Predictive resource allocation in computing systems

• US 7,594,229 B2
• Filed: 10/09/2001
• Issued: 09/22/2009
• Est. Priority Date: 10/09/2001
• Status: Expired due to Term

• Current Assignee: QuickSilver Controls, Inc.
• Original Assignee: NVIDIA Corporation
• Inventors: Hirschsohn, Ian
• Primary Examiner(s): Nguyen; Van H
• Assistant Examiner(s): Truong; Camquy
• Application Number:
  US09/974,521
• Publication Number:
  US 20030069916A1
• Time in Patent Office: 2,905 Days
• Field of Search: 718/104, 709/205, 709/231, 710/5
• US Class Current: 718/104
• CPC Class Codes: G06F 2209/506 Constraint
• CPC Class Codes: G06F 9/5016 the resource being the memory
• CPC Class Codes: G06F 9/5038 considering the execution order of a plurality of tasks, e.g. taking priority or time dependency constraints into consideration scheduling strategies G06F9/4881 and subgroups

Abstract

A system including a method employed by a dedicated processor for allocating resources to other processors with a multi-processor computing environment. The dedicated processor is dedicated only to providing resource allocation to the other processors. Specifically, a script file is provided to the dedicated processor, the script containing information related to the resources required by the other processors. The script file is parsed by the dedicated processor to determine the resources required by the second processor. Thereafter, the dedicated processor dynamically allocates the resources and synchronizes resource allocation at the time needed by the other processors.

Claims

1. A method by a processor for allocating resources for executing tasks in an application in a multi-processor computing environment, the method comprising:

providing a script file to the dedicated processor prior to beginning execution of the application, the dedicated processor being dedicated solely to executing the script file and the allocation of resources to a plurality of other processors, the script file including a map of execution sequences including an execution sequence of one or more tasks for each of the plurality of other processors;

running and parsing the script file, by the dedicated processor, to determine resources required by each of the plurality of other processors based on the map of execution sequences; and

dynamically allocating the resources, by the dedicated processor, immediately prior to execution of each of the one or more tasks to achieve the execution of the one or more tasks based on the map of execution sequences included in the script file, wherein resource allocation is synchronized when the resources are needed by the plurality of other processors for the execution of the one or more tasks, and each of the plurality of other processors is configured to determine what tasks can be performed without having to wait to receive information from a different one of the plurality of other processors.

2. The method of claim 1 wherein the script file is an I/O script file.

3. The method of claim 1 wherein each of the plurality of other processors executes multiple tasks as part of a single application.

4. A predictive resource allocation system for a multi-processor computing environment having two or more processors, comprising:

a plurality of other processors for executing an application;

a dedicated processor dedicated to providing resource allocation to the plurality of other processors;

a script file containing information related to the resources required by the plurality of other processors to execute the application including a map of execution sequences including an execution sequence of one or more tasks for each of the plurality of other processors;

the dedicated processor running the script file and parsing the script file to determine the resources required by the plurality of other processors prior to beginning execution of the application; and

the dedicated processor dynamically allocating resources prior to execution of each of the one or more tasks to achieve the execution of the one or more tasks based on the map of execution sequences included in the script file, wherein resource allocation is synchronized when the resources are needed by the plurality of other processors for the execution of the application, and each of the plurality of other processors is configured to determine what tasks can be performed without having to wait to receive information from a different one of the plurality of other processors.

5. A method for allocating resources for use by a first processor in execution of an application comprising a plurality of tasks in a multi-processor computing environment, the method comprising:

providing a script file to the first processor prior to beginning execution of the application, the first processor being dedicated solely to parsing the script and to allocation of resources to a plurality of other processors, the script file containing a map of execution sequences including an execution sequence of tasks for each of the plurality of other processors;

running and parsing the script file, by the first processor, to determine the execution sequence of the tasks for each of the plurality of other processors to execute the tasks and to determine the resources required by each of the plurality of other processors to execute the tasks; and

dynamically allocating the resources, by the first processor, to the plurality of other processors for execution of the application by the plurality of other processors based on the map of execution sequences included in the script, wherein resource allocation is synchronized when the resources are needed by the plurality of other processors for the execution of the tasks, and each of the plurality of other processors is configured to determine what tasks can be performed without having to wait to receive information from a different one of the plurality of other processors.

6. The method of claim 5 wherein allocating the resources to the plurality of other processors in the multi-processor environment further comprises dynamically allocating the resources at the time needed for the execution of the tasks.