A GPU code for analytic continuation through a sampling method

oleh: Johan Nordström, Johan Schött, Inka L.M. Locht, Igor Di Marco

Format: Article
Diterbitkan: Elsevier 2016-01-01

Deskripsi

We here present a code for performing analytic continuation of fermionic Green’s functions and self-energies as well as bosonic susceptibilities on a graphics processing unit (GPU). The code is based on the sampling method introduced by Mishchenko et al. (2000), and is written for the widely used CUDA platform from NVidia. Detailed scaling tests are presented, for two different GPUs, in order to highlight the advantages of this code with respect to standard CPU computations. Finally, as an example of possible applications, we provide the analytic continuation of model Gaussian functions, as well as more realistic test cases from many-body physics. Keywords: GPU, Analytic continuation, Parallelization, Green’s function