Multifrontal Computations on GPUs and Their Multi-core Hosts
Robert Lucas (University of Southern California)
Gene Wagenbreth (University of Southern California)
Dan Davis (University of Southern California)
Roger Grimes (Livermore Software Technology Corporation)
The use of GPUs to accelerate the factoring of large sparse symmetric indefinite matrices shows the potential of yielding important benefits to a large group of widely used applications. This paper examines how a multifrontal sparse solver performs when exploiting both the GPU and its multi-core host. It demonstrates that the GPU can dramatically accelerate the solver relative to one host CPU. Furthermore, the solver can profitably exploit both the GPU to factor its larger frontal matrices and multiple threads on the host to handle the smaller frontal matrices.
Parallel and Distributed Computing, Numerical Algorithms for CS&E, Performance Analysis, ,