AUTOMATED LEARNING TECHNOLOGY TO PARTITION COMPUTER APPLICATIONS FOR HETEROGENEOUS SYSTEMS

• US 20200133537A1
• Filed: 12/20/2019
• Published: 04/30/2020
• Est. Priority Date: 12/20/2019
• Status: Active Grant

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation
• Inventors: Haghighat, Mohammad R., Baghsorkhi, Sara
• Granted Patent: US 11,520,501 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 2209/5021 Priority
• CPC Class Codes: G06F 3/0611 in relation to response time
• CPC Class Codes: G06F 3/0631 by allocating resources to storage systems
• CPC Class Codes: G06F 3/0679 Non-volatile semiconductor memory device, e.g. flash memory, one time programmable memory [OTP]
• CPC Class Codes: G06F 9/50 Allocation of resources, e.g. of the central processing unit [CPU]
• CPC Class Codes: G06F 9/5027 the resource being a machine, e.g. CPUs, Servers, Terminals
• 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
• CPC Class Codes: G06F 9/5044 considering hardware capabilities
• CPC Class Codes: G06F 9/5083 Techniques for rebalancing the load in a distributed system
• CPC Class Codes: G06F 9/5094 where the allocation takes into account power or heat criteria power management in computers in general G06F1/3203; thermal management in computers in general G06F1/206
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: H04L 41/50 Network service management, e.g. ensuring proper service fulfilment according to agreements
• CPC Class Codes: H04L 41/5003 Managing SLA; Interaction between SLA and QoS
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

Systems, apparatuses and methods may provide for technology that identifies a prioritization data structure associated with a function, wherein the prioritization data structure lists hardware resource types in priority order. The technology may also allocate a first type of hardware resource to the function if the first type of hardware resource is available, wherein the first type of hardware resource has a highest priority in the prioritization data structure. Additionally, the technology may allocate, in the priority order, a second type of hardware resource to the function if the first type of hardware resource is not available.

Claims

1. A computing system comprising:

a network controller;

a processor coupled to the network controller; and

a memory coupled to the processor, the memory including a set of executable program instructions, which when executed by the processor, cause the computing system to;

identify a prioritization data structure associated with a function, wherein the prioritization data structure lists hardware resource types in priority order;

allocate a first type of hardware resource to the function if the first type of hardware resource is available, wherein the first type of hardware resource has a highest priority in the prioritization data structure; and

allocate, in the priority order, a second type of hardware resource to the function if the first type of hardware resource is not available, wherein the hardware resource types are one of processor types or memory types.

2. The computing system of claim 1, wherein the instructions, when executed, cause the computing system to:

collect telemetry information during an execution of the function; and

generate the prioritization data structure based on the telemetry information, wherein the second type of hardware resource is to be a next available type of hardware resource, wherein the telemetry information is to include one or more of a parameter size and value, a memory requirement, an execution time, a number of threads, or a power consumption, and wherein the prioritization data structure is to be one of a processor dispatch table or a memory allocation table.

3. The computing system of claim 1, wherein the instructions, when executed, cause the computing system to:

collect telemetry information during a plurality of executions of the function; and

modify the prioritization data structure based on the telemetry information.

4. The computing system of claim 3, wherein the instructions, when executed, cause the computing system to:

store first telemetry information to a first telemetry record, wherein the first telemetry information is associated with a first execution of the function; and

store second telemetry information to a second telemetry record, wherein the second telemetry information is associated with a second execution of the function.

5. The computing system of claim 3, wherein the instructions, when executed, cause the computing system to:

store first telemetry information to a telemetry record, wherein the first telemetry information is associated with a first execution of the function; and

store second telemetry information to the telemetry record, wherein the second telemetry information is associated with a second execution of the function.

6. A semiconductor apparatus comprising:

one or more substrates; and

logic coupled to the one or more substrates, wherein the logic is implemented at least partly in one or more of configurable logic or fixed-functionality hardware logic, the logic coupled to the one or more substrates to;

identify a prioritization data structure associated with a function, wherein the prioritization data structure lists hardware resource types in priority order;

allocate a first type of hardware resource to the function if the first type of hardware resource is available, wherein the first type of hardware resource has a highest priority in the prioritization data structure; and

allocate, in the priority order, a second type of hardware resource to the function if the first type of hardware resource is not available.

7. The semiconductor apparatus of claim 6, wherein the logic coupled to the one or more substrates is to:

collect telemetry information during an execution of the function; and

generate the prioritization data structure based on the telemetry information, wherein the second type of hardware resource is to be a next available type of hardware resource, wherein the telemetry information is to include one or more of a parameter size and value, a memory requirement, an execution time, a number of threads, or a power consumption, and wherein the prioritization data structure is to be one of a processor dispatch table or a memory allocation table.

8. The semiconductor apparatus of claim 6, wherein the logic coupled to the one or more substrates is to:

collect telemetry information during a plurality of executions of the function; and

modify the prioritization data structure based on the telemetry information.

9. The semiconductor apparatus of claim 8, wherein the logic coupled to the one or more substrates is to:

store first telemetry information to a first telemetry record, wherein the first telemetry information is associated with a first execution of the function; and

store second telemetry information to a second telemetry record, wherein the second telemetry information is associated with a second execution of the function.

10. The semiconductor apparatus of claim 8, wherein the logic coupled to the one or more substrates is to:

store first telemetry information to a telemetry record, wherein the first telemetry information is associated with a first execution of the function; and

store second telemetry information to the telemetry record, wherein the second telemetry information is associated with a second execution of the function.

11. The semiconductor apparatus of claim 6, wherein the hardware resource types are processor types.

12. The semiconductor apparatus of claim 6, wherein the hardware resource types are memory types.

13. At least one computer readable storage medium comprising a set of executable program instructions, which when executed by a computing system, cause the computing system to:

identify a prioritization data structure associated with a function, wherein the prioritization data structure lists hardware resource types in priority order;

allocate a first type of hardware resource to the function if the first type of hardware resource is available, wherein the first type of hardware resource has a highest priority in the prioritization data structure; and

allocate, in the priority order, a second type of hardware resource to the function if the first type of hardware resource is not available.

14. The at least one computer readable storage medium of claim 13, wherein the instructions, when executed, cause the computing system to:

collect telemetry information during an execution of the function; and

generate the prioritization data structure based on the telemetry information, wherein the second type of hardware resource is to be a next available type of hardware resource, wherein the telemetry information is to include one or more of a parameter size and value, a memory requirement, an execution time, a number of threads, or a power consumption, and wherein the prioritization data structure is to be one of a processor dispatch table or a memory allocation table.

15. The at least one computer readable storage medium of claim 13, wherein the instructions, when executed, cause the computing system to:

collect telemetry information during a plurality of executions of the function; and

modify the prioritization data structure based on the telemetry information.

16. The at least one computer readable storage medium of claim 15, wherein the instructions, when executed, cause the computing system to:

store first telemetry information to a first telemetry record, wherein the first telemetry information is associated with a first execution of the function; and

store second telemetry information to a second telemetry record, wherein the second telemetry information is associated with a second execution of the function.

17. The at least one computer readable storage medium of claim 15, wherein the instructions, when executed, cause the computing system to:

store first telemetry information to a telemetry record, wherein the first telemetry information is associated with a first execution of the function; and

store second telemetry information to the telemetry record, wherein the second telemetry information is associated with a second execution of the function.

18. The at least one computer readable storage medium of claim 13, wherein the hardware resource types are processor types.

19. The at least one computer readable storage medium of claim 13, wherein the hardware resource types are memory types.

20. A method comprising:

identifying a prioritization data structure associated with a function, wherein the prioritization data structure lists hardware resource types in priority order;

allocating a first type of hardware resource to the function if the first type of hardware resource is available, wherein the first type of hardware resource has a highest priority in the prioritization data structure; and

allocating, in the priority order, a second type of hardware resource to the function if the first type of hardware resource is not available, wherein the hardware resource types are one of processor types or memory types.

21. The method of claim 20, further comprising:

collecting telemetry information during an execution of the function; and

generating the prioritization data structure based on the telemetry information, wherein the second type of hardware resource is a next available type of hardware resource, wherein the telemetry information includes one or more of a parameter size and value, a memory requirement, an execution time, a number of threads, or a power consumption, and wherein the prioritization data structure is one of a processor dispatch table or a memory allocation table.

22. The method of claim 21, further including:

collecting telemetry information during a plurality of executions of the function; and

modifying the prioritization data structure based on the telemetry information.

23. The method of claim 22, further including:

storing first telemetry information to a first telemetry record, wherein the first telemetry information is associated with a first execution of the function; and

storing second telemetry information to a second telemetry record, wherein the second telemetry information is associated with a second execution of the function.

24. The method of claim 22, further including:

storing first telemetry information to a telemetry record, wherein the first telemetry information is associated with a first execution of the function; and

storing second telemetry information to the telemetry record, wherein the second telemetry information is associated with a second execution of the function.