Resource sharing using process delay
Methods and systems that reduce the number of instance of a shared resource needed for a processor to perform an operation and/or execute a process without impacting function are provided. a method of processing in a processor is provided. Aspects include determining that an operation to be performed by the processor will require the use of a shared resource. A command can be issued to cause a second operation to not use the shared resources N cycles later. The shared resource can then be used for a first aspect of the operation at cycle X and then used for a second aspect of the operation at cycle X+N. The second operation may be rescheduled according to embodiments.
1. A method of executing scheduled operations in a computer system, comprising:
determining that a first operation scheduled for execution will require access to multiple instances of a shared hardware resource at a predefined cycle;
restricting access to the shared hardware resource by a second operation scheduled to access the shared hardware resource at a cycle subsequent to said predefined cycle, which requires less cycles than cycles required to complete the first operation;
providing access to the shared hardware resource by said first operation during at least said predefined cycle and said cycle subsequent to said predefined cycle; and
re-scheduling the second operation to use the shared hardware resource after said first operation has completed use of said shared hardware resource.
2. The method of claim 1 , wherein re-scheduling the second operation comprises allowing the second operation to use the shared hardware resource in a cycle immediately following the completion of use of the shared hardware resource by the first operation.
3. The method of claim 1 , wherein the first operation comprises a store operation requiring that both an address and data be read from an internal memory.
4. The method of claim 1 , wherein the shared hardware resource is a read port of internal memory.
5. The method of claim 1 , wherein restricting access comprises issuing a command communicated in fewer cycles than needed for said first operation to complete use of said shared hardware resource.
6. A processor, comprising:
a shared hardware resource configured to be used by a plurality of operations during different processor cycles;
a scheduler configured to:
determine that a first operation will require the use of multiple instances of said shared hardware resource at a predefined cycle and to cause restriction of access to the shared resource by a second operation scheduled to access the shared hardware resource at a cycle subsequent to said predefined cycle, and
reschedule the second operation to use the shared hardware resource after said first operation has completed use of said shared resource; and
a processing component configured to execute said first operation by accessing the shared hardware resource during at least said predefined cycle and said cycle subsequent to said predefined cycle.
7. The processor of claim 6 , wherein the scheduler is configured to reschedule the second operation by allowing the second operation to use the shared hardware resource immediately following the completion of use of the shared hardware resource by the first operation.
8. The processor of claim 6 , wherein the first operation comprises a store operation requiring that both an address and data be read from an internal memory.
9. The processor of claim 8 , wherein the processing component is configured to write the address and the data to a load/store queue.
10. The processor of claim 6 , wherein the shared hardware resource is a read port of an internal memory.
11. A method of reducing the number of physical instances of a shared hardware resource needed to simultaneously process by a processor system different aspects of a scheduled first operation over a plurality of processor cycles, each aspect of said scheduled first operation requiring access to said shared hardware resource, comprising:
causing accesses to said shared hardware resource by said different aspects to be carried out at different processor cycles, while other functions of each of said different aspects are carried out during a same processor cycle;
restricting access to said shared hardware resource by a scheduled second operation during processor cycles in which said different aspects of said scheduled first operation are accessing said shared hardware resource; and
rescheduling said scheduled second operation to begin at a processor cycle subsequent to completion of use of said shared hardware resource by said first operation.
12. The method of claim 11 , wherein said scheduled first operation is a store operation having a store address aspect and a store data aspect.
13. The method of claim 11 , wherein said shared hardware resource is a port of an internal memory of said processor system.
14. The method of claim 13 , wherein said port is a read port.
15. The method of claim 11 , wherein restricting access to said shared hardware resource comprises issuing a command by a scheduler of said processor system.
16. The method of claim 15 , wherein rescheduling said scheduled second operation comprises adding said second operation to a ready queue by said scheduler.
17. The method of claim 16 , wherein rescheduling said scheduled second operation is carried out without rescheduling any other waiting operrations in said ready queue.
18. A method of executing scheduled operations in a computer system, comprising:
determining that a first operation scheduled for execution will require access to multiple instances of a shared hardware resource at a predefined cycle;
restricting access to the shared hardware resource by a second operation scheduled to access the shared hardware resource at a cycle subsequent to said predefined cycle;
providing access to the shared hardware resource by said first operation during at least said predefined cycle and said cycle subsequent to said predefined cycle; and
re-scheduling the second operation to use the shared hardware resource after said first operation has completed use of said shared hardware resource, without rescheduling other awaiting operations.