[AMDGPU] Don't skip regions in getRegionLiveInMap #151423
Merged
Conversation
This file contains hidden or 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
Change-Id: If8c3fe02d56aa390f921123e02443386cbc600a1
Member
|
@llvm/pr-subscribers-backend-amdgpu Author: Jeffrey Byrnes (jrbyrnes) ChangesCurrently, this skips any region that is not the first region in a block. This is because the only user of it only cares about the LiveIns per-block. However, as named, this is supposed to compute the per-region LiveIns. This doesn't have any effect on scheduling / CodeGen currently (aside from computing LiveIns for all regions) since only the per-block LiveIns are needed. However, I'm working on something that will use this. Intended User: Full diff: https://github.com/llvm/llvm-project/pull/151423.diff 1 Files Affected:
diff --git a/llvm/lib/Target/AMDGPU/GCNSchedStrategy.cpp b/llvm/lib/Target/AMDGPU/GCNSchedStrategy.cpp
index ce1ce687d0038..33b66a63300f0 100644
--- a/llvm/lib/Target/AMDGPU/GCNSchedStrategy.cpp
+++ b/llvm/lib/Target/AMDGPU/GCNSchedStrategy.cpp
@@ -896,15 +896,10 @@ GCNScheduleDAGMILive::getRegionLiveInMap() const {
assert(!Regions.empty());
std::vector<MachineInstr *> RegionFirstMIs;
RegionFirstMIs.reserve(Regions.size());
- auto I = Regions.rbegin(), E = Regions.rend();
- do {
- const MachineBasicBlock *MBB = I->first->getParent();
- auto *MI = &*skipDebugInstructionsForward(I->first, I->second);
- RegionFirstMIs.push_back(MI);
- do {
- ++I;
- } while (I != E && I->first->getParent() == MBB);
- } while (I != E);
+ for (auto &[RegionBegin, RegionEnd] : reverse(Regions))
+ RegionFirstMIs.push_back(
+ &*skipDebugInstructionsForward(RegionBegin, RegionEnd));
+
return getLiveRegMap(RegionFirstMIs, /*After=*/false, *LIS);
}
|
vpykhtin
approved these changes
Jul 31, 2025
Contributor
vpykhtin
left a comment
vpykhtin
left a comment
There was a problem hiding this comment.
You're probably don't need the reverse anymore, but LGTM.
Collaborator
|
LLVM Buildbot has detected a new failure on builder Full details are available at: https://lab.llvm.org/buildbot/#/builders/11/builds/20832 Here is the relevant piece of the build log for the reference |
Collaborator
|
LLVM Buildbot has detected a new failure on builder Full details are available at: https://lab.llvm.org/buildbot/#/builders/195/builds/12626 Here is the relevant piece of the build log for the reference |
jrbyrnes
added a commit
to jrbyrnes/llvm-project
that referenced
this pull request
Aug 13, 2025
Currently, this skips any region that is not the first region in a block. This is because the only user of it only cares about the LiveIns per-block. However, as named, this is supposed to compute the per-region LiveIns. This doesn't have any effect on scheduling / CodeGen currently (aside from computing LiveIns for all regions) since only the per-block LiveIns are needed. However, I'm working on something that will use this. Intended User: llvm#149367 https://github.com/llvm/llvm-project/blob/c62a2f127cba5d6df350474dfd4a6e5f9250fe4f/llvm/lib/Target/AMDGPU/GCNSchedStrategy.cpp#L1351
jrbyrnes
added a commit
to jrbyrnes/llvm-project
that referenced
this pull request
Aug 15, 2025
Currently, this skips any region that is not the first region in a block. This is because the only user of it only cares about the LiveIns per-block. However, as named, this is supposed to compute the per-region LiveIns. This doesn't have any effect on scheduling / CodeGen currently (aside from computing LiveIns for all regions) since only the per-block LiveIns are needed. However, I'm working on something that will use this. Intended User: llvm#149367 https://github.com/llvm/llvm-project/blob/c62a2f127cba5d6df350474dfd4a6e5f9250fe4f/llvm/lib/Target/AMDGPU/GCNSchedStrategy.cpp#L1351
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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.
Currently, this skips any region that is not the first region in a block. This is because the only user of it only cares about the LiveIns per-block. However, as named, this is supposed to compute the per-region LiveIns.
This doesn't have any effect on scheduling / CodeGen currently (aside from computing LiveIns for all regions) since only the per-block LiveIns are needed. However, I'm working on something that will use this.
Intended User:
#149367
llvm-project/llvm/lib/Target/AMDGPU/GCNSchedStrategy.cpp
Line 1351 in c62a2f1