Scratchpad-based operating system for multi-core embedded systems

• US 10,649,914 B1
• Filed: 06/30/2017
• Issued: 05/12/2020
• Est. Priority Date: 07/01/2016
• Status: Active Grant

• Current Assignee: Board of Trustees of The University of Illinois
• Original Assignee: Board of Trustees of The University of Illinois
• Inventors: Caccamo, Marco, Pellizzoni, Rodolfo, Mancuso, Renato, Tabish, Rohan, Wasly, Saud
• Primary Examiner(s): Snyder, Steven G
• Application Number:
  US15/639,666
• Time in Patent Office: 1,047 Days
• Field of Search: None
• CPC Class Codes: G06F 12/1081 for peripheral access to main memory, e.g. direct memory access [DMA]
• CPC Class Codes: G06F 13/1673 using buffers
• CPC Class Codes: G06F 13/28 using burst mode transfer, e.g. direct memory access DMA, cycle steal G06F13/32 takes precedence
• CPC Class Codes: G06F 13/30 with priority control
• CPC Class Codes: G06F 2212/656 Address space sharing
• CPC Class Codes: G06F 3/061 Improving I/O performance
• CPC Class Codes: G06F 3/0611 in relation to response time
• CPC Class Codes: G06F 3/0622 in relation to access
• CPC Class Codes: G06F 3/0656 Data buffering arrangements
• CPC Class Codes: G06F 3/0659 Command handling arrangements, e.g. command buffers, queues, command scheduling
• CPC Class Codes: G06F 3/068 Hybrid storage device
• CPC Class Codes: G06F 3/0683 Plurality of storage devices
• CPC Class Codes: G06F 9/445 Program loading or initiating bootstrapping G06F9/4401; security arrangements for program loading or initiating G06F21/57
• CPC Class Codes: G06F 9/5077 Logical partitioning of resources; Management or configuration of virtualized resources specific details on emulation or internal functioning of virtual machines G06F9/455

Abstract

An embodiment may involve determining that a first logical partition of a scratchpad memory coupled to a processor core is empty and a first application is scheduled to execute; instructing a direct memory access (DMA) engine to load the first application into the first logical partition and then instructing the processor core to execute the first application from the first logical partition; while the first application is being executed from the first logical partition, determining that a second logical partition of the scratchpad memory is empty and a second application is scheduled to execute; instructing the DMA engine to load the second application into the second logical partition; determining that execution of the first application has completed; and instructing the DMA engine to unload the first application from the first logical partition and instructing the processor core to execute the second application from the second logical partition.

Claims

1. A computing system comprising:

an application processor core coupled to an application scratchpad memory and configured to execute applications stored in the application scratchpad memory;

a main memory;

a direct memory access (DMA) engine;

a data bus communicatively connecting the application processor core, the application scratchpad memory, the main memory, and the DMA engine; and

an operating system configured to execute on the computing system and perform operations comprising;

determining that a first logical partition of the application scratchpad memory is empty and a first application stored in the main memory is scheduled to execute;

in response to determining that the first logical partition of the application scratchpad memory is empty and the first application stored in the main memory is scheduled to execute, instructing the DMA engine to load the first application from the main memory into the first logical partition and then instructing the application processor core to execute the first application from the first logical partition;

while the first application is being executed from the first logical partition, determining that a second logical partition of the application scratchpad memory is empty and a second application stored in the main memory is scheduled to execute;

in response to determining that the second logical partition of the application scratchpad memory is empty and the second application is scheduled to execute, instructing the DMA engine to load the second application from the main memory into the second logical partition;

determining that execution of the first application has completed; and

in response to determining that execution of the first application has completed, instructing the DMA engine to unload the first application from the first logical partition to the main memory and instructing the application processor core to execute the second application from the second logical partition, wherein operations that load applications from the main memory to empty partitions of the application scratchpad memory have precedence over operations that unload applications to the main memory from the application scratchpad memory.

2. The computing system of claim 1, wherein unloading an application from a logical partition of the application scratchpad memory empties the logical partition.

3. The computing system of claim 1, further comprising:

one or more peripheral components; and

an input/output (I/O) processor core coupled to an I/O scratchpad memory and configured to coordinate the scheduling and transfer of data between the main memory and the I/O scratchpad memory, and between the I/O scratchpad memory and the one or more peripherals.

4. The computing system of claim 3, wherein the one or more peripheral components, the I/O processor core, the I/O scratchpad memory, and the DMA engine are communicatively coupled by an I/O bus.

5. The computing system of claim 1, wherein the first application has higher priority than the second application, and wherein instructing the DMA engine to load the first application from the main memory into the first logical partition also occurs because the first application has higher priority than the second application.

6. The computing system of claim 1, wherein the application scratchpad memory is dual ported.

7. The computing system of claim 1, wherein the application scratchpad memory contains an active queue and a ready queue for applications.

8. The computing system of claim 7, the operations further comprising:

prior to determining that the first logical partition of the application scratchpad memory is empty and the first application is scheduled to execute, determining that the active queue contains representations of the first application and the second application, and the ready queue is empty.

9. The computing system of claim 8, wherein instructing the DMA engine to load the first application from the main memory into the first logical partition comprises copying the representation of the first application from the active queue to the ready queue.

10. The computing system of claim 9, wherein instructing the DMA engine to unload the first application from the first logical partition to the main memory comprises removing the first application from the ready queue.

11. The computing system of claim 1, wherein the operations further comprise:

while the second application is being executed from the second logical partition, determining that the first logical partition of the application scratchpad memory is empty and a third application stored in the main memory is scheduled to execute; and

in response to determining that the first logical partition of the application scratchpad memory is empty and the third application is scheduled to execute, instructing the DMA engine to load the third application from the main memory into the first logical partition.

12. A method comprising:

determining, by an operating system, that a first logical partition of an application scratchpad memory coupled to an application processor core is empty and a first application stored in a main memory is scheduled to execute;

in response to determining that the first logical partition of the application scratchpad memory is empty and the first application stored in the main memory is scheduled to execute, instructing, by the operating system, a DMA engine to load the first application from the main memory into the first logical partition and then instructing the application processor core to execute the first application from the first logical partition;

while the first application is being executed from the first logical partition, determining, by the operating system, that a second logical partition of the application scratchpad memory is empty and a second application stored in the main memory is scheduled to execute;

in response to determining that the second logical partition of the application scratchpad memory is empty and the second application is scheduled to execute, instructing, by the operating system, the DMA engine to load the second application from the main memory into the second logical partition;

determining, by the operating system, that execution of the first application has completed; and

in response to determining that execution of the first application has completed, instructing, by the operating system, the DMA engine to unload the first application from the first logical partition to the main memory and instructing the application processor core to execute the second application from the second logical partition, wherein operations that load applications from the main memory to empty partitions of the application scratchpad memory have precedence over operations that unload applications to the main memory from the application scratchpad memory.

13. The method of claim 12, wherein unloading an application from a logical partition of the application scratchpad memory empties the logical partition.

14. The method of claim 12, wherein the first application has higher priority than the second application, and wherein instructing the DMA engine to load the first application from the main memory into the first logical partition also occurs because the first application has higher priority than the second application.

15. The method of claim 12, wherein the application scratchpad memory contains an active queue and a ready queue for applications.

16. The method of claim 15, further comprising:

prior to determining that the first logical partition of the application scratchpad memory is empty and the first application is scheduled to execute, determining that the active queue contains representations of the first application and the second application, and the ready queue is empty.

17. The method of claim 16, wherein instructing the DMA engine to load the first application from the main memory into the first logical partition comprises copying the representation of the first application from the active queue to the ready queue.

18. An article of manufacture including a non-transitory computer-readable medium, having stored thereon program instructions that, upon execution by a computing system, cause the computing system to perform operations comprising:

determining that a first logical partition of an application scratchpad memory coupled to an application processor core is empty and a first application stored in a main memory is scheduled to execute;

in response to determining that the first logical partition of the application scratchpad memory is empty and the first application stored in the main memory is scheduled to execute, instructing a DMA engine to load the first application from the main memory into the first logical partition and then instructing the application processor core to execute the first application from the first logical partition;

while the first application is being executed from the first logical partition, determining that a second logical partition of the application scratchpad memory is empty and a second application stored in the main memory is scheduled to execute;

in response to determining that the second logical partition of the application scratchpad memory is empty and the second application is scheduled to execute, instructing the DMA engine to load the second application from the main memory into the second logical partition;

determining that execution of the first application has completed; and

in response to determining that execution of the first application has completed, instructing the DMA engine to unload the first application from the first logical partition to the main memory and instructing the application processor core to execute the second application from the second logical partition, wherein operations that load applications from the main memory to empty partitions of the application scratchpad memory have precedence over operations that unload applications to the main memory from the application scratchpad memory.

19. The article of manufacture of claim 18, wherein the application scratchpad memory contains an active queue and a ready queue for applications.

20. The article of manufacture of claim 19, the operations further comprising:

prior to determining that the first logical partition of the application scratchpad memory is empty and the first application is scheduled to execute, determining that the active queue contains representations of the first application and the second application, and the ready queue is empty.