A second-order distributed Trotter–Suzuki solver with a hybrid CPU–GPU kernel
Rights accessOpen Access
European Commission's projectHPC-EUROPA2 - Pan-European Research infrastructure on High Performance Computing for 21st century Science (EC-FP7-228398)
The Trotter-Suzuki approximation leads to an efficient algorithm for solving the timedependent Schrödinger equation. Using existing highly optimized CPU and GPU kernels, we developed a distributed version of the algorithm that runs efficiently on a cluster. Our implementation also improves single node performance, and is able to use multiple GPUs within a node. The scaling is close to linear using the CPU kernels, whereas the efficiency of GPU kernels improve with larger matrices. We also introduce a hybrid kernel that simultaneously uses multicore CPUs and GPUs in a distributed system. This kernel is shown to be efficient when the matrix size would not fit in the GPU memory. Larger quantum systems scale especially well with a high number nodes. The code is available under an open source license.
CitationWittek, Peter; Cucchietti, Fernando M. A second-order distributed Trotter–Suzuki solver with a hybrid CPU–GPU kernel. "Computer Physics Communications", Abril 2013, vol. 184, núm. 4, p. 1165-1171.