[cpu] remove branch prediction logic #678
Merged
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR removes the CPU front end 's "branch prediction" logic that was used to halt instruction fetch while a branch/jump instruction is in progress until the destination address is available (resulting in less bus traffic / congestion).
However, benchmarks show that this prediction actually lowers performance:
Exemplary CoreMark run with branch prediction:
Exemplary CoreMark run without branch prediction:
Adding caches results in the same speed up factor when the prediction logic is removed. Additionally, removing the prediction logic reduces core size and relaxes the critical path (= the branch taken / not taken logic).