Method and apparatus for processing a heterogeneous cluster-oriented task
The present disclosure provides a method and apparatus for processing a heterogeneous cluster-oriented task. The method comprises: receiving a task request and a basic execution environment; scheduling a heterogeneous device according to the task request; compiling the basic execution environment into an execution environment corresponding to the scheduled heterogeneous device, and deploying on the scheduled heterogeneous device; triggering the scheduled heterogeneous device to execute the task request. It is only necessary for the user to provide the basic execution environment with respect to the task, and unnecessary for the user to respectively write a version of execution environment for each type of hardware platform, thereby implementing quick development of the heterogeneous device code and reducing the development and maintenance costs.
1. A method for processing a heterogeneous cluster-oriented task, wherein the method comprises:
receiving a task request and a basic execution environment; wherein the basic execution environment is based on a CPU-type heterogeneous high-performance repository;
scheduling a heterogeneous device according to the task request;
compiling the basic execution environment into an execution environment corresponding to the scheduled heterogeneous device, and deploying the execution environment corresponding to the scheduled heterogeneous device on the scheduled heterogeneous device; wherein the execution environment corresponding to the scheduled heterogeneous device comprises at least one type of GPU, FPGA or ARM; and
triggering the scheduled heterogeneous device to execute the task request,
wherein the compiling the basic execution environment into an execution environment corresponding to the scheduled heterogeneous device comprises:
according to the type of the heterogeneous device scheduled for the task request, switching the CPU-type heterogeneous high-performance repository into the heterogeneous high-performance repository corresponding to the scheduled heterogeneous device, to generate the execution environment corresponding to the scheduled heterogeneous device.
2. The method according to claim 1 , wherein
the task request comprises: an identity of the basic execution environment, configuration information of the task, and data information of the task.
3. The method according to claim 2 , wherein the triggering the scheduled heterogeneous device to execute the task request comprises:
sending to the scheduled heterogeneous device a task instruction including data information of the task, so that the scheduled heterogeneous device performs distributed computation according to the task instruction.
4. The method according to claim 1 , wherein the scheduling a heterogeneous device according to the task request comprises:
scheduling the heterogeneous device for the task request in accordance with the data information of the task in the task request and a sum of available resources of the heterogeneous cluster.
5. A computer device, comprising a memory, a processor and a computer program which is stored on the memory and runnable on the processor, wherein the processor, upon executing the program, implements a method for processing a heterogeneous cluster-oriented task, wherein the method comprises:
receiving a task request and a basic execution environment; wherein the basic execution environment is based on a CPU-type heterogeneous high-performance repository;
scheduling a heterogeneous device according to the task request;
compiling the basic execution environment into an execution environment corresponding to the scheduled heterogeneous device, and deploying the execution environment corresponding to the scheduled heterogeneous device on the scheduled heterogeneous device; wherein the execution environment corresponding to the scheduled heterogeneous device comprises at least one type of GPU, FPGA or ARM; and
triggering the scheduled heterogeneous device to execute the task request,
wherein the compiling the basic execution environment into an execution environment corresponding to the scheduled heterogeneous device comprises:
according to the type of the heterogeneous device scheduled for the task request, switching the CPU-type heterogeneous high-performance repository into the heterogeneous high-performance repository corresponding to the scheduled heterogeneous device, to generate the execution environment corresponding to the scheduled heterogeneous device.
6. The computer device according to claim 5 , wherein
the task request comprises: an identity of the basic execution environment, configuration information of the task, and data information of the task.
7. The computer device according to claim 6 , wherein the triggering the scheduled heterogeneous device to execute the task request comprises:
sending to the scheduled heterogeneous device a task instruction including data information of the task, so that the scheduled heterogeneous device performs distributed computation according to the task instruction.
8. The computer device according to claim 5 , wherein the scheduling a heterogeneous device according to the task request comprises:
scheduling the heterogeneous device for the task request in accordance with the data information of the task in the task request and a sum of available resources of the heterogeneous cluster.
9. A non-transitory computer-readable storage medium on which a computer program is stored, wherein the program, when executed by a processor, implements a method for processing a heterogeneous cluster-oriented task, wherein the method comprises:
receiving a task request and a basic execution environment; wherein the basic execution environment is based on a CPU-type heterogeneous high-performance repository; scheduling a heterogeneous device according to the task request;
compiling the basic execution environment into an execution environment corresponding to the scheduled heterogeneous device, and deploying the execution environment corresponding to the scheduled heterogeneous device on the scheduled heterogeneous device; wherein the execution environment corresponding to the scheduled heterogeneous device comprises at least one type of GPU, FPGA or ARM; and
triggering the scheduled heterogeneous device to execute the task request,
wherein the compiling the basic execution environment into an execution environment corresponding to the scheduled heterogeneous device comprises:
according to the type of the heterogeneous device scheduled for the task request, switching the CPU-type heterogeneous high-performance repository into the heterogeneous high-performance repository corresponding to the scheduled heterogeneous device, to generate the execution environment corresponding to the scheduled heterogeneous device.
10. The non-transitory computer-readable storage medium according to claim 9 , wherein
the task request comprises: an identity of the basic execution environment, configuration information of the task, and data information of the task.
11. The non-transitory computer-readable storage medium according to claim 10 , wherein the triggering the scheduled heterogeneous device to execute the task request comprises:
sending to the scheduled heterogeneous device a task instruction including data information of the task, so that the scheduled heterogeneous device performs distributed computation according to the task instruction.
12. The non-transitory computer-readable storage medium according to claim 9 , wherein the scheduling a heterogeneous device according to the task request comprises:
scheduling the heterogeneous device for the task request in accordance with the data information of the task in the task request and a sum of available resources of the heterogeneous cluster.