Methods and apparatus for inflight data forwarding and invalidation of pending writes in store queue
Methods, apparatus, systems and articles of manufacture are disclosed to forward and invalidate inflight data in a store queue. An example apparatus includes a cache storage, a cache controller coupled to the cache storage and operable to receive a first memory operation, determine that the first memory operation corresponds to a read miss in the cache storage, determine a victim address in the cache storage to evict in response to the read miss, issue a read-invalidate command that specifies the victim address, compare the victim address to a set of addresses associated with a set of memory operations being processed by the cache controller, and in response to the victim address matching a first address of the set of addresses corresponding to a second memory operation of the set of memory operations, provide data associated with the second memory operation.
1 . A system, comprising:
a cache memory; and
a store queue coupled to the cache memory and configured to:
receive data associated with a first address that is specified to be stored by an instruction;
receive a second address associated with an eviction from the cache memory; and
prior to completing storage of the data to the cache memory,
determine whether the first address matches the second address; and
based on the first address matching the second address, discontinue the storage of the data to the cache memory.
2 . The system of claim 1 , wherein the store queue is configured to:
receive a set of addresses that includes the first address; and
compare the second address to each of the set of addresses to determine whether any of the set of addresses, including the first address, matches the second address.
3 . The system of claim 1 , wherein:
the cache memory is a main cache memory;
the system further comprises a victim cache memory; and
the store queue is configured to, based on the first address matching the second address, provide the data for storage to the victim cache memory.
4 . The system of claim 3 , wherein:
the store queue includes a set of pipeline stages;
each stage of the set of pipeline stages includes a respective set of latches; and
the store queue includes a multiplexer that includes a respective input coupled to each set of latches of the sets of latches of the set of pipeline stages and an output configured to provide the data for storage to the victim cache memory.
5 . The system of claim 1 , wherein:
the cache memory is a level one (L1) cache memory;
the system further comprises a level two (L2) cache memory; and
the store queue is configured to, based on the first address and the second address being the same, provide the data for storage to the L2 cache memory.
6 . The system of claim 5 , wherein:
the store queue includes a set of pipeline stages;
each stage of the set of pipeline stages includes a respective set of latches; and
the store queue includes a multiplexer that includes a respective input coupled to each set of latches of the sets of latches of the set of pipeline stages and an output configured to provide the data for storage to the L2 cache memory.
7 . The system of claim 1 , further comprising:
a cache controller coupled to the cache memory and to the store queue and configured to:
receive a read instruction;
determine that the read instruction corresponds to a miss in the cache memory; and
based on the read instruction corresponding to the miss, determine the eviction from the cache memory.
8 . The system of claim 7 , further comprising:
a tag memory coupled to the cache controller,
wherein the cache controller is configured to determine that the read instruction corresponds to the miss in the cache memory based on the tag memory.
9 . The system of claim 1 , wherein the instruction is a write instruction.
10 . The system of claim 1 , wherein the store queue is configured to receive the second address by receiving a read-invalidate instruction that specifies the second address.
11 . A method, comprising:
receiving, by a store queue, data associated with a first address that is specified to be stored by an instruction;
receiving, by the store queue, a second address associated with an eviction from a cache memory; and
prior to completing storage of the data to the cache memory,
determining whether the first address matches the second address; and
based on the first address matches the second address, discontinuing the storage of data to the cache memory.
12 . The method of claim 11 , further comprising:
receiving a set of addresses including the first address; and
comparing the second address to each of the set of address to determine whether any of the set of addresses, including the first address, matches the second address.
13 . The method of claim 11 , wherein:
the cache memory is a main cache memory; and
the method further comprises, based on the first address matches the second address, forwarding the data for storage to a victim cache memory.
14 . The method of claim 13 , wherein:
the store queue includes a set of pipeline stages;
each stage of the set of pipeline stages includes a respective set of latches; and
the store queue includes a multiplexer that includes a respective input coupled to each set of latches of the sets of latches of the set of pipeline stages and an output coupled to the victim cache memory so as to forward the data for storage to the victim cache memory.
15 . The method of claim 11 , wherein:
the cache memory is a level one (L1) cache memory; and
the method further comprises, based on the first address matches the second address are, forwarding the data for storage to a level two (L2) cache memory.
16 . The method of claim 15 , wherein:
the store queue includes a set of pipeline stages;
each stage of the set of pipeline stages includes a respective set of latches; and
the store queue includes a multiplexer that includes a respective input coupled to each set of latches of the sets of latches of the set of pipeline stages and an output coupled to the L2 cache memory so as to forward the data for storage to the L2 cache memory.
17 . The method of claim 11 , further comprising:
receiving a read instruction;
determining whether the read instruction corresponds to a miss in the cache memory; and
based on the read instruction corresponding to the miss in the cache memory, determining the eviction from the cache memory.
18 . The method of claim 17 , wherein determining whether the read instruction corresponds to the miss comprises determining whether the read instruction corresponds to the miss based on a tag memory.
19 . The method of claim 11 , wherein the instruction is a write instruction.
20 . The method of claim 11 , wherein receiving the second address comprises receiving the second address by receiving a read-invalidate instruction that specifies the second address.