@article{14270,
  keywords = {OpenMP, CUDA, MPI, CPU+GPU computing, source-to-source translation, code generation, code optimisation, stencil computation, heterogeneous computing},
  author = {Mohammed Sourouri and Scott Baden and Xing Cai},
  title = {Panda: A Compiler Framework for Concurrent CPU+GPU Execution of 3D Stencil Computations on GPU-accelerated Supercomputers},
  abstract = {We present a new compiler framework for truly heterogeneous 3D stencil computation on GPU clusters. Our framework consists of a simple directive-based programming model and a tightly integrated source-to-source compiler. Annotated with a small number of directives, sequential stencil C codes can be automatically parallelized for large-scale GPU clusters. The most distinctive feature of the compiler is its capability to generate hybrid MPI+CUDA+OpenMP code that uses concurrent CPU+GPU computing to unleash the full potential of powerful GPU clusters. The auto-generated hybrid codes hide the overhead of various data motion by overlapping them with computation. Test results on the Titan supercomputer and the Wilkes cluster show that auto-translated codes can achieve about 90\% of the performance of highly optimized handwritten codes, for both a simple stencil benchmark and a real-world application in cardiac modeling. The user-friendliness and performance of our domain-specific compiler framework allow harnessing the full power of GPU-accelerated supercomputing without painstaking coding effort.},
  year = {2016},
  journal = {International Journal of Parallel Programming},
  month = {10/2016},
  publisher = {ACM/Springer},
  doi = {10.1007/s10766-016-0454-1},
}