US2010325631A1PendingUtilityA1
Method and apparatus for increasing load bandwidth
Est. expirySep 28, 2021(expired)· nominal 20-yr term from priority
G06F 9/384G06F 9/3826G06F 9/3834
45
PatentIndex Score
0
Cited by
0
References
0
Claims
Abstract
A method and apparatus for dual-target register allocation is described, intended to enable the efficient mapping/renaming of registers associated with instructions within a pipelined microprocessor architecture.
Claims
exact text as granted — not AI-modified1 - 34 . (canceled)
35 . A method comprising:
scheduling a plurality of load operations to be performed within a load cycle, said plurality of load operations comprising a load operation predicted to be satisfied by accessing a store-forwarding buffer; and issuing a load operation predicted to be satisfied by accessing said store-forwarding buffer to the store-forwarding buffer and not a data load cache.
36 . The method of claim 35 further comprising issuing a load operation not predicted to be satisfied by accessing said store-forwarding buffer to the data load cache within said load cycle.
37 . The method of claim 35 further comprising issuing said load operation to said data load cache if the load operation is not predicted to be satisfied by accessing the store-forwarding buffer.
38 . The method of claim 35 wherein said predicting is a function of how often said load operation is satisfied by accessing a store-forwarding buffer.
39 . An apparatus comprising:
a prediction unit to predict whether a load operation will be satisfied by accessing a store-forwarding buffer, wherein said load operation predicted to be satisfied by accessing said store-forwarding buffer is to be issued to said store-forwarding buffer and not a data load cache unit if no other load operation has been issued to said data load cache unit within a load cycle.
40 . The apparatus of claim 39 wherein the scheduler unit is to schedule a plurality of load operations within a load cycle, wherein said scheduler unit is enabled to schedule a load operation not predicted to be satisfied by accessing said store-forwarding buffer within said load cycle.
41 . The apparatus of claim 40 wherein said load operation not predicted to be satisfied by accessing said store-forwarding buffer is issued to a data cache unit.
42 . The apparatus of claim 41 wherein said load operation not predicted to be satisfied by accessing said store-forwarding buffer is issued to said store-forwarding buffer within said load cycle.
43 . The apparatus of claim 42 , wherein said plurality of load operations comprises a load operation predicted by said prediction unit to be satisfied by accessing said store-forwarding buffer.
44 . The apparatus of claim 42 wherein said load operation predicted to be satisfied by accessing said store-forwarding buffer or said load operation not predicted to be satisfied by accessing said store-forwarding buffer is rescheduled if said prediction is incorrect.
45 . The apparatus of claim 44 wherein said rescheduling comprises rescheduling a dependent load operation, said dependent load operation being dependent upon said load operation predicted to be satisfied by accessing said store-forwarding buffer or upon said load operation not predicted to be satisfied by accessing said store-forwarding buffer.
46 . The apparatus of claim 39 further comprising a store buffer, said prediction unit being coupled to said store buffer.
47 . The apparatus of claim 46 wherein said predicting is a function of how often load operation is satisfied by accessing a store-forwarding buffer.
48 . The apparatus of claim 47 wherein said function is dependent upon whether said load operation predicted to be satisfied by accessing said store-forwarding buffer is present within said store buffer.
49 . A system comprising:
a prediction unit to predict whether a load operation will be satisfied by accessing a store-forwarding buffer; a scheduler unit to schedule a plurality of load operations within a load cycle, said plurality of load operations comprising a load operation predicted by said prediction unit to be satisfied by accessing said store-forwarding buffer, wherein the load operation is issued to a data load cache unit and not the store-forwarding buffer if the load operations is not predicted to be satisfied by accessing said store-forwarding buffer.
50 . The system of claim 49 wherein said scheduler unit is enabled to schedule a load operation not predicted to be satisfied by accessing said store-forwarding buffer within said load cycle.
51 . The system of claim 50 wherein said load operation not predicted to be satisfied by accessing said store-forwarding buffer is issued to said data load cache unit.
52 . The system of claim 51 wherein said load operation not predicted to be satisfied by accessing said store-forwarding buffer is issued to said store-forwarding buffer within said load cycle.
53 . The system of claim 52 wherein said load operation predicted to be satisfied by accessing said store-forwarding buffer or said load operation not predicted to be satisfied by accessing said store-forwarding buffer is rescheduled if said prediction is incorrect.Cited by (0)
No later patents cite this yet.
References (0)
No backward citations on record.