초록 ▼

A distributed, compiler-oriented database is disclosed with operating modes including parallel compilation, parallel simulation and parallel execution of computer programs and hardware models. The invention utilizes a hardware apparatus consisting of shared memory multiprocessors, optionally augment

A distributed, compiler-oriented database is disclosed with operating modes including parallel compilation, parallel simulation and parallel execution of computer programs and hardware models. The invention utilizes a hardware apparatus consisting of shared memory multiprocessors, optionally augmented by processors with re-configurable logic execution pipelines or independently scheduled re-configurable logic blocks and a software database apparatus, manifest in the hardware apparatus, in order to efficiently support parallel database clients such as a source code analyzer, an elaborator, an optimizer, mapping and scheduling, code generation, linking/loading, execution/simulation, debugging, profiling, user interface and a file interface.

대표청구항 ▼

[ What is claimed:] [1.] A parallel processor system with at least one node programmed to execute a distributed, compiler-oriented database, the parallel processor system including compilation, simulation and/or software execution operating modes, and comprising:at least two processors;memory operat

[ What is claimed:] [1.] A parallel processor system with at least one node programmed to execute a distributed, compiler-oriented database, the parallel processor system including compilation, simulation and/or software execution operating modes, and comprising:at least two processors;memory operationally connected to at least one processor wherein the memory is either local memory or shared memory;interconnection mechanisms for connecting the at least two processors and the memory; andre-configurable logic elements, wherein the programmed node is augmented to include a plurality of clients which may perform one or more of the following functions on the distributed, compiler-oriented database selected from a group of:incremental analysis of source code into the database;incremental elaboration and/or in-lining of previously analyzed information into the database to yield new or revised database entries;incremental optimization which transform database contents to yield more efficient simulation, more efficient execution or more observable execution;incremental code generation, assembly and linking which transform database contents to yield representations directly executable on a combination of programmable processors and reconfigurable logic elements;runtime, I/O and file systems operations which provide for scheduling, communication and callbacks within and among directly executable simulations/executions;debugging which provide for interactively starting, stopping and probing the state of simulation/execution;profiling or event logging of simulation/execution in order to make simulation/execution result accessible to external tools or users; andgraphical interactive user interface transfers wherein the database may coherently cache information having utility on said at least one node.