Distributed data driven process

• US 5,099,418 A
• Filed: 06/14/1990
• Issued: 03/24/1992
• Est. Priority Date: 06/14/1990
• Status: Expired due to Term

• Current Assignee: Hughes Electronics Corporation (AT&T, Inc.)
• Original Assignee: Hughes Aircraft Company (Rtx Corporation)
• Inventors: Juhre, Jeffrey E., Nguyen, Minh-Tram D., Posch, Theodore E., Pian, Chao-Kuang
• Primary Examiner(s): Fleming, Michael R.
• Assistant Examiner(s): Hauser, Robert S.
• Application Number:
  US07/538,349
• Time in Patent Office: 649 Days
• Field of Search: 364/200 MS File, 364/900 MS File
• US Class Current: 718/102
• CPC Class Codes: G06F 9/4494 data driven

Abstract

A data driven method for coordinating the processing of arithmetic tasks in a multiple computer system having a multiplicity of arithmetic processors by determining whether an arithmetic task is in a blocked condition or is in an execution ready condition. A source distributed processor stores data in a local memory for processing by a local processor and then transfers the processed data to a global memory for buffering in preparation for subsequent processing by a destination distributed processor. The source distributed processor generates a produce message to a destination distributed processor to indicate that the data to be transferred is available in a buffer in the global memory. The destination distributed processor loads the data to be transferred from the buffer in the global memory and then generates a consume message to the source distributed processor to indicate that the data has been transferred from the global memory and the buffer in the global memory is now available.

Claims

1. A data driven control method for coordinating the scheduling and control of arithmetic tasks in a multiple computer system having a plurality of arithmetic processors, said data driven control method comprising the following steps:

determining whether an arithmetic task has the necessary number of input data elements present at the input;

determining whether the arithmetic task has the necessary amount of buffer space available at the output;

determining whether the arithmetic task is in an execution ready condition; and

executing the arithmetic task when it is in an execution ready condition.

2. A data driven control method for coordinating the scheduling and control of arithmetic tasks in a multiple computer system having a plurality of arithmetic processors, said data driven control method comprising the following steps:

comparing the number of existing input data elements present at the input of an arithmetic task with a predetermined necessary number;

comparing the amount of existing output buffer space present at the output of the arithmetic task with a predetermined necessary amount;

determining whether the arithmetic task is in an execution ready condition; and

executing the arithmetic task when it is in an execution ready condition.

3. A data driven method for coordinating the processing of arithmetic tasks in a multiple computer system having a plurality of arithmetic processors by determining whether an arithmetic task is in a blocked condition or is in an execution ready condition, said method comprising the following steps:

receiving data comprising a first arithmetic task including input data elements in a first arithmetic processor;

transferring said data from said first arithmetic processor to global memory;

generating a produce message in said first arithmetic processor;

transferring said produce message to a second arithmetic processor;

determining availability of local memory in said second arithmetic processor in response to said produce message;

transferring said data from said global memory to the local memory in said second arithmetic processor in response to finding sufficient local memory available;

generating a consume message in said second arithmetic processor;

transferring said consume message to said first arithmetic processor;

comparing the number of input data elements present in said data with a predetermined necessary number to perform said first arithmetic task;

comparing the amount of local memory available with the necessary amount required to store the result after performing said first arithmetic task;

determining whether said first arithmetic task is in an execution ready condition or is in a blocked condition; and

executing said first arithmetic task when it is in an execution ready condition.