Monte Carlo simulations of Quantum systems on massively parallel computers

A large class of quantum physics applications uses operator representations that are discrete integers by nature. This class includes magnetic properties of solids, interacting bosons modeling super fiuids and Coo~er pairs in superconductors, and Hubbard models for strongly correlated electrons systems. This kind of application typically uses integer data representations and the resulting algorithms are dominated entirely by integer operations. We implemented an efficient algorithm for one such application on the Intel Touchstone Delta and iPSC/860. The algorithm uses a multispin coding technique which allows significant data compactification and efficient vectorization of Monte Carlo updates. The algorithm regularly switches between two data decompositions, corresponding naturally to different Monte Carlo updating processes and observable measurements such that only nearest-neighbor communications are needed within a given decomposition. On 128 nodes of Intel Delta, this algorithm updates 183 million spins per second (compared to 21 million on CM-2 and 6.2 million on a Cray Y-MP). A systematic performance analysis shows a better than 90% efficiency in the parallel implementation