references.bib

@inproceedings{bakhoda2009analyzing,
  title={Analyzing CUDA workloads using a detailed GPU simulator},
  author={Bakhoda, Ali and Yuan, George L and Fung, Wilson WL and Wong, Henry and Aamodt, Tor M},
  booktitle={Performance Analysis of Systems and Software, 2009. ISPASS 2009. IEEE International Symposium on},
  year={2009},
  organization={IEEE}
}
@manual{HBMstandard2015high,
  title={JEDEC Standard JESD235A: High Bandwidth Memory (HBM) DRAM},
  author={JEDEC},
  organization={JEDEC Solid State Technology Association, Virginia, USA.},
  year={2015}
}
@inproceedings{jouppi2017tpu,
     author= {Jouppi, Norman P and others},
     title = {In-Datacenter Performance Analysis of a Tensor Processing Unit},
     booktitle = {Proceedings of the 44th Annual International Symposium on Computer Architecture},
     series = {ISCA '17},
     year = {2017},
}
@misc{sharan2014cudnn,
    Author = {Sharan Chetlur and Cliff Woolley and Philippe Vandermersch and Jonathan Cohen and John Tran and Bryan Catanzaro and Evan Shelhamer},
    Title = {cuDNN: Efficient Primitives for Deep Learning},
    Year = {2014},
}
@article{lecun2015lenet,
    title={Gradient-based learning applied to document recognition},
    author={LeCun, Yann and others},
    journal={Proceedings of the IEEE},
    year={1998} 
}
@incollection{alex2012alexnet,
    title = {ImageNet classification with deep convolutional neural networks},
    author = {Alex Krizhevsky and Sutskever, Ilya and Hinton, Geoffrey E},
    booktitle = {Advances in neural information processing systems},
    year = {2012},
}
@inproceedings{joseph2016yolo,
    title={You only look once: Unified, real-time object detection},
    author={Redmon, Joseph and Divvala, Santosh and Girshick, Ross and Farhadi, Ali},
    booktitle={The IEEE Conference on Computer Vision and Pattern Recognition},
    year={2016},
    series={CVPR '16},
}
@inproceedings{cesc2017attend,
    author  = {Cesc Chunseong Park and Byeongchang Kim and Gunhee Kim},
    title   = {Attend to You: Personalized Image Captioning with Context Sequence Memory Networks},
    booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition},
    year    = {2017},
    series = {CVPR '17},
}
@incollection{ian2014gan,
title = {Generative Adversarial Nets},
author = {Goodfellow, Ian and Pouget-Abadie, Jean and Mirza, Mehdi and Xu, Bing and Warde-Farley, David and Ozair, Sherjil and Courville, Aaron and Bengio, Yoshua},
booktitle = {Advances in Neural Information Processing Systems 27},
year = {2014},
}
@inproceedings{he2016resnet,
    author = {He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
    title = {Deep residual learning for image recognition},
    booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition},
    Year = {2016},
    series = {CVPR '16},
}
@inproceedings{yb17, 
author={Y. Lee and H. Kim and S. Hong and S. Kim}, 
booktitle={2017 IEEE International Symposium on High Performance Computer Architecture}, 
title={Partial Row Activation for Low-Power DRAM System}, 
year={2017}, 
series={HPCA '17},
month={Feb},
}
@inproceedings{Zhang14,
 author = {Zhang, Tao and Chen, Ke and Xu, Cong and Sun, Guangyu and Wang, Tao and Xie, Yuan},
 title = {Half-DRAM: A High-bandwidth and Low-power DRAM Architecture from the Rethinking of Fine-grained Activation},
 booktitle = {Proceeding of the 41st Annual International Symposium on Computer Architecuture},
 series = {ISCA '14},
 year={2014}
}
@inproceedings{connor2017finedram,
 author = {O'Connor, Mike and Chatterjee, Niladrish and Lee, Donghyuk and Wilson, John and Agrawal, Aditya and Keckler, Stephen W. and Dally, William J.},
 title = {Fine-grained DRAM: Energy-efficient DRAM for Extreme Bandwidth Systems},
 booktitle = {Proceedings of the 50th Annual IEEE/ACM International Symposium on Microarchitecture},
 year = {2017},
}
@inproceedings{subchannel17, 
author={N. Chatterjee and M. O’Connor and D. Lee and D. R. Johnson and S. W. Keckler and M. Rhu and W. J. Dally}, 
booktitle={2017 IEEE International Symposium on High Performance Computer Architecture (HPCA)}, 
title={Architecting an Energy-Efficient DRAM System for GPUs}, 
serise={HPCA '17},
year={2017}, 
}
@inproceedings{udipi2010rethinking,
 author = {Udipi, Aniruddha N. and Muralimanohar, Naveen and Chatterjee, Niladrish and Balasubramonian, Rajeev and Davis, Al and Jouppi, Norman P.},
 title = {Rethinking DRAM Design and Organization for Energy-constrained Multi-cores},
 booktitle = {Proceedings of the 37th Annual International Symposium on Computer Architecture},
 year = {2010},
}
@article{copper2010fineact, 
  author={E. Cooper-Balis and B. Jacob}, 
  journal={IEEE Micro}, 
  title={Fine-Grained Activation for Power Reduction in DRAM}, 
  year={2010},
}
@inproceedings{imagenet,
    AUTHOR = {Deng, J. and Dong, W. and Socher, R. and Li, L.-J. and Li, K. and Fei-Fei, L.},
    TITLE = {{ImageNet: A Large-Scale Hierarchical Image Database}},
    booktitle={2009 IEEE Conference on Computer Vision and Pattern Recognition},
    serise = {CVPR '09},
    YEAR = {2009},
}
@inproceedings{fcram, 
author={Y. Sato and others}, 
booktitle={1998 Symposium on VLSI Circuits. Digest of Technical Papers}, 
title={Fast cycle RAM (FCRAM); a 20-ns random row access, pipe-lined operating DRAM}, 
year={1998}
}
@inproceedings{SALP12, 
author={Y. Kim and V. Seshadri and D. Lee and J. Liu and O. Mutlu}, 
booktitle={2012 39th Annual International Symposium on Computer Architecture (ISCA)}, 
title={A case for exploiting subarray-level parallelism (SALP) in DRAM}, 
year={2012}, 
serise={ISCA '12}
}
@inproceedings{cacti3dd,
 author = {Chen, Ke and Li, Sheng and Muralimanohar, Naveen and Ahn, Jung Ho and Brockman, Jay B. and Jouppi, Norman P.},
 title = {CACTI-3DD: Architecture-level Modeling for 3D Die-stacked DRAM Main Memory},
 booktitle = {Proceedings of the Conference on Design, Automation and Test in Europe},
 series = {DATE '12},
 year = {2012},
}
@inproceedings{halfpage, 
author={H. Ha and A. Pedram and S. Richardson and S. Kvatinsky and M. Horowitz}, 
booktitle={2016 49th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO)}, 
title={Improving energy efficiency of DRAM by exploiting half page row access}, 
year={2016}, 
series={MICRO '16}
}
@inproceedings{IMW17, 
author={H. Jun and J. Cho and K. Lee and H. Y. Son and K. Kim and H. Jin and K. Kim}, 
booktitle={2017 IEEE International Memory Workshop (IMW)}, 
title={HBM (High Bandwidth Memory) DRAM Technology and Architecture}, 
year={2017}, 
}
@inproceedings{APCM, 
author={G. Koo and Y. Oh and W. W. Ro and M. Annavaram}, 
booktitle={2017 ACM/IEEE 44th Annual International Symposium on Computer Architecture (ISCA)}, 
title={Access pattern-aware cache management for improving data utilization in GPU}, 
year={2017}, 
series={ISCA '17}
}
@manual{postedcas,
title={DDR2 Posted CAS\# Additive Latency},
organization={Micron Technology, Inc},
year={2003}
}
@manual{hmc,
     title = {Hybrid Memory Cube Specification 2.1},
     year = {2015},
     key = {Technical Report},
     organization = {Hybrid Memory Cube Consortium},
     howpublished="\url{http://hybridmemorycube.org/files/SiteDownloads/HMC-30G-VSR_HMCC_Specification_Rev2
1_20151105.pdf}"
}
@inproceedings{HynixHBM2, 
author={J. C. Lee and the others},
booktitle={IEEE International Solid-State Circuits Conference (ISSCC)}, 
title={18.3 A 1.2V 64Gb 8-channel 256GB/s HBM DRAM with peripheral-base-die architecture and small-swing technique on
heavy load interface}, 
year={2016}, 
}
@inproceedings{caffe,
 author = {Jia, Yangqing and Shelhamer, Evan and Donahue, Jeff and Karayev, Sergey and Long, Jonathan and Girshick,
Ross and Guadarrama, Sergio and Darrell, Trevor},
 title = {Caffe: Convolutional Architecture for Fast Feature Embedding},
 booktitle = {Proceedings of the 22nd ACM International Conference on Multimedia},
 series = {MM '14},
 year = {2014},
}
@inproceedings{gpuwattch,
 author = {Leng, Jingwen and Hetherington, Tayler and ElTantawy, Ahmed and Gilani, Syed and Kim, Nam Sung and Aamodt,
Tor M. and Reddi, Vijay Janapa},
 title = {GPUWattch: Enabling Energy Optimizations in GPGPUs},
 booktitle = {Proceedings of the 40th Annual International Symposium on Computer Architecture},
 series = {ISCA '13},
 year = {2013},
} 
@inproceedings{rodinia, 
author={S. Che and M. Boyer and J. Meng and D. Tarjan and J. W. Sheaffer and S. Lee and K. Skadron}, 
booktitle={2009 IEEE International Symposium on Workload Characterization (IISWC)}, 
title={Rodinia: A benchmark suite for heterogeneous computing}, year={2009}, 
}
@manual{P100,
     title = {https://images.nvidia.com/content/tesla/pdf/nvidia-tesla-p100-PCIe-datasheet.pdf},
     year = {2016},
     key = {Technical Report},
     organization = {NVIDIA},
     howpublished="\url{https://images.nvidia.com/content/tesla/pdf/nvidia-tesla-p100-PCIe-datasheet.pdf}"

}