@techreport{cs2-17-1,
  title = {{Roofline: An Insightful Visual Performance Model for Floating-Point Programs and Multicore Architectures}},
  author = {Williams, Samuel Webb and Waterman, Andrew and Patterson, David A.},
  year = {2008},
  url = {https://www2.eecs.berkeley.edu/Pubs/TechRpts/2008/EECS-2008-134.pdf},
  institution = {University of California, Berkeley, UCB/EECS-2008-134}
}

@misc{cs2-17-2,
  title = {{CUDA C++ Best Practices Guide}},
  author = {{NVIDIA}},
  year = {2026},
  url = {https://docs.nvidia.com/cuda/cuda-c-best-practices-guide/},
  howpublished = {NVIDIA Documentation}
}

@misc{cs2-17-3,
  title = {{Nsight Compute Profiling Guide}},
  author = {{NVIDIA}},
  year = {2026},
  url = {https://docs.nvidia.com/nsight-compute/ProfilingGuide/index.html},
  howpublished = {NVIDIA Documentation}
}

@misc{cs2-17-4,
  title = {{Efficient GEMM in CUDA}},
  author = {{NVIDIA}},
  year = {2026},
  url = {https://docs.nvidia.com/cutlass/latest/media/docs/cpp/efficient\_gemm.html},
  howpublished = {CUTLASS Documentation}
}

@techreport{cs2-17-5,
  title = {{Better Performance at Lower Occupancy}},
  author = {Volkov, Vasily},
  year = {2010},
  url = {https://www.nvidia.com/content/GTC-2010/pdfs/2238\_GTC2010.pdf},
  institution = {GPU Technology Conference}
}

@misc{cs2-17-6,
  title = {{Roofline Performance Model}},
  author = {{NERSC}},
  year = {2026},
  url = {https://docs.nersc.gov/tools/performance/roofline/},
  howpublished = {NERSC Documentation}
}