Abstract: A testing apparatus designed to check the completion of a command issued earlier in a multiprocessing system having a plurality of nodes. During an initialization phase, each command has been identified by a handle and a record containing the task to be performed asynchronously had been established. When a request for checking the completion of a command is issued, the pre-established record is simply checked for location of last task executed and completed. If the last or most current task is not the last task before the completion of the total command, the user application can choose to either continue the operation of command processing or permanently or temporarily abandon it.

Abstract: A method for testing the completion of a command issued earlier in a multiprocessing system having a plurality of nodes. During an initialization phase, each command has been identified by a handle and a record containing the task to be performed asynchronously had been established. When a request for checking the completion of a command is issued, the pre-established record is simply checked for location of last task executed and completed. If the last or most current task is not the last task before the completion of the total command, the user application can choose to either continue the operation of command processing or permanently or temporarily abandon it.

Abstract: A method and apparatus for distributing data in a multiprocessing system having a plurality of nodes. Each node has a user application for issuing a blocking or a non-blocking command. A request handle identifies each non-blocking command, while being set to a null value when in blocking mode.For each requested command issued by any of the user applications, a report is generated comprising of data structures, for recording the sequence of functions to be executed asynchronously given a non-blocking command. Blocking commands are processed synchronously. Once the report is generated the sequence of functions recorded in the report are executed in the sequence presented in the report. However, whenever an internal dependency is encountered the control is returned to user application until the internal dependency is resolved. Upon completion of requested command, the user application is notified.

Abstract: In a multi-processor parallel processing computer environment different communication modes are available for performing an information distribution operation (e.g., a broadcast) between processors. The technique comprises automatically selecting an optimal communications mode at operation run-time. The selection decision utilizes hardware parameters of the system (e.g., communication speed between processors) and run-time parameters (e.g., number of nodes to broadcast a message to). The communication mode selection decision seeks to optimize factors such as time required to execute or work space requirements of the distribution operation.