Fetch branch architecture for reducing branch penalty without branch prediction
AssigneeSTMicroelectronics S.r.l.
InventorsFaraydon O. Karim, Ramesh Chandra
Life of this patent
Estimating the term…
Loading patent…
AssigneeSTMicroelectronics S.r.l.
InventorsFaraydon O. Karim, Ramesh Chandra
Estimating the term…
In lieu of branch prediction, a merged fetch-branch unit operates in parallel with the decode unit within a processor. Upon detection of a branch instruction within a group of one or more fetched instructions, any instructions preceding the branch are marked regular instructions, the branch instruction is marked as such, and any instructions following branch are marked sequential instructions. Within two cycles, sequential instructions following the last fetched instruction are retrieved and marked, target instructions beginning at the branch target address are retrieved and marked, and the branch is resolved. Either the sequential or target instructions are then dropped depending on the branch resolution, incurring a fixed, 1 cycle branch penalty.
For use in a processor, a branch architecture for limiting branch penalty without branch prediction comprising:
A processor comprising:
For use in a processor, a method of processing branch instructions without branch prediction comprising:
Dependencies are inferred from the claim text.