organization={ACM}
}

@article{ruetsch2009optimizing,
  title={Optimizing matrix transpose in CUDA},
  author={Ruetsch, Greg and Micikevicius, Paulius},
  journal={Nvidia CUDA SDK Application Note},
  volume={18},
  year={2009}
}

@misc{gcc_optimize_options, title={ GCC Optimize Options}, url={https://gcc.gnu.org/onlinedocs/gcc/Optimize-Options.html}, journal={Using the GNU Compiler Collection (GCC): Optimize Options}}

@article{lamport1979make,
  title={How to make a multiprocessor computer that correctly executes multiprocess progranm},
  author={Lamport, Leslie},
  journal={IEEE transactions on computers},
  number={9},
  pages={690--691},
  year={1979},
  publisher={IEEE}
}



@article{harris2007optimizing,
  title={Optimizing cuda},
  author={Harris, Mark},
  journal={SC07: High Performance Computing With CUDA},
  year={2007}
}

@inproceedings{torres2011understanding,
  title={Understanding the impact of CUDA tuning techniques for Fermi},
  author={Torres, Yuri and Gonzalez-Escribano, Arturo and Llanos, Diego R},
  booktitle={High Performance Computing and Simulation (HPCS), 2011 International Conference on},
  pages={631--639},
  year={2011},
  organization={IEEE}
}