Abstract: Guidances are provided for database retrieval in a numerical simulation system. A user can execute numerical simulation without knowledge of mathematical and numerical techniques. A physical model is generated using information of a region shape, material name, physical phenomenon name, boundary condition name, and the like, respectively inputted by a user. A mathematical model generating step calculates physical characteristic values from the physical model, and in accordance with the physical characteristic values, retrieves proper equations from an equation database. A calculation model generating step detects mathematical characteristic values from the equations to retrieve proper numerical algorithms for solving the equations from an algorithm database. A simulation information generating step retrieves from a package database a simulation package for solving the given physical problem by using the selected algorithms, and generates simulation information for the retrieved package.

Abstract: A cross-domain call jacketing system is provided in a computer system that embodies a first hardware (X) architecture to executing X-code in an X-domain and which simulates at least a second computer hardware (Y) architecture executing Y-code in a Y-domain.Cross-domain routine calls are Jacketed for services in the cross-domain and for returns after the requested services have been performed. After Jacketing, X routine calls are transmitted for implementation by the simulating subsystem and Y calls are transmitted for implementation in the X domain. Call parameters are transformed from a representation that uses the call conventions of the calling domain to another representation that uses the call conventions of the called domain. Data in the memory is generally globally accessible and the Y calls include data references that require memory access handling in the X domain.A first Jacketing table is provided for each executable routine in the X domain.

Abstract: A massively parallel processing system comprising a plurality of processing nodes controlled in parallel by a controller. The processing nodes are interconnected by a plurality of communications links. Each processing node comprises a memory, a transposer module and a router node. The memory stores data in slice format. The transposer module is connected to the memory and generates transpose data words of selected ones of the data slices from the memory. The router node is connected to the transposer module and to the communications links and transfers transpose data words over the communications links to thereby transfer the data slices between processing nodes. Finally, the controller controls the memories, transposer modules and router nodes of the processing nodes in parallel, to facilitate transfer of data slices among the processing nodes in unison.