RequestArb: restrict concurrent number of Acquires with same set #143
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Consider a deadlock situation: given 4 ways in each slice, MSHR 0~3 are accessing separate ways, which makes all the ways occupied. At the same time, MSHR 4 already got CompData from HN, and is waiting for a free way to replace and to echo data through channel D to L1. Therefore MSHR 4 selects replacement way but fails repeatedly. If there is an incoming snoop that has the same address with MSHR 4, the snoop will be blocked because Grant message of MSHR 4 is blocked. Then CompData(s) corresponding to MSHR 0~3 could not be returned due to the blocked snoop. There goes the deadlock.
…ndshake Co-authored-by: zhanglinjuan <[email protected]>
Kumonda221-CrO3
force-pushed
the
chi-coupledl2-snp-deadlock
branch
from
1cad66e to
b2cd68b
Compare
Kumonda221-CrO3
approved these changes
May 7, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Consider a deadlock situation: given 4 ways in each slice, MSHR 0~3 are accessing separate ways, which makes all the ways occupied. At the same time, MSHR 4 already got CompData from HN, and is waiting for a free way to replace and to echo data through channel D to L1. Therefore MSHR 4 selects replacement way but fails repeatedly. If there is an incoming snoop that has the same address with MSHR 4, the snoop will be blocked because Grant message of MSHR 4 is blocked. Then CompData(s) corresponding to MSHR 0~3 could not be returned due to the blocked snoop. There goes the deadlock.
This pr breaks the deadlock by restricting the parallelism of L1 demand requests that share the same set to the number of ways.