CUDACLAW: A high-performance programmable GPU framework for the solution of hyperbolic PDEs
Type
PreprintKAUST Department
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) DivisionKAUST Supercomputing Laboratory (KSL)
Applied Mathematics and Computational Science Program
Date
2018-05-21Permanent link to this record
http://hdl.handle.net/10754/632531
Metadata
Show full item recordAbstract
We present cudaclaw, a CUDA-based high performance data-parallel framework for the solution of multidimensional hyperbolic partial differential equation (PDE) systems, equations describing wave motion. cudaclaw allows computational scientists to solve such systems on GPUs without being burdened by the need to write CUDA code, worry about thread and block details, data layout, and data movement between the different levels of the memory hierarchy. The user defines the set of PDEs to be solved via a CUDA- independent serial Riemann solver and the framework takes care of orchestrating the computations and data transfers to maximize arithmetic throughput. cudaclaw treats the different spatial dimensions separately to allow suitable block sizes and dimensions to be used in the different directions, and includes a number of optimizations to minimize access to global memory.Publisher
arXivarXiv
1805.08846Additional Links
http://arxiv.org/abs/1805.08846v1http://arxiv.org/pdf/1805.08846v1