MANAGING LOCK AND UNLOCK OPERATIONS USING ACTIVE SPINNING

• US 20180293113A1
• Filed: 05/31/2017
• Published: 10/11/2018
• Est. Priority Date: 04/05/2017
• Status: Active Grant

• Current Assignee: Marvell Asia Pte Limited (Marvell Technology Group Limited)
• Original Assignee: Cavium, LLC (Marvell Technology Group Limited)
• Inventors: Mukherjee, Shubhendu Sekhar, Akkawi, Isam Wadih, Asher, David, Bertone, Michael, Carlson, David Albert, Dobbie, Bradley, Kessler, Richard Eugene
• Granted Patent: US 10,248,420 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 9/3004 to perform operations on memory
• CPC Class Codes: G06F 9/30072 to perform conditional operations, e.g. using predicates or guards
• CPC Class Codes: G06F 9/30079 Pipeline control instructions, e.g. multicycle NOP
• CPC Class Codes: G06F 9/3009 Thread control instructions
• CPC Class Codes: G06F 9/3834 Maintaining memory consistency
• CPC Class Codes: G06F 9/4881 Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
• CPC Class Codes: G06F 9/526 Mutual exclusion algorithms
• CPC Class Codes: G06F 9/528 by using speculative mechanisms
• CPC Class Codes: G06F 9/546 Message passing systems or structures, e.g. queues

Abstract

Managing instructions on a processor includes: executing threads having access to a stored library of operations. For a first thread executing on the first processor core, for each instruction included in the first thread and identified as being associated with a lock operation corresponding to a particular lock, the managing includes determining if the particular lock has already been acquired for another thread executing on a processor core other than the first processor core, and if so, continuing to perform the lock operation for multiple attempts using a hardware lock operation different from the lock operation in the stored library, and if not, acquiring the particular lock for the first thread. The hardware lock operation performs a modified atomic operation that changes a result of the hardware lock operation for failed attempts to acquire the particular lock relative to a result of the lock operation in the stored library.

Claims

1. A method for managing instructions on a processor comprising a plurality of processor cores, the method comprising:

executing a plurality of threads on the processor cores, each thread having access to a stored library of operations including at least one lock operation and at least one unlock operation; and

managing instructions that are issued on a first processor core of the plurality of processor cores, for a first thread executing on the first processor core, the managing including;

for each instruction included in the first thread and identified as being associated with a lock operation corresponding to a particular lock, determining if the particular lock has already been acquired for another thread executing on a processor core other than the first processor core, and if the particular lock has already been acquired, continuing to perform the lock operation for a plurality of attempts using a hardware lock operation different from the lock operation in the stored library, and if the particular lock has not already been acquired, acquiring the particular lock for the first thread, wherein the hardware lock operation performs a modified atomic operation that changes a result of the hardware lock operation for failed attempts to acquire the particular lock relative to a result of the lock operation in the stored library, and

for each instruction included in the first thread and identified as being associated with an unlock operation corresponding to a particular lock, releasing the particular lock from the first thread.

2. The method of claim 1, wherein continuing to perform the lock operation for a plurality of attempts includes continuing to perform the lock operation for a plurality of attempts during which the first processor core is not able to execute threads other than the first thread.

3. The method of claim 2, wherein, after a predetermined threshold on the plurality of attempts, the first processor core places the first thread into an inactive state that enables the first processor core to temporarily execute threads other than the first thread until the first thread is placed back into an active state.

4. The method of claim 3, wherein, after releasing the particular lock from the first thread, the first processor core determines if there are any waiting threads executing on a processor core other than the first processor core that were placed into the inactive state after at least one attempt at acquiring the particular lock, and if so, places at least one waiting thread back into the active state.

5. The method of claim 1, wherein the hardware lock operation different from the lock operation in the stored library is used in response to the lock operation in the stored library being invoked.

6. The method of claim 1, wherein the hardware lock operation different from the lock operation in the stored library is performed by hardware within the first processor core that is configured to perform at least one of the plurality of attempts by re-issuing an instruction within a pipeline of the first processor core.

7. The method of claim 6, wherein the re-issuing of the instruction is transparent to software being executed by the first thread.

8. The method of claim 1, wherein interconnection circuitry configured to connect each processor core to a memory system of the processor is configured to preserve prioritization of selected messages associated with instructions identified as being associated with an unlock operation over messages associated with instructions identified as being associated with a lock operation.

9. The method of claim 1, wherein the first processor core includes circuitry configured to identify selected instructions as being associated with operations from the stored library, the identifying including, for a plurality of instructions included in a particular thread executing on the processor, identifying a first subset of the plurality of instructions as being associated with a lock operation based on predetermined characteristics of the plurality of instructions, and identifying a second subset of the plurality of instructions as being associated with an unlock operation based on predetermined characteristics of the plurality of instructions.

10. The method of claim 9, wherein the selected instructions are identified as being associated with operations from the stored library of operations using issue logic circuitry of a pipeline stage of the first processor core.

11. A processor comprising:

a plurality of processor cores, each configured to execute a plurality of threads, each thread having access to a stored library of operations including at least one lock operation and at least one unlock operation; and

instruction management circuitry in at least a first processor core of the plurality of processor cores, the instruction management circuitry configured to manage instructions that are issued on the first processor core, for a first thread executing on the first processor core, the managing including;

for each instruction included in the first thread and identified as being associated with a lock operation corresponding to a particular lock, determining if the particular lock has already been acquired for another thread executing on a processor core other than the first processor core, and if the particular lock has already been acquired, continuing to perform the lock operation for a plurality of attempts using a hardware lock operation different from the lock operation in the stored library, and if the particular lock has not already been acquired, acquiring the particular lock for the first thread, wherein the hardware lock operation performs a modified atomic operation that changes a result of the hardware lock operation for failed attempts to acquire the particular lock relative to a result of the lock operation in the stored library, and

for each instruction included in the first thread and identified as being associated with an unlock operation corresponding to a particular lock, releasing the particular lock for the first thread.

12. The processor of claim 11, wherein continuing to perform the lock operation for a plurality of attempts includes continuing to perform the lock operation for a plurality of attempts during which the first processor core is not able to execute threads other than the first thread.

13. The processor of claim 12, wherein, after a predetermined threshold on the plurality of attempts, the first processor core places the first thread into an inactive state that enables the first processor core to temporarily execute threads other than the first thread until the first thread is placed back into an active state.

14. The processor of claim 13, wherein, after releasing the particular lock from the first thread, the first processor core determines if there are any waiting threads executing on a processor core other than the first processor core that were placed into the inactive state after at least one attempt at acquiring the particular lock, and if so, places at least one waiting thread back into the active state.

15. The processor of claim 11, wherein the hardware lock operation different from the lock operation in the stored library is used in response to the lock operation in the stored library being invoked.

16. The processor of claim 11, wherein the hardware lock operation different from the lock operation in the stored library is performed by hardware within the first processor core that is configured to perform at least one of the plurality of attempts by re-issuing an instruction within a pipeline of the first processor core.

17. The processor of claim 16, wherein the re-issuing of the instruction is transparent to software being executed by the first thread.

18. The processor of claim 11, further comprising interconnection circuitry configured to connect each processor core to a memory system of the processor is configured to preserve prioritization of selected messages associated with instructions identified as being associated with an unlock operation over messages associated with instructions identified as being associated with a lock operation.

19. The processor of claim 11, wherein the first processor core includes circuitry configured to identify selected instructions as being associated with operations from the stored library, the identifying including, for a plurality of instructions included in a particular thread executing on the processor, identifying a first subset of the plurality of instructions as being associated with a lock operation based on predetermined characteristics of the plurality of instructions, and identifying a second subset of the plurality of instructions as being associated with an unlock operation based on predetermined characteristics of the plurality of instructions.

20. The processor of claim 11, wherein the selected instructions are identified as being associated with operations from the stored library of operations using issue logic circuitry of a pipeline stage of the first processor core.