Technique to share information among different cache coherency domains
A technique to enable information sharing among agents within different cache coherency domains. In one embodiment, a graphics device may use one or more caches used by one or more processing cores to store or read information, which may be accessed by one or more processing cores in a manner that does not affect programming and coherency rules pertaining to the graphics device.
1. An apparatus comprising:
a memory controller to provide access to a main memory;
at least one central processing unit having an L1 cache;
an L2 cache coupled to the at least one central processing unit;
a graphics processing unit in a different cache coherency domain than the L1 cache; and
interconnect logic including at least some hardware and coupled to the at least one central processing unit and coupled to the graphics processing unit, the interconnect logic to enable information sharing between the at least one central processing unit and the graphics processing unit and to allow the graphics processing unit to access information within the L2 cache without first resorting to main memory;
wherein the at least one central processing unit and the graphics processing unit maintain coherency with the L2 cache.
2. The apparatus of claim 1 , wherein the apparatus is a processor, and wherein the graphics processing unit is integrated with the at least one central processing unit within the processor.
3. The apparatus of claim 1 , wherein the graphics processing unit is to implement a first set of cache coherency rules and the at least one central processing unit is to implement a second set of cache coherency rules.
4. The apparatus of claim 3 , wherein the first set of cache coherency rules is different from the second set of cache coherency rules.
5. The apparatus of claim 1 , wherein the graphics processing unit is to use a different cache coherency protocol than one used for the L1 cache, and wherein the graphics processing unit is to access information from the L2 cache.
6. A microprocessor comprising:
an input/output (I/O) controller;
an audio I/O module;
at least one central processing unit having an L1 cache;
an L2 cache coupled to the at least one central processing unit;
a graphics processing unit in a different cache coherency domain than the L1 cache; and
interconnect logic including at least some hardware and coupled to the at least one central processing unit and coupled to the graphics processing unit, the interconnect logic to enable information sharing between the at least one central processing unit and the graphics processing unit and to allow the graphics processing unit to access information within the L2 cache without first resorting to main memory;
wherein the at least one central processing unit and the graphics processing unit maintain coherency with the L2 cache.
7. The microprocessor of claim 6 , wherein the graphics processing unit is to implement a first set of cache coherency rules and the at least one central processing unit is to implement a second set of cache coherency rules.
8. The microprocessor of claim 7 , wherein the first set of cache coherency rules is different from the second set of cache coherency rules.
9. A system comprising:
a display device;
a main memory;
an input/output (I/O) controller;
an audio I/O module;
at least one central processing unit having an L1 cache;
an L2 cache coupled to the at least one central processing unit;
a graphics processing unit in a different cache coherency domain than the L1 cache; and
interconnect logic including at least some hardware and coupled to the at least one central processing unit and coupled to the graphics processing unit, the interconnect logic to enable information sharing between the at least one central processing unit and the graphics processing unit and to allow the graphics processing unit to access information within the L2 cache without first resorting to main memory;
wherein the at least one central processing unit and the graphics processing unit maintain coherency with the L2 cache.
10. The system of claim 9 , wherein the graphics processing unit is integrated with the at least one central processing unit within a processor.
11. The system of claim 9 , wherein the graphics processing unit is to implement a first set of cache coherency rules and the at least one central processing unit is to implement a second set of cache coherency rules.
12. The system of claim 11 , wherein the first set of cache coherency rules is different from the second set of cache coherency rules.
13. A system comprising:
a peripheral control device;
an input/output (I/O) controller coupled to the peripheral control device;
at least one central processing unit having an L1 cache;
an L2 cache coupled to the at least one central processing unit;
a graphics processing unit in a different cache coherency domain than the L1 cache; and
interconnect logic including at least some hardware and coupled to the at least one central processing unit and coupled to the graphics processing unit, the interconnect logic to enable information sharing between the at least one central processing unit and the graphics processing unit and to allow the graphics processing unit to access information within the L2 cache without first resorting to main memory;
wherein the at least one central processing unit and the graphics processing unit maintain coherency with the L2 cache.
14. The system of claim 13 , wherein the graphics processing unit is integrated with the at least one central processing unit within a processor.
15. The system of claim 13 , wherein the graphics processing unit is to implement a first set of cache coherency rules and the at least one central processing unit is to implement a second set of cache coherency rules.
16. The system of claim 15 , wherein the first set of cache coherency rules is different from the second set of cache coherency rules.